Accurate crop disease diagnosis is critical for agricultural productivity and food security, yet existing deep learning systems often struggle to generalize across visually similar diseases and varying environmental conditions. Recent Vision-Language Models (VLMs) have demonstrated promising zero-shot reasoning capabilities; however, most agricultural diagnostic systems still rely on isolated single-model predictions without collaborative reasoning or consensus mechanisms. In this work, we propose VIDA+PANDA, a multi-agent Vision-Language framework for zero-shot crop disease diagnosis. The framework consists of two stages: VIDA, where multiple VLM agents independently analyze crop leaf images to establish baseline performance, and the Peer-Anchored Named Deliberation Architecture (PANDA), which introduces a structured multi-round debate among a selected group of high-performing and architecturally diverse agents. During deliberation, agents exchange reasoning, critique peer predictions, and revise decisions through evidence-grounded discussion, while an anti-sycophancy mechanism discourages unsupported consensus shifts. Final predictions are generated through performance-weighted consensus voting. Experiments are conducted on the CDDM benchmark using seven heterogeneous VLMs from four independent providers, including two open-source models, under a fully zero-shot setting. A non-participant GPT-5 model serves as an independent judge to assess the final diagnostic predictions. Beyond conventional accuracy, the framework introduces three semantic measures: Semantic Label Similarity (SLS), which measures how semantically close a predicted crop-disease pair is to the ground truth and captures partial correctness overlooked by exact-match evaluation; Reasoning Specificity (RS), which measures how concretely an agent’s explanation references visual evidence such as lesion color, shape, texture, or margins; and Inter-Agent Reasoning Convergence (IRC), which measures the extent to which agents rely on similar visual evidence, capturing epistemic alignment independently of label correctness. Experimental results show that collaborative multiagent deliberation improves individual diagnostic performance and semantic alignment, with the largest gains observed among weaker participating agents. The findings also reveal important relationships between predictive accuracy, persuasive influence, and consensus formation in VLM-based agricultural diagnosis.
Why it matches plant phenotyping methods葉画像から植物病害状態を推定するマルチエージェント画像・言語フレームワークを開発し、ベンチマークで性能評価しており、病害表現型の取得・推定手法が中心である。
abstractwe propose VIDA+PANDA, a multi-agent Vision-Language framework for zero-shot crop disease diagnosis.
With the rapid development of artificial intelligence, UAV remote sensing, and agricultural Internet of Things technologies, crop growth monitoring is evolving from manual inspection and single-source analysis toward intelligent decision-making based on multisource perception. However, existing methods still suffer from limited robustness under environmental variations, insufficient integration between UAV imagery and sparse ground sensor observations, and weak capability for transforming predictions into practical agricultural management recommendations. This study proposes a UAV–ground sensor collaborative lightweight framework for crop growth assessment and agricultural decision support. The proposed framework integrates UAV RGB and multispectral imagery with ground sensor observations through a region-level aerial–ground alignment mechanism and a sensor-guided attention fusion module, enabling environmental conditions to enhance visual feature interpretation. Furthermore, a fact-constrained decision module is developed to generate management recommendations based on crop status, environmental risks, and field information. Experimental results demonstrate that the proposed method achieves superior performance in crop growth classification and yield-trend prediction, reaching Accuracy, Precision, Recall, and F1-score values of 92.47%, 91.86%, 91.39%, and 91.62%, respectively, with an RMSE of 0.381 and an R2 of 0.902. The lightweight framework requires only 6.18M parameters and 0.91G FLOPs, achieving 39.56 ms inference latency and 25.28 FPS on edge devices. The proposed framework also improves decision reliability, achieving an expert agreement rate of 89.34% and a risk identification accuracy of 90.18%. Economic analysis indicates that the proposed framework reduces labor cost, water consumption, and fertilizer input by 49.7%, 26.7%, and 23.0%, respectively, while increasing net benefit by 46.1% compared with conventional field management practices. These results demonstrate that the proposed method provides an accurate, interpretable, and deployable AI-driven solution for intelligent crop management in smallholder and medium-sized farming systems.
Why it matches plant phenotyping methodsUAV画像と地上センサーを融合し、作物生育状態を評価する取得・推定フレームワーク自体を開発しており、植物状態の推定方法が中心的です。
abstractThis study proposes a UAV–ground sensor collaborative lightweight framework for crop growth assessment and agricultural decision support.
Accurate lesion segmentation is essential for automated plant disease analysis in precision agriculture. Although the Segment Anything Model (SAM) exhibits strong generalization ability, its direct application to plant disease images in natural field environments remains challenging due to cluttered backgrounds, dense leaf veins, uneven illumination, and frequent occlusions. In particular, SAM mainly relies on global structural cues and is often insufficiently sensitive to subtle lesion textures and weak local details, which can result in missed small or early-stage lesions and inaccurate boundary delineation. To address these limitations, we enhance SAM with a disease-specific detail compensation module for plant disease lesion segmentation. A ResNet-50based branch is employed to extract fine-grained local texture features that are difficult for SAM to capture. These fine-grained features are fused with SAM encoder representations and then injected into the SAM decoder, enabling more accurate lesion prediction while preserving SAM’s strong global modeling capability. More importantly, we propose a reliability-guided variational fusion framework to further improve the interaction between heterogeneous features. Specifically, instead of conventional similarity or addition-based fusion, we introduce an uncertainty-aware variational fusion strategy that explicitly quantifies the confidence of each feature stream. An uncertainty encoder models feature distributions probabilistically, and a variational fusion module dynamically assigns higher weights to more reliable features while suppressing uncertain or interfering responses. In addition, Kullback-Leibler divergence regularization is introduced to stabilize cross-feature alignment and improve fusion robustness. Extensive experiments on PlantSeg, PlantDoc-Seg, and ATLDSD demonstrate that the proposed method outperforms state-of-theart approaches, achieving DSC scores of 81.05%, 91.12%, and 88.27%, respectively. The proposed method addresses SAM’s weakness in fine-grained disease feature extraction, accurately identifies early and small lesions, and delivers reliable segmentation for field plant disease automatic diagnosis.
Why it matches plant phenotyping methods植物病斑を対象とする画像セグメンテーション手法を開発し、複数データセットで性能検証しているため、病害状態のフェノタイピング手法が中心である。
abstractwe enhance SAM with a disease-specific detail compensation module for plant disease lesion segmentation.
Reproduction assets foundThe paper evaluates ReLeaf-SAM on three public plant disease segmentation datasets. One of them, PlantDoc-Seg, is explicitly a community-provided Kaggle dataset with a verbatim URL matching an allowed URL; it is a public plant image/mask dataset directly used for this paper's segmentation measurements. PlantSeg and ATLDataset · publicTherefore, we used a community-provided segmentation subset from Kaggle 1 , which we refer to as PlantDoc-Seg in this study. This subset is derived from PlantDoc and contains 588 diseased leaf images with corresponding binary masks, enabling supervised leaf disease segmentation.Open asset ↗Kagglelines:48-115Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · checked 5 Sept 2026
ABSTRACT Conventional field phenotyping methods are typically manual, time‐consuming, and destructive, creating a bottleneck for breeding progress. To address this challenge, robotics and automation technologies offer efficient sensing tools to monitor field evolution and crop development throughout the season. This study presents an end‐to‐end automated pipeline for terrestrial laser scanning (TLS) in plant breeding trials, built around a Husky ground robot equipped with a high‐resolution survey‐grade FARO 3D LiDAR scanner. Unlike prior TLS phenotyping approaches relying on manual scan placement or heuristic site selection, our system integrates a novel analytical 3D ray‐casting method for optimized TLS site planning with an offline route optimization algorithm that accounts for crop growth stages and field accessibility constraints. This enables efficient planning in complex breeding environments, reduces manual labor, and improves data collection efficiency, addressing scalability challenges in large breeding trials. Leveraging Real Time Kinematic‐Global Navigation Satellite System (RTK‐GNSS) and sensor fusion, the system achieved average errors below 0.6 cm for position and for heading, enabling point cloud registration with mean errors around 2 cm, comparable to traditional manual methods that require artificial targets. The platform was successfully deployed and evaluated in two distinct cotton breeding field layouts, demonstrating the platform's capability to autonomously collect accurate TLS data for quantitative plant phenotyping across varying plot configurations. The proposed autonomous phenotyping system advances scalable, efficient phenotyping workflows to support breeding programs for crop improvement, highlighting the potential for broader deployment in field phenomics.
Why it matches plant phenotyping methods植物育種試験向けの自律走行TLS・LiDAR計測プラットフォームと、3D計画・経路最適化・データ収集の技術的評価が中心であり、定量的植物表現型取得を目的とする。
abstractThis study presents an end‐to‐end automated pipeline for terrestrial laser scanning (TLS) in plant breeding trials
Against the backdrop of the rapid development of smart agriculture, pest and disease monitoring and crop growth assessment for large-scale farmlands are of substantial importance for precision management and risk early warning. However, traditional unimodal visual methods are highly susceptible to illumination variation, canopy occlusion, scale differences, and background interference in real field environments, and thus fail to make full use of environmental sensing information and spatial priors. To address these issues, a multimodal target perception framework for intelligent farmland inspection is proposed in this study. By jointly integrating UAV imagery, time-series data from ground Internet of Things sensors, and spatial positional information, joint modeling of pest and disease recognition and crop growth assessment is achieved through cross-modal alignment and collaborative encoding, multi-scale target perception, and dynamic multimodal fusion and decision-making. Experimental results demonstrate that, in the pest and disease recognition task, the proposed method achieved a Precision of 91.63%, a Recall of 90.27%, an F1-score of 90.94%, and an mAP of 93.15%, significantly outperforming comparison models such as Faster R-CNN with ResNet50 backbone, YOLOv8-m, Swin Transformer-Tiny, and Multimodal Transformer. In the crop growth assessment task, an Accuracy of 89.96%, a Precision of 89.11%, a Recall of 88.74%, and a Macro-F1 of 88.92% were achieved, again clearly exceeding those of ResNet50, EfficientNet-B3, ViT-B/16, and conventional multimodal fusion models. The ablation study further verified the effectiveness of the cross-modal alignment module, the multi-scale target perception module, and the dynamic fusion module, with the complete model reaching 90.94%, 93.15%, and 88.92% in Pest F1, Pest mAP, and Growth Macro-F1, respectively. Furthermore, the net economic return regression experiment at the unit-area level further demonstrates that the proposed method can effectively connect state information with economic outcomes, showing strong application potential in return prediction, performance evaluation, and resource allocation optimization. These findings indicate that the proposed method can effectively improve perception accuracy and robustness in complex farmland environments, thereby providing reliable technical support for intelligent inspection, pest and disease early warning, and precision management in agricultural scenarios.
Why it matches plant phenotyping methodsUAV画像、IoT時系列データ、空間情報を統合したマルチモーダル手法を開発し、作物生育状態の評価を技術的に検証している。害虫認識単独ではなく、植物の生育評価を含む取得・推定手法が中心である。
abstracta multimodal target perception framework for intelligent farmland inspection is proposed in this study.
Abstract Satellite-based prediction of grain protein concentration (GPC) in wheat typically relies on spectral observations composited over fixed calendar windows, implicitly assuming phenological synchrony across fields. This study tests whether aligning multi-source remote sensing time series to field-specific phenology-based windows improves field-level GPC prediction. We integrated Sentinel-2 multispectral imagery (32 vegetation indices, 10 spectral bands), ERA5-Land meteorological reanalysis, gSSURGO soil properties, and USGS 3DEP topographic data, and systematically compared six temporal strategies, the factorial combination of two normalization approaches (peak-relative vs.\calendar) and three resolutions (monthly, biweekly, growth stages), across 228 commercial winter wheat fields in western Kansas (2024--2025). Three ensemble tree models (Random Forest, XGBoost, LightGBM) were trained under nested cross-validation with Boruta feature selection. Peak-relative monthly normalization achieved the highest accuracy (\((R^2 = 0.304 \pm 0.051)\), RMSE \((= 1.11)\)%), explaining an additional 5.1% of variance compared with the best calendar strategy (\((R^2 = 0.253)\)). A single 30-day post-peak window (M\((+)\)1, \((\sim)\)15--45 days after maximum canopy greenness) carried more predictive information than any broader aggregation. SHAP analysis identified topsoil organic matter, SWIR-based senescence indices (NBR2, MIRBI), and grain-filling temperature as the most influential predictors. Three-class quality classification reached 47--49% accuracy (versus 33.3% by chance), indicating practical utility for early grain segregation. While demonstrated for wheat GPC, the framework is transferable to other crop traits with temporally concentrated satellite signals, particularly those tied to specific developmental stages. The results highlight phenological alignment as a generalizable strategy for trait prediction from Earth observation data.
Why it matches plant phenotyping methods衛星リモートセンシング時系列を用いた小麦粒タンパク質濃度予測のため、フェノロジー整列と複数の時間集約戦略を体系的に比較・検証しており、植物形質推定手法が研究の中心である。
abstractThis study tests whether aligning multi-source remote sensing time series to field-specific phenology-based windows improves field-level GPC prediction.
Reproduction assets foundThe paper's data availability statement releases a de-identified field-level GPC dataset alongside a public authors' code repository (Ciampitti-Lab WheatGPCPipeline) implementing the data-acquisition, feature-engineering, and modeling pipeline. Both are paper-specific, public, and actionable.Code · publicthe figure-generation scripts is available at https://github.com/Ciampitti-Lab/Open asset ↗pdf-page:48 lines:1-55Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 13 Sept 2026
Modern agriculture operates at an unprecedented crossroads, it must simultaneously accelerate crop yields to feed an expanding global population and adapt to the severe, fluctuating pressures of climate change, structural soil degradation, abiotic water deficits, and evolving biological threats. Historically, selecting resilient crop varieties and implementing field-scale management strategies relied extensively on destructive, labor-intensive, and fundamentally subjective visual metrics. This manual processing approach has long been recognized as the primary operational bottleneck in agricultural advancement.To bridge the gap between rapidly expanding genomic data and actual field performance, the systematic, non-destructive quantification of structural and functional plant traits, plant phenotyping, has emerged as a transformative frontier. By integrating high-throughput engineering, multi-scale remote sensing, deep learning, and advanced molecular biology, modern phenotyping transitions crop science away from qualitative estimation toward highly reproducible, multidimensional data frameworks. This Research Topic presents new advances in advanced 3D reconstruction and deep semantic segmentation at the seedling stage; amodal fruit segmentation, morphological extraction, and early water-stress diagnostics; high-throughput in-field seedling counting and dynamic density modeling; multimodal foundation models, network pruning, and intelligent phytoprotection; aerial and spaceborne remote sensing for canopy analysis and weed monitoring; plant physiology, functional spectroscopy, and functional genomics under abiotic stress; and automated diagnostics for real-time orchard scouting and vineyard management.Automating the characterization of complex spatial layouts under controlled or greenhouse environments is essential for early variety selection and early-stage structural evaluation. Several contributions within this volume provide key breakthroughs in navigating overlapping tissues, severe occlusions, and low-contrast edge regions. showcases how substituting standard convolutions with deformable convolutions enables deep neural networks to accurately isolate the main stem of mature, high-density crops like soybeans. This architecture overcomes the traditional challenges of color mimicry and severe occlusion by pods and leaves, achieving an outstanding mIoU of 90.58% and providing reliable indices for lodging resistance and structural yield modeling (R 2 = 0.9746).Accurately extracting fruit morphology under commercial greenhouse conditions remains heavily constrained by overlapping crop structures, foliage cover, and variable shadows. Simple semantic masks typically fail when a target fruit is partially blocked, leading to a loss of key volumetric data.To resolve the challenge of hidden boundaries, Li, Yin, et al. (2025) developed CGA-ASNet, a specialized RGB-D amodal segmentation network driven by a Contextual and Global Attention (CGA) module designed to restore occluded tomato regions. Trained on a high-fidelity synthetic greenhouse dataset (Tomato-sim) generated via NVIDIA Isaac Sim's Replicator Composer and optimized with a mean coordinate fusion algorithm for real-world validation, this architecture expands the network's receptive field to predict the complete, hidden circular forms of occluded tomatoes, achieving an F@0.75 score of 94.2 and an amodal mIoU of 82.4%. This proves that simulation-to-real (Sim2Real) domain pathways can successfully decode full physical volumes under dense commercial canopies.Complementing this structural restoration, Yang, Li, et al. (2025) designed an integrated diagnostic framework to identify early water stress dynamics in greenhouse tomatoes. Built upon an optimized YOLOv11n core, their system integrates adaptive kernel convolutions (AKConv) into the network backbone's C3k2 modules and implements a recalibration feature pyramid detection head based on the specialized P2 small-target layer. This combination achieved a 5.4% increase in mAP50-95 for identifying fine phenotypic parts. By applying automated geometric analysis to the extracted bounding boxes, the system extracts plant heights and petiole count with low relative errors, feeding these phenotypic parameters into a Random Forest classification routine that flags water-stressed plants with 98% accuracy to guide targeted, automated drip irrigation.Accurate plant stands during early vegetative stages represent the foundational metric required to establish true field emergence rates, validate seed vigor across diverse breeding blocks, and perform early yield predictions.To solve the challenges of small targets, extreme spatial density, and adjacent leaf overlap, Zang et al. (2025) designed DM_IOC_fpn, a wheat seedling counting framework that balances local and global contextual features. By structuring a point-annotated dataset and embedding a densityenhanced encoder module, their network balances micro-scale spatial limits with macro-scale canopy structures. Optimized through a combined loss function tracking counting, classification, and regression parameters, this architecture achieved low error scores (RMSE = 2.91; MAE = 2.23), outperforming standard object-detection benchmarks in complex field environments.At the same time, scaling up to real-time aerial monitoring required major reductions in model complexity to support resource-constrained edge computers on autonomous aerial platforms. Feng, Nie, and Li (2025) engineered an ultra-lightweight YOLOv8n variant tailored for real-time maize seedling counting from high-speed UAV RGB overflights. By reparametrizing RepConv with HGNetV2, they constructed a lean Rep_HGNetV2 backbone, integrated a Bidirectional Feature Pyramid Network (BiFPN) for multi-scale feature alignment, and implemented a Task Dynamically Aligned Detection Head (TDADH). This architecture compressed total model parameters by 47% and reduced weight sizes to 3.5 MB while maintaining a 96.5% detection accuracy and an ultra-fast processing speed of 146.3 FPS, paving the way for low-cost, real-time field scouting.Automated phytoprotection requires machine-vision architectures capable of generalizing across highly diverse species, complex field conditions, and varying computational boundaries. A significant subset of the published papers addresses these challenges through foundation model adaptation, multi-modal alignment, and efficient network compression.A major paradigm shift presented in this collection involves moving away from task-specific training and toward foundation model adaptation. Chen, Ruan, et al. (2026) introduce a novel architecture integrating the DinoV3 foundation model with a Unet framework to achieve robust leaf lesion segmentation across diverse species (such as coffee and black gram). By incorporating a Spatial Prior Module (SPM), their approach surpassed standard benchmark networks by over 10.5% in IoU while reducing inference times by approximately 93.6%, demonstrating that highparameter foundation models can be highly optimized for resource-constrained edge devices in real-time scouting.To solve the perennial problem of limited training data for rare or emerging crop diseases, Cooper et al. ( 2026) developed an ingenious synthetic data generation pipeline. Combining 3D procedural leaf modeling in Blender with diffusion-based disease synthesis (Stable Diffusion fine-tuned with LoRA and ControlNet), they synthesized highly accurate plant disease images with perfect groundtruth annotation masks. When deployed in low-resource data settings, combining these synthetic pipelines with restricted real-world datasets consistently drives significant improvements in downstream segmentation tasks. To tackle specific, complex pathologies, Xu, Chang, et al. (2025) developed the TSSC deep learning model, which embeds three-neighbor channel attention paired with a complementary squeeze-and-excitation mechanism. This specific architecture minimizes structural degradation risks while pushing classification accuracy to 99.61% for highly complex pea leaf pathologies. Similarly, Feng, Liu, et al. (2025) tackled overlapping leaf occlusions and small lesion footprints in citrus groves with YOLO-Citrus, an optimized framework integrating C3K2-STA, ADown modules, and a Wise-Inner-MPDIoU loss function to strike a balance between edge computational constraints and field deployment.UAVs and high-resolution satellite imagery have expanded the operational scale of phenotyping from individual pots to vast breeding blocks and commercial fields, allowing researchers to capture macro-dynamic parameters over time.In complex canopy systems that defy standard top-down aerial sensing, such as single-staked white Guinea yams, Iseki et al. (2026) demonstrated the distinct advantage of utilizing multi-angle (combined nadir and oblique) UAV imaging configurations. When coupled with support vector regression, this method captures complementary canopy-structure information to model shoot biomass trajectories (R 2 = 0.79) across multiple years and management zones. These nondestructive, time-series datasets enabled the fitting of genotype-specific Richard's growth curves using Bayesian inference, isolating valuable genetic variations in early growth allocation.To capture full-season vertical physiological changes over large scales, Li, Yue, and Luo (2025) developed a hybrid CNN-LSTM-Attention (CLA) model designed to estimate the full-period Leaf Area Index (LAI) in rice using multi-temporal UAV multispectral imagery. By using the CNN layer to extract instantaneous spatial features, the LSTM block to process seasonal time-series intervals, and a self-attention mechanism to weight critical growth transitions, their platform achieved a high coefficient of determination (R 2 = 0.92) and kept relative root mean square errors (RRMSE) below 9%. This network minimized soil background noise during early vegetative stages (LAI values 1-
Why it matches plant phenotyping methods植物フェノタイピングの技術動向を扱うEditorialであり、画像解析、UAVセンシング、深層学習、形質抽出などの方法が中心的に整理されている。
In Japan, the quantity of domestically produced fruit has been gradually decreasing, while wholesale prices have continued to rise due to declining production volumes and a shift toward high-quality varieties. To address these trends, improving quality and reducing labor through automation have become urgent challenges. In precision viticulture, monitoring the growth of grape clusters plays a key role in yield estimation, disease management, and optimal harvest timing. Although recent advances in deep learning and 3D reconstruction have enabled accurate fruit detection and modeling in vineyards, tracking the same clusters on different days remains challenging because of branch movement, fruit growth, and varying imaging conditions. This study proposes a branch-based 3D alignment framework for the cross-day tracking of grape clusters. Stable vine structures, such as trunks and main branches, are reconstructed using Structure from Motion, and their spatial correspondences are estimated through SIFT-based matching and similarity transformation. Once the coordinate systems of different days are aligned, the grape clusters detected by CenterNet are associated based on spatial proximity in the unified 3D space. Experiments over multiple observation days demonstrated that the proposed method successfully maintained the consistent tracking of grape clusters throughout the growth period. These results indicate that branch-based alignment effectively stabilizes multi-day observations and facilitates the temporal monitoring of fruit growth, supporting automated phenotyping and future field robot applications in viticulture.
Why it matches plant phenotyping methodsブドウ房の経日追跡を目的とする3D画像アライメント手法を開発し、果実成長の時系列モニタリングと自動フェノタイピングへの利用を実験的に検証しているため、フェノタイピング手法が中心である。
abstractThis study proposes a branch-based 3D alignment framework for the cross-day tracking of grape clusters.
High-throughput phenotyping is essential for resolving genotype-by-environment interactions and accelerating crop breeding. In greenhouse potted-plant systems, narrow aisles, global navigation satellite system (GNSS)-denied operation, variable pot layouts, and plant-level data traceability constrain repeatable automated phenotyping. This study presents PhenoRob-P, a modular autonomous robotic system designed for potted crops in structured facility environments. The system integrates a compact two-wheel differential chassis, a LiDAR–vision fusion framework for row-level navigation, pot-level target identification and local alignment, a six-degree-of-freedom robotic arm with inverse-kinematics-based real-time pose compensation for repeatable multi-view close-range imaging, and a three-tier User–Cloud–Robot platform for task scheduling, remote monitoring, and closed-loop data management. Greenhouse validation showed throughputs of 520 pots/h in continuous scanning mode and 187 pots/h in multi-view fine inspection mode. At travel speeds of 0.2–0.3 m/s, mean terminal positioning errors remained within 30 mm, and approximately 87% of lateral and longitudinal errors fell within ±30 mm. Biological validation demonstrated time-resolved stress phenotyping in wheat, with color indices capturing drought progression and rewatering recovery. For maize, multi-view three-dimensional reconstruction estimated plant height and stem diameter with R 2 values of 0.940 and 0.845, respectively, relative to manual measurements. These results show that PhenoRob-P provides an integrated perception-localization-acquisition-analysis workflow for high-throughput, traceable, and time-resolved phenotyping of potted crops.
Why it matches plant phenotyping methods植物形質の取得を中核とする自律ロボット型ハイスループット表現型解析プラットフォームを開発・検証しており、画像取得、3D再構成、ストレス・形態形質の推定性能も評価している。
abstractThis study presents PhenoRob-P, a modular autonomous robotic system designed for potted crops in structured facility environments.
Reproduction assets foundThe paper's Data availability statement explicitly deposits authors' source code and sample datasets in a public GitHub repository, matching the allowed URL.Code · publicThe source code and sample datasets supporting the findings of this study are openly available at the following GitHub repository: https://github.com/Sunniersy/PhenoRob-P .Open asset ↗https://github.com/Sunniersy/PhenoRob-P · Sunniersy/PhenoRob-Plines:388-431Plant phenotyping relevance match · UnverifiedOpenAlex · checked 15 Sept 2026
Abstract Background This study evaluates the performance of two UAV (Unmanned Aerial Vehicle) platforms for vineyard monitoring, focusing on geometric accuracy, effective resolution, and vegetation index consistency. Methods Two UAV (Unmanned Aerial Vehicle) platforms were compared over a vineyard using multiple flights with a consumer-grade drone and a single RTK (Real-Time Kinematic) enabled flight at similar altitude over a single vineyard block under comparable acquisition conditions, followed by photogrammetric reconstruction, DSM (Digital Surface Model) co-registration, effective resolution analysis, and RGB (Red-Green-Blue) based vegetation index comparison. Results This study demonstrates that the integration of RTK (Real-Time Kinematic) technology in the Mavic 3E improves the absolute accuracy of DSMs (Digital Surface Models), eliminating systematic vertical offsets of ~ 35 m observed in the Mavic 2E products. After applying a robust Z-shift (vertical) correction, DSMs (Digital Surface Models) from both platforms became directly comparable, with RMSE (Root Mean Square Error) values reduced to ~ 1.3 m while NMAD (Normalized Median Absolute Deviation) remained stable. RTK (Real-Time Kinematic) positioning in the Mavic 3E ensured reliable absolute georeferencing, whereas DSMs (Digital Surface Models) derived from the Mavic 2 Enterprise Zoom remained internally consistent after post-processing, though with lower absolute positional accuracy. Effective resolution analysis further showed that the Mavic 3E imagery preserves higher spatial detail than the Mavic 2E, underscoring the importance of sensor optics and stability for vineyard monitoring. Comparisons of vegetation indices revealed that normalized indices such as NGRDI (Normalized Green Red Difference Index) and VARI (Visible Atmospherically Resistant Index) provide consistent results across platforms, while ExG (Excess Green Index) exhibited strong biases and wide limits of agreement, reflecting its sensitivity to radiometric differences. Conclusions For cross-platform or multi-temporal monitoring, NGRDI (Normalized Green Red Difference Index) and VARI (Visible Atmospherically Resistant Index) proved to be more robust, whereas ExG (Excess Green Index) should only be applied after radiometric harmonization. This study provides a replicable workflow for UAV (Unmanned Aerial Vehicle) based vineyard monitoring that integrates geometric alignment, DSM (Digital Surface Model) correction, effective resolution assessment, and index comparison, offering practical recommendations for researchers and practitioners aiming to ensure reliable and comparable UAV (Unmanned Aerial Vehicle) derived vineyard metrics.
Why it matches plant phenotyping methodsUAV画像・写真測量・DSM補正・植生指数を比較検証し、ブドウ園の植物状態を再現可能に測定するワークフローを中心に扱っているため、植物フェノタイピング手法研究に該当する。
abstractThis study evaluates the performance of two UAV (Unmanned Aerial Vehicle) platforms for vineyard monitoring, focusing on geometric accuracy, effective resolution, and vegetation index consistency.
Accurate and efficient 3D reconstruction of trees is of paramount importance for studying forest spatial structures and dynamic resource patterns, optimizing forest management, protecting environments, and analyzing carbon cycles. Currently, Light Detection and Ranging (LiDAR) remains the dominant method for generating 3D models of forest scenes. However, with advancements in computer vision, photogrammetry has emerged as a crucial tool for forest inventory and 3D reconstruction due to its cost-effectiveness. Nevertheless, in practical forestry applications, traditional photogrammetry often suffers from low reconstruction efficiency and poor quality during feature extraction and matching. These issues stem from the complex structure of forest scenes, severe occlusion, and repetitive texture patterns. To address these challenges, this paper proposes an improved 3D tree reconstruction approach based on images, integrating deep learning-based methods. In the sparse reconstruction stage, we utilize the ALIKED (A LIghter Keypoint and descriptor Extraction network with Deformable transformation) algorithm and construct an image pyramid to extract multi-scale robust features. Furthermore, by combining the LightGlue matching algorithm with a neighborhood search constraint strategy, we enhance the stability of camera pose recovery while reducing redundant computations. Experimental results demonstrate that our method outperforms traditional algorithms in both accuracy and robustness regarding image matching. Compared to baseline models, the proposed approach increases the number of feature points by approximately 50% with a more widespread distribution, improves matching accuracy by 4% to 8%, and achieves a 100% image registration rate. Consequently, under the condition of maintaining equivalent re-projection errors, the subsequent sparse point clouds exhibit an average track length increase of 0.6 to 1.4 and a density increase of up to 1.2 times. Notably, this method effectively mitigates artifacts and spurious reconstructions caused by pose drift in forest photogrammetry.
Why it matches plant phenotyping methods森林内の樹木の3次元形態を画像から再構成する特徴抽出・マッチング手法を開発し、精度と頑健性を評価しており、植物形態の取得方法が研究の中心である。
abstractthis paper proposes an improved 3D tree reconstruction approach based on images, integrating deep learning-based methods.
Northern Corn Leaf Blight (NCLB; also, Turcicum Leaf Blight, TLB), caused by Exserohilum turcicum (teleomorph: Setosphaeria turcica), is one of the most destructive foliar diseases of maize worldwide, often causing severe yield losses under favorable conditions. We developed a maize-specific, web-based Decision Support System (DSS) for real-time NCLB detection and management ( https://maize-nclb.streamlit.app/ ), integrating advanced deep-learning for automated diagnosis and fungicide advisory. Among thirteen Machine-learning and deep-learning models evaluated for classification, the Visual Geometry Group 16-layer convolutional neural network (VGG16) outperformed all others, achieving 94.0% accuracy, with balanced precision, recall, and F1-score of 0.94, and an AUC-ROC of 0.93. Confusion matrix analysis revealed minimal misclassification, with only 12 errors out of 357 samples, confirming the model's high reliability in distinguishing healthy and infected plants, while Grad-CAM visualizations consistently highlighted biologically meaningful lesion regions, supporting the model's interpretability and alignment with plant pathological symptoms. Field validation of DSS-guided fungicide recommendations (Azoxystrobin 18.2% + Difenoconazole 11.4% w/w SC) demonstrated significant benefits, reducing disease incidence to 6.8% compared with 67.4% in controls, achieving 90% disease reduction, and enhancing grain yield by 35.4% (8.55 t/ha), with a favorable cost-benefit ratio of 1:2.49. Seasonal disease progression analysis further confirmed DSS effectiveness, with cumulative disease burden reduced by approximately 85% compared with untreated control. These results highlight the potential of integrating deep-learning with field-validated management strategies into a practical DSS, demonstrating its potential for precision disease management in maize.
Why it matches plant phenotyping methods葉の病斑を画像から分類・可視化する深層学習法を開発し、野外で検証した研究であり、植物病害状態のフェノタイピング手法が中心です。
abstractintegrating advanced deep-learning for automated diagnosis and fungicide advisory
Reproduction assets foundThe paper explicitly states that the complete implementation (model training, preprocessing, evaluation, Grad-CAM visualization) and the final trained VGG16 model are publicly available on GitHub, and the deployed Streamlit DSS is publicly accessible. The Scribd link is a cited prior-work bulletin, not a paper-specificCode · publicthe complete implementation, including model training, preprocessing, evaluation, and Grad-CAM visualization, along with deployment instructions, is publicly available at: https://github.com/anuragd02/NCLB-VGG16-Detection.Open asset ↗anuragd02/NCLB-VGG16-Detectionhtml-lines:133-143Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Plant disease and pest surveillance is undergoing a profound technological transition. Conventional crop protection has historically depended on episodic field scouting, expert visual inspection, and broad-spectrum preventative spraying, all of which are constrained by labour intensity, uneven diagnostic accuracy, and weak temporal resolution. In contrast, recent advances in artificial intelligence, deep learning, the Internet of Things, remote sensing, and edge computing have enabled crop-health monitoring systems that are more continuous, data-rich, and spatially explicit. This review analyses the evolution of AI-driven plant disease and pest surveillance, with particular attention to how image-based deep learning, connected environmental sensing, unmanned aerial vehicle platforms, cloud-edge infrastructures, and multimodal analytics are reshaping next-generation crop protection. The article argues that the central innovation is not merely automated diagnosis, but the emergence of surveillance ecosystems capable of recognising symptoms, estimating risk, localising hotspots, and informing more selective intervention. The review synthesises major developments in convolutional neural networks, object detection, semantic segmentation, transfer learning, domain adaptation, transformer-based computer vision, anomaly detection, environmental time-series modelling, and multimodal analytics. It also evaluates the practical obstacles that still limit real-world deployment, including dataset bias, annotation uncertainty, poor cross-domain generalisation, limited interoperability, energy and connectivity constraints, weak model explainability, and uneven economic accessibility. The article further considers how AI-based surveillance may strengthen integrated pest management by supporting earlier warning, more precise treatment timing, reduced blanket pesticide use, and stronger alignment between biological risk and management action. It concludes that the future of crop protection will depend less on isolated improvements in benchmark accuracy and more on the development of trustworthy, scalable, and biologically meaningful surveillance systems that can support sustainable decisions under real agricultural conditions.
Why it matches plant phenotyping methods植物病害の症状認識・リスク推定・ホットスポット局在化を行う画像解析、センサー、UAV、マルチモーダル手法を中心にレビューしており、植物の病害状態を推定するフェノタイピング手法レビューに該当する。
abstractThis review analyses the evolution of AI-driven plant disease and pest surveillance, with particular attention to how image-based deep learning, connected environmental sensing, unmanned aerial vehicle platforms, cloud-edge infrastructures, and multimodal analytics are reshaping next-generation crop protection.
Conventional two-dimensional image-based methods are limited in measuring the three-dimensional morphology of tobacco stems, especially thickness and curved geometry. This study proposes a point-cloud-based method for three-dimensional tobacco stem measurement using a dual-laser scanning system. The method combines improved centerline skeleton extraction, upper–lower surface registration, and skeleton-guided cross-sectional analysis to estimate length, width, thickness, and fineness. Adaptive neighborhood re-weighting and curvature-constrained regularization are introduced to improve skeleton extraction, and reference-assisted registration is used to support thickness measurement. For a standard gauge block, the proposed method achieved mean absolute errors below 0.009 mm and root mean square errors below 0.011 mm for length, width, and thickness measurements. Validation on 30 tobacco stem samples showed good agreement with the YC image-based method for length and width, with correlation coefficients of 0.998 and 0.997, respectively. The results demonstrate the feasibility of thickness-aware three-dimensional morphological measurement of tobacco stems under the tested conditions.
Why it matches plant phenotyping methodsタバコ茎の長さ・幅・厚さ・細さという植物形態形質を、点群・レーザースキャン・骨格抽出で測定する手法の開発と検証が研究の中心である。
abstractThis study proposes a point-cloud-based method for three-dimensional tobacco stem measurement using a dual-laser scanning system.
Unmanned aerial vehicles (UAVs) are broadly used for high-throughput plant phenotyping, yet their long-term use in public-sector research is increasingly challenged by regulatory restrictions and reliance on proprietary platforms. This study presented a regulation-compliant, modular multi-sensor unmanned aerial system (UAS) designed to deliver flexible, high-quality phenotyping data without dependence on restricted ecosystems. A dual-mount, open-architecture payload integrated RGB, multispectral, and thermal sensors, enabling simultaneous acquisition of structural, spectral, and thermal information within a unified workflow. Field validation in a lantana (Lantana camara) breeding trial demonstrated high-precision multi-sensor data fusion and reliable trait extraction. Spatial co-registration achieved centimeter-level accuracy, with alignment errors of 0.88 cm (multispectral) and 3.23 cm (thermal) relative to the RGB reference. UAV-derived canopy height closely matched ground measurements (R2 up to 0.98; RMSE as low as 1.57 cm), while canopy coverage estimates showed consistency across sensing modalities (R2 = 0.99; RMSE = 0.02 m2). Calibrated thermal orthomosaics provided robust canopy temperature estimation (RMSE = 3.13 °C), supporting a quantitative assessment of plant physiological status. Together, these results demonstrate that a regulation-compliant, open-architecture UAV platform can achieve high accuracy in multi-modal phenotyping while maintaining flexibility and cost efficiency. This work demonstrates a scalable and sustainable framework for UAV-based phenotyping, enabling researchers to adapt to evolving regulations while advancing data-driven crop improvement.
Why it matches plant phenotyping methods植物フェノタイピング用のマルチセンサーUAVプラットフォームを設計・検証し、植物形質の抽出精度を評価しているため、方法が中心的である。
abstractThis study presented a regulation-compliant, modular multi-sensor unmanned aerial system (UAS) designed to deliver flexible, high-quality phenotyping data without dependence on restricted ecosystems.
This study proposes the Hydroponic Plant Growth Analysis System (HPGAS), a public-data-based preliminary framework for multimodal plant growth state analysis toward future filter-free aquaponic validation. The HPGAS integrates plant images, water quality signals, and environmental signals to estimate an image-centered growth index, growth stage, and proxy abnormal state probability. Because no public dataset jointly provides plant images, direct growth labels, fish metabolic variables, suspended solids, and nitrification-related measurements from a real filter-free aquaponic system, this study is not a direct operational validation. A two-stage evaluation was conducted using the Autonomous Greenhouse Challenge (AGC), HydroGrowNet, and two aquaponic Internet of Things (IoT) water quality datasets. Stage 1 implemented dataset loaders, image–sensor alignment, proxy label generation, and unimodal and fusion baselines. Stage 2 expanded handcrafted image and sensor-context features and adopted month-wise hold-out evaluation. The image-only model achieved the best growth index regression performance, with a root mean square error (RMSE) of 0.0492 ± 0.0187, whereas the fusion model showed a RMSE of 0.0837 ± 0.0196. Conversely, the fusion model achieved the best proxy abnormal state classification performance, with a F1 score of 0.9695 ± 0.0057 under the clean condition, decreasing to 0.9232 ± 0.0263 under sensor dropout and 0.9132 ± 0.0169 under image noise. Under sensor dropout, the fusion model was more stable than the sensor-only model, whereas under image noise it degraded more than the image-only model. These results indicate that multimodal fusion is most useful for proxy abnormal state classification and robust state interpretation, rather than universally superior scalar growth regression. The HPGAS provides a reproducible baseline for future real filter-free aquaponic experiments, while its operational validity remains to be tested using real filter-free aquaponic data.
Why it matches plant phenotyping methods植物画像とセンサーデータを統合し、成長指数・成長段階・異常状態確率を推定する再現可能な解析フレームワークを開発・評価しており、植物表現型の取得・推定手法が中心である。
abstractThis study proposes the Hydroponic Plant Growth Analysis System (HPGAS), a public-data-based preliminary framework for multimodal plant growth state analysis
Three-dimensional (3D) phenotyping of plants plays a crucial role for understanding plant growth, yield prediction, and disease control. We present a pipeline capable of generating high-quality 3D reconstructions of individual agricultural plants. To acquire data, a small commercially available Unmanned aerial vehicle (UAV) captures images of a selected plant. Apart from placing ArUco markers, the entire image acquisition process is fully autonomous, controlled by a self-developed Android application running on the drone's controller. The reconstruction task is particularly challenging due to environmental wind and downwash of the UAV. Our proposed pipeline supports the integration of arbitrary state-of-the-art 3D reconstruction methods. To mitigate errors caused by leaf motion during image capture, we use an iterative method that gradually adjusts the input images through deformation. Motion is estimated using optical flow between the original input images and intermediate 3D reconstructions rendered from the corresponding viewpoints. This alignment gradually reduces scene motion, resulting in a canonical representation. After a few iterations, our pipeline improves the reconstruction of state-of-the-art methods and enables the extraction of high-resolution 3D meshes.
Why it matches plant phenotyping methodsUAV画像から植物個体の高解像度3D形状を再構成する手法を開発しており、植物フェノタイピングの取得・抽出方法が研究の中心である。
abstractWe present a pipeline capable of generating high-quality 3D reconstructions of individual agricultural plants.
To address the issue of 3D reconstruction information loss caused by occlusion during single-view camera acquisition of crop phenotypic parameters, this study proposes a detection method for tomato plant phenotypic parameters based on multi-view 3D point cloud reconstruction. The Kinect 2.0 sensor was employed to acquire point cloud data of tomato plants from three different viewpoints. Background noise was effectively removed using a combination of Conditional Filtering and Statistical Outlier Removal methods. By extracting surface normal features and calculating Fast Point Feature Histograms (FPFH), the Sample Consensus Initial Alignment (SAC-IA) and Iterative Closest Point (ICP) algorithms were utilized to accomplish coarse and accurate registration of the point clouds, respectively, ultimately achieving 3D reconstruction. Experimental results demonstrated that the reconstructed 3D model of the tomato plant was clear in outline and complete in structure. For the phenotypic parameters of plant height, canopy width, and leaf angle, the coefficients of determination (R²) between the calculated and manually measured values were 0.98, 0.94, and 0.89, respectively, with Root Mean Square Errors (RMSE) of 0.75 cm, 1.10 cm, and 4.43 °. Compared to single-view measurements, the accuracy of plant height and maximum canopy width derived from multi-view reconstruction increased by 15.31% and 13.12%, respectively. This method provides technical support for the rapid and accurate extraction of phenotypic parameters in tomato plants.
Why it matches plant phenotyping methodsトマトの草丈、キャノピー幅、葉角を抽出するマルチビュー3D点群再構成法を開発し、手動測定との精度検証も行っており、植物表現型取得が研究の中心である。
abstractthis study proposes a detection method for tomato plant phenotypic parameters based on multi-view 3D point cloud reconstruction.
Abstract 3D Gaussian Splatting (3DGS) [KKLD23] has transformed novel‐view synthesis from RGB images, yet remains restricted to the visible spectrum. Many applications, including agricultural monitoring, rely on multi‐spectral imaging, where spectral camera alignment and scalability pose major challenges. We present MS‐Splatting—a multi‐spectral 3DGS framework enabling unified multi‐view consistent reconstruction and rendering across both visible and invisible spectra. Our key component is a neural color representation that encodes per‐primitive features shared across spectral bands, decoded through a shallow multi‐layer perceptron into spectrum‐specific radiance. By leveraging inter‐band correlations, this formulation enhances detail while reducing memory consumption compared to independent band modeling via per‐channel modeling with spherical harmonics. Our method enables accurate parallax‐free novel‐view vegetation index rendering for plant monitoring and enhances RGB novel view synthesis quality by exploiting details revealed through multi‐spectral bands. Our evaluation demonstrates that MS‐Splatting exceeds the current leading methods in both categories. In addition, we introduce a multi‐spectral dataset from aerial captures covering outdoor environments, specifically designed for evaluating these applications. We will release our code and dataset to facilitate further research. The project page is located at: https://meyerls.github.io/ms_splatting
Why it matches plant phenotyping methodsマルチスペクトル3D再構成法を開発し、植物モニタリング用の植生指数レンダリングを実現することが中心で、評価用データセットも提供している。
abstractWe present MS‐Splatting—a multi‐spectral 3DGS framework enabling unified multi‐view consistent reconstruction and rendering across both visible and invisible spectra.
Image / point-cloud registrationGrowth / development / phenology
The increasing complexity and volume of plant phenotypic data have driven the emergence of new computational and standardization frameworks to enable data integration, reproducibility, and reuse. This systematic literature review examines the current state of software tools, data models, and interoperability standards in plant phenomics, focusing on the implementation of the FAIR (Findable, Accessible, Interoperable, Reusable) principles. Using a structured PRISMA-based methodology, we analyze two major community driven initiatives MIAPPE and BrAPI as representative solutions for standardized data description and exchange. Furthermore, the study evaluates the role of High-Performance Computing (HPC) and deep learning in addressing computational challenges associated with large-scale datasets, including multi-sensor and 3D capture technologies. Special consideration is given to data governance, encompassing secure access, ethical use, and GDPR compliance within expanding phenomics ecosystems. The synthesis identifies persistent gaps in data harmonization and semantic alignment, proposing future research directions toward more integrated, secure, and scalable infrastructures. This review emphasizes that the success of plant phenomics depends on bridging the gap between standard definitions and their practical implementation within high-performance workflows.
Why it matches plant phenotyping methods植物フェノミクスのデータ標準、ソフトウェア、相互運用性を扱う方法論的レビューであり、MIAPPE・BrAPIや大規模フェノタイピング基盤が中心です。
abstractThis systematic literature review examines the current state of software tools, data models, and interoperability standards in plant phenomics
In perennial crops, inner wood degradation by pathogens often escapes detection until irreversible damage has occurred. Grapevine trunk diseases (GTD) are a well-known example in viticulture that alter plants from within, years before foliar symptoms arise, making early assessment difficult. To overcome this limitation, we present a novel non-destructive 3D + t pipeline for high-resolution Magnetic Resonance Imaging (MRI) spatial quantification and monitoring of early internal host tissue degradation resulting from fungal pathogen colonization. The pipeline integrates spatio-temporal anatomical alignment and rigid registration; a generalized cylindrical-coordinate transformation; supervised segmentation of water-depleted regions; and population-level statistical analyses, including population mean images, probabilistic atlases, and 3D lesion descriptors. Applied to multiple Vitis vinifera cultivars inoculated with a fungal wood pathogen, our approach enables in vivo time-lapse comparisons between cultivars and treatments. The results reveal reproducible early degradation signals across individuals and cultivar-dependent differences in lesion progression. Overall, this methodological innovation provides a new paradigm for internal plant phenotyping, enabling non-invasive quantification of disease development and comparative spatio-temporal assessment of host responses in woody plants, with strong potential to advance early diagnosis and management of GTDs and internal diseases.
Why it matches plant phenotyping methodsMRI画像と計算パイプラインにより、ブドウ樹内部の病変・組織劣化を非破壊かつ時空間的に定量化する手法を開発・適用しており、植物表現型取得が中心である。
abstractwe present a novel non-destructive 3D + t pipeline for high-resolution Magnetic Resonance Imaging (MRI) spatial quantification and monitoring of early internal host tissue degradation resulting from fungal pathogen colonization.
Reproduction assets foundThe paper's MRI phenotyping data (~160 GB raw, 1.4 TB processed) is only available upon request, but the authors' processing pipeline (scripts and parameters) is publicly deposited on Zenodo with an explicit URL.Code · publicThe processing pipeline (including scripts and parameters required to reproduce the processed outputs from the raw data) is available at https://doi.org/10.5281/zenodo.17944369 .Open asset ↗Zenodo · 10.5281/zenodo.17944369lines:370-484Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · checked 15 Sept 2026
Abstract Root system architecture plays a critical role in water and nutrient acquisition, particularly in semi‐arid environments where drought stress limits crop productivity. Despite advances in three‐dimensional (3D) root phenotyping, no dedicated low‐cost imaging platform currently exists for sorghum ( Sorghum bicolor (L.) Moench) in the United States. The objective of this study was to design and construct an affordable laboratory‐based 3D imaging system for sorghum root phenotyping modeled after the digital imaging of root traits (3D) framework. The system consists of a rotating aluminum frame equipped with eight high‐resolution digital cameras controlled by Raspberry Pi microcomputers, uniform LED lighting, and background reference markers to ensure accurate image alignment. Approximately 2000–3000 overlapping images are captured in under 5 min and processed using structure‐from‐motion algorithms to generate colorized 3D point clouds. The total system cost was approximately $6000, substantially lower than commercial imaging technologies such as computed tomography or magnetic resonance imaging. Initial assembly demonstrated strong geometric alignment and minimal distortion, enabling measurement of key root traits including volume, nodal root angle, and whorl spacing. This platform provides a reproducible and scalable approach for sorghum root phenotyping and addresses a critical gap in crop research tools for semi‐arid production systems. The system also offers educational value by integrating engineering design, programming, and plant science, supporting interdisciplinary training and future genotype‐phenotype studies aimed at improving drought resilience.
Why it matches plant phenotyping methodsソルガム根の形態形質を取得する低コスト3D画像プラットフォームの設計・構築が研究の中心であり、根体積や根角度などの測定法を提供している。
abstractThe objective of this study was to design and construct an affordable laboratory‐based 3D imaging system for sorghum root phenotyping modeled after the digital imaging of root traits (3D) framework.
High-fidelity acquisition of canopy phenotypic data is critical for the advancement of orchard Artificial Intelligence (AI). Yet, an improper Light Detection and Ranging (LiDAR) installation height (IH) frequently induces data occlusion and substantial measurement errors. To address this limitation, this study developed an information collection vehicle (ICV) integrated with a 16-channel three-dimensional (3D) LiDAR to determine the optimal LiDAR IH. Three representative LiDAR IHs (1.4 m, 2.0 m, and 2.6 m) were evaluated on spindle-shaped cherry trees under both forward and reverse driving strategies. Subsequently, a novel 12-zone refined evaluation framework was introduced to quantify localized errors that are conventionally obscured by traditional whole-canopy metrics. Results demonstrated a profound nonlinear relationship between IH and measurement accuracy. Specifically, the 2.0 m IH (approximating the canopy’s geometric center) emerged as the optimal setup, maintaining relative errors (REs) below 5% with minimal dispersion. Conversely, the 2.6 m IH caused lower-canopy volume REs to surge beyond 16% owing to restricted downward viewing angles. Additionally, reverse driving at higher IHs exacerbated mechanical vibrations via the “lever arm effect”, thereby significantly degrading point cloud registration accuracy. Ultimately, these findings underscore the critical necessity of aligning sensors with the canopy geometric center, supplying essential theoretical guidelines for the hardware design of future orchard robots.
Why it matches plant phenotyping methods果樹キャノピー形質の高精度取得を目的に、LiDAR搭載車両、設置高さ、走行条件、局所誤差評価法を開発・比較検証しており、フェノタイピング手法が中心である。
abstractHigh-fidelity acquisition of canopy phenotypic data is critical for the advancement of orchard Artificial Intelligence (AI).
In modern orchards, the pollination process of apple blossoms plays a crucial role in determining both the quality and yield of the fruit. While most current studies concentrate on identifying individual apple flowers, there is limited research on assessing the developmental stages of apple flowers in dynamic and complex orchard settings. Challenges arise due to the intricate environmental factors and subtle color changes in the anthers following the maturation of the apple flowers, which complicate accurate detection. To overcome these challenges, ADA-Net, an efficient YOLOv8n-based detection model, is proposed to evaluate the maturity stages of apple flowers. First, the adaptive downsampling network module replaces the conventional downsampling convolution, which reduces the size of the convolutional kernels and groups input feature mean average precision (maps). This modification helps reduce the model’s parameter count and computational complexity, while simultaneously improving detection of small targets. In addition, inspired by the task alignment technique of the task-aligned one-stage object detection (TOOD) model, a DAD Head is employed to separate the classification from localization tasks, thus minimizing task interference and improving overall accuracy. A custom apple flower dataset is used to test the model, and the results show detection accuracies of 80.7% for mature flowers and 82.4% for immature flowers, with a total model parameter count of just 1.8 million. These results offer important insights for advancing the development of automated pollination systems in orchards.
Why it matches plant phenotyping methodsリンゴ花の成熟段階という植物状態を画像から推定する軽量検出モデルを開発し、専用データセットで精度検証しているため、フェノタイピング手法が中心である。
abstractADA-Net, an efficient YOLOv8n-based detection model, is proposed to evaluate the maturity stages of apple flowers.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
We propose a lightweight Multi-Head Self-Attention (MHSA) mechanism for plant phenotypic feature extraction, which integrates cross-species transfer learning with dynamic head pruning to improve efficiency without compromising accuracy. The primary challenge stems from minimizing redundant computations without compromising the model's capacity to generalize over varied plant species, an issue intensified by the substantial dimensionality of attention mechanisms in Vision Transformers. Our solution, the Transferable Attention Head Alignment (TAHA) framework, operates in three stages: pre-training on a source species, cross-species alignment via a Domain Alignment Loss (DAL), and head pruning based on a transferability score. The framework selects and keeps solely the attention heads with the highest transferability, thus diminishing model intricacy without compromising the ability to distinguish phenotypic traits. Furthermore, the pruned MHSA module is smoothly combined with standard Transformer backbones, which makes efficient deployment on edge devices possible. Experiments were conducted on real edge hardware (Raspberry Pi 4, NVIDIA Jetson Nano) and GPU platforms, showing our approach attains accuracy similar to full-head models yet cuts computational expenses by as much as 40% (14.1 ms inference latency on Raspberry Pi 4, 519 M parameters). The method holds special importance for scalable plant phenotyping, in situations where computational capacity is frequently constrained yet generalization across species is essential. Moreover, the repeated alignment and pruning procedure permits gradual adjustment to novel species without complete retraining, which increases feasibility for agricultural applications in practical settings. Supplementary experiments on phylogenetically distant species (Arabidopsis → pine) demonstrate the framework's generalization limits, with a 7.2% F1-score drop compared to close-species transfer (Arabidopsis → maize), highlighting the need for trait-specific head adaptation in distant transfers. The proposed method improves lightweight feature extraction by merging transfer learning and attention head optimization, achieving a balanced compromise between performance and efficiency.
Why it matches plant phenotyping methods植物表現型特徴抽出のためのVision Transformer剪定・転移学習手法を開発し、複数種およびエッジデバイスで精度と計算効率を検証しており、表現型取得・抽出法が研究の中心である。
abstractWe propose a lightweight Multi-Head Self-Attention (MHSA) mechanism for plant phenotypic feature extraction
3D phenotyping of seedlings is crucial to tomato cultivation in greenhouse facilities. Current studies focus on high-quality point cloud reconstruction and artificial intelligence (AI) 3D segmentation to derive phenotypic traits like plant height and crown width, which heavily rely on manual annotation and possess high complexity in deployment. This study proposes a novel AI framework from pixels to points, for efficient 3D plant phenotyping of tomato seedlings. Through the integration of 2D-3D coordinate mapping and AI vision language models, the proposed method enables accurate reconstruction and analysis of 3D phenotypic traits from single-view data. Top-down RGB images and corresponding point clouds with spatial alignment are captured using a binocular camera. Vision language models are employed with the text prompt “plant” to automatically generate bounding boxes and masks, thereby minimizing manual annotation. These outputs are further transferred to a lightweight YOLO11-segment model. The core innovation is established in our 2D-3D mapping strategy, through which plant-specific 3D points are efficiently extracted using only 2D masks. Non-plant points within initial masks are repurposed to determine ground height for improved plant height estimation, while masks are refined using the Excess Green Index to enhance crown width measurement. An mAP₅₀ of 96.0% is achieved by the YOLO11-segment model. Concerning sparse canopy, highly accurate results are yielded by our phenotyping approach, with RMSE values of 1.7 cm for plant height and 1.0 cm for crown width, and R 2 values of 0.93 and 0.95 against manual measurements. For dense canopy, the usage of a reference chessboard improves the performance (RMSE was reduced from 9.57 cm to 2.07 cm). Annotation dependency is significantly reduced, computational complexity is decreased, edge deployment is supported, and efficient technology transfer is enabled by the presented method. Considerable potential is offered for high-throughput screening of elite tomato varieties with desirable agronomic traits. • Real-time low-cost 3D phenotyping of tomato plants is proposed. • Weak labels simplify the 3D plant segmentation. • Segment the 3D point cloud using 2D pixel-masks with spatial alignment. • Vision language models and knowledge transfer further simplify the AI application.
Why it matches plant phenotyping methodsトマト苗の3D表現型を抽出する画像・点群・AI統合手法を開発し、手動測定との精度検証も行っており、表現型取得法が研究の中心である。
abstractThis study proposes a novel AI framework from pixels to points, for efficient 3D plant phenotyping of tomato seedlings.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · OpenAlex · checked 15 Sept 2026
Accurate estimation of crop water status is essential for monitoring plant senescence and enabling intelligent agricultural management. This study proposes a pixel-aligned co-registration and DSM-grid fusion framework that integrates high-resolution point clouds, multispectral (MS) images, and thermal imagery acquired by Unmanned Aerial Vehicles (UAVs) to enable three-dimensional prediction and visualization of cotton canopy leaf water content (LWC) and equivalent water thickness (LEWT). To address the low spatial resolution of thermal imagery, a downsampling–upsampling simulation framework was developed to evaluate interpolation errors. This framework quantitatively compares three common interpolation methods—nearest neighbor, bilinear, and bicubic interpolation—using RMSE and PSNR metrics. Results show that bicubic interpolation performs best in preserving spatial details and minimizing errors, and is therefore adopted in the subsequent image fusion process. A 3D grid was constructed based on the digital surface model (DSM), enabling grid-cell (pixel-aligned) spectral and thermal features to be mapped onto point-cloud units. Vegetation and thermal indices extracted from the mapped features were used as input variables. Combined with recursive feature elimination (RFE) and random forest (RF) models, the prediction of LEWT and LWC achieved R² values of 0.792 and 0.752, and rRMSE values of 13.84% and 9.68%, respectively. These results significantly outperformed those of partial least squares regression (PLSR), support vector machine (SVM), and extreme learning machine (ELM) models. By integrating the predicted results with the point cloud data, a 3D representation of canopy water parameters was constructed, revealing a typical top-down gradient of water loss. The experiment also revealed that nitrogen treatment significantly influenced the vertical distribution of water content. High-nitrogen application delayed water loss in the middle and lower canopy layers, highlighting the coupled regulation between nitrogen and water. Parameter comparisons showed that LEWT exhibited higher sensitivity than LWC across both temporal and spatial scales, making it a more robust indicator for canopy water monitoring. Additionally, point clouds generated from Cross-circling oblique (CCO) photogrammetry outperformed UAV LiDAR systems in terms of point density, structural completeness, and image fusion potential. In summary, this study validated the feasibility and effectiveness of integrating point cloud, MS, and thermal imagery via the proposed pixel-aligned co-registration and DSM-grid fusion framework for 3D crop water monitoring. The proposed method provides a reliable technical foundation for drought detection, irrigation management, and yield prediction in precision agriculture.
Why it matches plant phenotyping methodsUAVマルチスペクトル・熱画像・点群を融合し、綿花の葉水分状態を3D推定・可視化する手法の開発と検証が研究の中心である。
abstractThis study proposes a pixel-aligned co-registration and DSM-grid fusion framework that integrates high-resolution point clouds, multispectral (MS) images, and thermal imagery acquired by Unmanned Aerial Vehicles (UAVs) to enable three-dimensional prediction and visualization of cotton canopy leaf water content (LWC) and equivalent water thickness (LEWT).
CottonAerial / UAVLiDAR / point cloudMultispectral / hyperspectralThermalLeafPhysiological trait estimation2D/3D reconstructionImage / point-cloud registrationWater status / transpiration
Accurate estimation of crop water status is essential for monitoring plant senescence and enabling intelligent agricultural management. This study proposes a pixel-aligned co-registration and DSM-grid fusion framework that integrates high-resolution point clouds, multispectral (MS) images, and thermal imagery acquired by Unmanned Aerial Vehicles (UAVs) to enable three-dimensional prediction and visualization of cotton canopy leaf water content (LWC) and equivalent water thickness (LEWT). To address the low spatial resolution of thermal imagery, a downsampling–upsampling simulation framework was developed to evaluate interpolation errors. This framework quantitatively compares three common interpolation methods—nearest neighbor, bilinear, and bicubic interpolation—using RMSE and PSNR metrics. Results show that bicubic interpolation performs best in preserving spatial details and minimizing errors, and is therefore adopted in the subsequent image fusion process. A 3D grid was constructed based on the digital surface model (DSM), enabling grid-cell (pixel-aligned) spectral and thermal features to be mapped onto point-cloud units. Vegetation and thermal indices extracted from the mapped features were used as input variables. Combined with recursive feature elimination (RFE) and random forest (RF) models, the prediction of LEWT and LWC achieved R² values of 0.792 and 0.752, and rRMSE values of 13.84% and 9.68%, respectively. These results significantly outperformed those of partial least squares regression (PLSR), support vector machine (SVM), and extreme learning machine (ELM) models. By integrating the predicted results with the point cloud data, a 3D representation of canopy water parameters was constructed, revealing a typical top-down gradient of water loss. The experiment also revealed that nitrogen treatment significantly influenced the vertical distribution of water content. High-nitrogen application delayed water loss in the middle and lower canopy layers, highlighting the coupled regulation between nitrogen and water. Parameter comparisons showed that LEWT exhibited higher sensitivity than LWC across both temporal and spatial scales, making it a more robust indicator for canopy water monitoring. Additionally, point clouds generated from Cross-circling oblique (CCO) photogrammetry outperformed UAV LiDAR systems in terms of point density, structural completeness, and image fusion potential. In summary, this study validated the feasibility and effectiveness of integrating point cloud, MS, and thermal imagery via the proposed pixel-aligned co-registration and DSM-grid fusion framework for 3D crop water monitoring. The proposed method provides a reliable technical foundation for drought detection, irrigation management, and yield prediction in precision agriculture.
Why it matches plant phenotyping methodsUAVマルチスペクトル・熱画像・点群を統合し、綿花キャノピーの水分形質を3D推定・可視化する手法の開発と検証が中心である。
abstractThis study proposes a pixel-aligned co-registration and DSM-grid fusion framework that integrates high-resolution point clouds, multispectral (MS) images, and thermal imagery acquired by Unmanned Aerial Vehicles (UAVs) to enable three-dimensional prediction and visualization of cotton canopy leaf water content (LWC) and equivalent water thickness (LEWT).
Rubber tree phenotyping is transitioning from labor-intensive manual techniques toward high-throughput intelligent sensing platforms. However, the advancement of high-throughput phenotyping remains hindered by complex canopy architectures and pronounced seasonal morphological variations. To address these challenges, this paper introduces a unified phenotyping framework that leverages a novel Wood Salient Keypoint (WSK)-based registration algorithm to achieve seamless data fusion from unmanned aerial vehicle laser scanning (ULS) and handheld laser scanning (HLS) systems. The proposed approach begins by extracting stable wooden structures through a region-of-interest (ROI) segmentation process. Repeatable WSKs are then generated using a newly proposed wood structure significance (WSS) score, which quantifies and identifies salient regions across multi-view data. For transformation estimation, descriptor matching, WSS constraints, and geometric consistency optimization are integrated into a fast global registration (FGR) pipeline. Extensive evaluation across 25 plots covering 5 sites at the National rubber plantation base in Danzhou, Hainan, China, demonstrates that the method achieves a mean co-registration accuracy of 9 cm. Further analysis under varying seasonal canopy complexities confirms its robustness and critical role in enabling high-precision rubber tree phenotyping.
Why it matches plant phenotyping methodsゴム樹の表現型取得を目的に、UAVおよびハンドヘルドLiDARのデータ融合・位置合わせ手法を開発し、複数圃場で精度と季節変動下の頑健性を評価しているため、方法が中心的である。
abstractthis paper introduces a unified phenotyping framework that leverages a novel Wood Salient Keypoint (WSK)-based registration algorithm to achieve seamless data fusion from unmanned aerial vehicle laser scanning (ULS) and handheld laser scanning (HLS) systems.
Reproduction assets foundThe authors publicly released the ULS-HLS rubber plantation point cloud dataset (25 plots, 5 sites, leaf-on/leaf-off, >400M points) used for this paper's phenotyping/registration analysis, via an explicit Data Availability Statement with a Hugging Face URL matching an allowed URL.Dataset · publicThe dataset is available at https://huggingface.co/datasets/TanJunxiang/ULS-HLS-Rubber/tree/main (accessed on 20 January 2026).Open asset ↗TanJunxiang/ULS-HLS-Rubberlines:670-670Code / dataset availability confirmedCrossref · Europe PMC · checked 14 Sept 2026
Abstract Time-resolved phenotyping of disease symptoms enables dissection of resistance mechanisms and improves diagnosis, but acquiring phenotypic data at satisfactory scale remains challenging. Advances in imaging and image processing have improved measurement precision, robustness, and throughput, but further improvements are needed for practical application. We present a data set comprising 12,520 high-resolution (~0.03 mm/pixel) RGB images representing 1,032 time series of wheat leaves with developing disease symptoms. All images are geometrically aligned with a median precision of 0.16 mm (≈5 pixels). The dataset includes transformation matrices, symptom segmentation masks, metadata on treatments, weather, crop phenology, and disease occurrence, and a lightweight Python toolkit for loading, aligning, inspecting, and editing image sequences. These resources enable detailed investigation of leaf-level disease dynamics such as lesion, pustule, and fruiting body emergence rates, lesion growth, and dynamic interactions of disease development with spatial and environmental contexts. They offer a broad basis for developing improved methods for image alignment and symptom detection, segmentation, and tracking, possibly by tackling these connected challenges within a single end-to-end framework.
Why it matches plant phenotyping methods葉の病徴を対象とした高解像度時系列画像データセットで、幾何位置合わせ、病徴セグメンテーション、追跡用ツールを提供しており、植物病害表現型の取得・解析基盤が中心である。
abstractWe present a data set comprising 12,520 high-resolution (~0.03 mm/pixel) RGB images representing 1,032 time series of wheat leaves with developing disease symptoms.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicWe provide a lightweight Python toolkit to facilitate loading, inspection, and curation of the image sequences and their associated processing products in the associated Git repository (https://github.com/and-jonas/sympathique-wheat).Open asset ↗github.com/and-jonas/sympathique-wheathtml-lines:317-337Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · checked 15 Sept 2026
Field / plotNeRF / 3D Gaussian SplattingPhotogrammetry / SfM / MVSLiDAR / point cloudLeafWhole plant / canopy / plot / field2D/3D reconstructionImage / point-cloud registrationGrowth / time-series analysisTracking
Land management and stewardship teams continue to lack the tools to capture 3D spatiotemporal insights of the ecosystems they oversee. For wildfire management at the wildland-urban interface, teams face challenges in capturing vegetation growth over time after a fuel reduction program and connecting seasonal changes to the vegetation distribution across the treated area. Current approaches rely on triangle meshes or point clouds generated from photogrammetry or LiDAR surveys on drones or hiked traverses. However, the difficulties in optimizing these meshes lead to large triangles that inadequately approximate the bulk vegetation shape, and the point cloud data is often too sparse for local plant-scale understanding. To address this gap, we extend recent machine learning-based computer graphics techniques in 3D Gaussian Splatting (3DGS) to reconstruct scenes at the wildland-urban interface from handheld imagery with sufficient detail to identify species, capture individual leaves, recover plant stature, and disambiguate overhanging plant individuals. We develop a new method to match the 3DGS reconstruction of these scenes across months, associating plant growth across seasons interactively in 3D. To achieve the centimeter-level matching, we adapt the Umeyama algorithm and the iterative closest point algorithm from point cloud maps to the 3DGS scene, leveraging the probabilistic interpretation of the 3D Gaussian data structure and robustly handling visual and geometric changes associated with vegetation phenology over time. We have applied our method to recent pile burns at Stanford’s Jasper Ridge ’Ootchamin ’Ooyakma Biological Preserve at monthly intervals. We demonstrate differences in ecological response where some piles featured the unexpected return of a rare and threatened bushmallow, and others remained more barren. This pile burn microcosm implicates the need for plant-level 3D spatiotemporal models to understand ecosystem recovery to fire mitigation practices. Please visit the project page for the spatiotemporal alignment video and more information: https://danineamati.github.io/burn-ecorecovery.github.io/
Why it matches plant phenotyping methods植物の3D画像再構成と時系列位置合わせを開発し、植物の個体・葉・草丈・成長を抽出することが中心であるため、植物フェノタイピング手法として含める。
abstractwe extend recent machine learning-based computer graphics techniques in 3D Gaussian Splatting (3DGS) to reconstruct scenes at the wildland-urban interface from handheld imagery with sufficient detail to identify species, capture individual leaves, recover plant stature, and disambiguate overhanging plant individuals.
Accurate measurement of plant height in leafy vegetables is challenging due to their short stature, high planting density, and severe canopy occlusion during later growth stages. These factors often limit the reliability of single-plant monitoring across the full growth cycle in open-field environments. To address this, we propose a multi-temporal point cloud alignment method for accurate plant height measurement, focusing on Choy Sum (Brassica rapa var. parachinensis). The method estimates plant height by calculating the vertical distance between the canopy and the ground. Multi-temporal point cloud maps are reconstructed using an enhanced Oriented FAST and Rotated BRIEF–Simultaneous Localization and Mapping (ORB-SLAM3) algorithm. A fixed checkerboard calibration board, leveled using a spirit level, ensures proper vertical alignment of the Z-axis and unifies coordinate systems across growth stages. Ground and plant points are separated using the Excess Green (ExG) index. During early growth stages, when the soil is minimally occluded, ground point clouds are extracted and used to construct a high-precision reference ground model through Cloth Simulation Filtering (CSF) and Kriging interpolation, compensating for canopy occlusion and noise. In later growth stages, plant point cloud data are spatially aligned with this reconstructed ground surface. Individual plants are identified using an improved Euclidean clustering algorithm, and consistent measurement regions are defined. Within each region, a ground plane is fitted using the Random Sample Consensus (RANSAC) algorithm to ensure alignment with the X–Y plane. Plant height is then determined by the elevation difference between the canopy and the interpolated ground surface. Experimental results show mean absolute errors (MAEs) of 7.19 mm and 18.45 mm for early and late growth stages, respectively, with coefficients of determination (R2) exceeding 0.85. These findings demonstrate that the proposed method provides reliable and continuous plant height monitoring across the full growth cycle, offering a robust solution for high-throughput phenotyping of leafy vegetables in field environments.
Why it matches plant phenotyping methods葉菜類の草丈を取得するための点群位置合わせ・地面復元・個体抽出・高さ推定手法を開発し、誤差と決定係数で検証している。植物フェノタイピング手法が研究の中心である。
abstractTo address this, we propose a multi-temporal point cloud alignment method for accurate plant height measurement
Reconstructing the three-dimensional structure of forests in complex and heterogeneous environments is a persistent challenge in forest remote sensing, particularly when integrating multi-source LiDAR datasets with varying acquisition geometries. Traditional registration methods such as the Iterative Closest Point (ICP) algorithm have shown promise but often suffer from accuracy degradation in dense canopies and understorey clutter, limiting their applicability in operational forest monitoring. To address these limitations, this study systematically evaluates the robustness of classical ICP (point-to-point and point-to-plane) in forests with different stand densities and introduces a novel segmented registration strategy that integrates canopy height stratification.Three representative forest types were analyzed—Type I (700–1100 trees/ha), Type II (1100–1400 trees/ha), and Type III (1400–1800 trees/ha)—by jointly utilizing UAV Laser Scanning (ULS) and Backpack Laser Scanning (BLS) data. Registration performance was examined across five stratified scenarios (Type 0–0 m, 0–2 m, 0–4 m, 0–6 m, and 0–8 m), reflecting varying thresholds of aboveground points. Results demonstrate that while classical ICP consistently achieved sub-meter accuracy (RMSE < 0.50 m), the point-to-plane variant induced rigid-body displacement, leading to artifacts such as ground-negative values and stem noise. In contrast, the proposed segmented strategy, which incorporates height-based filtering of ULS data, effectively suppresses interference from understory vegetation and low-canopy structures, yielding substantial gains in registration stability and precision.Notably, Type II plots achieved the highest overall registration accuracy (average RMSE: 0.27 m), while Type I plots exhibited the most pronounced relative improvement, underscoring the method’s adaptability across stand densities. Importantly, this strategy ensures consistent canopy alignment while significantly mitigating stem-related distortions and ground-level errors.By integrating multi-source LiDAR fusion with stratified height-domain constraints, this work advances beyond conventional ICP implementations, providing a scalable framework for precise forest 3D reconstruction. The findings not only refine registration methodologies for heterogeneous forest environments but also lay the groundwork for enhanced forest inventory, biomass estimation, and ecosystem monitoring at scale.
Why it matches plant phenotyping methods森林LiDARデータから樹冠・林分の3次元構造を取得するための点群登録手法を提案・評価しており、植物構造の測定基盤が中心的な貢献である。
abstractintroduces a novel segmented registration strategy that integrates canopy height stratification
Abstract Phenotyping is crucial for understanding crop trait variation and advancing research, but is currently limited by expensive, labor-intensive monitoring. New phenotypic trait monitoring methods are being proposed to reduce this so-called phenotyping bottleneck via automation. These methods are often data-driven, requiring a dataset recorded with a specific sensor and corresponding reference values for developing novel methods. To this end, we present the MuST-C (Multi-Sensor, multi-Temporal, multiple Crops) dataset, which contains field data from various sensors collected over a growing season, covering six crop species. All data was georeferenced for alignment across sensors and dates. To collect our dataset, we deployed aerial and ground robotic platforms equipped with RGB cameras, LiDARs, and multispectral cameras, aiming to capture a wide variety of modalities and observations from different viewpoints. In addition to sensor data, we also provide manually collected leaf area index and biomass reference measurements. Our dataset enables the development of novel automatic phenotypic trait estimation methods, allows comparisons across different sensors, and generalizability across crop species.
Why it matches plant phenotyping methods複数センサー・ロボットプラットフォームによる圃場フェノタイピング用データセットを構築・提供し、形質推定法の開発、センサー比較、汎化評価を可能にすることが中心的な貢献である。
abstractwe present the MuST-C (Multi-Sensor, multi-Temporal, multiple Crops) dataset
Reproduction assets foundThe paper's MuST-C multi-sensor, multi-temporal crop phenotyping dataset (RGB/multispectral images, LiDAR point clouds, LAI and biomass reference measurements) is publicly available via the authors' project webpage, and the authors' custom Python processing/loading code is publicly available on GitHub.Dataset · publicThe MuST-C dataset is available via our project webpage https://www.ipb.uni-bonn.de/data/MuST-C/or directly via the bonndata public access repository 10.60507/FK2/OX9XTM34Open asset ↗html-lines:421-440Code / dataset availability confirmedOpenAlex · Europe PMC · bioRxiv · checked 15 Sept 2026
Abstract In perennial crops, inner wood degradation by pathogens often escapes detection until irreversible damage has occurred. Grapevine trunk disease (GTD) is a well-known example in viticulture that alters plants from within, years before foliar symptoms arise, making early assessment difficult. To overcome this limitation, we present a novel non-destructive 3D + t pipeline for Magnetic Resonance Imaging (MRI) spatial quantification and monitoring of early internal tissue degradation resulting from fungal colonization. This pipeline integrates (i) anatomical alignment and rigid time-series registration of volumetric MRI scans, (ii) a generalized cylindrical coordinate transformation for cross-sectional trunk anatomy normalization, (iii) supervised classification to segment water-depleted (diseased/non-functional) regions, and (iv) population-level statistical analyses including construction of population mean images, probabilistic atlases of lesions, and 3D lesion descriptors. Applied to multiple Vitis vinifera cultivars inoculated with a fungal trunk pathogen, our approach enables time-lapse comparisons between cultivar and treatment in vivo. The results reveal consistent early degradation signals across individuals and cultivar-dependent lesion differences. By combining high-resolution MRI with advanced image processing and statistical atlas tools, this method provides a new paradigm for 3D plant phenotyping of internal disease progression. This methodological innovation allows non-invasive quantification of disease development and comparative assessment of host responses in woody plants, demonstrating its potential to advance understanding and management of GTDs.
Why it matches plant phenotyping methodsMRI画像と画像処理・統計アトラスを統合し、ブドウ樹内部の病変・組織劣化を3Dで定量化する植物フェノタイピング手法の開発が中心である。
abstractwe present a novel non-destructive 3D + t pipeline for Magnetic Resonance Imaging (MRI) spatial quantification and monitoring of early internal tissue degradation resulting from fungal colonization.
Reproduction assets foundThe paper's raw/processed MRI datasets are only available from the corresponding author upon reasonable request, but the authors' processing pipeline (scripts and parameters to reproduce processed outputs from raw data) is publicly deposited on Zenodo with an explicit DOI.Code · publiceer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made
available under a CC-BY 4.0 International license.
1 reasonable request. The processing pipeline (including scripts and parameters required to reproduce the
2 processed outputs from the raw data) is available at https://doi.org/10.5281/zenodo.17944369.
3
Plant Phenomics Page 26 of 29Open asset ↗zenodo · 10.5281/zenodo.17944369pdf-layout-page:26 lines:1-14Plant phenotyping relevance match · UnverifiedOpenAlex · checked 15 Sept 2026
Limited annotated data often constrain accurate yield prediction in underrepresented crops. To address this challenge, we developed a cross-crop deep transfer learning (TL) framework that leverages potato (Solanum tuberosum L.) as the source domain to predict sweet potato (Ipomoea batatas L.) yield using multi-temporal uncrewed aerial vehicle (UAV)-based multispectral imagery. A hybrid convolutional–recurrent neural network (CNN–RNN–Attention) architecture was implemented with a robust parameter-based transfer strategy to ensure temporal alignment and feature-space consistency across crops. Cross-crop feature migration analysis showed that predictors capturing canopy vigor, structure, and soil–vegetation contrast exhibited the highest distributional similarity between potato and sweet potato. In comparison, pigment-sensitive and agronomic predictors were less transferable. These robustness patterns were reflected in model performance, as all architectures showed substantial improvement when moving from the minimal 3 predictor subset to the 5–7 predictor subsets, where the most transferable indices were introduced. The hybrid CNN–RNN–Attention model achieved peak accuracy (R2≈0.64 and RMSE ≈ 18%) using time-series data up to the tuberization stage with only 7 predictors. In contrast, convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and bidirectional long short-term memory (BiLSTM) baseline models required 11–13 predictors to achieve comparable performance and often showed reduced or unstable accuracy at higher dimensionality due to redundancy and domain-shift amplification. Two-way ANOVA further revealed that cover crop type significantly influenced yield, whereas nitrogen rate and the interaction term were not significant. Overall, this study demonstrates that combining robustness-aware feature design with hybrid deep TL model enables accurate, data-efficient, and physiologically interpretable yield prediction in sweet potato, offering a scalable pathway for applying TL in other underrepresented root and tuber crops.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から作物収量を推定する深層転移学習法を開発し、複数モデル・予測子構成で性能を比較検証しているため、植物表現型推定法が中心である。
abstractwe developed a cross-crop deep transfer learning (TL) framework that leverages potato (Solanum tuberosum L.) as the source domain to predict sweet potato (Ipomoea batatas L.) yield using multi-temporal uncrewed aerial vehicle (UAV)-based multispectral imagery.
The Distributed System for Scientific Collections (DiSSCo) is a research infrastructure to integrate European natural science collections (NSCs) digitally. The aim is to facilitate and enhance the access, management and analysis of collection assets in one unified digital collection. The Machine Annotation Services (MAS) are essential components of DiSSCo’s Digital Specimen Architecture (DSArch). These services automate the annotation of digital objects to enable labelling and categorisation of NSC's digital assets. To further advance this, a Machine Learning as a Service (MLaaS) approach was developed which provides researchers with the access to pre-trained machine-learning models for complex tasks, such as instance segmentation and morphological analysis of datasets. MLaaS enhances the DiSSCo’s scalability and flexibility and allows the integration of machine-learning tools in close alignment with the FAIR (Findable, Accessible, Interoperable, Reusable) principles. This study employs DiSSCO's MLaaS framework for the quantitative analysis of herbarium specimens. Machine-learning models, such as Mask R-CNN and YOLO11, are comparatively applied to detect and generate the pixel-level masks of plant organs in herbarium sheets. Subsequently, these models are used to reconstruct the scale in the herbarium sheet and to calculate the surface area of identified plant organs. The determination of quantitative characteristics of plant specimens, such as measuring leaf area or the timestamp of the floral transition, opens up herbarium data for reuse in the large prognosis platforms currently developed in the framework of the Common European Data Spaces. In this way, plant trait data mobilised from natural science collections can improve the predictive capability of the vegetation model components of climate-related data spaces.
Why it matches plant phenotyping methodsハーバリウム画像から植物器官を検出・セグメンテーションし、葉面積などの形質を定量化する機械学習手法と基盤の応用が研究の中心である。
abstractThis study employs DiSSCO's MLaaS framework for the quantitative analysis of herbarium specimens.
Volume electron microscopy (vEM) provides nanometer-scale, three-dimensional imaging of cells, but applying it to plant systems remains challenging. Cell walls, large vacuoles, and tissue thickness complicate sample preparation and cryogenic imaging. Here we report a cryogenic vEM (cryo-vEM) workflow for unstained plant protoplasts that achieves volumetric imaging of whole vitrified sorghum stem protoplasts without chemical fixation, dehydration, resin embedding, or heavy-metal staining. The method integrates optimized protoplast isolation, plunge-freezing vitrification for native-state preservation, automated cryogenic focus ion beam scanning electron microscopy (cryo-FIB-SEM) slice-and-view acquisition, contrast enhancement and stack alignment, and AI-assisted human-in-the-loop 3D segmentation. Using sorghum stem protoplasts as a demonstration, the workflow captured large-volume frozen-hydrated protoplast ultrastructure, allowing visualization of major organelles, including the nucleus, mitochondria, vacuoles, ER/Golgi-like membranes, lipid bodies, and subcellular features consistent with nuclear-envelope pores. We further quantified organelle volumes and surface areas from the segmented 3D data, highlighting the potential for quantitative cellular ultrastructure analysis. This cryo-vEM workflow provides a platform for near-native structural studies of isolated plant protoplasts.
Why it matches plant phenotyping methods植物プロトプラストの三次元画像取得・セグメンテーション・オルガネラ形態量化を中核とする手法開発であり、植物の細胞形態形質を抽出するため。
abstractHere we report a cryogenic vEM (cryo-vEM) workflow for unstained plant protoplasts that achieves volumetric imaging of whole vitrified sorghum stem protoplasts
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · public369 The codes are freely available at https://github.com/xzhang0123/vEMOpen asset ↗https://github.com/xzhang0123/vEM · xzhang0123/vEMpdf-page:10 lines:1-24Plant phenotyping relevance match · UnverifiedOpenAlex · checked 15 Sept 2026
Published10 Dec 2025ISPRS Open Journal of Photogrammetry and Remote SensingCited by 3 · OpenAlex ↗
Light drones provide a cheap and effective tool to monitor forest canopy, especially in tropical and equatorial contexts, where infrastructure and resources are limiting. In these regions, good quality optical satellite images are rare, yet the stakes are maximal to characterize forest function, dynamics, diversity, and phenology, and more generally the vegetation-climate interplay. We describe a complete processing chain based on photogrammetric tools that seeks to optimize the spatial and spectral coherence between repeat image mosaics at centimetric resolution. Our target is to allow individual tree-level monitoring over tens to hundreds of hectare scales with consumer grade equipment (i.e., quadcopter with stabilized RGB camera, standard GNSS positioning). We demonstrate the increase in spatial accuracy achieved using Time-SIFT and Arosics algorithms, which allow (individually and synergistically) to reduce global and local spatial misalignment between mosaics from several meters to a few centimeters. Time-SIFT provides the advantage of increased robustness in initial image alignment and 3D reconstruction, and hence reduces occasional distortions or data gaps. Using Agisoft's color and white balance corrections combined with the use of vegetation indices provides meaningful quantitative signal despite considerable changes in acquisition conditions. In particular, indices that are less sensitive to illumination changes, like the green chromatic coordinate (GCC), allowed evidencing a seasonal signal over four years of monitoring in the evergreen moist forest at Paracou in French Guiana. The signal was decorrelated from obvious geometrical effect (sun height), and provided information on the vegetative stage at tree, species, and stand levels.
Why it matches plant phenotyping methodsドローン画像のステレオフォトグラメトリ処理チェーンを開発・検証し、個体樹木レベルで植生状態や季節変動を定量化する方法を中心的に扱っている。
abstractWe describe a complete processing chain based on photogrammetric tools that seeks to optimize the spatial and spectral coherence between repeat image mosaics at centimetric resolution.
With the continuous progress in micro-optical machine technology, miniature spectral imaging devices have been rapidly developed; however, three-dimensional (3D) imaging measurement technology has become increasingly mature and widely used. The evolution of these technologies has established a robust foundation for the integration of three-dimensional imaging and spectral information. To achieve accurate alignment between 3D data and spectral information to obtain a more comprehensive spectral representation of objects in 3D space, we developed a binocular multispectral stereo imaging (BMSI) system. This system acquires images in synchrony with a binocular multispectral imager, thereby ensuring accurate alignment between 3D data and spectral data at the pixel level and facilitating the construction of a four-dimensional (4D) dataset. The segmentation of leaf regions from shadow backgrounds in two distinct plant species was achieved through optimal band fusion and hue-saturation value (HSV) color space transformation, significantly improving the segmentation accuracy, processing efficiency, and robustness across different plant species. A systematic evaluation was conducted to quantify the reconstruction precision and system stability at different measurement distances. The designed system acquired 4D image spectral data with plants as the objects to be tested. The distribution characteristics of chlorophyll (Chl) on the 3D surface of plants were obtained by first-order derivatives of the spectral data and the normalized difference red edge (NDRE) index. This technique provides a new means for plant phenotyping research and a more effective technical approach for the digitalization and precision monitoring of the agricultural industry.
Why it matches plant phenotyping methods植物の3D・マルチスペクトル画像取得、葉領域分割、再構成精度・安定性評価を中核とする新規フェノタイピングシステムの開発研究である。
abstractwe developed a binocular multispectral stereo imaging (BMSI) system.
Reproduction assets foundThe paper's data availability statement explicitly deposits raw data and essential source code for the BMSI plant phenotyping analysis on a public GitHub repository.Code · publicThe raw data and the essential parts of the source code have been uploaded to Github: https://github.com/wwxsoul1234/BMSI/tree/master.Open asset ↗wwxsoul1234/BMSI · BMSIhtml-lines:278-306Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Dec 2025Computers and Electronics in Agriculture.
We present the first application of geometry-based relationship constraints for point-cloud registration and unsupervised 3D reconstruction of tree structure in semi-arid forest using unmanned aerial vehicle (UAV) photogrammetry. Accurate three-dimensional (3D) reconstruction of tree structure is essential for a plethora of subsequent tasks like assessing ecosystem health and informing sustainable forest management strategies, in particular over ecologically sensitive arid and semi-arid ecosystems that increasingly face decline due to prevalence of environmental stressors. This highlights the need for high-resolution geospatial monitoring approaches. While UAV-based photogrammetry offers a flexible and cost-effective means of capturing forest structure, conventional top-of-canopy imaging fails to sufficiently represent critical under-canopy features, including stem morphology and lower crown structure. Here, we suggest an integrated 3D reconstruction framework that combines dual-layer UAV photogrammetry, acquiring data from both above and below the canopy, with an innovative geometry-based point cloud registration method. Unlike conventional approaches like Iterative Closest Point (ICP) and Random Sample Consensus (RANSAC), this method leverages spatial relationships among individual trees to robustly align multi-view point clouds acquired under occluded and variable conditions. To further refine the reconstructed tree models, we suggest an updated unsupervised Generative Adversarial Network (Denoise-GAN), enabling both noise reduction and structural completion without reliance on labeled training data. The resulting models were used to extract key phenotypic features with high accuracy compared to reference data (root collar diameter (DRC) R² = 0.93, height R² = 0.97,Crown area R² = 0.99, number of stems R² = 1), providing vital indicators for quantifying forest structure and health. The presented methodology not only enhances the completeness and accuracy of 3D tree reconstruction in semi-arid forest, but also represents a significant advancement toward a scalable, data-driven semi-arid forest monitoring system. This workflow offers substantial potential for ecological applications, particularly in degraded and topographically complex ecosystems.
Why it matches plant phenotyping methodsUAV画像からの3D樹木再構成、点群登録、ノイズ除去・構造補完を開発し、樹木形質の抽出精度を検証しているため、植物フェノタイピング手法が中心である。
abstractWe present the first application of geometry-based relationship constraints for point-cloud registration and unsupervised 3D reconstruction of tree structure in semi-arid forest using unmanned aerial vehicle (UAV) photogrammetry.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · bioRxiv · checked 6 Sept 2026
Abstract Recent advances in unmanned aerial vehicles (UAVs) and multispectral sensor technologies have transformed high-throughput phenotyping as an efficient alternative to traditional approaches. In this study, we employed UAV-based multispectral imaging to monitor early-stage drought stress in wheat. A panel of 221 historical spring wheat cultivars from Pakistan, representing over a century of breeding history, were evaluated under irrigated and drought conditions. UAV flights were conducted twice at early growth stages to capture multispectral imagery, which was processed in Pix4D mapper for image alignment and orthomosaic generation. Plot segmentation and trait extraction were performed in QGIS. Eight drought-responsive vegetative indices (VIs) were analyzed to assess genotypic variation. Significant to highly significant differences were observed among genotypes, treatments, and their interactions across all VIs. Broad-sense heritability estimates were moderate to high for most traits, with predominantly additive gene action. Vegetative indices such as NDVI, GNDVI, EVI, and SAVI showed strong correlations with each other and effectively detected early canopy stress under drought. Principal component analysis based on 23.897K SNPs indicated a mixed genetic population. Genome-wide association studies identified 115 significant QTNs linked to VIs under both conditions, corresponding to 74 loci, including 26 pleiotropic loci. Of these, 10 pleiotropic loci detected under drought were annotated and six putative candidate genes were identified which showed expression in multiple tissues based on transcriptome data. Two genes i.e., TraesCS1D01G217600.1 ( HSP70 ) and TraesCS6D01G254000.1 ( ZmMDAR3 ), showed differential expression pattern among control and drought treatment. These findings highlight the potential of UAV-based phenotyping for early drought detection and provide candidate genes for improving drought tolerance in wheat. Future research should focus on the functional roles of these genes under drought stress.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から植生指数を抽出し、コムギの干ばつストレスという植物状態を評価するフェノタイピング手法が研究の主要な基盤であり、単なる補助的測定ではない。
abstractUAV-based multispectral imaging to monitor early-stage drought stress in wheat
This work demonstrates the use of optical coherence tomography (OCT) for studying a plant’s long-range signaling in real time, in vivo , and non-invasively. This feat is achieved using OCT as a novel technique to visualize minute cellular displacements and deformations within the plant’s leaves. The use of bespoke registration algorithms enables tracking displacements with a precision greater than 0.1 μm. This measurement precision is one order of magnitude better than the typical ~1-μm optical resolution of OCT images. In the present work, OCT is used to analyze the time evolution of deformations incurred by wounding. The use of OCT enabled to 1) visualize, in real time, the propagation and evolution of the morphological changes associated with slow wave potentials (onset, peak, and recovery); 2) compute propagation speeds (~0.07 cm s −1 ); and 3) distinguish the type of deformation incurred (transient bending of the leaf due to changes in turgor cell pressure). This proof-of-concept study thus exemplifies the potential of OCT as a convenient and complementary tool to study the plant’s response mechanisms in vivo and in real time.
Why it matches plant phenotyping methodsOCT画像と登録アルゴリズムを用いて葉内の微小変位・形態変形を非侵襲的に取得・定量する手法が研究の中心であり、植物表現型の測定法として明確に該当する。
abstractThis work demonstrates the use of optical coherence tomography (OCT) for studying a plant’s long-range signaling in real time, in vivo , and non-invasively.
In facility horticultural production, intelligent disease recognition and precise intervention are vital for crop health and economic efficiency. We construct a multi-source dataset from Bayan Nur, Weifang, and Honghe that integrates handheld camera photos, drone field images, and laboratory-controlled samples. Handheld images capture fine lesion texture for close-up diagnosis common in greenhouses; drone images provide canopy-scale patterns and spatial context suited to open-field management; laboratory images offer controlled illumination and background for stable supervision and cross-crop feature learning. Our objective is robust cross-crop, cross-regional diagnosis and economically rational control. To this end, a model named CCGD-Net is proposed. It is designed as a multi-task framework. The framework incorporates a multi-scale perception module (MSFE) to produce hierarchical representations. It includes a cross-domain alignment module (CDAM) that reduces distribution shifts between greenhouse and open-field environments. The training follows an unsupervised domain adaptation setting that uses unlabeled target-region images. When such images are not available, the model functions in a pure generalization mode. The framework also integrates a regional economic strategy module (RESM) that transforms recognition outputs and local cost information into optimized intervention intensity. Experiments show an accuracy of 91.6%, an F1-score of 89.8%, and an mAP of 88.9%, outperforming Swin Transformer and ConvNeXt; removing RESM reduces F1 to 87.2%. In cross-regional testing (Weifang training → Honghe testing), the model attains an F1 of 88.0% and mAP of 86.5%. These results indicate that integrating complementary imaging modalities with domain alignment and economic optimization provides an effective solution for disease diagnosis across greenhouse and field systems.
Why it matches plant phenotyping methods植物病斑・冠層画像から病害状態を推定するマルチモーダル深層学習法を開発し、データセット、ドメイン適応、交差地域検証を含むため、植物フェノタイピング手法が中心である。
abstractWe construct a multi-source dataset from Bayan Nur, Weifang, and Honghe that integrates handheld camera photos, drone field images, and laboratory-controlled samples.
Amid growing challenges to global food security, high-throughput crop phenotyping has become an essential tool, playing a critical role in genetic improvement, biomass estimation, and disease prevention. Unlike controlled laboratory environments, field-based phenotypic data collection is highly vulnerable to unpredictable factors, significantly complicating the data acquisition process. As a result, the choice of appropriate data collection equipment and processing methods has become a central focus of research. Currently, three key technologies for extracting crop phenotypic parameters are Light Detection and Ranging (LiDAR), Multi-View Stereo (MVS), and depth camera systems. LiDAR is valued for its rapid data acquisition and high-quality point cloud output, despite its substantial cost. MVS offers the potential to combine low-cost deployment with high-resolution point cloud generation, though challenges remain in the complexity and efficiency of point cloud processing. Depth cameras strike a favorable balance between processing speed, accuracy, and cost-effectiveness, yet their performance can be influenced by ambient conditions such as lighting. Data processing techniques primarily involve point cloud denoising, registration, segmentation, and reconstruction. This review summarizes advances over the past five years in 3D reconstruction technologies—focusing on both hardware and point cloud processing methods—with the aim of supporting efficient and accurate 3D phenotype acquisition in high-throughput crop research.
Why it matches plant phenotyping methods作物キャノピーの3D形質取得に用いるLiDAR、MVS、深度カメラと点群処理を中心に扱うレビューであり、植物フェノタイピング手法が主題。
titleApplications of 3D Reconstruction Techniques in Crop Canopy Phenotyping: A Review
Point cloud registration is a critical technology for 3D reconstruction and personalized management of fruit trees. While ensuring the accuracy and completeness of 3D point cloud reconstruction, the simplest and most efficient approach is to acquire and register point clouds from two stations separated by 180°. For this, we propose BranchMatch, a low-overlap viewpoints acquisition and registration method tailored for tall-spindle individual apple trees during dormancy. The method requires only two point clouds captured from stations 180° apart. Then, it leverages key branch segments in a single viewpoint, utilizing their spatial and geometric structure features in combination with a dynamically weighted feature discriminant function to perform feature matching and initial rigid-body transformation under low overlap conditions. Subsequently, an iterative closest point algorithm, enhanced with local feature matching optimization based on the tree-specific point cloud, is applied to refine the registration and prevent over-registration. Experiments conducted on multiple individual apple trees with two low-overlap point clouds (180° apart) demonstrate a registration success rate of 90%. Compared to the spherical markers registration method, BranchMatch achieves average rotation and translation errors of 1.93 mrad and 4.33 mm, respectively, with a pointwise error of 2.70 mm. Furthermore, compared to multi-site high-overlap registration methods under similar conditions, BranchMatch significantly reduces computational costs while maintaining registration accuracy and reconstruction completeness, highlighting its efficiency and reliability in individual tree registration.
Why it matches plant phenotyping methods個体リンゴ樹の3D点群取得・登録・再構成を目的とする手法を開発し、複数樹体で成功率と誤差を検証しており、植物形態・樹体構造のフェノタイピング基盤として中心的です。
abstractwe propose BranchMatch, a low-overlap viewpoints acquisition and registration method tailored for tall-spindle individual apple trees during dormancy.
Accurate 3D phenotyping of agricultural produce remains challenging due to the trade-off between reconstruction quality and acquisition throughput in existing sensing technologies. While RGB-D cameras enable high-throughput scanning in operational settings like harvesting conveyors, they produce incomplete, low-quality 3D models. Conversely, close-range Structure-from-Motion (SfM) produces high-quality reconstructions but is not suitable for high-throughput field application. This study bridges this gap through 3DPotatoTwin , a paired dataset containing 339 tuber samples across three cultivars collected in Hokkaido, Japan. Our dataset uniquely combines: (1) conveyor-acquired RGB-D point clouds, (2) ground measurement, (3) SfM reconstructions under indoor controlled environment, and (4) aligned model pairs with transformation matrices. The multi-sensory alignment employs an semi-supervised pin-guided pipeline incorporating single-pin extraction and referencing, cross-strip matching, and binary-color-enhanced ICP, achieving 0.59 ± 0.11 mm registration accuracy. Beyond serving as a benchmark for 3D phenotyping algorithms, the dataset enables training of 3D completion networks to reconstruct high-quality 3D models from partial RGB-D point clouds. Meanwhile, the proposed semi-automated annotation pipeline has the potential to accelerate 3D dataset generation for similar studies. The presented methodology demonstrates broader applicability for multi-sensor data fusion across crop phenotyping applications. The dataset and pipeline source code are publicly available at HuggingFace and GitHub, respectively.
Why it matches plant phenotyping methodsジャガイモ塊茎の3D表現型計測を対象に、RGB-D・SfM・地上計測を統合したデータセット、位置合わせパイプライン、ベンチマークを開発しており、表現型取得手法が中心である。
abstractAccurate 3D phenotyping of agricultural produce remains challenging due to the trade-off between reconstruction quality and acquisition throughput in existing sensing technologies.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicAll the batch processing scripts mentioned in this section were provided in the 3dscan folder at Github (https://github.com/UTokyo-FieldPhenomics-Lab/PotatoScan/).Open asset ↗UTokyo-FieldPhenomics-Lab/PotatoScanhtml-lines:119-131Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Oct 2025Computers and Electronics in Agriculture.
Accurate estimation of comprehensive traits such as yield and quality is crucial for optimizing agricultural management practices across the tomato industry chain. Traditional manual methods are time-consuming, labor-intensive, and prone to errors, reducing estimation accuracy. In contrast, modern intelligent estimation approaches based on multi-temporal spatial and spectral feature fusion offer improved efficiency and accuracy but still face challenges such as non-generalizable segmentation models, asynchronous feature extraction and weak correlations. This study proposes a novel pipeline for estimating yield and quality of greenhouse tomatoes using temporal semantic multispectral (TSM) point clouds. An unsupervised deep learning model was designed to register RGB-D images and multispectral (MS) images collected by an unmanned ground vehicle (UGV) plant phenotyping platform. The digital number (DN) point clouds of tomato organs were reconstructed based on the masks predicted by SegFormer with fusion of multispectral and depth modalities (MSD-SF). These point clouds were then radiometrically calibrated using neural reference field with sparse viewpoints (NeREF-S) to generate accurate reflectance point clouds. Finally, multi-temporal spatial-spectral features of tomatoes were extracted from the TSM point clouds, and random forest regression models were developed to estimate traits such as fruit flavor preference, water content, brix, acidity, brix-to-acid ratio, vitamin C content, single-fruit mass, and single-plant yield. The image registration model achieved high accuracy on the test set, with average structural similarity index measure, peak signal-to-noise ratio and learned perceptual image patch similarity of 0.238, 13.116 dB, and 0.374, respectively. The MS point clouds calibrated by NeREF-S significantly improved the signal-to-noise ratio to 11.56 dB. The average rRMSE for all trait estimations was 9.03 %. The results indicate that the proposed estimation method is efficient and accurate, holding promise to become a new paradigm for estimating the comprehensive traits of greenhouse tomatoes.
Why it matches plant phenotyping methods温室トマトの収量・品質形質を推定するため、UGVフェノタイピングプラットフォーム、マルチスペクトル点群生成、画像登録・放射較正、特徴抽出および回帰推定パイプラインを中心的に開発・評価している。
abstractThis study proposes a novel pipeline for estimating yield and quality of greenhouse tomatoes using temporal semantic multispectral (TSM) point clouds.
The use of multiple camera technologies in a combined multimodal monitoring system for plant phenotyping offers promising benefits. Compared to configurations that rely on a single camera technology, cross-modal patterns can be recorded that allow a more comprehensive assessment of plant phenotypes. However, the effective utilization of cross-modal patterns depends on image registration to achieve pixel-precise alignment - a challenge often complicated by parallax and occlusion effects inherent in plant canopy imaging. In this study, we propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process. By leveraging depth data, our method mitigates parallax effects, facilitating more accurate pixel alignment across camera modalities. Additionally, we introduce an automated mechanism to identify and differentiate various types of occlusions, thereby minimizing registration errors. To evaluate the efficacy of our approach, we conduct experiments on a diverse dataset comprising six distinct plant species with varying leaf geometries. Our results demonstrate the robustness of the proposed registration algorithm, showcasing its ability to achieve accurate alignment across different plant types and camera compositions. Compared to previous methods our approach is not reliant on detecting plant-specific image features, making it suitable for a wide range of applications in plant sciences. Moreover, the registration approach can scale to arbitrary numbers of cameras with varying resolutions and wavelengths. Overall, our study contributes to advancing the field of plant phenotyping by offering a robust and reliable solution for multimodal image registration.
Why it matches plant phenotyping methods植物フェノタイピング向けのマルチモーダル3D画像位置合わせ手法を開発し、複数植物種のデータセットで性能評価しているため、方法が研究の中心である。
abstractIn this study, we propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process.
The use of multiple camera technologies in a combined multimodal monitoring system for plant phenotyping offers promising benefits. Compared to configurations that rely on a single camera technology, cross-modal patterns can be recorded that allow a more comprehensive assessment of plant phenotypes. However, the effective utilization of cross-modal patterns depends on image registration to achieve pixel-precise alignment - a challenge often complicated by parallax and occlusion effects inherent in plant canopy imaging. In this study, we propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process. By leveraging depth data, our method mitigates parallax effects, facilitating more accurate pixel alignment across camera modalities. Additionally, we introduce an automated mechanism to identify and differentiate various types of occlusions, thereby minimizing registration errors. To evaluate the efficacy of our approach, we conduct experiments on a diverse dataset comprising six distinct plant species with varying leaf geometries. Our results demonstrate the robustness of the proposed registration algorithm, showcasing its ability to achieve accurate alignment across different plant types and camera compositions. Compared to previous methods our approach is not reliant on detecting plant-specific image features, making it suitable for a wide range of applications in plant sciences. Moreover, the registration approach can scale to arbitrary numbers of cameras with varying resolutions and wavelengths. Overall, our study contributes to advancing the field of plant phenotyping by offering a robust and reliable solution for multimodal image registration.
Why it matches plant phenotyping methods植物フェノタイピング向けのマルチモーダル3D画像位置合わせ手法を開発・評価しており、表現型取得ワークフローの技術的中心である。
abstractwe propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 6 Sept 2026
Introduction: Accurate 3D reconstruction is essential for plant phenotyping. However, point clouds generated directly by binocular cameras using single-shot mode often suffer from distortion, while self-occlusion among plant organs complicates complete data acquisition. Methods: To address these challenges, this study proposes and validates an integrated, two-phase plant 3D reconstruction workflow. In the first phase, we bypass the integrated depth estimation module on camera and instead apply Structure from Motion (SfM) and Multi-View Stereo (MVS) techniques to the captured high-resolution images. It produces high-fidelity, single-view point clouds, effectively avoiding distortion and drift. In the second phase, to overcome self-occlusion, we register point clouds from six viewpoints into a complete plant model. This process involves a rapid coarse alignment using a marker-based Self-Registration (SR) method, followed by fine alignment with the Iterative Closest Point (ICP) algorithm. Results: The workflow was validated on two Ilex species (Ilex verticillata and Ilex salicina). The results demonstrate the high accuracy and reliability of the workflow. Furthermore, key phenotypic parameters extracted from the models show a strong correlation with manual measurements, with coefficients of determination (R²) exceeding 0.92 for plant height and crown width, and ranging from 0.72 to 0.89 for leaf parameters. Discussion: These findings validate our workflow as an accurate, reliable, and accessible tool for quantitative 3D plant phenotyping.
Why it matches plant phenotyping methods植物の3D再構成と形質抽出ワークフロー自体を開発・検証しており、植物形質計測が中心的な方法論的貢献である。
abstractthis study proposes and validates an integrated, two-phase plant 3D reconstruction workflow
Three-dimensional(3D) seedling reconstruction technology can provide critical technical support for monitoring plant growth, phenotyping high-throughput plants, and conducting precision agriculture. However, multiview image-based reconstruction methods, which rely on image registration and feature matching, are susceptible to issues such as similar textures and viewpoint differences, leading to matching errors and the loss of key structural information. This can result in local deficiencies and reduced accuracy in the reconstructed models. Therefore, to attain improved reconstruction accuracy under low-cost constraints, deep learning-based feature extraction and matching methods are employed in this study, the SuperPoint network is utilized to increase the robustness of the feature point detection and description processes, and the LightGlue algorithm is introduced to improve the accuracy and stability of matching. Additionally, to reduce the impact of shooting and platform jitter on image quality, a dedicated plant 3D reconstruction platform is designed and constructed, and a dataset of densely planted rice seedlings under light stress conditions is collected, comprising three factors (light quality, light quantity, and the photoperiod) × three levels, totaling nine groups. Experimental results show that the proposed method achieves optimal performance in terms of its point cloud completeness and reprojection error. The phenotypic parameters (e.g., plant height) extracted from the reconstruction data are strongly correlated with the actual measurements (R 2 = 0.989, RMSE = 4.54 mm), validating the potential of the proposed method for applications related to simulating plant growth processes, analyzing the effects of environmental factors (e.g., light), and optimizing crop cultivation schemes.
Why it matches plant phenotyping methodsマルチビュー画像によるイネ幼苗の3D再構成プラットフォームとデータセットを開発し、再構成精度および抽出形質を実測値と検証しており、表現型取得手法が研究の中心である。
abstractdeep learning-based feature extraction and matching methods are employed in this study
Reproduction assets foundThe paper's authors explicitly state their analysis code is publicly available on GitHub; the phenotype/image dataset is only available upon request, so it does not qualify as a public asset.Code · publicThe code used in this study is available at https://github.com/Terrywewee/3D-reconstruction-of-densely-planted-rice-seedlings---superpoint-lightglue.git .Open asset ↗https://github.com/Terrywewee/3D-reconstruction-of-densely-planted-rice-seedlings---superpoint-lightglue.gitlines:433-485Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 6 Sept 2026
Aiming to address the issues of low efficiency and large errors in the manual measurement process of phenotypic parameters in Schima Superba seedlings, an automated non-destructive method for acquiring phenotypic parameters based on three-dimensional point clouds is proposed, which includes the main steps of alignment, skeleton extraction, and automatic phenotypic calculation. Aiming to overcome the technical challenges of stem and leaf separation in Schima Superba , a density-weighted voxel centroid method is proposed to extract skeleton points, combined with minimum spanning tree (MST) and principal component analysis (PCA) techniques to accurately identify the stem skeleton point cloud, effectively addressing the problem of stem-leaf separation. The separation process encounters difficulties at the stem-leaf junction, resulting in suboptimal separation accuracy. An improved K-means++ algorithm is proposed to initially estimate the number of adhering leaves based on coarse segmentation, followed by fine segmentation to achieve higher precision in leaf segmentation, effectively improving the accuracy and efficiency of the segmentation process. Following the completion of stem and leaf segmentation, a fully automated phenotypic characterization method based on the segmented point cloud is proposed for the first time. The method automatically outputs relevant phenotypic parameters, including plant height, stem length, stem diameter, and leaf area. The predicted correlation coefficients for the experimental phenotypes were 0.994, 0.992, 0.938, and 0.873, meeting the requirements for on-site measurement of phenotypic parameters in Schima Superba and providing strong technical support for plantation management and cultivar improvement.
Why it matches plant phenotyping methods3D点群による茎葉分離、骨格抽出、形質自動計算を開発・検証しており、植物表現型取得手法が研究の中心である。
abstractan automated non-destructive method for acquiring phenotypic parameters based on three-dimensional point clouds is proposed
This study proposes an Automatic Branch Modeling (ABM) framework that combines AdTree and AdQSM algorithms to reconstruct individual tree models and estimate timber volume from fused Hand-held Laser Scanners (HLS) and Unmanned Aerial Vehicle Laser Scanners (UAV-LS) point cloud data. The research focuses on two 50 × 50 m primary tropical rainforest plots in Hainan Island, China, characterized by dense and vertically stratified vegetation. Key steps include multi-source point cloud registration and noise removal, individual tree segmentation using the Comparative Shortest Path (CSP) algorithm, extraction of diameter at breast height (DBH) and tree height, and 3D reconstruction and volume estimation via cylindrical fitting and convex polyhedron decomposition. Results demonstrate high accuracy in parameter extraction, with DBH estimation achieving R2 = 0.89–0.90, RMSE = 2.93–3.95 cm and RMSE% = 13.95–14.75%, while tree height estimation yielded R2 = 0.89–0.94, RMSE = 1.26–1.81 m and RMSE% = 9.41–13.2%. Timber volume estimates showed strong agreement with binary volume models (R2 = 0.90–0.94, RMSE = 0.10–0.18 m3, RMSE% = 32.33–34.65%), validated by concordance correlation coefficients (CCC) of 0.95–0.97. The fusion of HLS (ground-level trunk details) and UAV-LS (canopy structure) data significantly improved structural completeness, overcoming occlusion challenges in dense forests. This study highlights the efficacy of multi-source LiDAR fusion and 3D modeling for precise forest inventory in complex ecosystems. The ABM framework provides a scalable, non-destructive alternative to traditional methods, supporting carbon stock assessment and sustainable forest management in tropical rainforests. Future work should refine individual tree segmentation and wood-leaf separation to further enhance accuracy in heterogeneous environments.
Why it matches plant phenotyping methodsマルチソースLiDAR融合、個体樹木セグメンテーション、3D再構成によってDBH・樹高・材積を抽出する手法を開発し、精度検証まで行っており、植物形質計測が研究の中心である。
abstractThis study proposes an Automatic Branch Modeling (ABM) framework that combines AdTree and AdQSM algorithms to reconstruct individual tree models and estimate timber volume from fused Hand-held Laser Scanners (HLS) and Unmanned Aerial Vehicle Laser Scanners (UAV-LS) point cloud data.
The swift progress of close-range remote sensing necessitates a quantitative evaluation of its accuracy in estimating forest above-ground biomass (AGB) across diverse scales, forest types, methodologies, and variables. These evaluations will enhance the effectiveness of remote sensing in forest monitoring, reveal the carbon sequestration capability of forest vegetation, and underscore the critical function of forests as terrestrial carbon sinks. In this study, we designated R 2 as the effect size for the meta-analysis given that it is commonly regarded as a measure for estimating accuracy in AGB research, which indicates the explanatory capacity of independent variables. Utilizing 187 global investigations and 233 datasets, this research systematically assessed the accuracy ( R 2 ) of ground light detection and ranging (LiDAR), unmanned aerial vehicles (UAVs), spectra, and red-green-blue (RGB) sensors across the single-tree, plot, and stand scales. The discrepancies in accuracy across the various research methods and the independent variables in the allometric growth equation were also assessed. The research indicated that ground lidar exhibited the best accuracy across all studies and was the most effective approach at both the single-tree and plot scales. Nonetheless, as the scale of the research broadened, both accuracy and sample size diminished. Furthermore, the variations from different approaches among different forest types were substantial; therefore, it was necessary to model these forest types explicitly. By integrating diameter at breast height (DBH or D) and tree height (H) as independent variables in the allometric growth equation, the method showed improved estimation accuracy. The estimation of AGB must address the issue of accumulated error arising from the interconversion of DBH and H, single-tree segmentation, and specific allometric growth equations, which are subsequently compounded at the plot and stand levels. Close-range remote sensing is currently the most efficient method for estimating forest AGB, surpassing conventional measurement techniques. Yet, due to sensor limitations, no single sensor achieved optimal results independently. The integration of multi-source data and scale adaptation strategies further enhanced the efficacy of close-range remote sensing, surpassing the conventional survey methods. Moving forward, efforts should prioritize cross-platform data standardization, deep learning model refinement, and the establishment of non-destructive validation systems to support high-precision forest carbon monitoring, in alignment with carbon management goals.
Why it matches plant phenotyping methods森林の地上部バイオマスという植物個体・林分レベルの形質推定について、近距離リモートセンシング手法の精度をメタ解析で比較・評価しており、測定法の技術的妥当性が中心です。
abstractThe swift progress of close-range remote sensing necessitates a quantitative evaluation of its accuracy in estimating forest above-ground biomass (AGB) across diverse scales, forest types, methodologies, and variables.
Published31 Jul 2025The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesCited by 1 · OpenAlex ↗
Abstract. Monitoring post-fire vegetation dynamics is essential for understanding forest recovery processes and informing management strategies. UAV-based ultra-high resolution multi-temporal imagery, combined with the Structure-from-Motion andMulti-View Stereo (SfM-MVS) workflow, provides a cost-effective and scalable solution for forest monitoring. However, challenges remain in co-aligning multi-temporal datasets, segmenting individual trees in dense canopies, and ensuring classification accuracy. This study presents a comprehensive workflow for post-fire forest monitoring using UAV imagery, covering data acquisition, co-alignment, tree segmentation, species classification, and biophysical parameter estimation using growth models. The workflow was tested on three sites in Central Yakutia, with varying post-fire regeneration scenarios. Co-alignment was applied to multi-temporal UAV datasets, and tree segmentation was performed using the algorithms developed for Airborne Laser Scanning (ASL) forest point clouds. Tree species classification relied on statistical spatial variables of point clouds, and growth models were used to estimate parameters such as tree height, age, canopy area, above-ground biomass, and net primary productivity. The results demonstrated that co-alignment enabled consistent multi-temporal analysis, but performance was sensitive to flight planning consistency and lighting conditions. Tree segmentation accuracy was high in open-canopy areas but decreased in dense canopies. The classification of larch and birch species achieved relatively high precision and recall values, while dead trees showed lower classification accuracy due to challenging lighting conditions. Growth models successfully estimated biophysical parameters, but further validation using dendrochronological methods is required. This study highlights the potential of UAV-based multi-temporal monitoring for post-fire forest assessment. Future research should focus on improving tree segmentation of SfM-MVS point clouds in dense canopies, optimizing co-alignment under varying environmental conditions, and integrating additional point cloud classification methods to improve accuracy in areas with complex species distribution.
Why it matches plant phenotyping methodsUAV画像とSfM-MVSを用いて個体樹木を分割・分類し、樹高、樹冠面積、バイオマスなどの植物形質を推定するワークフローが研究の中心であり、精度評価も行っている。
abstractThis study presents a comprehensive workflow for post-fire forest monitoring using UAV imagery, covering data acquisition, co-alignment, tree segmentation, species classification, and biophysical parameter estimation using growth models.
Abstract. Extensive urban expansion has significantly impacted green spaces leading to the degradation of urban vegetation. Hence, monitoring variations in vegetation using remote sensing methods is essential. However, 2D remote sensing methods have drawbacks as they lack vertical structures in urban areas, shadows caused by buildings, cloud cover and require substantial preprocessing to encounter these limitations. This study focuses on identifying and quantifying changes in Malminkartano, Helsinki during the leaf-off and leaf-on seasons for the year 2022. The research utilized terrestrial laser scanning (TLS) and UAV-photogrammetry datasets for change detection in urban vegetation and point cloud-based algorithms for seasonal variations such as C2C, C2M, and M3C2. Notably, many existing methods involve rasterizing point clouds as DSM which results in the loss of significant information. Therefore, this paper investigates the potential of utilized datasets in detecting changes directly on point clouds. However, there are uncertainties associated with point clouds including data registration, point density, weather effects, and misalignment therefore this study aims to take these limitations into account. The results from TLS and UAV-photogrammetry demonstrated competence in identifying the maximum growth of urban vegetation up to 2.0 m and 2.8 m respectively. However, the accuracy assessment of data corresponded to a 4 cm difference in both datasets at a 95% confidence threshold and potential vertical height differences accounted for the difference in change detection. This study underscores data processing uncertainties associated with registration, vertical height, and data noise and proposes the integration of point clouds with different sensors for completeness and improved change detection in urban vegetation.
Why it matches plant phenotyping methodsUAVフォトグラメトリと地上レーザースキャンを比較し、点群処理によって都市植生の成長量・高さ変化を定量化する技術的評価が中心である。
abstractThis study focuses on identifying and quantifying changes in Malminkartano, Helsinki during the leaf-off and leaf-on seasons for the year 2022.
In orchard automation, dense foliage during the canopy season severely occludes tree structures, minimizing visibility to various canopy parts such as trunks and branches, which limits the ability of a machine vision system. However, canopy structure is more open and visible during the dormant season when trees are defoliated. In this work, we present an information fusion framework that integrates multi-seasonal structural data to support robotic and automated crop load management during the entire growing season. The framework combines high-resolution RGB-D imagery from both dormant and canopy periods using YOLOv9-Seg for instance segmentation, Kinect Fusion for 3D reconstruction, and Fast Generalized Iterative Closest Point (Fast GICP) for model alignment. Segmentation outputs from YOLOv9-Seg were used to extract depth-informed masks, which enabled accurate 3D point cloud reconstruction via Kinect Fusion; these reconstructed models from each season were subsequently aligned using Fast GICP to achieve spatially coherent multi-season fusion. The YOLOv9-Seg model, trained on manually annotated images, achieved a mean squared error (MSE) of 0.0047 and segmentation mAP@50 scores up to 0.78 for trunks in dormant season dataset. Kinect Fusion enabled accurate reconstruction of tree geometry, validated with field measurements resulting in root mean square errors (RMSE) of 5.23 mm for trunk diameter, 4.50 mm for branch diameter, and 13.72 mm for branch spacing. Fast GICP achieved precise cross-seasonal registration with a minimum fitness score of 0.00197, allowing integrated, comprehensive tree structure modeling despite heavy occlusions during the growing season. This fused structural representation enables robotic systems to access otherwise obscured architectural information, improving the precision of pruning, thinning, and other automated orchard operations.
Why it matches plant phenotyping methods果樹の幹・枝の形態を3D再構成・季節間融合で推定する画像ベースの表現型取得手法を開発し、実測値で検証しているため、方法が中心である。
abstractIn this work, we present an information fusion framework that integrates multi-seasonal structural data to support robotic and automated crop load management during the entire growing season.
Plant phenotyping relevance match · UnverifiedbioRxiv · OpenAlex · Europe PMC · checked 13 Sept 2026
O_LILight drones provide a cheap and effective tool to monitor forest canopy, especially in tropical and equatorial contexts, where infrastructure and resources are limiting. In these regions, good quality optical satellite images are rare, yet the stakes are maximal to characterize forest function, dynamics, diversity, and phenology, and more generally the vegetation-climate interplay. C_LIO_LIWe describe a complete processing chain based on photogrammetric tools that seeks to optimize the spatial and spectral coherence between repeat image mosaics at centimetric resolution. Our target is to allow individual tree-level monitoring over tens to hundreds of hectare scales with consumer grade equipment (i.e., quadcopter with stabilized RGB camera, standard GNSS positioning). C_LIO_LIWe demonstrate the increase in spatial precision achieved using Time-SIFT and Arosics algorithms, which allow (individually and synergistically) to reduce global and local spatial misalignment between mosaics from several meters to a few centimeters. Time-SIFT provides the advantage of increased robustness in initial image alignment and 3D reconstruction, and hence reduces occasional distortions or data gaps. Using Agisofts color and white balance corrections combined with the use of vegetation indices provides meaningful quantitative signal despite considerable changes in acquisition conditions. C_LIO_LIIn particular, indices that are less sensitive to illumination changes, like the green chromatic coordinate (GCC), allowed evidencing a seasonal signal over four years of monitoring in the evergreen moist forest at Paracou in French Guiana. The signal was decorrelated from obvious geometrical effect (sun height), and provided information on the vegetative stage at tree, species, and stand levels. C_LI Data/Code for peer reviewThe complete processing chain, as well as the data and scripts used for producing the analyses presented here, are available for review on Zenodo: https://zenodo.org/records/15449377?token=eyJhbGciOiJIUzUxMiJ9.eyJpZCI6IjdjNWExMzIzLThkNDMtNDllNy1iYWY4LTY2MGZlZjkyZmQ3OCIsImRhdGEiOnt9LCJyYW5kb20iOiI5MGQ4NTE2YTE4OGViNDQ3YTFiZmMyYTFkZDlhZTZmMiJ9.CsJ0VRuQ90A1qzO1VJC1Q9eXFSp1N5UpeJlyr6otgXRPlf-I-jcwBJ6ytiBbbu8enCNJ2Ke6-oxNV8aeJ_AWIw
Why it matches plant phenotyping methodsドローン画像のステレオフォトグラメトリ処理、画像整合化、色補正、植生指数を組み合わせた処理チェーンを開発・実証し、個体樹木から林分レベルの植生状態・季節性を定量化しているため、植物フェノタイピング手法が中心である。
abstractWe describe a complete processing chain based on photogrammetric tools that seeks to optimize the spatial and spectral coherence between repeat image mosaics at centimetric resolution.
Ensuring food security has become a global challenge owing to climate change and population growth. High-throughput phenotyping can effectively drive crop genetic enhancement, which can potentially solve food crisis. Phenotyping robot is an essential part of crop ground phenotyping information monitoring, although there are challenges such as the inability to adjust the fixed track width, poor load capacity of the detection robotic arm, and inability to fuse information in real-time. This study reports a phenotyping robot with a gantry-style chassis featuring an adjustable wheeltrack (1400–1600 mm) to adapt to different row spacing arrangements and reduced damage, and function effectively in both dry field and paddy field environments. A six-degree-of-freedom sensor gimbal with high payload capacity is also developed to enable precise height (1016–2096 mm) and angle adjustments. Additionally, this study introduces an enhanced method for data acquisition from multiple imaging sensors through registration and fusion using Zhang's calibration and feature point extraction algorithm, calculating a homography matrix for high-throughput data collection at fixed positions and heights. The experimental validation results demonstrate that the RMSE of the registration algorithm does not exceed 3 pixels. The gimbal data strongly correlated with that of a handheld instrument data (r² > 0.90). The robot is practical, reliable, and fully functional, offering a solid theoretical foundation and equipment support for high-throughput phenotyping.
Why it matches plant phenotyping methods小麦の高スループット表現型取得を目的とするロボット、センサージンバル、多センサー画像登録・融合手法を開発し、精度検証まで実施しており、表現型取得技術が研究の中心である。
titleDesign and implementation of a high-throughput field phenotyping robot for acquiring multisensor data in wheat
Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · Europe PMC · checked 6 Sept 2026
Ensuring food security has become a global challenge owing to climate change and population growth. High-throughput phenotyping can effectively drive crop genetic enhancement, which can potentially solve food crisis. Phenotyping robot is an essential part of crop ground phenotyping information monitoring, although there are challenges such as the inability to adjust the fixed track width, poor load capacity of the detection robotic arm, and inability to fuse information in real-time. This study reports a phenotyping robot with a gantry-style chassis featuring an adjustable wheeltrack (1400–1600 mm) to adapt to different row spacing arrangements and reduced damage, and function effectively in both dry field and paddy field environments. A six-degree-of-freedom sensor gimbal with high payload capacity is also developed to enable precise height (1016–2096 mm) and angle adjustments. Additionally, this study introduces an enhanced method for data acquisition from multiple imaging sensors through registration and fusion using Zhang's calibration and feature point extraction algorithm, calculating a homography matrix for high-throughput data collection at fixed positions and heights. The experimental validation results demonstrate that the RMSE of the registration algorithm does not exceed 3 pixels. The gimbal data strongly correlated with that of a handheld instrument data (r 2 > 0.90). The robot is practical, reliable, and fully functional, offering a solid theoretical foundation and equipment support for high-throughput phenotyping.
Why it matches plant phenotyping methods小麦の高スループット表現型計測ロボット、マルチセンサー画像取得・登録融合手法を開発し、登録精度とセンサー性能を検証しており、フェノタイピング手法が研究の中心である。
abstractThis study reports a phenotyping robot with a gantry-style chassis featuring an adjustable wheeltrack
Accurate temporal reconstructions of plant growth are essential for plant phenotyping and breeding, yet remain challenging due to complex geometries, occlusions, and non-rigid deformations of plants. We present a novel framework for building temporal digital twins of plants by combining 3D Gaussian Splatting with a robust sample alignment pipeline. Our method begins by reconstructing Gaussian Splats from multi-view camera data, then leverages a two-stage registration approach: coarse alignment through feature-based matching and Fast Global Registration, followed by fine alignment with Iterative Closest Point. This pipeline yields a consistent 4D model of plant development in discrete time steps. We evaluate the approach on data from the Netherlands Plant Eco-phenotyping Center, demonstrating detailed temporal reconstructions of Sequoia and Quinoa species. Videos and Images can be seen at https://berkeleyautomation.github.io/GrowSplat/
Why it matches plant phenotyping methods植物の多視点画像からGaussian Splattingと位置合わせを用いて、成長の時間的な3D/4Dデジタルツインを構築する手法が研究の中心であり、植物フェノタイピングへの応用も明示されている。
abstractWe present a novel framework for building temporal digital twins of plants by combining 3D Gaussian Splatting with a robust sample alignment pipeline.
Phenotypic traits of crops reflect their physiological characteristics and provide a theoretical basis for predicting their growth. The 3D point cloud has a direct and accurate rendering ability, which has been widely used in phenotype extraction, especially with the help of accurate segmentation techniques. However, the inherent discrete nature of point clouds makes accurate organ segmentation an ongoing challenge in the field. In this study, we propose a tree phenotype acquisition method based on point cloud registration and skeleton segmentation. First, the Convex Hull-indexed Gaussian Mixture Model (CH-GMM) is employed to register the ground and aerial point cloud data. Then, a Laplace-multi-scale adaptive algorithm (LMSA) was proposed to obtain the crop skeleton structure, on the basis of which four phenotypic parameters, namely, plant height, crown width, branching number, and initial branching height, were extracted for fruit trees. In addition, the relationship between crown width and the number of branches was explored, where branches included initial, secondary, and tertiary branches. The results show that the proposed CH-GMM algorithm has a rotation error of less than 1.01°, a translation error of less than 10 mm, and a success rate of more than 95 %. The average precision, average recall, average F1 score, and average overall accuracy of the LMSA are 93.7 %, 96.2 %, 92.6 %, and 95.3 %, respectively. Finally, this study found a polynomial and exponential relationship between the number of bifurcations and crown size of fruit trees. The results of this study may provide new ideas for fruit tree phenotype acquisition and phenotype management.
Why it matches plant phenotyping methodsリンゴ樹の3D点群登録・骨格分割アルゴリズムを開発し、樹高や樹冠幅などの形態形質を抽出・精度評価しており、表現型取得手法が研究の中心である。
abstractwe propose a tree phenotype acquisition method based on point cloud registration and skeleton segmentation.
This study aims to construct digital fruit trees with high-precision geolocation and high-quality canopy phenotypic details, supporting the development of digital fruit tree technology and the establishment of smart orchards. The Neural Radiance Fields (NeRF) theory was integrated with georeferencing technology. Firstly, multiple ground control points were placed around the tree, and their WGS-84 coordinates were recorded using an RTK surveying instrument. Next, a drone captured multi-view images of the fruit tree, recording the camera poses during the image acquisition. The multi-view fruit tree images undergo ray casting, hierarchical sampling, and high-frequency position encoding before being input into a Multilayer Perceptron (MLP). The MLP was then supervised through volume rendering to obtain a convergent radiance field that reflects the true form of the fruit tree, resulting in the generation of a fruit tree point cloud. Finally, by establishing correspondences between the points in the fruit tree point cloud and the ground control points in the real world, a rigid transformation matrix was computed to convert the point cloud from a local coordinate system to WGS-84 coordinates, yielding a geographically informed digital fruit tree. The experiments demonstrate that the constructed digital fruit tree exhibits excellent phenotypic details and accurately represents multi-scale characteristics. The accuracy of tree morphology indicators, such as tree height, crown length, and width, reached 99.12%, 99.34%, and 99.22%, respectively. Compared to point clouds generated by traditional Structure from Motion-Multi View Stereo (SFM-MVS) methods, the root mean square errors were reduced by 61.24%, 73.48%, and 62.32%, respectively. Additionally, the georeferencing accuracy achieved millimeter-level precision, with registration errors generally below 2 mm. The proposed method can construct digital fruit trees with high geolocation accuracy, detailed phenotypic information, and scale consistency, overcoming key barriers in the development of digital fruit tree technology. It can provide comprehensive data for various production operations in smart orchards.
Why it matches plant phenotyping methodsNeRFと地理参照を統合し、果樹の点群から樹高・樹冠長・幅などの形態表現型を抽出する手法を開発・検証しており、表現型取得が研究の中心である。
abstractThe Neural Radiance Fields (NeRF) theory was integrated with georeferencing technology.
Rapid and accurate plant phenotyping is vital to plant breeding and monitoring. Hyperspectral imaging (HSI) is the popular phenotypic technique to acquire spectral and spatial information of plants. However, the close-range HSI of plant canopies is greatly affected by the complex interaction of canopy geometry with illumination, which leads to biased or contaminated spectral information. Thus, the mitigation of these effects is imperative but challenging. In this study, a three-dimensional (3D) spectral compensation method on close-range canopy HSI was proposed, to correct the reflectance of canopies affected by imaging distance and leaf angle. First, the hyperspectral and depth images of canopies were registered and fused to generate hyperspectral 3D point clouds. Next, the full-spectrum reflectance on canopies was compensated based on the depth and angle information provided by the hyperspectral 3D point clouds. Then, the performance of spectral compensation results was evaluated by cluster analysis, spectral curve validation, and chlorophyll regression. Results on two plant types (perilla and tea seedlings) showed that after spectral compensation, the reflectance variations within canopies reduced greatly, the reflectance of whole canopies became more homogeneous, with a dominant cluster accounting for over 67% pixels of canopies. And using the mean reflectance curves of in vitro flattened leaves as the reference, the canopy reflectance after compensation were closer to the reference level, that the Euclidean Distance (ED) between them reduced by 50.6%. The determination coefficient (R²) for chlorophyll regression after compensation reached 0.75, increasing about 17% compared to that before compensation. The overall results demonstrated that the proposed 3D spectral compensation method was effective in mitigating the effects of imaging distance and leaf angle on plant canopies in close-range HSI. This could further facilitate the revelation of plant optical characteristics, which is of high significance for the accurate close-range plant phenotyping.
Why it matches plant phenotyping methods植物キャノピーの近接ハイパースペクトル画像に対する3Dスペクトル補償法を開発し、複数の評価で性能検証しており、表現型取得・抽出手法が研究の中心である。
abstractIn this study, a three-dimensional (3D) spectral compensation method on close-range canopy HSI was proposed, to correct the reflectance of canopies affected by imaging distance and leaf angle.
Monitoring flowers over time is essential for precision robotic pollination in agriculture. To accomplish this, a continuous spatial-temporal observation of plant growth can be done using stationary RGB-D cameras. However, image registration becomes a serious challenge due to changes in the visual appearance of the plant caused by the pollination process and occlusions from growth and camera angles. Plants flower in a manner that produces distinct clusters on branches. This paper presents a method for matching flower clusters using descriptors generated from RGB-D data and considers allowing for spatial uncertainty within the cluster. The proposed approach leverages the Unscented Transform to efficiently estimate plant descriptor uncertainty tolerances, enabling a robust image-registration process despite temporal changes. The Unscented Transform is used to handle the nonlinear transformations by propagating the uncertainty of flower positions to determine the variations in the descriptor domain. A Monte Carlo simulation is used to validate the Unscented Transform results, confirming our method's effectiveness for flower cluster matching. Therefore, it can facilitate improved robotics pollination in dynamic environments.
Why it matches plant phenotyping methodsRGB-D画像から花房を時系列追跡・マッチングする画像登録手法が研究の中心で、植物成長の観測に直接用いられるため、植物フェノタイピング手法として含める。
abstractThis paper presents a method for matching flower clusters using descriptors generated from RGB-D data and considers allowing for spatial uncertainty within the cluster.
Automatic plant growth monitoring is an important task in modern agriculture for maintaining high crop yield and boosting the breeding procedure. The advancement of 3D sensing technology has made 3D point clouds to be a better data form on presenting plant growth than images, as the new organs are easier identified in 3D space and the occluded organs in 2D can also be conveniently separated in 3D. Despite the attractive characteristics, analysis on 3D data can be quite challenging. We present 3D-NOD, a framework to detect new organs from time-series 3D plant data by spatiotemporal point cloud deep semantic segmentation. The design of 3D-NOD framework drew inspiration from how a well-experienced human utilizes spatiotemporal information to identify growing buds from a plant at two different growth stages. In the training phase, by introducing the Backward & Forward Labeling, the Registration & Mix-up, and the Humanoid Data Augmentation step, our backbone network can be trained to recognize growth events with organ correlation from both temporal and spatial domains. In testing, 3D-NOD has shown better sensitivity at segmenting new organs against the conventional way of using a network to conduct direct semantic segmentation. On a time-series dataset containing multiple species, Our method reached a mean F1-measure at 88.13 % and a mean IoU at 80.68 % on detecting both new and old organs with the DGCNN backbone.
Why it matches plant phenotyping methods植物の時系列3D点群から新生器官を検出・分割する手法を開発し、複数種データセットで性能評価しており、植物表現型取得が中心である。
abstractWe present 3D-NOD, a framework to detect new organs from time-series 3D plant data by spatiotemporal point cloud deep semantic segmentation.
Reproduction assets foundThe authors explicitly state that both the dataset (labeled time-series plant point clouds for tobacco, tomato, and sorghum) and the analysis code for the 3D-NOD framework are publicly available in a GitHub repository.Dataset · publicOur data and the code are available at: https://github.com/zingersu/3D-New-Organ-Detection-in-Plant-Growth-from-Spatiotemporal-Point-Clouds.Open asset ↗https://github.com/zingersu/3D-New-Organ-Detection-in-Plant-Growth-from-Spatiotemporal-Point-Cloudshtml-lines:481-514Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · checked 15 Sept 2026
Plant phenotyping, which involves measuring and analysing plant traits, has seen significant advances in recent years by integrating autonomous platforms and sophisticated sensor systems. In contrast to traditional methods, modern unmanned ground vehicles (UGVs) provide robust and accurate phenotyping capabilities by enabling close, detailed and continuous monitoring of crops under different environmental conditions. This study presents the configuration and validation of a multi-sensor platform (MSP) integrated with a UGV to improve plant phenotyping through advanced data fusion and co-registration techniques. The platform incorporates red, green, and blue channel (RGB), hyperspectral from visible light (VIS) and near-infrared light (NIR) spectrum, thermal sensors, and a three-dimensional (3D) light detection and ranging (LiDAR), all subjected to extensive calibration to ensure precise temporal and spatial alignment. Intrinsic calibration was applied, including correcting the spectral signatures of VIS and NIR. Additionally, timestamps were synchronised using the VIS sensor as the primary reference due to its central position and higher data acquisition frequency. Homography matrices were computed using checkerboard patterns for geometric alignment across sensors, and motion corrections accounted for UGV movement and ground sample distance. LiDAR point clouds were transformed into depth-maps (DMs) using radial basis function interpolation, enriching the spatial data for further analysis. The co-registered and synchronised MSP was tested for detecting Cercospora leaf spot (CLS) in sugar beet plants during a field experiment. Two models were implemented: (1) a soil and plant segmentation model based on the DeepLabV3+ architecture, achieving an F1-score of 0.85 and an accuracy of 0.95, and (2) a CLS severity scoring model using a custom convolutional neural network (CNN). The severity model, leveraging NIR and DM channels, achieved an F1-score of 0.7066, accuracy of 0.7104, and recall of 0.7167, with NIR wavelengths between 814 and 851 contributing significantly to performance. These results highlight the importance of accurate data fusion and synchronisation in multi-sensor systems for plant phenotyping. Moreover, the study demonstrates the potential of integrating multiple sensors on a UGV for precision agriculture, thereby enhancing MSP effectiveness in crop monitoring and disease detection. • Multi-sensor platform supports detailed plant phenotyping using data fusion. • Effective synchronization ensured accurate temporal alignment across sensors. • RGB, hyperspectral, thermal, and LiDAR sensors calibrated for accurate alignment. • Soil-plant and segmentation Cercospora leaf spot disease severity estimated using neural network. • NIR and depth map sensor fusion enhance plant phenotyping accuracy for Cercospora leaf spot disease severity.
Why it matches plant phenotyping methodsマルチセンサーUGVプラットフォームの構成、校正、同期、データ融合を開発・検証し、植物病害の重症度という表現型を推定しているため、方法が研究の中心である。
abstractThis study presents the configuration and validation of a multi-sensor platform (MSP) integrated with a UGV to improve plant phenotyping through advanced data fusion and co-registration techniques.
Monitoring the growth dynamics of plants in three-dimensional (3D) space is one of the most fundamental data acquisition requirements for plant breeding and cultivation. The rapid development of high-throughput plant phenotyping platforms (HTPPP) makes it possible to obtain big data in plant phenomics. However, how to extract phenotypes from the raw phenotyping data to obtain the agronomic indicators demanded by agronomists has become an urgent issue. In this study, time-series point clouds of potted lettuce plants were generated via multi-view stereo (MVS) method using top-view Red, Green, Blue (RGB) images acquired by a rail-driven HTPPP in a greenhouse. A time-series point cloud registration method was proposed by extracting pots as features, and daily population-individual plant point cloud segmentation was achieved based on the registration information and contrasted with two other different segmentation methods. Then vegetation and pot was segmented using the random forest (RF). Finally, the phenotypes including plant height, crown width, and convex hull volume of each plant were extracted. The results show that the average mean intersection over union (mIoU), mean precision (mPᵣ), mean recall (mRₑ), and mean F1-score (mF₁) of the population-individual plant segmentation were 71.86%, 97.38%, 86.08%, and 91.02%, respectively. The vegetation-pot point cloud segmentation achieved an accuracy of 98.81%. The averaged coefficient of determination (R²) for the extracted plant height and crown width were 0.79 and 0.60, respectively, with the averaged root mean square error (RMSE) being 0.05 m and 0.03 m, respectively. The accuracy of plant height was significantly higher than that of PlantEye. The extracted phenotypes can be used to quantitatively differentiate the growth dynamics of different sub-populations of lettuce plants. This study presents an automated solution for extracting time-series 3D phenotypes under HTPPP in a greenhouse. It provides crucial technological support for efficient phenotype acquisition in plant breeding and cultivation.
Why it matches plant phenotyping methods温室HTPPPの3D点群から植物個体を分割し、草高・冠幅・凸包体積を抽出する手法を開発・検証しており、表現型取得が研究の中心です。
abstractA time-series point cloud registration method was proposed by extracting pots as features, and daily population-individual plant point cloud segmentation was achieved based on the registration information and contrasted with two other different segmentation methods.
The global attention to the utilization of unmanned aerial vehicle remote sensing drones in crop disease-wide detection has led to the urgent need to find an adapted model for different environmental conditions. Therefore, the current study has focused on spatiotemporal usage of different multispectral cameras in acquiring spectral reflectance models of in-field rice bacterial blight stresses. Where, long short-term memory (LSTM) model was compared with the other models in transfer learning strategy for assessing the blight stress severity. The results revealed that by extracting 30% of the data from the target domain and transferring it to the source domain, the adaptability of the model across different sites was effectively enhanced. Besides, LSTM showed high tuning transfer efficiency that demonstrated optimal predictive performance and the shortest training time in transfer tasks. Its coefficient of the prediction set was 0.82, and its residual prediction deviation has reached 2.26. In practice, LSTM enabled the acquisition of reliable prediction results at a minimal sample collection cost while circumventing feature reduction resulting from inter-domain data alignment. When the transfer ratio reached 20%, the coefficient of determination of the prediction set reached 0.71, and the residual prediction deviation reached 1.79. The novelty of this study came from the transfer learning efficiency in improving the model’s application capabilities across the different sites, environment, and unmanned aerial vehicle in farmland disease detection.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像からイネ白葉枯病の発病ストレス重症度を推定するモデルを開発・比較し、異なる環境・圃場への転移性能を検証しているため、植物表現型取得手法が中心である。
abstractThe novelty of this study came from the transfer learning efficiency in improving the model’s application capabilities across the different sites, environment, and unmanned aerial vehicle in farmland disease detection.
Maize leaf area offers valuable insights into physiological processes, playing a critical role in breeding and guiding agricultural practices. The Azure Kinect DK possesses the real-time capability to capture and analyze the spatial structural features of crops. However, its further application in maize leaf area measurement is constrained by RGB–depth misalignment and limited sensitivity to detailed organ-level features. This study proposed a novel approach to address and optimize the limitations of the Azure Kinect DK through the multimodal coupling of RGB-D data for enhanced organ-level crop phenotyping. To correct RGB–depth misalignment, a unified recalibration method was developed to ensure accurate alignment between RGB and depth data. Furthermore, a semantic information-guided depth inpainting method was proposed, designed to repair void and flying pixels commonly observed in Azure Kinect DK outputs. The semantic information was extracted using a joint YOLOv11-SAM2 model, which utilizes supervised object recognition prompts and advanced visual large models to achieve precise RGB image semantic parsing with minimal manual input. An efficient pixel filter-based depth inpainting algorithm was then designed to inpaint void and flying pixels and restore consistent, high-confidence depth values within semantic regions. A validation of this approach through leaf area measurements in practical maize field applications—challenged by a limited workspace, constrained viewpoints, and environmental variability—demonstrated near-laboratory precision, achieving an MAPE of 6.549%, RMSE of 4.114 cm2, MAE of 2.980 cm2, and R2 of 0.976 across 60 maize leaf samples. By focusing processing efforts on the image level rather than directly on 3D point clouds, this approach markedly enhanced both efficiency and accuracy with the sufficient utilization of the Azure Kinect DK, making it a promising solution for high-throughput 3D crop phenotyping.
Why it matches plant phenotyping methodsAzure Kinect RGB-D再較正、深度補間、意味解析を開発し、トウモロコシ葉面積測定で検証した、植物表現型取得法が中心の研究。
abstractThis study proposed a novel approach to address and optimize the limitations of the Azure Kinect DK through the multimodal coupling of RGB-D data for enhanced organ-level crop phenotyping.
Wheat is a globally cultivated cereal crop with substantial protein content present in its seeds. This research aimed to develop robust methods for predicting seed protein concentration in wheat seeds using bench-top hyperspectral imaging in the visible, near-infrared (VNIR), and shortwave infrared (SWIR) regions. To fully utilize the spectral and texture features of the full VNIR and SWIR spectral domains, a computer-vision-aided image co-registration methodology was implemented to seamlessly align the VNIR and SWIR bands. Sensitivity analyses were also conducted to identify the most sensitive bands for seed protein estimation. Convolutional neural networks (CNNs) with attention mechanisms were proposed along with traditional machine learning models based on feature engineering including Random Forest (RF) and Support Vector Machine (SVM) regression for comparative analysis. Additionally, the CNN classification approach was used to estimate low, medium, and high protein concentrations because this type of classification is more applicable for breeding efforts. Our results showed that the proposed CNN with attention mechanisms predicted wheat protein content with R 2 values of 0.70 and 0.65 for ventral and dorsal seed orientations, respectively. Although, the R 2 of the CNN approach was lower than of the best performing feature-based method, RF (R 2 of 0.77), end-to-end prediction capabilities with CNN hold great promise for the automation of wheat protein estimation for breeding. The CNN model achieved better classification of protein concentrations between low, medium, and high protein contents, with an R 2 of 0.82. This study's findings highlight the significant potential of hyperspectral imaging and machine learning techniques for advancing precision breeding practices, optimizing seed sorting processes, and enabling targeted agricultural input applications.
Why it matches plant phenotyping methods小麦種子のタンパク質含量という植物器官形質を、ハイパースペクトル画像と画像位置合わせ・機械学習で推定する方法を開発・比較しており、表現型取得と推定手法が中心である。
abstractThis research aimed to develop robust methods for predicting seed protein concentration in wheat seeds using bench-top hyperspectral imaging in the visible, near-infrared (VNIR), and shortwave infrared (SWIR) regions.
Tracking plant cells in three-dimensional (3D) tissue captured through light microscopy presents significant challenges due to the large number of densely packed cells, non-uniform growth patterns, and variations in cell division planes across different cell layers. In addition, images of deeper tissue layers are often noisy, and systemic imaging errors further exacerbate the complexity of the task. In this paper, we propose a novel learning-based method DEGAST3D: Learning Deformable 3D GrAph Similarity to Track Plant Cells in Unregistered Time Lapse Images exploits the tightly packed 3D cell structure of plant cells to create a three-dimensional graph for accurate cell tracking. We also propose a novel algorithm for cell division detection and an effective three-dimensional registration, improving state-of-the-art algorithms. On a public dataset, our novel cell pair matching method outperforms the baseline by $6.83 \%$, $5.96 \%$, $6.40 \%$ in precision, recall, and F-1 score, respectively. On the same dataset, our proposed novel cell division technique improves the results of the baseline method by $15.38 \%$ and $14.78 \%$ in terms of recall and F1-score, respectively.
Why it matches plant phenotyping methods植物細胞の3D画像から細胞追跡・分裂検出・画像登録を行う手法を開発し、公開データセットで性能評価しているため、植物フェノタイピング手法が中心です。
abstractIn this paper, we propose a novel learning-based method DEGAST3D: Learning Deformable 3D GrAph Similarity to Track Plant Cells in Unregistered Time Lapse Images
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 14 Sept 2026
ABSTRACT Unmanned aerial vehicles (UAVs) are increasingly used for high throughput phenotyping. In principle, freely flown vehicles would permit real-time flexibility in identifying and scouting regions of interest. Mosaicking multiple images provides a high resolution global image and consumer-grade UAVs offer low cost, ease of flying, and excellent RGB cameras. The vehicles’ inaccurate telemetry complicates estimating the homographies between pairs of frames, the standard mosaicking approach. Moreover, errors accumulate during computation, distorting later portions of the mosaic. Finally, crop fields are particularly challenging to mosaic because their planting is so regular and the plants are so similar, eliminating distinctive features that could guide mosaicking. We propose MaiZaic , an end-to-end pipeline that dynamically samples video frames using optical flow, automates camera and gimbal calibration, estimates homographies with an unsupervised convolutional neural network, detects shots among frames, and generates mini-mosaics. Together, these techniques significantly reduce errors in the output mosaics. Our deep learning model is trained on a comprehensive video dataset comprising different flight trajectories, maize lines, growth stages, and augmented illumination data. MaiZaic is more accurate and faster than ASIFT and more robust than our earlier CorNet and CorNetv2 . We demonstrate MaiZaic ’s effectiveness in generating accurate mosaics of imagery captured by freely-flown UAVs and explore its generalizability. Core ideas MaiZaic is an end-to-end pipeline to mosaic freely flown agricultural imagery captured with consumer-grade UAVs. MaiZaic introduces novel algorithms that efficiently choose video frames, calibrate, and mosaic the imagery. Our unsupervised deep homography estimator, CorNetv3 , is 14 times faster and 8.59% more accurare than ASIFT. MaiZaic generalizes well and mosaicks maize at different growth stages, objects, trajectories, cameras, and pilots. The mini-mosaicking algorithm improves mosaic accuracy by interrupting error accumulation.
Why it matches plant phenotyping methods農業画像のモザイク化を中核とするUAV高スループット・フェノタイピング基盤であり、画像取得・幾何補正・統合の技術開発と性能比較を実施しているため。
abstractUnmanned aerial vehicles (UAVs) are increasingly used for high throughput phenotyping.
Selective harvesting robots for broccoli face significant challenges in field operations, where occlusions by leaves and stems, varying maturity stages and lighting interferences greatly affect performance. Addressing the need for a robust network capable of maturity recognition and localisation under various occlusion conditions for spherical crops, OccluInst-a single-stage instance segmentation network based on RGB-D and CNN-Transformer architecture was proposed. The solution is to make full use of visible information and crop characteristics. This model builds a dual-branch cross-modal calibration framework to generate instance-aware kernels and segmentation mask features. The proposed Attention Weight Interactive Fusion Module (AWIF) enhances the fusion efficiency of multi-scale RGB and depth features in complex scenarios, while the designed Adaptive Fusion Ratio Module (AFR) filters out noisy depth data and extracts valuable information to achieve feature alignment. Additionally, the developed Material Awareness Module (MA) highlights critical areas, improving feature extraction for irregular, multi-scale targets. The improved circular boundary anchor box accurately localises broccoli under various levels of occlusion. Ablation studies confirm the effectiveness of each module. OccluInst can swiftly and accurately identify the maturity categories and coordinates of broccoli under different occlusion levels. It achieves a mAP₅₀ of 86.2% and mAR of 83.5%, with an average centre point deviation of 3.68 pixels on images with a resolution of 848×480, and a detection speed of 51.4 frames per second, providing a robust visual foundation for selective harvesting robots.
Why it matches plant phenotyping methodsRGB-D画像からブロッコリーの成熟カテゴリーという植物状態を推定するセグメンテーション手法を開発し、遮蔽条件下で性能評価している。単なる収穫対象の位置検出にとどまらず、成熟度推定が中心的である。
abstractOccluInst can swiftly and accurately identify the maturity categories and coordinates of broccoli under different occlusion levels.
Hyperspectral imaging provides a powerful tool for analyzing above-ground plant characteristics in fabricated ecosystems, offering rich spectral information across diverse wavelengths. This study presents an efficient workflow for hyperspectral data segmentation and subsequent data analytics, minimizing the need for user annotation through the use of ensembles of sparse mixed-scale convolution neural networks. The segmentation process leverages the diversity of ensembles to achieve high accuracy with minimal labeled data, reducing labor-intensive annotation efforts. To further enhance robustness, we incorporate image alignment techniques to address spatial variability in the dataset. Down-stream analysis focuses on using the segmented data for processing spectral data, enabling monitoring of plant health. This approach not only provides a scalable solution for spectral segmentation but also facilitates actionable insights into plant conditions in complex, controlled environments. Our results demonstrate the utility of combining advanced machine learning techniques with hyperspectral analytics for high-throughput plant monitoring.
Why it matches plant phenotyping methods植物のハイパースペクトル画像を対象に、少量アノテーションで高精度に分割する解析ワークフローを開発し、植物状態のモニタリングに用いる方法研究である。
abstractThis study presents an efficient workflow for hyperspectral data segmentation and subsequent data analytics, minimizing the need for user annotation through the use of ensembles of sparse mixed-scale convolution neural networks.
Pepper / chilliGreenhouseLaboratory / benchtopNeRF / 3D Gaussian SplattingLiDAR / point cloudFruitMorphology / geometry measurement2D/3D reconstructionImage / point-cloud registrationGrowth / development / phenology
Accurate collection of plant phenotyping is critical to optimising sustainable farming practices in precision agriculture. Traditional phenotyping in controlled laboratory environments, while valuable, falls short in understanding plant growth under real-world conditions. Emerging sensor and digital technologies offer a promising approach for direct phenotyping of plants in farm environments. This study investigates a learning-based phenotyping method using neural implicit surfaces reconstruction to achieve accurate in situ phenotyping of pepper plants in greenhouse environments. To quantitatively evaluate the performance of this method, traditional point cloud registration on 3D scanning data is implemented for comparison. Experimental result shows that NIR (neural implicit surfaces reconstruction) achieves competitive accuracy compared to the 3D scanning method. The mean distance error between the scanner-based method and the NeRF (neural radiance fields)-based method is 0.811 mm. This study shows that the learning-based NeRF method has similar accuracy to the 3D scanning-based method but with greater scalability and faster deployment capabilities.
Why it matches plant phenotyping methods植物の3D表現型を取得するNeRFベース手法を開発し、3Dスキャン法と精度比較・検証しており、表現型取得法が研究の中心である。
abstractThis study investigates a learning-based phenotyping method using neural implicit surfaces reconstruction to achieve accurate in situ phenotyping of pepper plants in greenhouse environments.
The three-dimensional reconstruction of fruit trees plays a crucial role in assessing their growth status, analyzing agronomic traits, and categorizing their organs. This is vital for implementing intelligent orchard management. This study aims to develop a cost-effective and efficient method for the three-dimensional reconstruction and skeleton extraction of fruit trees. The proposed method leverages the 3D geometric structure captured by Time-of-Flight (TOF) sensors and addresses common issues such as occlusion and perspective ambiguity. Firstly, the TOF sensor and its supporting components are used to build an acquisition platform to collect the full range point cloud of fruit trees in the key growth period. The noise information is filtered through the point cloud preprocessing operation to obtain the complete target point cloud and extract its structural invariant features. The IWOA-RANSAC-NDT algorithm is introduced for 3D model registration. Secondly, the Delaunay triangulation algorithm and Dijkstra shortest path algorithm are used to calculate the Minimum Spanning Tree. Branch segmentation is expedited using the Kd-tree data structure. The Levenberg Marquardt algorithm and the cylindrical fitting method are used to obtain the full fruit tree skeleton model. Finally, taking walnut tree as the experimental object, a high-precision fruit tree point cloud model is constructed, and the actual verification is carried out based on the measured data. Findings indicate that the proposed methodology can accurately construct both 3D point cloud and skeleton models of fruit trees with accuracy deviations from the measured data remaining within 7 %. The proposed method offers valuable data and technical support for the future development of highly autonomous, practical, and user-oriented fruit tree pruning systems.
Why it matches plant phenotyping methods果樹の3D形態・骨格を取得および抽出するTOFセンサベースの手法と取得プラットフォームを開発し、実測データで検証しているため、植物フェノタイピング手法が中心である。
abstractThis study aims to develop a cost-effective and efficient method for the three-dimensional reconstruction and skeleton extraction of fruit trees.
Common beanMultispectral / hyperspectralWhole plant / canopy / plot / fieldObject detectionImage / point-cloud registrationGrowth / development / phenology
Green roofs offer ecological benefits but harsh rooftop environment stressors like heat, water scarcity, and wind can limit optimal plant growth. Monitoring plant health is crucial for optimizing green roof performance and remote sensing provides a non-destructive approach, yet challenges persist in tight, urban settings. This allows for close-range ground monitoring as a viable solution in these emerging environments. Recent studies explored automatic image registration techniques, showing promise in homogeneous settings, but faced uncertainties in mixed species systems or early plant growth stages. Feature detection techniques such as Speeded up Robust Features (SURF) using fixed and moving image spaces have been proposed for alignment. This study aimed to assess feature detection, matching, and image registration techniques in mixed species plant communities on green roofs throughout the growing season. This study developed a sophisticated monitoring system using close-range multispectral sensors for aligning bands in mixed species plant communities, contributing to enhanced green roof management and sustainability. The results of the study showed no significant differences in band alignment accuracy between growth stages for mixed species bush bean/sedum and single species sedum modules, but significant differences were found in single species bush bean systems. Additionally, mixed species modules showed better accuracy compared to single species bush bean modules, indicating that heterogenous systems provide better alignment accuracy due to more diverse feature extractions.
Why it matches plant phenotyping methods混合集団植物の近接マルチスペクトル画像について、特徴検出・バンドマッチング・画像位置合わせを開発・評価する研究であり、植物モニタリング用の画像取得・解析手法が中心である。
abstractThis study aimed to assess feature detection, matching, and image registration techniques in mixed species plant communities on green roofs throughout the growing season.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Abstract Background The early and specific detection of abiotic and biotic stresses, particularly their combinations, is a major challenge for maintaining and increasing plant productivity in sustainable agriculture under changing environmental conditions. Optical imaging techniques enable cost-efficient and non-destructive quantification of plant stress states. Monomodal detection of certain stressors is usually based on non-specific/indirect features and therefore is commonly limited in their cross-specificity to other stressors. The fusion of multi-domain sensor systems can provide more potentially discriminative features for machine learning models and potentially provide synergistic information to increase cross-specificity in plant disease detection when image data are fused at the pixel level. Results In this study, we demonstrate successful multi-modal image registration of RGB, hyperspectral (HSI) and chlorophyll fluorescence (ChlF) kinetics data at the pixel level for high-throughput phenotyping ofA. thalianagrown in Multi-well plates and an assay with detached leaf discs ofRosa × hybridainoculated with the black spot disease-inducing fungusDiplocarpon rosae. Here, we showcase the effects of (i) selection of reference image selection, (ii) different registrations methods and (iii) frame selection on the performance of image registration via affine transform. In addition, we developed a combined approach for registration methods through NCC-based selection for each file, resulting in a robust and accurate approach that sacrifices computational time. Since image data encompass multiple objects, the initial coarse image registration using a global transformation matrix exhibited heterogeneity across different image regions. By employing an additional fine registration on the object-separated image data, we achieved a high overlap ratio. Specifically, for theA. thalianatest set, the overlap ratios (ORConvex) were 98.0 ± 2.3% for RGB-to-ChlF and 96.6 ± 4.2% for HSI-to-ChlF. For theRosa × hybridatest set, the values were 98.9 ± 0.5% for RGB-to-ChlF and 98.3 ± 1.3% for HSI-to-ChlF. Conclusion The presented multi-modal imaging pipeline enables high-throughput, high-dimensional phenotyping of different plant species with respect to various biotic or abiotic stressors. This paves the way for in-depth studies investigating the correlative relationships of the multi-domain data or the performance enhancement of machine learning models via multi modal image fusion.
Why it matches plant phenotyping methodsRGB・HSI・クロロフィル蛍光画像の画素レベル登録手法と統合パイプラインを開発・評価し、高スループット植物表現型解析に直接利用しているため。
abstractwe demonstrate successful multi-modal image registration of RGB, hyperspectral (HSI) and chlorophyll fluorescence (ChlF) kinetics data at the pixel level for high-throughput phenotyping
Background Quantitative disease resistance (QR) is a complex, dynamic trait that is most reliably quantified in field-grown crops. Traditional disease assessments offer limited potential to disentangle the contributions of different components to overall QR at critical crop developmental stages. Yet, a better functional understanding of QR could greatly support a more targeted, knowledge-based selection for QR and improve predictions of seasonal epidemics. Image-based approaches together with advanced image processing methodologies recently emerged as valuable tools to standardize relevant disease assessments, increase measurement throughput, and describe diseases along multiple dimensions. Results We present a simple, affordable, and easy-to-operate imaging set-up and imaging procedure for in-field acquisition of wheat leaf image sequences. The development of Septoria tritici blotch and leaf rusts was monitored over time via robust methods for symptom detection and segmentation, spatial alignment of images, symptom tracking, and leaf- and symptom characterization. The average accuracy of the spatial alignment of images in a time series was approximately 5 pixels (~ 0.15 mm). Leaf-level symptom counts as well as individual symptom property measurements revealed stable patterns over time that were generally in excellent agreement with visual impressions. This provided strong evidence for the robustness of the methodology to variability typically inherent in field data. Contrasting patterns in the number of lesions resulting from separate infection events and lesion expansion dynamics were observed across wheat genotypes. The number of separate infection events and average lesion size contributed to different degrees to overall disease intensity, possibly indicating distinct and complementary mechanisms of QR. Conclusions The proposed methodology enables rapid, non-destructive, and reproducible measurement of several key epidemiological parameters under field conditions. Such data can support decomposition and functional understanding of QR as well as the parameterization, fine-tuning, and validation of epidemiological models. Details of pathogenesis can translate into specific symptom phenotypes resolvable using time series of high-resolution RGB images, which may improve biological understanding of plant-pathogen interactions as well as interactions in disease complexes.
Why it matches plant phenotyping methods圃場での植物病徴を画像から取得・追跡・定量する撮像および画像解析手法を開発・検証しており、植物表現型測定が中心である。
abstractWe present a simple, affordable, and easy-to-operate imaging set-up and imaging procedure for in-field acquisition of wheat leaf image sequences.
Reproduction assets foundThe paper explicitly states that all image-processing/analysis code is publicly available on the authors' GitHub repository, and that a sample dataset plus the trained reference mark detection model are downloadable from the ETH Research Collection. Both are paper-specific, public, and actionable.Code · publicAll code related to the processing of image time series and leaf- and lesion-level trait extraction is available from https://github.com/and-jonas/sympathique-wheat for documentation.Open asset ↗and-jonas/sympathique-wheatlines:98-107Dataset · publicA sample data set and the trained reference mark detection model can be downloaded from ETH research collection at https://doi.org/10.3929/ethz-b-000659812 .Open asset ↗10.3929/ethz-b-000659812lines:98-107Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published30 Sept 2024Journal of the Korea Academia-Industrial cooperation SocietyCited by 0 · OpenAlex ↗
컴퓨터 비전 분야에서 객체 분할은 식물 영상에서 표현형 특징을 정량화하고 식별 및 분류를 위한 중요한 작업이다. 분할의 목적은 영상의 표현을 좀 더 의미있고 해석하기 쉽도록 단순화하거나 변환하는 것이고, 그중에서도 의미적 분할은 영상을 픽셀별로 분류하는 것이다. 본 연구에서는 멀티 렌즈 카메라를 사용해서 식물의 다중분광 영상을 얻은 후, 각 밴드별 영상을 정합하여 의미적 분할 데이터셋을 구축하는 방법을 제안한다. 촬영에 사용한 카메라는 7개의 렌즈로 각각 단일 파장의 영상을 취득하는 시스템이기 때문에 분석을 위해서는 영상을 정합하는 과정이 필수적이다. 영상 정합에는 칼라와 관련된 5개의 파장 영상 중 하나를 기준으로 나머지 영상을 정합하는 방식을 적용했다. 정합을 위한 방법으로는 ORB를 사용하였다. 그리고 정합된 영상들을 기반으로 딥러닝 학습을 위한 의미적 분할 데이터셋을 구축한다. 식물은 일반적으로 가시광 영역에서 green 채널의 픽셀 값이 red, blue 채널에 비해 상대적으로 높은 값을 가지는 경향이 있으며, 적외선 영역에서도 픽셀 값이 크다는 특성이 있다. 그러므로 R, G, B, NIR 파장을 모두 활용해서 픽셀 값에 적절한 임계값을 설정하면 영상에서 식물 부분만 의미적 분할하는 것이 가능하다. 실험을 통해 DeepLab v3+을 사용하여 학습 데이터 셋 100장을 기준으로 Mean IOU 0.991142, Cross Entropy 0.011507의 결과를 얻었다. 본 연구를 통해 RGB 영상만으로도 라벨링없이 식물의 의미적 분할 영상 데이터 양을 쉽게 늘릴 수 있다.
Why it matches plant phenotyping methods植物画像の多波長画像位置合わせと閾値ベースの意味分割により、植物領域を抽出するデータセット構築手法が中心であり、植物表現型解析のための画像取得・抽出ワークフローに該当する。
abstract본 연구에서는 멀티 렌즈 카메라를 사용해서 식물의 다중분광 영상을 얻은 후, 각 밴드별 영상을 정합하여 의미적 분할 데이터셋을 구축하는 방법을 제안한다.
Multiple source images acquired from diverse sensors mounted on unmanned aerial vehicles (UAVs) offer valuable complementary information for ground vegetation analysis. However, accurately aligning heterogeneous UAV images poses challenges due to differences in geometry, intensity, and noise resulting from varying imaging principles. This paper presents a two-stage registration method aimed at fusing visible RGB and multispectral images for cotton leaf lesion grading. The coarse alignment stage utilizes Scale Invariant Feature Transform (SIFT), while the refined alignment stage employs a novel correlation coefficient-based template matching. The proposed method first employs the EfficientDet network to detect infected cotton leaves with lesions in RGB images. Subsequently, lesion leaves in multiple spectral imagery (red, green, red edge, and near-infrared bands) are located using the perspective transformation matrix derived from SIFT and the coordinates of lesion leaves in RGB images. Refined registration between RGB and multispectral imagery is achieved through template matching with the new correlation coefficient. The registered reflectance data from the different spectral bands and RGB components are utilized to classify pixels in each infected leaf into lesion, healthy, and soil parts. The lesion grade is determined based on the ratio of lesion pixels to the total corresponding leaf area. Experimental results, compared with manual assessment, demonstrate a lesion leaves detection model with a mAP@0.5 of 91.01% and a leaf lesion grading accuracy of 92.01%. These results validate the suitability of the proposed method for UAV RGB and multispectral image registration, enabling automated cotton leaf lesion grading.
Why it matches plant phenotyping methodsUAV RGB・マルチスペクトル画像の位置合わせと病斑画素抽出を開発・検証し、ワタ葉の病斑重症度という植物状態を自動推定しているため、フェノタイピング手法が中心である。
abstractThis paper presents a two-stage registration method aimed at fusing visible RGB and multispectral images for cotton leaf lesion grading.
Cotton is one of the crops that requires the most time and labor. Precision agriculture technology is required for efficient management of cotton, and the identification of cotton attribute information in the field is a necessary and crucial step towards implementing precision agriculture. Unmanned aerial vehicles (UAVs) and Light Detection and Ranging (LiDAR) have evolved into essential instruments for plant phenotyping research. In this study, in order to address the demand for cotton attribute identification over wide areas in the field, an airborne LiDAR system was built based on LiDAR detection technology. This work acquired a dual-view point cloud of a cotton field in order to address the high density and low accuracy of the cotton point cloud attributes. Following pre-processing of the data, the point cloud was first coarsely regenerated using a combination of Fast Point Feature Histograms (FPFH) and Intrinsic Shape Signatures (ISS) techniques. The dual-view point cloud registration was then refined and finished using an Iterative Closest Point (ICP) algorithm. The height of the cotton plant was determined using the reconstructed point cloud of the cotton canopy, and a method combining Graham’s algorithm and the Alpha-Shape algorithm was suggested to determine the porosity of the cotton layers. The findings revealed that the root mean square errors (RMSE) between calculated and measured values of cotton plant height and stratified porosity were, respectively, 3.98 cm and 5.21%, and that their mean absolute percentage errors (MAPE) were 4.39% and 9.31%, with correlation coefficients (R2) of 0.951 and 0.762, respectively. On the whole, our study has demonstrated the effectiveness of the proposed method in terms of providing accurate and reliable cotton parameters in agriculture.
Why it matches plant phenotyping methods綿花キャノピーの点群取得・再構成・特徴量抽出手法を開発し、草高と層別空隙率を実測値と比較して検証しているため、植物フェノタイピング手法が中心である。
abstractIn this study, in order to address the demand for cotton attribute identification over wide areas in the field, an airborne LiDAR system was built based on LiDAR detection technology.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 7 Sept 2026
Understanding the complex interactions between genotype-environment dynamics is fundamental for optimizing crop improvement. However, traditional phenotyping methods limit assessments to the end of the growing season, restricting continuous crop monitoring. To address this limitation, we developed a methodology for spatiotemporal registration of time-series 3D point cloud data, enabling field phenotyping over time for accurate crop growth tracking. Leveraging multi-scan terrestrial laser scanning (TLS), we captured high-resolution 3D LiDAR data in a cotton breeding field across various stages of the growing season to generate four-dimensional (4D) crop models, seamlessly integrating spatial and temporal dimensions. Our registration procedure involved an initial pairwise terrain-based matching for rough alignment, followed by a bird’s-eye view adjustment for fine registration. Point clouds collected throughout nine sessions across the growing season were successfully registered both spatially and temporally, with average registration errors of approximately 3 cm. We used the generated 4D models to monitor canopy height (CH) and volume (CV) for eleven cotton genotypes over two months. The consistent height reference established via our spatiotemporal registration process enabled precise estimations of CH ( R 2 = 0.95, RMSE = 7.6 cm). Additionally, we analyzed the relationship between CV and the interception of photosynthetically active radiation (IPAR f ), finding that it followed a curve with exponential saturation, consistent with theoretical models, with a standard error of regression (SER) of 11%. In addition, we compared mathematical models from the Richards family of sigmoid curves for crop growth modeling, finding that the logistic model effectively captured CH and CV evolution, aiding in identifying significant genotype differences. Our novel TLS-based digital phenotyping methodology enhances precision and efficiency in field phenotyping over time, advancing plant phenomics and empowering efficient decision-making for crop improvement efforts.
Why it matches plant phenotyping methodsTLSによる時系列3D点群の登録と4D作物モデル構築を開発し、綿の草高・群落体積を継続的に推定・検証することが研究の中心である。
abstractwe developed a methodology for spatiotemporal registration of time-series 3D point cloud data, enabling field phenotyping over time for accurate crop growth tracking.
The use of multiple camera technologies in a combined multimodal monitoring system for plant phenotyping offers promising benefits. Compared to configurations that only utilize a single camera technology, cross-modal patterns can be recorded that allow a more comprehensive assessment of plant phenotypes. However, the effective utilization of cross-modal patterns is dependent on precise image registration to achieve pixel-accurate alignment, a challenge often complicated by parallax and occlusion effects inherent in plant canopy imaging. In this study, we propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process. By leveraging depth data, our method mitigates parallax effects and thus facilitates more accurate pixel alignment across camera modalities. Additionally, we introduce an automated mechanism to identify and differentiate different types of occlusions, thereby minimizing the introduction of registration errors. To evaluate the efficacy of our approach, we conduct experiments on a diverse image dataset comprising six distinct plant species with varying leaf geometries. Our results demonstrate the robustness of the proposed registration algorithm, showcasing its ability to achieve accurate alignment across different plant types and camera compositions. Compared to previous methods it is not reliant on detecting plant specific image features and can thereby be utilized for a wide variety of applications in plant sciences. The registration approach principally scales to arbitrary numbers of cameras with different resolutions and wavelengths. Overall, our study contributes to advancing the field of plant phenotyping by offering a robust and reliable solution for multimodal image registration.
Why it matches plant phenotyping methods植物フェノタイピングのためのマルチモーダル3D画像登録手法を開発し、複数植物種の画像データセットで性能評価しているため、方法が研究の中心である。
abstractIn this study, we propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process.
Reproduction assets foundThe paper's multimodal plant image dataset (six plant species recorded with the RGBD/thermal/hyperspectral setup) is publicly available on the authors' GitHub repository, which is an allowed URL.Dataset · publiclity of our registration algorithm across diverse scenarios, we recorded a dataset comprising images of six distinct plant species. This was done to encompass a wide variety of leaf and canopy structures, thus offering a representative sample for evaluation purposes. The recorded dataset can be found on the project github page: https://github.com/eric-stumpe/Plant3DImageReg . The chosen plant species are as follows:
1.
Grapevine ( Vitis vinifera )
2.
Leopard lily ( Dieffenbachia )
3.Open asset ↗eric-stumpe/Plant3DImageReglines:287-310Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
In recent years, the integration of smartphone technology with novel sensing technologies, Artificial Intelligence (AI), and Deep Learning (DL) algorithms has revolutionized crop pest and disease surveillance. Efficient and accurate diagnosis is crucial to mitigate substantial economic losses in agriculture caused by diseases and pests. An innovative Apple® and Android™ mobile application for citizen science has been developed, to enable real-time detection and identification of plant leaf diseases and pests, minimizing their impact on horticulture, viticulture, and olive cultivation. Leveraging DL algorithms, this application facilitates efficient data collection on crop pests and diseases, supporting crop yield protection and cost reduction in alignment with the Green Deal goal for 2030 by reducing pesticide use. The proposed citizen science tool involves all Farm to Fork stakeholders and farm citizens in minimizing damage to plant health by insect and fungal diseases. It utilizes comprehensive datasets, including images of various diseases and insects, within a robust Decision Support System (DSS) where DL models operate. The DSS connects directly with users, allowing them to upload crop pest data via the mobile application, providing data-driven support and information. The application stands out for its scalability and interoperability, enabling the continuous integration of new data to enhance its capabilities. It supports AI-based imaging analysis of quarantine pests, invasive alien species, and emerging and native pests, thereby aiding post-border surveillance programs. The mobile application, developed using a Python-based REST API, PostgreSQL, and Keycloak, has been field-tested, demonstrating its effectiveness in real-world agriculture scenarios, such as detecting Tuta absoluta (Meyrick) infestation in tomato cultivations. The outcomes of this study in T. absoluta detection serve as a showcase scenario for the proposed citizen science tool’s applicability and usability, demonstrating a 70.2% accuracy (mAP50) utilizing advanced DL models. Notably, during field testing, the model achieved detection confidence levels of up to 87%, enhancing pest management practices.
Why it matches plant phenotyping methods植物の葉画像から病害・害虫状態を推定するAI搭載スマートフォン／市民科学プラットフォームを開発し、野外試験と検出精度評価まで行っており、植物状態の取得・抽出法が中心である。
abstractAn innovative Apple® and Android™ mobile application for citizen science has been developed, to enable real-time detection and identification of plant leaf diseases and pests
3D reconstruction of seedling can provide comprehensive and quantitative spatial structure information, offering an effective digital tool for breeding research. However, accurate and efficient reconstruction of seedling is still a challenging work due to limited performance of depth sensor for seedling with small-size stem and unavoidable error for multi-view point cloud registration. Therefore, in this paper, we propose an accurate multi-view 3D reconstruction method for seedling using 2D image contour to constrain 3D point cloud. The rotation axis is calibrated and optimised by minimising point-to-contour distance between 2D image contour and projected exterior points from 3D point cloud. Then, to remove outliers and noise, we introduce the seedling mask of 2D image to constrained and delete projected outlier points of 3D model from corresponding view. Furthermore, we propose a residual-guided method to recognise missing region for 3D model and complete 3D model of small-size stem. Finally, we can obtain an accurate 3D model of seedling. The reconstruction accuracy is evaluated by average distance between projected contour of 3D model and 2D image contour of all views (0.3185 mm). Then, the phenotypic parameters were calculated from 3D model and the results are close to manual measurements (Plant height: R² = 0.98, RMSE = 2.3 mm, rRMSE = 1.52%; Petioles inclination angle: R² = 0.99, RMSE = 0.73°, rRMSE = 1.41%; Leaf area: R² = 0.66, RMSE = 1.05 cm², rRMSE = 7.63%; Leaf inclination angle: R² = 0.99, RMSE = 1.01°, rRMSE = 1.72%; Stem diameter: R² = 0.95, RMSE = 0.12 mm, rRMSE = 5.43%). Breeders can improve the selection of more resilient varieties and cultivars to different growing conditions starting from the dynamic analysis of their phenotype.
Why it matches plant phenotyping methods苗の多視点3D再構成法を開発し、輪郭制約による精度評価と複数の表現型形質の手測定比較を行っており、表現型取得手法が研究の中心です。
abstractwe propose an accurate multi-view 3D reconstruction method for seedling using 2D image contour to constrain 3D point cloud.
Field / plotRGB-D / ToFStem / branchImage / point-cloud registrationSegmentation
Automated robots are emerging as a solution for labor-intensive fruit orchard management. Three-dimensional (3D) reconstruction of tree branches is a fundamental requirement for robots to perform tasks like pruning and fruit harvesting. Current branch sensing methods often rely on planar segmentation with limited 3D information or computationally expensive point cloud segmentation, which may not be suitable for natural orchards with obscured tree branches. This study proposes a novel scheme that reconstructs occluded branches from RGB-D (Red-Green-Blue-Depth) images by integrating the point clouds converted from planar segmentation masks and depth images. The proposed approach extends the existing 2D branch sensing techniques to 3D, leveraging multi-view information. The deep learning models DeeplabV3+ and Pix2pix are employed to generate the segmentation masks, separately. And the Fast Global Registration (FGR) is used to register the multi-view point clouds. The results demonstrate that the output point clouds have at least a 24 % increase in the number of corresponding points after FGR. Furthermore, the time cost per hundred corresponding points is reduced by 85 % and 69 % when using the DeepLabV3 + and Pix2pix-based schemes, respectively, compared to the PointNet++ approach. These findings indicate that the proposed scheme significantly improves the sensing of occluded branches in terms of output richness and computational efficiency, making it applicable to natural orchard working spaces.
Why it matches plant phenotyping methodsRGB-D画像のセグメンテーションと点群登録により、遮蔽された樹枝の3D形状を再構成する植物形質センシング手法の開発が中心である。
abstractThis study proposes a novel scheme that reconstructs occluded branches from RGB-D (Red-Green-Blue-Depth) images by integrating the point clouds converted from planar segmentation masks and depth images.
LiDAR / point cloudRGB-D / ToFImage / point-cloud registration
Abstract Precision agriculture benefits from point set registration, which can monitor plant health and growth in real time, promote the precise application of fertilizers and pesticides, and provide technical support for achieving sustainable development of agriculture. In this work, we propose a robust point set registration method for precision agriculture based on L*a*b* color guidance, bidirectional search and Cauchy distribution. First, the L*a*b* color guidance is applied to establish accurate correspondences between agricultural RGB‐D data. Second, the bidirectional nearest neighbor search strategy between point sets improves the reliability of establishing correspondences and broadens the convergence domain of the algorithm. Third, Cauchy distribution is utilized as an energy function for noise suppression, which further improves the robustness of the algorithm in dealing with complex vegetation scenes. Finally, results of ablation and simulation experiments indicate that the proposed registration algorithm can achieve more accurate and robust alignment results than other classic and state‐of‐the‐art point cloud registration algorithms to achieve monitoring and comparison of plant growth.
Why it matches plant phenotyping methods植物RGB-D点群を対象に、色彩誘導・双方向探索・Cauchyカーネルを用いた点群位置合わせ手法を開発し、植物の成長モニタリングと比較に適用・評価しているため、表現型取得の中核手法に該当する。
abstractwe propose a robust point set registration method for precision agriculture based on L*a*b* color guidance, bidirectional search and Cauchy distribution.
ABSTRACT An integrated sensing device for irrigation scheduling was developed to assess the soil–plant–atmosphere continuum for irrigation scheduling. A field experiment was carried out to evaluate ISDI performance and CWSI estimation across various irrigation regimes in wheat crop at WTC farm, ICAR-IARI, New Delhi, India. The experiment considered were full irrigation (FI) and various deficit irrigation levels (DI-15, DI-30, DI-45, and DI-60), receiving 15, 30, 45, and 60% less water in comparison to FI, respectively. The calibration and performance of the ISDI sensor probes was done with gravimetric methods along with time domain reflectometry (TDR) and a handheld infrared thermometer. The field calibration of the ISDI's soil moisture probe and TDR gave promising results, with R2 values ranging from 0.76 to 0.81 and 0.81 to 0.86, respectively, for soil depths up to 45 cm. ISDI's infrared sensor probe also demonstrated strong alignment with a handheld infrared thermometer (R2: 0.95), indicating reliable methods. Furthermore, a regression equation of lower baseline and upper threshold for CWSI computation was derived as (Tc–Ta)ll = 1.97 × VPD – 1.43 (R2:0.86) and 1.93 °C, respectively. It was recommended to initiate irrigation when CWSI ≥ 0.35 for wheat to achieve optimal crop yields.
Why it matches plant phenotyping methods小麦の水ストレス状態を推定する統合センシング装置を開発し、土壌水分・赤外温度センサーとCWSI推定を校正・検証しており、植物状態の取得手法が中心である。
abstractAn integrated sensing device for irrigation scheduling was developed to assess the soil–plant–atmosphere continuum for irrigation scheduling.
Stem diameter is a critical phenotypic parameter for maize, integral to yield prediction and lodging resistance assessment. Traditionally, the quantification of this parameter through manual measurement has been the norm, notwithstanding its tedious and laborious nature. To address these challenges, this study introduces a non-invasive field-based system utilizing depth information from RGB-D cameras to measure maize stem diameter. This technology offers a practical solution for conducting rapid and non-destructive phenotyping. Firstly, RGB images, depth images, and 3D point clouds of maize stems were captured using an RGB-D camera, and precise alignment between the RGB and depth images was achieved. Subsequently, the contours of maize stems were delineated using 2D image processing techniques, followed by the extraction of the stem's skeletal structure employing a thinning-based skeletonization algorithm. Furthermore, within the areas of interest on the maize stems, horizontal lines were constructed using points on the skeletal structure, resulting in 2D pixel coordinates at the intersections of these horizontal lines with the maize stem contours. Subsequently, a back-projection transformation from 2D pixel coordinates to 3D world coordinates was achieved by combining the depth data with the camera's intrinsic parameters. The 3D world coordinates were then precisely mapped onto the 3D point cloud using rigid transformation techniques. Finally, the maize stem diameter was sensed and determined by calculating the Euclidean distance between pairs of 3D world coordinate points. The method demonstrated a Mean Absolute Percentage Error ( MAPE ) of 3.01%, a Mean Absolute Error ( MAE ) of 0.75 mm, a Root Mean Square Error ( RMSE ) of 1.07 mm, and a coefficient of determination ( R ²) of 0.96, ensuring accurate measurement of maize stem diameter. This research not only provides a new method of precise and efficient crop phenotypic analysis but also offers theoretical knowledge for the advancement of precision agriculture.
Why it matches plant phenotyping methodsRGB-Dカメラと画像・3D処理によりトウモロコシ茎径を非破壊測定する手法を開発し、誤差指標で精度検証しており、フェノタイピング手法が中心である。
abstractthis study introduces a non-invasive field-based system utilizing depth information from RGB-D cameras to measure maize stem diameter
Reproduction assets foundThe paper's data availability statement points to a public Figshare deposit (DOI 10.6084/m9.figshare.25450039) containing the study's datasets (RGB/depth imagery and stem diameter measurements used for the maize stem diameter phenotyping analysis). No author analysis code or trained models are explicitly deposited.Dataset · publicThe datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: http://dx.doi.org/10.6084/m9.figshare.25450039 .Open asset ↗figshare · 10.6084/m9.figshare.25450039lines:909-917Plant phenotyping relevance match · UnverifiedOpenAlex · checked 15 Sept 2026
Traditional field phenotyping methods are often manual, time-consuming, and destructive, posing a challenge for breeding progress. To address this bottleneck, robotics and automation technologies offer efficient sensing tools to monitor field evolution and crop development throughout the season. This study aimed to develop an autonomous ground robotic system for LiDAR-based field phenotyping in plant breeding trials. A Husky platform was equipped with a high-resolution three-dimensional (3D) laser scanner to collect in-field terrestrial laser scanning (TLS) data without human intervention. To automate the TLS process, a 3D ray casting analysis was implemented for optimal TLS site planning, and a route optimization algorithm was utilized to minimize travel distance during data collection. The platform was deployed in two cotton breeding fields for evaluation, where it autonomously collected TLS data. The system provided accurate pose information through RTK-GNSS positioning and sensor fusion techniques, with average errors of less than 0.6 cm for location and 0.38$^{\circ}$ for heading. The achieved localization accuracy allowed point cloud registration with mean point errors of approximately 2 cm, comparable to traditional TLS methods that rely on artificial targets and manual sensor deployment. This work presents an autonomous phenotyping platform that facilitates the quantitative assessment of plant traits under field conditions of both large agricultural fields and small breeding trials to contribute to the advancement of plant phenomics and breeding programs.
Why it matches plant phenotyping methods自律走行ロボットとLiDAR/TLSによる圃場フェノタイピング基盤を開発・評価しており、植物形質を定量評価するための取得・解析手法が研究の中心である。
abstractThis study aimed to develop an autonomous ground robotic system for LiDAR-based field phenotyping in plant breeding trials.
Germline cells are critical for transmitting genetic information to subsequent generations in biological organisms. While their differentiation from somatic cells during embryonic development is well-documented in most animals, the regulatory mechanisms initiating plant germline cells are not well understood. To thoroughly investigate the complex morphological transformations of their ultrastructure over developmental time, nanoscale 3D reconstruction of entire plant tissues is necessary, achievable exclusively through electron microscopy imaging. This paper presents a full-process framework designed for reconstructing large-volume plant tissue from serial electron microscopy images. The framework ensures end-to-end direct output of reconstruction results, including topological networks and morphological analysis. The proposed 3D cell alignment, denoise, and instance segmentation pipeline (3DCADS) leverages deep learning to provide a cell instance segmentation workflow for electron microscopy image series, ensuring accurate and robust 3D cell reconstructions with high computational efficiency. The pipeline involves five stages: the registration of electron microscopy serial images; image enhancement and denoising; semantic segmentation using a Transformer-based neural network; instance segmentation through a supervoxel-based clustering algorithm; and an automated analysis and statistical assessment of the reconstruction results, with the mapping of topological connections. The 3DCADS model's precision was validated on a plant tissue ground-truth dataset, outperforming traditional baseline models and deep learning baselines in overall accuracy. The framework was applied to the reconstruction of early meiosis stages in the anthers of Arabidopsis thaliana, resulting in a topological connectivity network and analysis of morphological parameters and characteristics of cell distribution. The experiment underscores the 3DCADS model's potential for biological tissue identification and its significance in quantitative analysis of plant cell development, crucial for examining samples across different genetic phenotypes and mutations in plant development. Additionally, the paper discusses the regulatory mechanisms of Arabidopsis thaliana's germline cells and the development of stamen cells before meiosis, offering new insights into the transition from somatic to germline cell fate in plants.
Why it matches plant phenotyping methods植物組織の3D画像再構成・細胞インスタンス分割・形態解析を行う手法が研究の中心であり、植物組織データセットで検証されています。
abstractThis paper presents a full-process framework designed for reconstructing large-volume plant tissue from serial electron microscopy images.
Field / plotLiDAR / point cloudCalibration / preprocessingImage / point-cloud registration
The creation of precise and high-resolution crop point clouds in agricultural fields has become a key challenge for high-throughput phenotyping applications. This work implements a novel calibration method to calibrate the laser scanning system of an agricultural field robot consisting of two industrial-grade laser scanners used for high-precise 3D crop point cloud creation. The calibration method optimizes the transformation between the scanner origins and the robot pose by minimizing 3D point omnivariances within the point cloud. Moreover, we present a novel factor graph-based pose estimation method that fuses total station prism measurements with IMU and GNSS heading information for high-precise pose determination during calibration. The root-mean-square error of the distances to a georeferenced ground truth point cloud results in 0.8 cm after parameter optimization. Furthermore, our results show the importance of a reference point cloud in the calibration method needed to estimate the vertical translation of the calibration. Challenges arise due to non-static parameters while the robot moves, indicated by systematic deviations to a ground truth terrestrial laser scan.
Why it matches plant phenotyping methods農業用フィールドロボットのレーザースキャナによる作物3D点群取得を対象とし、スキャナ校正・姿勢推定法を開発して精度検証しているため、植物表現型取得基盤の技術論文として中心的である。
abstractThis work implements a novel calibration method to calibrate the laser scanning system of an agricultural field robot consisting of two industrial-grade laser scanners used for high-precise 3D crop point cloud creation.
Accurate collection of plant phenotyping is critical to optimising sustainable farming practices in precision agriculture. Traditional phenotyping in controlled laboratory environments, while valuable, falls short in understanding plant growth under real-world conditions. Emerging sensor and digital technologies offer a promising approach for direct phenotyping of plants in farm environments. This study investigates a learning-based phenotyping method using the Neural Radiance Field to achieve accurate in-situ phenotyping of pepper plants in greenhouse environments. To quantitatively evaluate the performance of this method, traditional point cloud registration on 3D scanning data is implemented for comparison. Experimental result shows that NeRF(Neural Radiance Fields) achieves competitive accuracy compared to the 3D scanning methods. The mean distance error between the scanner-based method and the NeRF-based method is 0.865mm. This study shows that the learning-based NeRF method achieves similar accuracy to 3D scanning-based methods but with improved scalability and robustness.
Why it matches plant phenotyping methodsNeRFを用いた植物の3D表現・形質取得法を開発し、3Dスキャン法との精度比較で検証しており、フェノタイピング手法が研究の中心である。
abstractThis study investigates a learning-based phenotyping method using the Neural Radiance Field to achieve accurate in-situ phenotyping of pepper plants in greenhouse environments.
Abstract Background. Quantitative disease resistance (QR) is a complex, dynamic trait that is most reliably quantified in field-grown crops. Traditional disease assessments offer limited potential to disentangle the contributions of different components to overall QR at critical crop developmental stages. Yet, a better functional understanding of QR could greatly support a more targeted, knowledge-based selection for QR and improve predictions of seasonal epidemics. Image-based approaches together with advanced image processing methodologies recently emerged as valuable tools to standardize relevant disease assessments, increase measurement throughput, and describe diseases along multiple dimensions. Results. We present a simple, affordable, and easy-to-operate imaging set-up and imaging procedure for in-field acquisition of wheat leaf image sequences. The development of Septoria tritici blotch and leaf rusts was monitored over time via robust methods for symptom detection and segmentation, image registration, symptom tracking, and leaf- and symptom characterization. The average accuracy of the co-registration of images in a time series was approximately 5 pixels (~ 0.15 mm). Leaf-level symptom counts as well as individual symptom property measurements revealed stable patterns over time that were generally in excellent agreement with visual impressions. This provided strong evidence for the robustness of the methodology to variability typically inherent in field data. Contrasting patterns in lesion numbers and lesion expansion dynamics were observed across wheat genotypes. The number of separate infection events and average lesion size contributed to different degrees to overall disease intensity, possibly indicating distinct and complementary mechanisms of QR. Conclusions. The proposed methodology enables rapid, non-destructive, and reproducible measurement of several key epidemiological parameters under natural field conditions. Such data can support decomposition and functional understanding of QR as well as the parameterization, fine-tuning, and validation of epidemiological models. Details of pathogenesis can translate into specific symptom phenotypes resolvable using time series of high-resolution RGB images, which may improve biological understanding of plant-pathogen interactions as well as interactions in disease complexes.
Why it matches plant phenotyping methods圃場での画像取得、症状検出・追跡・セグメンテーション、葉および病斑形質の定量化手法を開発・検証しており、植物病害表現型の取得が研究の中心です。
abstractWe present a simple, affordable, and easy-to-operate imaging set-up and imaging procedure for in-field acquisition of wheat leaf image sequences.
Reproduction assets foundThe paper explicitly states that all image-processing/analysis code is available at the authors' GitHub repository (and-jonas/sympathique-wheat), and that a sample data set plus the trained reference mark detection model can be downloaded from the ETH research collection (doi 10.3929/ethz-b-000659812). Both are paper-Code · publicAll code related to the processing of image time series and leaf- and lesion-level trait extraction is available from https://github.com/and-jonas/sympathique-wheat for documentation.Open asset ↗and-jonas/sympathique-wheatlines:80-87Dataset · publicA sample data set and the trained reference mark detection model can be downloaded from ETH research collection at https://doi.org/10.3929/ethz-b-000659812 .Open asset ↗10.3929/ethz-b-000659812lines:80-87Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Mar 2024Computers and Electronics in Agriculture.
MaizeLiDAR / point cloudLeafMorphology / geometry measurement2D/3D reconstructionImage / point-cloud registrationGrowth / development / phenologyLeaf traits
Three-dimensional models of plants provide valuable phenotypic information. Phenotypic measurements of plant structures are essential for monitoring plant growth and understanding plant responses to environmental changes. Existing 3D reconstruction techniques have achieved accurate reconstruction models of some plants such as corn and soybeans. However, several drawbacks exist in current plant 3D reconstruction systems, including high cost, fixed capture perspectives and complex operation. To address these issues and considering the influence of camera capture angles on model reconstruction accuracy, we investigated a viewpoint planning reconstruction method. We designed a plant seedling reconstruction system that utilizes a consumer-grade L515 LiDAR sensor and a precision turntable. We establish a viewpoint rule based on the camera imaging model of the three-dimensional spatial structure of leaves, constructing minimum constraints on the leaf normal vector and the camera optical axis. This enables to determine the optimal capture viewpoint for each leaf to obtain the maximum leaf information. The angle β between the leaf normal vector and the camera optical axis serves as the basis for the turntable rotation, systematically planning the rotation of the turntable to enable the camera to capture the maximum useful leaf information. Unlike static camera-based turntable reconstruction systems that capture images at fixed angle intervals, we plan the rotation of the turntable based on the acquired information. This allows us to obtain more effective point cloud information of plant seedlings from the same or even fewer images, reducing the collection of redundant images and reconstructing more accurate plant seedling 3D models. Additionally, we measured commonly used leaf traits in plant phenotypic studies, such as leaf length, leaf width, and leaf area. The leaf area measured based on the reconstructed seedling model exhibited high accuracy (R² > 0.99). The results of this study demonstrate that the consumer-grade L515 LiDAR sensor combined with the proposed viewpoint planning method can effectively reconstruct accurate seedling 3D models and measure phenotypic information. Due to the absence of error accumulation caused by adjacent view registration, this approach offers advantages such as shorter reconstruction time, higher efficiency and increased accuracy compared to some multi-view point cloud registration and reconstruction methods. Therefore, this system can be applied to three-dimensional reconstruction and phenotype analysis of plant seedlings due to its high efficiency and accuracy.
Why it matches plant phenotyping methods植物苗の3D再構成と葉形質抽出のための視点計画・LiDARシステムを開発し、葉面積を検証しており、表現型取得手法が研究の中心である。
abstractwe investigated a viewpoint planning reconstruction method.
Accurate and rapid acquisition of tomato canopies’ phenotypic traits was significant for variety breeding, cultivation, and scientific management. Manual measurements were time-consuming, laborious, and error-prone. The large devices in the field were lack of mobility, while the single perspective was limited by the environment’s obstruction, making it challenging to achieve high-throughput detection of tomato plants’ phenotypes. Therefore, a method for high-throughput detection of tomato canopy’s phenotypic traits was proposed based on three-dimensional (3D) structure reconstruction with multi-views. First, the tomato variety named Dongnong 708 was set as an experimental object. The acquisition platform was constructed using three Kinect 2.0 sensors to acquire a full range point cloud of tomato canopy at crucial growth stages, including the initial flowering stage, florescence, and primary fruit stage. Second, the background and interference noises were removed by Conditional filtering and Statistical Outlier Removal (SOR) filtering. Then, its structural characteristic points were extracted, and spatial position was registered by combining with Intrinsic Shape Signatures (ISS) and Iterative Closest Point (ICP) algorithms. In addition, the 3D-Normal Distributions Transform (NDT) algorithm was used to realize accurate registration of three perspectives’ point clouds. Compared with NDT and ICP algorithms, the average error of the proposed methods here was 0.027, reduced by 0.02 and 0.04, respectively. Finally, the contour of tomato canopy was extracted using the AlphaShape algorithm. Based on the reconstructed result, plant height, canopy width, and leafstalk angle, were calculated. The results showed that the correlation coefficients were 0.9615, 0.809 and 0.9014 between the calculated values and measured values. The average errors were 1.38 cm, 5.1° and 1.92 cm, respectively. The methods proposed in the paper could be used as a rapid detection method for quantitative indexes of the phenotypic traits for the tomato canopy and provide technical support for breeding, scientific cultivation, and environmental regulation.
Why it matches plant phenotyping methodsトマト群落の3D画像取得・再構成に基づく表現型形質抽出法を開発し、実測値との比較で検証しており、方法が研究の中心である。
abstractTherefore, a method for high-throughput detection of tomato canopy’s phenotypic traits was proposed based on three-dimensional (3D) structure reconstruction with multi-views.
Optical 3D measurement technology plays a vital role in diverse industries, particularly with the advancements in line laser scanning 3D imaging. In this paper, we propose a line laser scanning-based investigation for detecting Carya cathayensis Sarg. The Carya cathayensis Sarg specimens are scanned using a line laser to achieve three-dimensional reconstruction, enabling the calculation of their volume and quantity based on the acquired point cloud map. Through binocular acquisition and subsequent point cloud alignment and fusion, the error in the three-dimensional reconstruction is significantly reduced. The point cloud map facilitates the automatic identification of the number of scanned areas of Carya cathayensis Sarg areas and accurate volume calculations, with an error control of approximately 0.6% when compared to the actual volume. The application of this research in agriculture allows farmers to classify fruit sizes and optimize their selection, thus facilitating intelligent agricultural practices.
Why it matches plant phenotyping methods線レーザースキャンと点群融合を用いて植物果実の3D再構成、個数・体積推定を行う測定法が研究の中心であり、実測値との誤差による技術検証も含むため。
abstractThe Carya cathayensis Sarg specimens are scanned using a line laser to achieve three-dimensional reconstruction, enabling the calculation of their volume and quantity based on the acquired point cloud map.
Grapevine downy mildew (GDM), caused by the oomycete Plasmopara viticola, can cause 100% yield loss and vine death under conducive conditions. Growers currently rely on frequent fungicide applications for control, but this practice has led to widespread resistance. Rapid remote detection and surveillance of GDM outbreaks would enable precision pesticide applications to target effective but resistance-prone fungicides where and when most needed, while relying on less resistance-prone protectants elsewhere. High resolution commercial satellite platforms offer the opportunity to track rapidly spreading diseases like GDM over large, heterogeneous fields. Here, we investigate the capacity of PlanetScope (3 m) and SkySat (50 cm) imagery for season-long GDM detection and surveillance. A team of trained scouts rated GDM severity and incidence in two acres of Chardonnay grapevines in Geneva, NY, USA in June-August of 2020, 2021, and 2022. Satellite imagery acquired within 72 hours of scouting was processed to extract single-band reflectance and vegetation indices (VIs). Random forest models trained on spectral bands and VIs derived from both image datasets could classify areas of high and low GDM incidence and severity with maximum accuracies of 0.88 (SkySat) and 0.94 (PlanetScope). However, we do not observe significant differences between VIs of high and low damage classes until late July-early August. We identify cloud cover, image co-registration, and low spectral resolution as key challenges to operationalizing satellite-based GDM surveillance. This work establishes the capacity of spaceborne multispectral sensors to detect late-stage GDM and outlines steps towards incorporating satellite remote sensing in grapevine disease surveillance systems.
Why it matches plant phenotyping methods衛星画像と機械学習を用いてブドウのべと病の発生・重症度を直接推定し、精度評価と運用上の課題を検証しているため、植物病害フェノタイピング手法が中心である。
abstractHere, we investigate the capacity of PlanetScope (3 m) and SkySat (50 cm) imagery for season-long GDM detection and surveillance.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 7 Sept 2026
Abstract The 3D crop data obtained during cultivation is of great significance to screening excellent varieties in modern breeding and improvement on crop yield. With the rapid development of deep learning, researchers have been making innovations in aspects of both data preparation and deep network design for segmenting plant organs from 3D data. Training of the deep learning network requires the input point cloud to have a fixed scale, which means all point clouds in the batch should have similar scale and contain the same number of points. A good down-sampling strategy can reduce the impact of noise and meanwhile preserve the most important 3D spatial structures. As far as we know, this work is the first comprehensive study of the relationship between multiple down-sampling strategies and the performances of popular networks for plant point clouds. Five down-sampling strategies (including FPS, RS, UVS, VFPS, and 3DEPS) are cross evaluated on five different segmentation networks (including PointNet + + , DGCNN, PlantNet, ASIS, and PSegNet). The overall experimental results show that currently there is no strict golden rule on fixing down-sampling strategy for a specific mainstream crop deep learning network, and the optimal down-sampling strategy may vary on different networks. However, some general experience for choosing an appropriate sampling method for a specific network can still be summarized from the qualitative and quantitative experiments. First, 3DEPS and UVS are easy to generate better results on semantic segmentation networks. Second, the voxel-based down-sampling strategies may be more suitable for complex dual-function networks. Third, at 4096-point resolution, 3DEPS usually has only a small margin compared with the best down-sampling strategy at most cases, which means 3DEPS may be the most stable strategy across all compared. This study not only helps to further improve the accuracy of point cloud deep learning networks for crop organ segmentation, but also gives clue to the alignment of down-sampling strategies and a specific network.
Why it matches plant phenotyping methods植物器官の3D点群セグメンテーションにおけるダウンサンプリング戦略を比較・評価し、表現型抽出ワークフローの技術性能を検証しているため、方法中心の研究である。
abstractFive down-sampling strategies (including FPS, RS, UVS, VFPS, and 3DEPS) are cross evaluated on five different segmentation networks
Published19 Oct 2023The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesCited by 3 · OpenAlex ↗
Field / plotLiDAR / point cloudWhole plant / canopy / plot / field2D/3D reconstructionImage / point-cloud registration
Abstract. Terrestrial 3D reconstruction is a research topic that has recently received significant attention in the forestry sector. This practice enables the acquisition of high-quality 3D data, which can be used not only to derive physical forest criteria such as tree positions and diameters, but also more detailed analyses related to ecological parameters such as habitat availability and biomass. However, several challenges must be addressed before fully integrating this technology into forestry practices. The primary challenge is accurately georeferencing surveyed 3D data acquired in the same location and placing them into a national projection reference system. Unfortunately, due to the forest canopy, the GNSS signal is often obstructed, and it cannot guarantee sub-meter accuracy. In this paper, we have implemented an indirect georeferencing methodology based on spheres with known coordinates placed at the forest’s edge where GNSS reception was more reliable and accurate than under the canopy. We evaluated its performance through three analyses that confirmed the validity of our approach. Indeed, the accuracy of the TLS point cloud, georeferenced using our method, is within a centimetre level (4.7 cm), whereas mobile scanning methods demonstrate accuracy within the decimetre range but still less than a metre. Additionally, we have initiated the analysis of a potential future application for mixed reality headsets, which could enable real-time acquisition and visualisation of 3D data.
Why it matches plant phenotyping methods森林TLS・モバイルスキャンの3Dデータを用いて樹木位置や直径などの明示的な植物形質を取得可能にする測量・ジオリファレンス手法を実装し、精度比較で検証しているため、方法検証・プラットフォーム研究として含める。
abstractThis practice enables the acquisition of high-quality 3D data, which can be used not only to derive physical forest criteria such as tree positions and diameters
For high-value precision agriculture, monitoring plant growth trends, pest and disease control, and automation processes will standardize operations and increase yield while reducing losses as much as possible. In greenhouse scenarios, one method for monitoring plant growth requires localization, modeling, and post-processing of the plants. However, recognizing and extracting the root position of the plant is difficult for a robotic arm. To overcome this challenge, this paper uses a marker-based localization method to provide the root position directly. After acquiring and iteratively registering the point cloud, the main stem of the plant is extracted for future plant organ segmentation and clustering. Nevertheless, extracting the main stem is a complex task, and although there are studies on skeleton extraction for ordinary trees or wheat, there are few solutions for high-wire plant stem extraction. Therefore, an optimized geometric-based stem extraction algorithm (SEA) can extract the stem point cloud with a high success rate under conditions no matter whether the cloud is intact or the main stem region is occluded.
Why it matches plant phenotyping methods植物の点群から主茎を抽出する手法を開発しており、将来の器官分割に利用可能な植物形態特徴の取得が研究の中心であるため。
abstractAfter acquiring and iteratively registering the point cloud, the main stem of the plant is extracted for future plant organ segmentation and clustering.
Three-dimensional (3D) reconstruction is an essential technique to visualize and monitor the growth of agricultural and forestry plants. However, inspecting tall plants (trees) remains a challenging task for single-camera systems. A combination of low-altitude remote sensing (an unmanned aerial vehicle) and a terrestrial capture platform (a mobile robot) is suggested to obtain the overall structural features of trees including the trunk and crown. To address the registration problem of the point clouds from different sensors, a registration method based on a fast point feature histogram (FPFH) is proposed to align the tree point clouds captured by terrestrial and airborne sensors. Normal vectors are extracted to define a Darboux coordinate frame whereby FPFH is calculated. The initial correspondences of point cloud pairs are calculated according to the Bhattacharyya distance. Reliable matching point pairs are then selected via random sample consensus. Finally, the 3D transformation is solved by singular value decomposition. For verification, experiments are conducted with real-world data. In the registration experiment on noisy and partial data, the root-mean-square error of the proposed method is 0.35% and 1.18% of SAC-IA and SAC-IA + ICP, respectively. The proposed method is useful for the extraction, monitoring, and analysis of plant phenotypes.
Why it matches plant phenotyping methods樹木の航空・地上センサによる3D点群を登録・統合し、植物表現型の抽出・監視・解析に用いる中心的な手法を開発・検証している。
abstractThe proposed method is useful for the extraction, monitoring, and analysis of plant phenotypes.
Taking maize seedlings as the object, the implementation of crops 3D reconstruction based on RGB-D binocular vision and the selection of some key parameters are investigated in this research. First, multiple images are taken from different angles around the target. By mapping the maize seedling region coordinate values after the Otsu algorithm and global threshold segmentation to the corresponding depth image, the depth data of the maize seedling region can be obtained accurately. An improved mean filter is proposed to adaptively fill the holes in the depth image. Then, the different point clouds with the fixed step angle of the maize seedling are registered and fuzed. Finally, after the fusion point cloud is simplified, the 3D model of crops can be reconstructed. Experimental results show that the simplification effect of the octree algorithm is better than that of the voxel grid filter. Among all the step angles, the reconstruction error of the step angle with 60° is the smallest. Under this condition, the height error between the model and the maize seedling is 2.22%, and the error in stem diameter is 11.67%.
Why it matches plant phenotyping methodsRGB-D双目视觉三维重建方法是论文核心，并对玉米幼苗高度和茎径等表型测量误差进行了验证。
abstractthe implementation of crops 3D reconstruction based on RGB-D binocular vision and the selection of some key parameters are investigated
In this work, a Multispectral-Depth (MS-D) imaging system for close range plant inspection is presented. The proposed system is comprised of multispectral cameras calibrated with respect to an RGB-D camera. It is ultimately tested and quantitatively compared to state-of-the-art feature-based methods for multispectral image registration. The results show that MS-D system outperforms state-of-the-art methods in all experimental trials, from registration of checkerboard images (where the accuracy of the MS-D system was on a sub-pixel level) to registration of feature-rich plant images, both real and synthetic. While the greatest registration error of the MS-D system amounted to 9 pixels, registration error of the feature-based method was up to 19 times greater. Additionally, contrast to the state-of-the-art feature matching approaches, the MS-D system, once calibrated, is applicable as is, without the need for recalibration. As a part of this work, MS-D has been deployed in encapsulated growth chambers for rapid data collection and in a small indoor organic farm for automated plant monitoring. As a part of the experimental plant monitoring study, it was shown that vegetation indices calculated with the MS-D system can be used to estimate water stress in Spathiphyllum plants equally well as with the spectroradiometer, human operated device for measurement of plant vegetation indices. The biggest relative change between the vegetation indices calculated for the plants exposed to the short term water stress and the control group was found in values of NDRE, amounting to 94.8%, followed by the relative change of 64.9% observed for the values of SR.
Why it matches plant phenotyping methodsMS-Dマルチスペクトル・深度画像システムを開発し、画像レジストレーション性能を定量比較するとともに、植物モニタリングと水ストレス推定へ応用しており、植物表現型取得法が中心的である。
abstracta Multispectral-Depth (MS-D) imaging system for close range plant inspection is presented
A critical element in preventing a major outbreak is the detection of plant leaves. An important research issue is the automatic detection of plant diseases. For both human life and condition, a plant's dedication is essential. Like humans and other animals, plants do suffer the negative impacts of illnesses. A plant's normal development is influenced by the frequency of plant diseases that occur. The entire plant, including the leaf, stem, organic material, root, and flower, is affected by these diseases. Most of the time, if a plant's ailment is not treated, it dies or may cause leaves, blooms, organic products, and so forth to fall off. For accurate identification and treatment of plant diseases, appropriate determination of these disorders is necessary. Plant pathology is the study of plant infections, their causes, and methods for preventing, managing, and eradicating them. However, the current approach includes human inclusion for structure and identifying disease proof. This tactic is time-consuming and expensive. Instead of using the current method, a programmed division of diseases from plant leaf images utilising a delicate registration methodology may be more beneficial. In this study, we describe a method for identifying and characterising plant leaf diseases naturally called Bacterial Searching Improvement Based Radial Basis Function Neural Network (BRBFNN). We use bacterial search streamlining (BFO), which increases the speed and accuracy of the system to recognise and organise the regions contaminated by diverse illnesses on the plant leaves, to assign Radial Basis Function Neural Network (RBFNN) the proper weight. The location development calculation increases the system's efficiency by searching for and gathering seed focuses on typical traits for the highlighted extraction operation. To make progress against parasite diseases including early curse, leaf twist, leaf spot, late scourge, and basic, cedar apple, and leaf rust. The suggested approach achieves more accuracy in identifying evidence and characterizing infections.
Why it matches plant phenotyping methods植物葉画像から病害領域を自動抽出・識別するCNN系手法が研究の中心であり、植物の病害状態を画像から推定するため、植物フェノタイピング手法に該当する。
abstractwe describe a method for identifying and characterising plant leaf diseases naturally called Bacterial Searching Improvement Based Radial Basis Function Neural Network (BRBFNN).
Unmanned aerial vehicle (UAV)-borne light detection and ranging (LiDAR) scanners have been adopted as a promising instrument for plant parameter estimation in agricultural studies recently. However, accurate LiDAR data registration typically requires expensive external navigation devices such as survey-grade global navigation satellite systems (GNSSs) and tactical-grade inertial measurement units (IMUs). Although algorithmic point cloud registration can be an alternative method, the lack of unique landmarks in agricultural fields might bring much difficulty to accurate aerial LiDAR data alignment. In this study, we developed a UAV-LiDAR system employing UAV’s built-in navigation units, and proposed a novel approach for registering UAV-LiDAR data of level agricultural fields utilizing a colored iterative closest point (ICP) algorithm and GNSS location and IMU orientation information from the UAV. The proposed algorithm was tested in a peach tree parameter estimation experiment in comparison to GNSS and IMU-based georeferencing. Using manually measured crown widths in two perpendicular dimensions and heights of 11 trees as evaluation metrics, our proposed algorithm achieved a root mean square error (RMSE) range of 0.05 to 0.2 m depending on the tree parameter and flight altitude, and it was able to register tree point clouds up to 67% more accurately in terms of the extracted tree parameters than the georeferencing method. The results demonstrated the potential of the proposed algorithm being a low-cost solution to crop inspection using single-pass aerial LiDAR point clouds from straight-pathed flights, yet future work is still needed to improve the algorithm’s adaptability to multi-pass LiDAR data of complex landscapes from flights with curved paths.
Why it matches plant phenotyping methodsUAV-LiDAR点群登録アルゴリズムを開発し、モモ樹の樹冠幅・樹高という植物形質の推定精度で検証しており、フェノタイピング取得・抽出法が中心である。
abstractwe developed a UAV-LiDAR system employing UAV’s built-in navigation units, and proposed a novel approach for registering UAV-LiDAR data of level agricultural fields utilizing a colored iterative closest point (ICP) algorithm and GNSS location and IMU orientation information from the UAV.
Individual plants vary in their ability to respond to environmental changes. The plastic response of a plant enhances its ability to avoid environmental constraints, and hence supports growth, reproduction, and evolutionary and agricultural success.Major progress in the analysis of above- and belowground processes on individual plants has been made by the application of non-invasive imaging methods including Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET).MRI allows for repetitive measurements of roots growing in soil and facilitates quantification of root system architecture traits in 3D. PET, on the other hand, opens a door to analyze dynamic physiological processes in plants such as long-distance carbon transport in a repeatable manner. Combining MRI with PET enables monitoring of short livedCarbon tracer (11C) allocation along the transport paths (i.e. roots visualized by MRI) into active sink structures.To analyse the link between root-internal C allocation patterns and C metabolism in the rhizosphere, we are combining 11CO2 with stable 13CO2 labelling of plants. Isotope ratio mass spectrometry (IRMS) analyses of rhizosphere soil is applied to link root-internal C allocation patterns with distribution of 13C in the rhizosphere soil. The metabolically active rhizosphere organisms are subsequently identified based on DNA 13C stable isotope probing.In our presentation we will highlight our approaches for gathering quantitative data from both image-based technologies in combination with destructive analysis that provides insights into the functioning and dynamics of C transport processes in the plant-soil system.
Why it matches plant phenotyping methodsMRIとPETを組み合わせ、根系形態と植物体内の炭素輸送を定量的に取得する画像基盤が研究の中心であり、植物フェノタイピング手法の実質的応用に該当する。
abstractthe application of non-invasive imaging methods including Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET)
Accurate and high-throughput plant phenotyping is important for accelerating crop breeding. Spectral imaging that can acquire both spectral and spatial information of plants related to structural, biochemical, and physiological traits becomes one of the popular phenotyping techniques. However, close-range spectral imaging of plants could be highly affected by the complex plant structure and illumination conditions, which becomes one of the main challenges for close-range plant phenotyping. In this study, we proposed a new method for generating high-quality plant 3-dimensional multispectral point clouds. Speeded-Up Robust Features and Demons was used for fusing depth and snapshot spectral images acquired at close range. A reflectance correction method for plant spectral images based on hemisphere references combined with artificial neural network was developed for eliminating the illumination effects. The proposed Speeded-Up Robust Features and Demons achieved an average structural similarity index measure of 0.931, outperforming the classic approaches with an average structural similarity index measure of 0.889 in RGB and snapshot spectral image registration. The distribution of digital number values of the references at different positions and orientations was simulated using artificial neural network with the determination coefficient ( R 2 ) of 0.962 and root mean squared error of 0.036. Compared with the ground truth measured by ASD spectrometer, the average root mean squared error of the reflectance spectra before and after reflectance correction at different leaf positions decreased by 78.0%. For the same leaf position, the average Euclidean distances between the multiview reflectance spectra decreased by 60.7%. Our results indicate that the proposed method achieves a good performance in generating plant 3-dimensional multispectral point clouds, which is promising for close-range plant phenotyping.
Why it matches plant phenotyping methods植物の3次元マルチスペクトル点群生成と反射補正・画像融合手法を開発し、既存手法や分光計を用いて性能検証しており、植物表現型取得が研究の中心である。
abstractIn this study, we proposed a new method for generating high-quality plant 3-dimensional multispectral point clouds.
Automatic plant phenotype measurement technology based on the rapid and accurate reconstruction of maize structures at the seedling stage is essential for the early variety selection, cultivation, and scientific management of maize. Manual measurement is time-consuming, laborious, and error-prone. The lack of mobility of large equipment in the field make the high-throughput detection of maize plant phenotypes challenging. Therefore, a global 3D reconstruction algorithm was proposed for the high-throughput detection of maize phenotypic traits. First, a self-propelled mobile platform was used to automatically collect three-dimensional point clouds of maize seedling populations from multiple measurement points and perspectives. Second, the Harris corner detection algorithm and singular value decomposition (SVD) were used for the pre-calibration single measurement point multi-view alignment matrix. Finally, the multi-view registration algorithm and iterative nearest point algorithm (ICP) were used for the global 3D reconstruction of the maize seedling population. The results showed that the R2 of the plant height and maximum width measured by the global 3D reconstruction of the seedling maize population were 0.98 and 0.99 with RMSE of 1.39 cm and 1.45 cm and mean absolute percentage errors (MAPEs) of 1.92% and 2.29%, respectively. For the standard sphere, the percentage of the Hausdorff distance set of reconstruction point clouds less than 0.5 cm was 55.26%, and the percentage was 76.88% for those less than 0.8 cm. The method proposed in this study provides a reference for the global reconstruction and phenotypic measurement of crop populations at the seedling stage, which aids in the early management of maize with precision and intelligence.
Why it matches plant phenotyping methodsKinectを用いたトウモロコシ幼植物集団の3D再構成と、草丈・最大幅のフェノタイプ抽出法を開発し、精度検証しているため。
abstractAutomatic plant phenotype measurement technology based on the rapid and accurate reconstruction of maize structures at the seedling stage is essential
Stereo matching is a depth perception method for plant phenotyping with high throughput. In recent years, the accuracy and real-time performance of the stereo matching models have been greatly improved. While the training process relies on specialized large-scale datasets, in this research, we aim to address the issue in building stereo matching datasets. A semi-automatic method was proposed to acquire the ground truth, including camera calibration, image registration, and disparity image generation. On the basis of this method, spinach, tomato, pepper, and pumpkin were considered for experiment, and a dataset named PlantStereo was built for reconstruction. Taking data size, disparity accuracy, disparity density, and data type into consideration, PlantStereo outperforms other representative stereo matching datasets. Experimental results showed that, compared with the disparity accuracy at pixel level, the disparity accuracy at sub-pixel level can remarkably improve the matching accuracy. More specifically, for PSMNet, the EPE and bad−3 error decreased 0.30 pixels and 2.13%, respectively. For GwcNet, the EPE and bad−3 error decreased 0.08 pixels and 0.42%, respectively. In addition, the proposed workflow based on stereo matching can achieve competitive results compared with other depth perception methods, such as Time-of-Flight (ToF) and structured light, when considering depth error (2.5 mm at 0.7 m), real-time performance (50 fps at 1046 × 606), and cost. The proposed method can be adopted to build stereo matching datasets, and the workflow can be used for depth perception in plant phenotyping.
Why it matches plant phenotyping methods植物フェノタイピング用のステレオマッチングデータセット構築法を開発し、精度・性能を検証した研究であり、表現型取得手法が中心である。
abstractStereo matching is a depth perception method for plant phenotyping with high throughput.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 7 Sept 2026
Introduction: Nondestructive detection of crop phenotypic traits in the field is very important for crop breeding. Ground-based mobile platforms equipped with sensors can efficiently and accurately obtain crop phenotypic traits. In this study, we propose a dynamic 3D data acquisition method in the field suitable for various crops by using a consumer-grade RGB-D camera installed on a ground-based movable platform, which can collect RGB images as well as depth images of crop canopy sequences dynamically. Methods: A scale-invariant feature transform (SIFT) operator was used to detect adjacent date frames acquired by the RGB-D camera to calculate the point cloud alignment coarse matching matrix and the displacement distance of adjacent images. The data frames used for point cloud matching were selected according to the calculated displacement distance. Then, the colored ICP (iterative closest point) algorithm was used to determine the fine matching matrix and generate point clouds of the crop row. The clustering method was applied to segment the point cloud of each plant from the crop row point cloud, and 3D phenotypic traits, including plant height, leaf area and projected area of individual plants, were measured. Results and Discussion: ) and projected area (R² = 0.96~0.99) have strong correlations with the manual measurement results. Additionally, 3D reconstruction results with different moving speeds and times throughout the day and in different scenes were also verified. The results show that the method can be applied to dynamic detection with a moving speed up to 0.6 m/s and can achieve acceptable detection results in the daytime, as well as at night. Thus, the proposed method can improve the efficiency of individual crop 3D point cloud data extraction with acceptable accuracy, which is a feasible solution for crop seedling 3D phenotyping outdoors.
Why it matches plant phenotyping methodsRGB-Dカメラと移動プラットフォームによる動的3D形質取得法を開発し、個体の草丈・葉面積・投影面積を手動測定と検証しており、植物フェノタイピング手法が中心である。
abstractwe propose a dynamic 3D data acquisition method in the field suitable for various crops by using a consumer-grade RGB-D camera installed on a ground-based movable platform
As the largest component of crops, water has an important impact on the growth and development of crops. Timely, rapid, continuous, and non-destructive detection of crop water stress status is crucial for crop water-saving irrigation, production, and breeding. Indices based on leaf or canopy temperature acquired by thermal imaging are widely used for crop water stress diagnosis. However, most studies fail to achieve high-throughput, continuous water stress detection and mostly focus on two-dimension measurements. This study developed a low-cost three-dimension (3D) motion robotic system, which is equipped with a designed 3D imaging system to automatically collect potato plant data, including thermal and binocular RGB data. A method is developed to obtain 3D plant fusion point cloud with depth, temperature, and RGB color information using the acquired thermal and binocular RGB data. Firstly, the developed system is used to automatically collect the data of the potato plants in the scene. Secondly, the collected data was processed, and the green canopy was extracted from the color image, which is convenient for the speeded-up robust features algorithm to detect more effective matching features. Photogrammetry combined with structural similarity index was applied to calculate the optimal homography transform matrix between thermal and color images and used for image registration. Thirdly, based on the registration of the two images, 3D reconstruction was carried out using binocular stereo vision technology to generate the original 3D point cloud with temperature information. The original 3D point cloud data were further processed through canopy extraction, denoising, and k-means based temperature clustering steps to optimize the data. Finally, the crop water stress index (CWSI) of each point and average CWSI in the canopy were calculated, and its daily variation and influencing factors were analyzed in combination with environmental parameters. The developed system and the proposed method can effectively detect the water stress status of potato plants in 3D, which can provide support for analyzing the differences in the three-dimensional distribution and spatial and temporal variation patterns of CWSI in potato.
Why it matches plant phenotyping methods熱画像と双眼ステレオビジョンを統合した3D植物表現型取得システムと、温度付き点群からCWSIを算出する手法が研究の中心であるため。
abstractThis study developed a low-cost three-dimension (3D) motion robotic system, which is equipped with a designed 3D imaging system to automatically collect potato plant data, including thermal and binocular RGB data.
The dormant pruning of jujube is a labor-intensive and time-consuming activity in the production and management of jujube orchards, which mainly depends on manual operation. Automatic pruning using robots could be a better way to solve the shortage of skilled labor and improve efficiency. In order to realize automatic pruning of jujube trees, a method of pruning point identification based on skeleton information is presented. This study used an RGB-D camera to collect multi-view information on jujube trees and built a complete point cloud information model of jujube trees. The space colonization algorithm acts on the global point cloud to generate the skeleton of jujube trees. The iterative relationship between skeleton points was represented by constructing a directed graph. The proposed skeleton analysis algorithm marked the skeleton as the trunk, the primary branches, and the lateral branches and identified the pruning points under the guidance of pruning rules. Finally, the visual model of the pruned jujube tree was established through the skeleton information. The results showed that the registration errors of individual jujube trees were less than 0.91 cm, and the average registration error was 0.66 cm, which provided a favorable database for skeleton extraction. The skeleton structure extracted by the space colonization algorithm had a high degree of coincidence with jujube trees, and the identified pruning points were all located on the primary branches of jujube trees. The study provides a method to identify the pruning points of jujube trees and successfully verifies the validity of the pruning points, which can provide a reference for the location of the pruning points and visual research basis for automatic pruning.
Why it matches plant phenotyping methodsRGB-D点群からナツメ樹の樹幹・一次枝・側枝の骨格を抽出し、剪定点を推定する画像・計算手法が研究の中心であり、植物形態・樹体構造の表現型取得として妥当。
abstractThis study used an RGB-D camera to collect multi-view information on jujube trees and built a complete point cloud information model of jujube trees.
Pod phenotypic traits are closely related to grain yield and quality. Pod phenotype detection in soybean populations in natural environments is important to soybean breeding, cultivation, and field management. For an accurate pod phenotype description, a dynamic detection method is proposed based on an improved YOLO-v5 network. First, two varieties were taken as research objects. A self-developed field soybean three-dimensional color image acquisition vehicle was used to obtain RGB and depth images of soybean pods in the field. Second, the red–green–blue (RGB) and depth images were registered using an edge feature point alignment metric to accurately distinguish complex environmental backgrounds and establish a red–green–blue-depth (RGB-D) dataset for model training. Third, an improved feature pyramid network and path aggregation network (FPN+PAN) structure and a channel attention atrous spatial pyramid pooling (CA-ASPP) module were introduced to improve the dim and small pod target detection. Finally, a soybean pod quantity compensation model was established by analyzing the influence of the number of individual plants in the soybean population on the detection precision to statistically correct the predicted pod quantity. In the experimental phase, we analyzed the impact of different datasets on the model and the performance of different models on the same dataset under the same test conditions. The test results showed that compared with network models trained on the RGB dataset, the recall and precision of models trained on the RGB-D dataset increased by approximately 32% and 25%, respectively. Compared with YOLO-v5s, the precision of the improved YOLO-v5 increased by approximately 6%, reaching 88.14% precision for pod quantity detection with 200 plants in the soybean population. After model compensation, the mean relative errors between the predicted and actual pod quantities were 2% to 3% for the two soybean varieties. Thus, the proposed method can provide rapid and massive detection for pod phenotyping in soybean populations and a theoretical basis and technical knowledge for soybean breeding, scientific cultivation, and field management.
Why it matches plant phenotyping methods大豆莢数という植物形質を対象に、RGB-D画像取得、画像登録、改良YOLO-v5、補正モデルを開発・検証しており、フェノタイピング手法が研究の中心である。
abstractFor an accurate pod phenotype description, a dynamic detection method is proposed based on an improved YOLO-v5 network.
RiceLaboratory / benchtopX-ray / CTRootImage / point-cloud registrationGrowth / time-series analysisTrackingGrowth / development / phenologyRoot system architecture
Background Root system architecture (RSA) is an essential characteristic for efficient water and nutrient absorption in terrestrial plants; its plasticity enables plants to respond to different soil environments. Better understanding of root plasticity is important in developing stress-tolerant crops. Non-invasive techniques that can measure roots in soils nondestructively, such as X-ray computed tomography (CT), are useful to evaluate RSA plasticity. However, although RSA plasticity can be measured by tracking individual root growth, only a few methods are available for tracking individual roots from time-series three-dimensional (3D) images. Results We developed a semi-automatic workflow that tracks individual root growth by vectorizing RSA from time-series 3D images via two major steps. The first step involves 3D alignment of the time-series RSA images by iterative closest point registration with point clouds generated by high-intensity particles in potted soils. This alignment ensures that the time-series RSA images overlap. The second step consists of backward prediction of vectorization, which is based on the phenomenon that the root length of the RSA vector at the earlier time point is shorter than that at the last time point. In other words, when CT scanning is performed at time point A and again at time point B for the same pot, the CT data and RSA vectors at time points A and B will almost overlap, but not where the roots have grown. We assumed that given a manually created RSA vector at the last time point of the time series, all RSA vectors except those at the last time point could be automatically predicted by referring to the corresponding RSA images. Using 21 time-series CT volumes of a potted plant of upland rice (Oryza sativa), this workflow revealed that the root elongation speed increased with age. Compared with a workflow that does not use backward prediction, the workflow with backward prediction reduced the manual labor time by 95%. Conclusions We developed a workflow to efficiently generate time-series RSA vectors from time-series X-ray CT volumes. We named this workflow 'RSAtrace4D' and are confident that it can be applied to the time-series analysis of RSA development and plasticity.
Why it matches plant phenotyping methods根系形態を時系列X線CT画像から抽出・追跡する半自動ワークフローを開発しており、植物フェノタイピング手法が研究の中心である。
abstractWe developed a semi-automatic workflow that tracks individual root growth by vectorizing RSA from time-series 3D images via two major steps.
Reproduction assets foundThe paper's authors publicly released RSAtrace4D, the software implementing the backward-prediction workflow for time-series X-ray CT root system architecture analysis, on GitHub, and state that the datasets used are available via their GitHub account and project homepage.Code · publicThe implementation of this workflow, which is specified for rice, was named RSAtrace4D and is available at the GitHub repository ( https://github.com/st707311g/RSAtrace4D ).Open asset ↗st707311g/RSAtrace4Dlines:116-124Dataset · publicThe datasets used in this study are available at the GitHub repository ( https://github.com/st707311g/ ) and the project homepage ( https://rootomics.dna.affrc.go.jp/en/ ).Open asset ↗st707311glines:136-191Code / dataset availability confirmedOpenAlex · Europe PMC · Crossref · checked 8 Sept 2026
BACKGROUND: High-throughput phenotyping is crucial for the genetic and molecular understanding of adaptive root system development. In recent years, imaging automata have been developed to acquire the root system architecture of many genotypes grown in Petri dishes to explore the Genetic x Environment (GxE) interaction. There is now an increasing interest in understanding the dynamics of the adaptive responses, such as the organ apparition or the growth rate. However, due to the increasing complexity of root architectures in development, the accurate description of the topology, geometry, and dynamics of a growing root system remains a challenge. RESULTS: We designed a high-throughput phenotyping method, combining an imaging device and an automatic analysis pipeline based on registration and topological tracking, capable of accurately describing the topology and geometry of observed root systems in 2D + t. The method was tested on a challenging Arabidopsis seedling dataset, including numerous root occlusions and crossovers. Static phenes are estimated with high accuracy ([Formula: see text] and [Formula: see text] for primary and second-order roots length, respectively). These performances are similar to state-of-the-art results obtained on root systems of equal or lower complexity. In addition, our pipeline estimates dynamic phenes accurately between two successive observations ([Formula: see text] for lateral root growth). CONCLUSIONS: We designed a novel method of root tracking that accurately and automatically measures both static and dynamic parameters of the root system architecture from a novel high-throughput root phenotyping platform. It has been used to characterise developing patterns of root systems grown under various environmental conditions. It provides a solid basis to explore the GxE interaction controlling the dynamics of root system architecture adaptive responses. In future work, our approach will be adapted to a wider range of imaging configurations and species.
Why it matches plant phenotyping methods根系の静的・動的形質を画像から自動抽出する高スループット手法と解析パイプラインを開発・検証しており、表現型取得法が研究の中心である。
abstractWe designed a high-throughput phenotyping method, combining an imaging device and an automatic analysis pipeline based on registration and topological tracking
Reproduction assets foundThe paper's root reconstruction/phenotyping pipeline (RootSystemTracker) is released as open-source code on GitHub with an ImageJ plugin documentation page; an example time-lapse movie of the reconstruction is also available on YouTube. No public dataset of the 1000 time-lapse images or RSML outputs is stated in thesupCode · publicThe architecture reconstruction pipeline is supplied as an ImageJ plugin with online documentation (Plugin page: https://imagej.net/plugins/rootsystemtracker [ 9 ]) and as open-source code on GitHub ( https://github.com/Rocsg/RootSystemTracker ).Open asset ↗Rocsg/RootSystemTrackerlines:208-277Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 14 Sept 2026
Hyperspectral imaging is a non-destructive imaging technique used in plant phenotyping to collect and analyze an array of electromagnetic information in visible (380-700 nm) and near-infrared wavelengths region (700-2,500 nm). Hyperspectral imaging can provide information of plant responses under various biotic and abiotic stress, e.g., drought, temperature rising, disease, and nutrition deficiency. We present a hyperspectral data processing pipeline designed for the data collected at Ag Alumni Seed Phenotyping Facility (AAPF) in Purdue University, USA. The procedure consists of initializing a processing session, radiometric calibration with white and dark references, geometric calibration (registration) of visible and near infrared (VNIR) and shortwave infrared (SWIR) images, vegetation and non-vegetation classification, vegetation indices calculation of a plant area, exporting data products, and quality control. In concern of large data size of hyperspectral data, we highlight the need to save memory usage during computation and save disk space for data products. We also address the need of human interpretable images in the hyperspectral data products for plant scientists without experiences in hyperspectral imaging. We expect the developed procedure could improve robustness of large hyperspectral data processing and promote the usage of hyperspectral data by increasing interpretability.
Why it matches plant phenotyping methods植物フェノタイピング用のハイパースペクトル画像処理パイプラインを開発し、校正・位置合わせ・植生分類・植生指数算出・品質管理までを体系化しており、表現型取得・抽出手法が中心である。
abstractWe present a hyperspectral data processing pipeline designed for the data collected at Ag Alumni Seed Phenotyping Facility (AAPF) in Purdue University, USA.
MaizeTobaccoTomatoLiDAR / point cloudLeafImage / point-cloud registrationSegmentationTrackingGrowth / development / phenology
Plant phenotypic analysis is of great importance to the development of agricultural engineering, and is one of the core issues in crop science and plant breeding. Since plant growth is spatio-temporal and synchronous, understanding the growth and development of individual plants can help to reveal the growth potential of the whole plot and thus improve planting methods. In recent years, the technical means to analyze the growth situation using 3D point cloud data has received extensive attention. The plant point cloud obtained by scanning plants with LiDAR has the characteristics of high resolution, high precision, etc. Periodic scanning of the same plant for spatio-temporal point cloud data sets allows monitoring of growth through subtle changes of plant organs. Organ tracking of growing plants remains challenging due to the lightward nature of growth, the potential for topological changes and the unpredictability of plant growth over time, with the possibility of new leaf growth and leaf death. This paper designs a plant organ growth tracking method based on point cloud. First of all, for growing plants, we have established a crop point cloud spatio-temporal dataset based on two publicly available point cloud datasets. The data set includes four species, tomato, tobacco, sorghum and maize, each species contains complete organ instance labels, and each organ of the same plant has a unique label, which means that the labels of the same organ of an individual at different scan dates correspond one-to-one. Second, this paper proposes a point cloud data-based plant organ growth tracking method, which uses a cost correlation matrix to automatically track growing plant organs. Finally, based on the set of quantitative evaluation metrics, our algorithm achieves a matching accuracy of 82.89% on the plant spatio-temporal dataset and good growth tracking results in the qualitative analysis.
Why it matches plant phenotyping methods植物器官の成長を3D点群から追跡・定量化する手法を開発し、ラベル付き時系列データセットと評価指標で検証しており、植物フェノタイピング手法が中心である。
abstractThis paper designs a plant organ growth tracking method based on point cloud.
The 3D reconstruction of tree seedlings can help to assess phenotypic architectures, conceive virtual urban landscapes and design computer games. The existing multicamera photograph technology already has the capability to accurately reconstruct 3D models for small scene plants, such as corn and vegetable seedlings. However, the existing plant 3D reconstruction system has several shortcomings, such as its high cost, complicated operation procedure, and unsuitability for seedling trees. Therefore, this paper proposes an autonomous alignment method for seedling point clouds that can realize the low-cost and fast 3D reconstruction of batch seedlings. In this study, we designed a system based on a low-cost Kinect camera and a precision turntable to construct 3D seedling models. A special turntable was adopted to achieve self-registration for the seedling point clouds. It was efficient for us to obtain several 3D seedlings models with only one registration. The system could capture images automatically from different viewpoints and submit these images to a graphic workstation for processing. In our work, we set three fixed views, V₂, V₃ and V₄, to evaluate the cumulative errors caused by multiview matching. It needn’t touch any parts of the seedings to create 3D models at different view by the proposed method. Herein, the large proportions of 0 0.985) when using the 3D reconstruction models of seedlings. Experiments demonstrate that the proposed method has the potential to obtain high-precision 3D reconstruction models and phenotypic parameters for seedlings via low-cost equipment with high-efficiency processing algorithms.
Why it matches plant phenotyping methods低コストKinectと回転台を用いて苗木の3D再構成および表現型パラメータ取得システムを開発しており、植物表現型取得手法が研究の中心である。
abstractTherefore, this paper proposes an autonomous alignment method for seedling point clouds that can realize the low-cost and fast 3D reconstruction of batch seedlings.
Abstract Background High-throughput phenotyping platforms allow the study of the form and function of a large number of genotypes subjected to different growing conditions (GxE). A number of image acquisition and processing pipelines have been developed to automate this process, for micro-plots in the field and for individual plants in controlled conditions. Capturing shoot development requires extracting from images both the evolution of the 3D plant architecture as a whole, and a temporal tracking of the growth of its organs. Results We propose PhenoTrack3D, a new pipeline to extract a 3D+t reconstruction of maize at organ level from plant images. It allows the study of plant architecture and individual organ development over time during the entire growth cycle. PhenoTrack3D improves a former method limited to 3D reconstruction at a single time point [Artzet et al ., 2019] by (i) a novel stem detection method based on deep-learning and (ii) a new and original multiple sequence alignment method to perform the temporal tracking of ligulated leaves. Our method exploits both the consistent geometry of ligulated leaves over time and the unambiguous topology of the stem axis. Growing leaves are tracked afterwards with a distance-based approach. This pipeline is validated on a challenging dataset of 60 maize hybrids imaged daily from emergence to maturity in the PhenoArch platform (ca. 250,000 images). Stem tip was precisely detected over time (RMSE < 2.1cm). 97.7% and 85.3% of ligulated and growing leaves respectively were assigned to the correct rank after tracking, on 30 plants x 43 dates. The pipeline allowed to extract various development and architecture traits at organ level, with good correlation to manual observations overall, on random subsets of 10 to 355 plants. Conclusions We developed a novel phenotyping method based on sequence alignment and deep-learning. It allows to characterise automatically and at a high-throughput the development of maize architecture at organ level. It has been validated for hundreds of plants during the entire development cycle, showing its applicability to the GxE analyses of large maize datasets.
Why it matches plant phenotyping methodsトウモロコシ器官の3D再構成・時系列追跡による表現型抽出パイプラインを開発し、大規模データセットで技術検証しており、方法が研究の中心である。
abstractWe propose PhenoTrack3D, a new pipeline to extract a 3D+t reconstruction of maize at organ level from plant images.
Reproduction assets foundThe paper explicitly states that the PhenoTrack3D pipeline source code and examples are publicly available on GitHub under an Open Source licence (Cecill-C). This is the authors' analysis code for the paper's maize phenotyping pipeline. No public phenotype dataset or trained model checkpoint URL is stated in the blocksCode · publicThe source code and examples are available on Github
(https://github.com/openalea/phenotrack3d) under an Open Source licence (Cecill-C).Open asset ↗openalea/phenotrack3dpdf-page:28 lines:1-62Plant phenotyping relevance match · UnverifiedOpenAlex · checked 15 Sept 2026
ArabidopsisLaboratory / benchtopRootMorphology / geometry measurementImage / point-cloud registrationSkeletonization / topologyGrowth / time-series analysisTrackingGrowth / development / phenologyRoot system architecture
Abstract Background High-throughput phenotyping is crucial for the genetic and molecular understanding of adaptive root system development. In recent years, imaging automata have been developed to acquire the root system architecture of many genotypes grown in Petri dishes to explore the Genetic x Environment (GxE) interaction. There is now an increasing interest in understanding the dynamics of the adaptive responses, such as the organ apparition or the growth rate. However, due to the increasing complexity of root architectures in development, the accurate description of the topology, geometry, and dynamics of a growing root system remains a challenge. Results We designed a high-throughput phenotyping method, combining an imaging device and an automatic analysis pipeline based on registration and topological tracking, capable of accurately describing the topology and geometry of observed root systems in 2D+t. The method was tested on a challenging Arabidopsis seedling dataset, including numerous root occlusions and crossovers. Static phenes are estimated with high accuracy ( R 2 = 0.996 and 0, 923 for primary and second-order roots length, respectively). These performances are similar to state-of-the-art results obtained on root systems of equal or lower complexity. In addition, our pipeline estimates dynamic phenes accurately between two successive observations ( R 2 = 0. 938 for lateral root growth). Conclusions We designed a novel method of root tracking that accurately and automatically measures both static and dynamic RSA parameters from a novel high-throughput root phenotyping platform. It has been used to characterize developing patterns of root systems grown under various environmental conditions. It provides a solid basis to explore the GxE interaction controlling the dynamics of root system architecture adaptive responses. In future work, our approach will be adapted to a wider range of imaging configurations and species.
Why it matches plant phenotyping methods根系の静的・動的形質を画像取得と自動解析で抽出する高スループット手法の設計・精度検証が研究の中心であるため。
abstractWe designed a high-throughput phenotyping method, combining an imaging device and an automatic analysis pipeline based on registration and topological tracking
In agriculture, the majority of vision systems perform still image classification. Yet, recent work has highlighted the potential of spatial and temporal cues as a rich source of information to improve the classification performance. In this paper, we propose novel approaches to explicitly capture both spatial and temporal information to improve the classification of deep convolutional neural networks. We leverage available RGB-D images and robot odometry to perform inter-frame feature map spatial registration. This information is then fused within recurrent deep learnt models, to improve their accuracy and robustness. We demonstrate that this can considerably improve the classification performance with our best performing spatial-temporal model (ST-Atte) achieving absolute performance improvements for intersection-over-union (IoU[%]) of 4.7 for crop-weed segmentation and 2.6 for fruit (sweet pepper) segmentation. Furthermore, we show that these approaches are robust to variable framerates and odometry errors, which are frequently observed in real-world applications.
Why it matches plant phenotyping methodsRGB-D画像とロボットオドメトリを用いて空間・時間情報を統合する画像解析手法を開発し、作物・果実のセグメンテーション性能を検証しているため、植物表現型取得手法が中心である。
abstractWe demonstrate that this can considerably improve the classification performance with our best performing spatial-temporal model (ST-Atte) achieving absolute performance improvements for intersection-over-union (IoU[%]) of 4.7 for crop-weed segmentation and 2.6 for fruit (sweet pepper) segmentation.
Vegetation indices (VIs), such as the green chlorophyll index and normalized difference vegetation index, are calculated from visible and near-infrared band images for plant diagnosis in crop breeding and field management. The DJI P4 Multispectral drone combined with the Agisoft Metashape Structure from Motion/Multi View Stereo software is some of the most cost-effective equipment for creating high-resolution orthomosaic VI images. However, the manufacturer's procedure results in remarkable location estimation inaccuracy (average error: 3.27–3.45 cm) and alignment errors between spectral bands (average error: 2.80–2.84 cm). We developed alternative processing procedures to overcome these issues, and we achieved a higher positioning accuracy (average error: 1.32–1.38 cm) and better alignment accuracy between spectral bands (average error: 0.26–0.32 cm). The proposed procedure enables precise VI analysis, especially when using the green chlorophyll index for corn, and may help accelerate the application of remote sensing techniques to agriculture.
Why it matches plant phenotyping methods植物の生育観測に用いるマルチスペクトル正射画像について、位置推定・スペクトルバンド整合の処理手順を開発し、精度を検証しているため、植物表現型取得手法が中心である。
abstractWe developed alternative processing procedures to overcome these issues, and we achieved a higher positioning accuracy (average error: 1.32–1.38 cm) and better alignment accuracy between spectral bands (average error: 0.26–0.32 cm).
Reconstructing three-dimensional (3D) point cloud model of maize plants can provide reliable data for its growth observation and agricultural machinery research. The existing data collection systems and registration methods have low collection efficiency and poor registration accuracy. A point cloud registration method for maize plants based on conical surface fitting-iterative closest point (ICP) with automatic point cloud collection platform was proposed in this paper. Firstly, a Kinect V2 was selected to cooperate with an automatic point cloud collection platform to collect multi-angle point clouds. Then, the conical surface fitting algorithm was employed to fit the point clouds of the flowerpot wall to acquire the fitted rotation axis for coarse registration. Finally, the interval ICP registration algorithm was used for precise registration, and the Delaunay triangle meshing algorithm was chosen to triangulate the point clouds of maize plants. The maize plant at the flowering and kernel stage was selected for reconstruction experiments, the results show that: the full-angle registration takes 57.32 s, and the registration mean distance error is 1.98 mm. The measured value's relative errors between the reconstructed model and the material object of maize plant are controlled within 5%, the reconstructed model can replace maize plants for research.
Why it matches plant phenotyping methodsトウモロコシの3D点群を自動収集・登録・再構成する手法とプラットフォームを開発し、誤差を検証しており、植物形態計測が研究の中心である。
abstractA point cloud registration method for maize plants based on conical surface fitting-iterative closest point (ICP) with automatic point cloud collection platform was proposed in this paper.
Ratiometric time-lapse FRET analysis requires a robust and accurate processing pipeline to eliminate bias in intensity measurements on fluorescent images before further quantitative analysis can be conducted. This level of robustness can only be achieved by supplementing automated tools with built-in flexibility for manual ad-hoc adjustments. FRET-IBRA is a modular and fully parallelized configuration file-based tool written in Python. It simplifies the FRET processing pipeline to achieve accurate, registered, and unified ratio image stacks. The flexibility of this tool to handle discontinuous image frame sequences with tailored configuration parameters further streamlines the processing of outliers and time-varying effects in the original microscopy images. FRET-IBRA offers cluster-based channel background subtraction, photobleaching correction, and ratio image construction in an all-in-one solution without the need for multiple applications, image format conversions, and/or plug-ins. The package accepts a variety of input formats and outputs TIFF image stacks along with performance measures to detect both the quality and failure of the background subtraction algorithm on a per frame basis. Furthermore, FRET-IBRA outputs images with superior signal-to-noise ratio and accuracy in comparison to existing background subtraction solutions, whilst maintaining a fast runtime. We have used the FRET-IBRA package extensively to quantify the spatial distribution of calcium ions during pollen tube growth under mechanical constraints. Benchmarks against existing tools clearly demonstrate the need for FRET-IBRA in extracting reliable insights from FRET microscopy images of dynamic physiological processes at high spatial and temporal resolution. The source code for Linux and Mac operating systems is released under the BSD license and, along with installation instructions, test images, example configuration files, and a step-by-step tutorial, is freely available at github.com/gmunglani/fret-ibra.
Why it matches plant phenotyping methods植物の動的な生理状態を画像から定量化するFRET画像処理ツールの開発・ベンチマークが中心であり、花粉管内カルシウム分布の抽出に実質的に応用されている。
abstractFRET-IBRA is a modular and fully parallelized configuration file-based tool written in Python.
Reproduction assets foundThe paper's authors publicly released the FRET-IBRA analysis toolkit (Python source code, test images, example configuration files, and tutorial) under a BSD license on GitHub. The test images include the FRET microscopy image stacks of growing Arabidopsis pollen tubes used in the paper's calcium-distribution phenotypiCode · publicThe source code for Linux and Mac operating systems is released under the BSD license and, along with installation instructions, test images, example configuration files, and a step-by-step tutorial, is freely available at github.com/gmunglani/fret-ibra.Open asset ↗github.com/gmunglani/fret-ibralines:113-128Plant phenotyping relevance match · UnverifiedOpenAlex · checked 13 Sept 2026
To assist plant scientists, geneticists, and growers to understand crop-environment interactions, plant phenotyping is a powerful tool for improving crop cultivars and developing decision support systems in farm management. Recent trends use LiDAR to capture three-dimensional (3D) information from plants to analyze traits vital to plant growth and development. However, current terrestrial-based 3D analysis methodologies are time and labor intensive and can be a bottleneck when large agricultural fields need to be analyzed. Robotic technologies can be used to accelerate the field-based measurements of relevant plant features and optimize the high-throughput phenotyping process. In this paper, we present a robotic system with a 3D LiDAR and a data processing pipeline for efficient, high-throughput field phenotyping of cotton crops. The robotic system consists of a Husky robotic platform equipped with a FARO Focus 3D laser scanner. The components of the system are integrated under the ROS framework to ensure interoperability and data integrity and availability at any given time. The data processing pipeline involves the data collection, registration, and analysis tasks for measuring crop traits at the plot level—canopy height, volume, and light interception—and estimating yield. This work demonstrates a crop phenotyping platform that leverages two off-the-shelf equipment for the quantitative assessment of cotton plant traits in the field. This methodology can be extended to other agricultural crops contributing to the advancement of plant phenomics.
Why it matches plant phenotyping methods3D LiDARロボットとデータ処理パイプラインを開発し、綿の草冠高・体積・光遮断および収量を圃場で定量化する高スループット表現型解析基盤であり、手法が研究の中心である。
abstractIn this paper, we present a robotic system with a 3D LiDAR and a data processing pipeline for efficient, high-throughput field phenotyping of cotton crops.
High-throughput platforms for plant phenotyping usually demand expensive high-density LiDAR devices with computational intense methods for characterizing several morphological variables. In fact, most platforms require offline processing to achieve a comprehensive plant architecture model. In this paper, we propose a low-cost plant phenotyping system based on the sensory fusion of low-density LiDAR data with multispectral imagery. Our contribution is twofold: (i) an integrated phenotyping platform with embedded processing methods capable of providing real-time morphological data, and (ii) a multi-sensor fusion algorithm that precisely match the 3D LiDAR point-cloud data with the corresponding multispectral information, aiming for the consolidation of four-dimensional plant models. We conducted extensive experimental tests over two plants with different morphological structures, demonstrating the potential of the proposed solution for enabling real-time plant architecture modeling in the field, based on low-density LiDARs.
Why it matches plant phenotyping methods低密度LiDARとマルチスペクトル画像を融合し、リアルタイムに植物形態・構造を抽出するフェノタイピング基盤とアルゴリズムを開発しており、方法が研究の中心である。
abstractan integrated phenotyping platform with embedded processing methods capable of providing real-time morphological data
Banana is a fruit plant that is widely produced in Indonesia. Unfortunately, this plant is very susceptible to diseases which can reduce the quality and quantity of the crop. This paper proposes disease detection in banana plants using a thermal camera. The detection is carried out using image processing techniques with multilevel thresholding methods. The image is captured using a thermal camera, then the image is preprocessed to suit what is desired. After that, so that the position is the same as the image taken using a digital camera, the image produced by the thermal camera is carried out by an image registration process. The image processing result is compared with the ground truth image obtained from a digital camera to determine the effectiveness of the proposed method. The effectiveness of the proposed method is measured using the parameters Recall, Precision, F-measure, and Accuracy. The effectiveness of the proposed method is quite effective because it produces parameter values above 80%, namely the recall value of 86,59%, the Precision of 99,1%, the F-measure of 92%, and the accuracy of 89,78%.
Why it matches plant phenotyping methods熱画像とマルチレベル閾値処理によりバナナ植物の病徴を検出・評価する手法を提案し、デジタル画像を基準に性能検証しているため、植物フェノタイピング手法が中心である。
abstractThis paper proposes disease detection in banana plants using a thermal camera.
Global warming and water resource shortage greatly influence the crop growth and negatively affect the crop yield. Breeding water–stress resistant crop varieties is one of the effective ways to handle this problem. The surface temperatures of the crop are essential for assessing their water stress resistance. Thermal imaging has been widely used to acquire the crop surface temperatures. However, most studies focus on 2D measurement. A 3D thermal imaging system is designed, and a method is developed by using the thermal and RGB-D data to acquire 3D thermal information of maize under water stress conditions. First, thermal and RGB-D cameras were used to collect the thermal and color images, and depth data of maize at the jointing stage and the thermal and color images were processed to extract the edge images of maize. Second, the KAZE feature was selected to register the edge images. Testing results showed that the KAZE feature has better performance than the SURF and BRISK features in the thermal and color image registration of maize. On the basis of the thermal and color image registration, the depth data of maize were assigned with temperature values. Third, the depth data of maize were further processed with denoising, maize extraction, amplification, smoothing, and temperature correction steps to improve the data qualities. Finally, the crop water stress index and canopy–air temperature difference values of each point were calculated. The results demonstrated that the system and the proposed method can effectively detect the water stress characteristics of maize in 3D, which can be combined with the morphological traits of leaves to synthetically analyze the water stress resistance of the crop.
Why it matches plant phenotyping methodsトウモロコシの3D熱情報を取得し、水ストレス指標を算出する画像・センサ計測法の開発が中心であり、植物表現型測定法に該当する。
abstractA 3D thermal imaging system is designed, and a method is developed by using the thermal and RGB-D data to acquire 3D thermal information of maize under water stress conditions.
We present several methods for improving plant reconstruction from multiple 3D observations. Producing 3D data useful for plant phenotyping requires proximal sensing (e.g. line scanner, depth camera) at multiple incident angles (φ) and often with multiple passes. These resulting individual point clouds must then be assembled into a single point cloud for analysis. Our interest in improving the registration of individual plants is focused specifically on observations made within field settings which present additional challenges over laboratory 3D scans, where background, overlap and light conditions can be controlled. To develop these methods, we use several season’s worth of data from the University of Arizona’s Field Scanalyzer located in Maricopa, Arizona. Our approach prioritizes: (1) plant completeness, (2) noise reduction, (3) temporal similarity and (4) computational efficiency. The first priority is accomplished simply by prioritizing individual point clouds that contain the majority of the individual plant. 3D field scanning can result in component point clouds that are from near-identical φ and cover the same portions of the individual plant. This results in both additional noise and uncertainties due to small georeferencing errors and plant movement between scans. Thus, we remove the data that is furthest in time with non-unique φ in order to achieve priorities 2 and 3. Our method results in small scene reconstruction which has low memory and computational demands. In order to improve registration further, we investigate iterative closest point (ICP) registration fitting using weights defined by crop height distributions and semantic segmentation point labeling.
Why it matches plant phenotyping methods個体植物の3Dスキャンを統合・再構成する点群登録法を開発しており、植物フェノタイピングに利用する形状データ取得・抽出が研究の中心である。
abstractWe present several methods for improving plant reconstruction from multiple 3D observations.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 9 Sept 2026
The miniaturization of hyperspectral cameras has opened a new path to capture spectral information. One such camera, called the hybrid linescan camera, requires accurate control of its movement. Contrary to classical linescan cameras, where one line is available for every band in one shot, the latter asks for multiple shots to fill a line with multiple bands. Unfortunately, the reconstruction is corrupted by a parallax effect, which affects each band differently. In this article, we propose a two-step procedure, which first reconstructs an approximate datacube in two different ways, and second, performs a corrective warping on each band based on a multiple homography framework. The second step combines different stitching methods to perform this reconstruction. A complete synthetic and experimental comparison is performed by using geometric indicators of reference points. It appears throughout the course of our experimentation that misalignment is significantly reduced but remains non-negligible at the potato leaf scale.
Why it matches plant phenotyping methodsジャガイモ葉のスペクトル画像を再構成・補正する手法を開発し、合成および実験比較で幾何学的に検証しており、植物表現型取得の技術的方法が中心である。
abstractwe propose a two-step procedure, which first reconstructs an approximate datacube in two different ways, and second, performs a corrective warping on each band based on a multiple homography framework.
Cytosolic pH (pHcyt) regulates a wide range of cellular processes in plants. Changes in pHcyt occurring under the effect of different stressors can participate in signal transmission. The dynamics of pHcyt under the action of external factors, including significant factors for open ground crops such as temperature, remains poorly understood, which is largely due to the difficulty of intracellular pH registration using standard methods. In this work, model plants of potato (one of the essential crops) expressing a fluorescent ratiometric pH sensor Pt-GFP were created. The calibration obtained in vivo allowed for the determination of the pHcyt values of the cells of the leaves, which is 7.03 ± 0.03 pH. Cooling of the whole leaf caused depolarization and rapid acidification of the cytosol, the amplitude of which depended on the cooling strength, amounting to about 0.2 pH units when cooled by 15 °C. When the temperature rises to 35–40 °C, the cytosol was alkalized by 0.2 pH units. Heating above the threshold temperature caused the acidification of cytosol and generation of variation potential. The observed rapid changes in pHcyt can be associated with changes in the activity of H+-ATPases, which was confirmed by inhibitory analysis.
Why it matches plant phenotyping methods遺伝子コード型蛍光センサーを用いた植物細胞質pHの全植物測定法を構築し、生体内校正と温度応答測定を行っており、植物の生理状態取得が中心である。
To assist plant scientists, geneticists, and growers to understand crop-environment interactions, plant phenotyping is a powerful tool for improving crop cultivars and developing decision support systems in farm management. Recent trends use LiDAR to capture three-dimensional (3D) information from plants to analyze traits vital to plant growth and development. However, current terrestrial-based 3D analysis methodologies are time and labor intensive and can be a bottleneck when large agricultural fields need to be analyzed. Robotic technologies can be used to accelerate the field-based measurements of relevant plant features and optimize the high-throughput phenotyping process. In this paper, we present a robotic system with a 3D LiDAR and a data processing pipeline for efficient, high-throughput field phenotyping of cotton crops. The robotic system consists of a Husky robotic platform equipped with a FARO Focus 3D laser scanner. The components of the system are integrated under the ROS framework to ensure interoperability and data integrity and availability at any given time. The data processing pipeline involves the data collection, registration, and analysis tasks for measuring crop traits at the plot level—canopy height, volume, and light interception—and estimating yield. This work demonstrates a crop phenotyping platform that leverages two off-the-shelf equipment for the quantitative assessment of cotton plant traits in the field. This methodology can be extended to other agricultural crops contributing to the advancement of plant phenomics.
Why it matches plant phenotyping methods3D LiDAR搭載ロボットとデータ処理パイプラインを開発し、圃場レベルで綿の樹冠高・体積・光遮断および収量を定量化する、植物フェノタイピング基盤が中心である。
abstractwe present a robotic system with a 3D LiDAR and a data processing pipeline for efficient, high-throughput field phenotyping of cotton crops.
Fruit three-dimensional (3D) model is crucial to estimating its geometrical and mechanical properties and improving the level of fruit mechanical processing. Considering the complex geometrical features and the required model accuracy, this paper proposed a 3D point cloud reconstruction method for the Rosa roxburghii fruit based on a three-dimensional laser scanner, including 3D point cloud generation, point cloud registration, fruit thorns segmentation, and 3D reconstruction. The 3D laser scanner was used to obtain the original 3D point cloud data of the Rosa roxburghii fruit, and then the fruit thorns data were removed by the segmentation algorithm combining the statistical outlier removal and radius outlier removal. By analyzing the effects of five-point cloud simplification methods, the optimal simplification method was determined. The Poisson reconstruction algorithm, the screened Poisson reconstruction algorithm, the greedy projection triangulation algorithm, and the Delaunay triangulation algorithm were utilized to reconstruct the fruit model. The number of model vertices, the number of facets, and the relative volume error were used to determine the best reconstruction algorithm. The results indicated that this model can better reconstruct the actual surface of Rosa roxburghii fruit. The method provides a reference for the related application.
Why it matches plant phenotyping methodsバラ科果実の3D形状をレーザースキャンと点群処理で再構築する方法が研究の中心であり、果実形態という植物形質を定量化している。
abstractthis paper proposed a 3D point cloud reconstruction method for the Rosa roxburghii fruit based on a three-dimensional laser scanner
We propose a 3D colour point cloud processing pipeline to count apples on individual apple trees in trellis structured orchards. Fruit counting at the tree level requires separating trees, which is challenging in dense orchards. We employ point clouds acquired from the leaf-off orchard in winter period, where the branch structure is visible, to delineate tree crowns. We localise apples in point clouds acquired in harvest period. Alignment of the two point clouds enables mapping apple locations to the delineated winter cloud and assigning each apple to its bearing tree. Our apple assignment method achieves an accuracy rate higher than 95%. In addition to presenting a first proof of feasibility, we also provide suggestions for further improvement on our apple assignment pipeline.
Why it matches plant phenotyping methods3D点群処理により個体樹ごとのリンゴ数を推定・割り当てる手法を開発し、精度評価も行っており、果実数という植物器官・収量関連形質の取得が中心である。
abstractWe propose a 3D colour point cloud processing pipeline to count apples on individual apple trees in trellis structured orchards.
Understanding the growth and development of individual plants is of central importance in modern agriculture, crop breeding, and crop science. To this end, using 3D data for plant analysis has gained attention over the last years. High-resolution point clouds offer the potential to derive a variety of plant traits, such as plant height, biomass, as well as the number and size of relevant plant organs. Periodically scanning the plants even allows for performing spatio-temporal growth analysis. However, highly accurate 3D point clouds from plants recorded at different growth stages are rare, and acquiring this kind of data is costly. Besides, advanced plant analysis methods from machine learning require annotated training data and thus generate intense manual labor before being able to perform an analysis. To address these issues, we present with this dataset paper a multi-temporal dataset featuring high-resolution registered point clouds of maize and tomato plants, which we manually labeled for computer vision tasks, such as for instance segmentation and 3D reconstruction, providing approximately 260 million labeled 3D points. To highlight the usability of the data and to provide baselines for other researchers, we show a variety of applications ranging from point cloud segmentation to non-rigid registration and surface reconstruction. We believe that our dataset will help to develop new algorithms to advance the research for plant phenotyping, 3D reconstruction, non-rigid registration, and deep learning on raw point clouds. The dataset is freely accessible at https://www.ipb.uni-bonn.de/data/pheno4d/.
Why it matches plant phenotyping methods植物フェノタイピング用の時系列3D点群データセットを構築し、手動アノテーションと複数の解析ベースラインを提供することが中心であり、再利用可能なデータ基盤として適格です。
abstractwe present with this dataset paper a multi-temporal dataset featuring high-resolution registered point clouds of maize and tomato plants, which we manually labeled for computer vision tasks
Reproduction assets foundThe paper's core contribution is the Pheno4D dataset of labeled maize and tomato plant point clouds, explicitly stated to be freely and publicly available at the authors' Bonn repository. A companion public data-loader API (Python/C++) is also provided on GitHub. Both are paper-specific, public, and directly actionableDataset · publicThe dataset is freely accessible at https://www.ipb.uni-bonn.de/data/pheno4d/.Open asset ↗https://www.ipb.uni-bonn.de/data/pheno4d/pdf-page:1 lines:1-65Code · publicWe provide the
code and the examples for loading the data at https://github.com/AIS-Bonn/data_loaders.Open asset ↗https://github.com/AIS-Bonn/data_loaderspdf-page:10 lines:1-57Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · checked 15 Sept 2026
High-throughput phenotyping is playing an increasingly important role in many areas of agriculture. Breeders will use it to obtain values for the traits of interest so that they can estimate genetic value and select promising varieties; growers may be interested in having predictions of yield well in advance of the actual harvest. In most phenotyping applications, image analysis plays an important role, drastically reducing the dependence on manual labor while being non-destructive. An automatic phenotyping system combines a reliable acquisition system, a high-performance segmentation algorithm for detecting fruits in individual images, and a registration algorithm that brings the images (and the corresponding detected plants or plant components) into a coherent spatial reference frame. Recently, significant advances have been made in the fields of robotics, image registration, and especially image segmentation, which each individually have improved the prospect of developing a fully integrated automatic phenotyping system. However, so far no complete phenotyping systems have been reported for routine use in a production environment. This work catalogs the outstanding issues that remain to be resolved by describing a prototype phenotyping system for a production tomato greenhouse, for many reasons a challenging environment.
Why it matches plant phenotyping methodsトマトの生産温室向けに、ロボット撮像、果実セグメンテーション、画像登録を統合した自動フェノタイピングシステムのプロトタイプを開発・記述しており、表現型取得手法が研究の中心である。
abstractThis work catalogs the outstanding issues that remain to be resolved by describing a prototype phenotyping system for a production tomato greenhouse
Background Surface roughness has a significant effect on leaf wettability. Consequently, it influences the efficiency and effectiveness of pesticide application. Therefore, roughness measurement of leaf surface offers support to the relevant research efforts. To characterize surface roughness, the prevailing methods have drawn support from large equipment that often come with high costs and poor portability, which is not suitable for field measurement. Additionally, such equipment may even suffer from inherent drawbacks like the absence of relationship between pixel intensity and corresponding height for scanning electron microscope (SEM). Results An imaging system with variable object distance was created to capture images of plant leaves, and a method based on shape from focus (SFF) was proposed. The given space-variantly blurred images were processed with the proposed algorithm to obtain the surface roughness of plant leaves. The algorithm improves the current SFF method through image alignment, focus distortion correction, and the introduction of NaN values that allows it to be applied for precise 3d-reconstruction and small-scale surface roughness measurement. Conclusion Compared with methods that rely on optical three-dimensional interference microscope, the method proposed in this paper preserves the overall topography of leaf surface, and achieves superior cost performance at the same time. It is clear from experiments on standard gauge blocks that the RMSE of step was approximately 4.44 µm. Furthermore, according to the Friedman/Nemenyi test, the focus measure operator SML was expected to demonstrate the best performance.
Why it matches plant phenotyping methods植物葉面の表面粗さという形態特性を、画像ベースのshape-from-focus法で3D再構成・定量化する手法を開発しており、方法が研究の中心である。
abstractThe algorithm improves the current SFF method through image alignment, focus distortion correction, and the introduction of NaN values that allows it to be applied for precise 3d-reconstruction and small-scale surface roughness measurement.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 8 Sept 2026
The three-dimensional reconstruction method using RGB-D camera has a good balance in hardware cost and point cloud quality. However, due to the limitation of inherent structure and imaging principle, the acquired point cloud has problems such as a lot of noise and difficult registration. This paper proposes a 3D reconstruction method using Azure Kinect to solve these inherent problems. Shoot color images, depth images and near-infrared images of the target from six perspectives by Azure Kinect sensor with black background. Multiply the binarization result of the 8-bit infrared image with the RGB-D image alignment result provided by Microsoft corporation, which can remove ghosting and most of the background noise. A neighborhood extreme filtering method is proposed to filter out the abrupt points in the depth image, by which the floating noise point and most of the outlier noise will be removed before generating the point cloud, and then using the pass-through filter eliminate rest of the outlier noise. An improved method based on the classic iterative closest point (ICP) algorithm is presented to merge multiple-views point clouds. By continuously reducing both the size of the down-sampling grid and the distance threshold between the corresponding points, the point clouds of each view are continuously registered three times, until get the integral color point cloud. Many experiments on rapeseed plants show that the success rate of cloud registration is 92.5% and the point cloud accuracy obtained by this method is 0.789 mm, the time consuming of a integral scanning is 302 s, and with a good color restoration. Compared with a laser scanner, the proposed method has considerable reconstruction accuracy and a significantly ahead of the reconstruction speed, but the hardware cost is much lower when building a automatic scanning system. This research shows a low-cost, high-precision 3D reconstruction technology, which has the potential to be widely used for non-destructive measurement of rapeseed and other crops phenotype.
Why it matches plant phenotyping methodsRGB-D画像による植物体の3D再構成・点群登録手法を開発し、精度・成功率・処理時間を検証しており、非破壊的な作物表現型計測が中心である。
abstractThis paper proposes a 3D reconstruction method using Azure Kinect to solve these inherent problems.
Ratiometric time-lapse FRET analysis requires a robust and accurate processing pipeline to eliminate bias in intensity measurements on fluorescent images before further quantitative analysis can be conducted. This level of robustness can only be achieved by supplementing automated tools with built-in flexibility for manual ad-hoc adjustments. FRET-IBRA is a modular and fully parallelized configuration file-based tool written in Python. It simplifies the FRET processing pipeline to achieve accurate, registered, and unified ratio image stacks. The flexibility of this tool to handle discontinuous image frame sequences with tailored configuration parameters further streamlines the processing of outliers and time-varying effects in the original microscopy images. FRET-IBRA offers cluster-based channel background subtraction, photobleaching correction, and ratio image construction in an all-in-one solution without the need for multiple applications, image format conversions, and/or plug-ins. The package accepts a variety of input formats and outputs TIFF image stacks along with performance measures to detect both the quality and failure of the background subtraction algorithm on a per frame basis. Furthermore, FRET-IBRA outputs images with superior signal-to-noise ratio and accuracy in comparison to existing background subtraction solutions, whilst maintaining a fast runtime. The FRET-IBRA package has been extensively used in quantifying the spatial distribution of calcium ions during pollen tube growth under mechanical constraints. Benchmarks against existing tools clearly demonstrate the need for FRET-IBRA in extracting reliable insights from FRET microscopy images of dynamic physiological processes at high spatial and temporal resolution. The source code for Linux and Mac operating systems is released under the BSD license and, along with installation instructions, test images, example configuration files, and a step-by-step tutorial, is freely available at github.com/gmunglani/fret-ibra . Author Summary FRET is a fundamental imaging technique used to generate fluorescence signals sensitive to molecular conformations and interactions. Despite its wide use and the large body of literature on the theoretical steps required to process images generated from this procedure, we were unable to locate a tool that contained the entire processing workflow, whilst allowing the user the flexibility to adjust parameters for maximum accuracy and runtime efficiency. FRET-IBRA was thus created to be an all-in-one, open-source, parallel solution to process FRET images, while eliminating complications arising from repeated image format conversions. Besides enhancing the background subtraction algorithm for FRET images, several additional options were implemented for the user to extract the cleanest signal possible for their specific use case. FRET-IBRA is primarily built for flexibility when handling large image stacks by supporting sequences of image frames to be treated independently, greatly reducing time spent on splitting and concatenating image stacks. In accuracy and speed benchmarks against more general background subtraction packages, FRET-IBRA was able to provide the cleanest results with a fast runtime, leading to reliable analysis without additional tuning.
Why it matches plant phenotyping methodsFRET画像の背景補正・補正処理・比画像構築を一体化したソフトウェアを開発し、既存ツールとのベンチマークで検証している。花粉管成長中のカルシウム分布という植物生理状態の抽出にも適用され、方法が中心である。
abstractFRET-IBRA is a modular and fully parallelized configuration file-based tool written in Python.
Reproduction assets foundThe paper's authors publicly release the FRET-IBRA analysis toolkit (source code, test images, example configuration files, and tutorial) on GitHub, directly supporting the paper's FRET image processing and ratiometric analysis of pollen tube calcium imaging.Code · publicThe source code for Linux and Mac operating systems is released under the
BSD license and, along with installation instructions, test images, example configuration
files, and a step-by-step tutorial, is freely available at github.com/gmunglani/fret-ibra.Open asset ↗github.com/gmunglani/fret-ibrapdf-page:1 lines:1-66Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · checked 8 Sept 2026
Published30 Jun 2021The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesCited by 3 · OpenAlex ↗
MaizeTomatoX-ray / CTRootImage / point-cloud registrationSkeletonization / topologyRoot system architecture
Abstract. Breakthrough imaging technologies are a potential solution to the plant phenotyping bottleneck in marker-assisted breeding and genetic mapping. X-Ray CT (computed tomography) technology is able to acquire the digital twin of root system architecture (RSA), however, advances in computational methods to digitally model spatial disposition of root system networks are urgently required.We extracted the root skeleton of the digital twin based on 3D data from X-ray CT, which is optimized for high-throughput and robust results. Significant root architectural traits such as number, length, growth angle, elongation rate and branching map can be easily extracted from the skeleton. The curve-skeleton extraction is computed based on a constrained Laplacian smoothing algorithm. This skeletal structure drives the registration procedure in temporal series. The experiment was carried out at the Ag Alumni Seed Phenotyping Facility (AAPF) at Purdue University in West Lafayette (IN, USA). Three samples of tomato root at 2 different times and three samples of corn root at 3 different times were scanned. The skeleton is able to accurately match the shape of the RSA based on a visual inspection.The results based on a visual inspection confirm the feasibility of the proposed methodology, providing scalability to a comprehensive analysis to high throughput root phenotyping.
Why it matches plant phenotyping methodsX線CT画像から根系骨格を抽出し、根の形態形質を高スループットに推定する計算手法の開発が中心であるため。
abstractWe extracted the root skeleton of the digital twin based on 3D data from X-ray CT, which is optimized for high-throughput and robust results.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 14 Sept 2026
Abstract BackgroundBreakthrough imaging technologies are a potential solution to address the plant phenotyping bottleneck regarding marker-assisted breeding and genetic mapping. X-Ray CT (computed tomography) technology is able to acquire the digital twin of root system architecture (RSA) but computational methods to quantify RSA traits and analyze their changes over time are limited. RSA traits extremely affect agricultural productivity. We develop a spatial-temporal root architectural modeling method based on 4D data from X-ray CT. This novel approach is optimized for high-throughput phenotyping considering the cost-effective time to process the data and the accuracy and robustness of the results. Significant root architectural traits, including root elongation rate, number, length, growth angle, height, diameter, branching map, and volume of axial and lateral roots are extracted from the model based on the digital twin. Our pipeline is divided into two major steps: (i) first, we compute the curve-skeleton based on a constrained Laplacian smoothing algorithm. This skeletal structure determines the registration of the roots over time; (ii) subsequently, the RSA is robustly modeled by a cylindrical fitting. The experiment was carried out at the Ag Alumni Seed Phenotyping Facility (AAPF) from Purdue University in West Lafayette (IN, USA). ResultsRoots from three samples of tomato plants at two different times and three samples of corn plants at three different times were scanned. Regarding the first step, the PCA analysis of the skeleton is able to accurately and robustly register temporal roots. From the second step, the volume from the cylindrical model was compared against the root digital twin, reaching a coefficient of determination (R2) of 0.84 and a P < 0.001. ConclusionsThe results confirm the feasibility of the proposed methodology, providing scalability to a comprehensive analysis to high throughput root phenotyping.
Why it matches plant phenotyping methodsX線CTの4Dデータから根系構造形質を抽出する計算手法を開発・検証しており、植物フェノタイピング手法が研究の中心です。
abstractWe develop a spatial-temporal root architectural modeling method based on 4D data from X-ray CT.
We developed a software tool enabling user-friendly and standardized pre- and post-processing of images of rooted soil by combining image processing techniques such as image registration, calibration, and segmentation in a graphical user interface. The added benefits of this image processing approach include an improved workflow in soil zymography. For evaluation, we conducted a rhizobox experiment with maize and determined the activity of leucine-aminopeptidase before and after glucose addition based on soil zymography. The temporal and spatial distribution of enzyme activity at the root-soil interface can be visualized by Root-o-Mat which offers 1) standardized image pre-processing, 2) calibration, 3) identification of hotspots of various intensity thresholds, 4) spatial analysis for selected roots, 5) inter-active illustration of enzyme activity profile lines, 6) image viewer, and 7) detection of temporal changes of enzyme activity. Registering images of the same rhizobox taken in successive periods allows further temporal and spatial analysis. We conclude that Root-o-Mat simplifies and firmly anchors image processing and image analyses in soil zymography. The new software can be downloaded for free (www.root-o-mat.de).
Why it matches plant phenotyping methods根圏画像の登録・校正・分割・空間解析を行い、根—土壌界面における酵素活性の時空間分布を抽出するソフトウェアを開発・評価しており、植物状態の画像解析手法が中心である。
abstractWe developed a software tool enabling user-friendly and standardized pre- and post-processing of images of rooted soil by combining image processing techniques such as image registration, calibration, and segmentation in a graphical user interface.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 14 Sept 2026
The 3D reconstruction method using RGB-D camera has a good balance in hardware cost, point cloud quality and automation. However, due to the limitation of inherent structure and imaging principle, the acquired point cloud has problems such as a lot of noise and difficult registration. This paper proposes a three-dimensional reconstruction method using Azure Kinect to solve these inherent problems. Shoot color map, depth map and near-infrared image of the target from six perspectives by Azure Kinect sensor. Multiply the 8-bit infrared image binarization with the general RGB-D image alignment result provided by Microsoft to remove ghost images and most of the background noise. In order to filter the floating point and outlier noise of the point cloud, a neighborhood maximum filtering method is proposed to filter out the abrupt points in the depth map. The floating points in the point cloud are removed before generating the point cloud, and then using the through filter filters out outlier noise. Aiming at the shortcomings of the classic ICP algorithm, an improved method is proposed. By continuously reducing the size of the down-sampling grid and the distance threshold between the corresponding points, the point clouds of each view are continuously registered three times, until get the complete color point cloud. A large number of experimental results on rape plants show that the point cloud accuracy obtained by this method is 0.739mm, a complete scan time is 338.4 seconds, and the color reduction is high. Compared with a laser scanner, the proposed method has considerable reconstruction accuracy and a significantly ahead of the reconstruction speed, but the hardware cost is much lower and it is easy to automate the scanning system. This research shows a low-cost, high-precision 3D reconstruction technology, which has the potential to be widely used for non-destructive measurement of crop phenotype.
Why it matches plant phenotyping methodsRGB-Dカメラによる植物3D再構成法を開発・検証し、作物表現型の非破壊測定への利用可能性を評価しており、表現型取得手法が研究の中心である。
abstractThis paper proposes a three-dimensional reconstruction method using Azure Kinect to solve these inherent problems.
Computer vision based plant phenomics can be used to monitor the health and the growth of plants. This letter presents the extension of 2-D maximum likelihood matching to 3-D maximum likelihood estimation sample consensus (MLEASAC) and provides a comparative evaluation of some popular 3-D correspondence grouping algorithms. We test these algorithms on 3-D point clouds of plants along with two standard benchmarks addressing shape retrieval and point cloud registration scenarios. The performance of the correspondence grouping algorithms is evaluated in terms of precision and recall. The results show that of all the evaluated algorithms, 3-D random sample consensus (RANSAC) and MLEASAC perform the best, with MLEASAC being slightly more efficient while being computationally less intense than RANSAC.
Why it matches plant phenotyping methods3-D植物点群に対する対応付けアルゴリズムを開発・比較評価しており、植物フェノタイピング向けの計算画像解析手法が中心です。
abstractThis letter presents the extension of 2-D maximum likelihood matching to 3-D maximum likelihood estimation sample consensus (MLEASAC) and provides a comparative evaluation of some popular 3-D correspondence grouping algorithms.
Multimodal images fusion has the potential to enrich the information gathered by multi-sensor plant phenotyping platforms. Fusion of images from multiple sources is, however, hampered by the technical lock of image registration. The aim of this paper is to provide a solution to the registration and fusion of multimodal wheat images in field conditions and at close range. Eight registration methods were tested on nadir wheat images acquired by a pair of red, green and blue (RGB) cameras, a thermal camera and a multispectral camera array. The most accurate method, relying on a local transformation, aligned the images with an average error of 2 mm but was not reliable for thermal images. More generally, the suggested registration method and the preprocesses necessary before fusion (plant mask erosion, pixel intensity averaging) would depend on the application. As a consequence, the main output of this study was to identify four registration-fusion strategies: (i) the REAL-TIME strategy solely based on the cameras’ positions, (ii) the FAST strategy suitable for all types of images tested, (iii) and (iv) the ACCURATE and HIGHLY ACCURATE strategies handling local distortion but unable to deal with images of very different natures. These suggestions are, however, limited to the methods compared in this study. Further research should investigate how recent cutting-edge registration methods would perform on the specific case of wheat canopy.
Why it matches plant phenotyping methods小麦のマルチモーダル画像を用いた植物フェノタイピングのために、画像位置合わせ・融合手法を開発、比較検証しており、手法が研究の中心である。
abstractThe aim of this paper is to provide a solution to the registration and fusion of multimodal wheat images in field conditions and at close range.
In this research, multispectral and depth images were utilized for tea moisture content detection, the problems on leaf surface orientation and detection height were studied specifically. For the leaf surface orientation issue, multispectral images (25 bands) of the front surface and back surface of tea leaves were collected. Based on the spectra with same surface orientation, regression models of tea moisture content were established. The R²P values of LSSVR models reach 0.77 and 0.68 for the front surface and back surface, respectively. To distinguish the surface orientation of tea leaves, an LDA classifier was built based on spectral band ratio information. The overall classification accuracy reaches 87.8%. The distribution map of tea moisture content was successfully generated by importing the spectra into the classifier and the regression model. For the detection height issue, the multispectral image and depth image of tea leaves were collected simultaneously. First, an experiment was designed to figure out the attenuation coefficient of each band and the calibration model of detection height. Then, the detection height information was introduced into each pixel of the multispectral image by image registration. According to the detection height and calibration model, the spectrum of each pixel was calibrated. Finally, through importing the modified spectra into the classifier and regression model, the visual detection of tea moisture content was realized with detection height calibration. This research promoted the practicability of tea moisture content detection, and improved the visualization detection technology based on the fusion of multispectral image and depth image.
Why it matches plant phenotyping methods茶葉の水分含量という植物器官の状態を、マルチスペクトル・深度画像、分類、回帰、画像登録、検出高さ補正により推定・可視化する方法が研究の中心である。
abstractmultispectral and depth images were utilized for tea moisture content detection
Background Particle-tracking in 3D is an indispensable computational tool to extract critical information on dynamical processes from raw time-lapse imaging. This is particularly true with in vivo time-lapse fluorescence imaging in cell and developmental biology, where complex dynamics are observed at high temporal resolution. Common tracking algorithms used with time-lapse data in fluorescence microscopy typically assume a continuous signal where background, recognisable keypoints and independently moving objects of interest are permanently visible. Under these conditions, simple registration and identity management algorithms can track the objects of interest over time. In contrast, here we consider the case of transient signals and objects whose movements are constrained within a tissue, where standard algorithms fail to provide robust tracking. Results To optimize 3D tracking in these conditions, we propose the merging of registration and tracking tasks into a registration algorithm that uses random sampling to solve the identity management problem. We describe the design and application of such an algorithm, illustrated in the domain of plant biology, and make it available as an open-source software implementation. The algorithm is tested on mitotic events in 4D data-sets obtained with light-sheet fluorescence microscopy on growing Arabidopsis thaliana roots expressing CYCB::GFP. We validate the method by comparing the algorithm performance against both surrogate data and manual tracking. Conclusion This method fills a gap in existing tracking techniques, following mitotic events in challenging data-sets using transient fluorescent markers in unregistered images.
Why it matches plant phenotyping methods植物組織のタイムラプス画像から細胞分裂イベントを追跡・抽出する計算手法を開発し、代理データおよび手動追跡と比較検証しているため、植物フェノタイピング手法が中心である。
abstractwe propose the merging of registration and tracking tasks into a registration algorithm that uses random sampling to solve the identity management problem.
Plant phenotyping is a central task in crop science and plant breeding. It involves measuring plant traits to describe the anatomy and physiology of plants and is used for deriving traits and evaluating plant performance. Traditional methods for phenotyping are often time-consuming operations involving substantial manual labor. The availability of 3D sensor data of plants obtained from laser scanners or modern depth cameras offers the potential to automate several of these phenotyping tasks. This automation can scale up the phenotyping measurements and evaluations that have to be performed to a larger number of plant samples and at a finer spatial and temporal resolution. In this paper, we investigate the problem of registering 3D point clouds of the plants over time and space. This means that we determine correspondences between point clouds of plants taken at different points in time and register them using a new, non-rigid registration approach. This approach has the potential to form the backbone for phenotyping applications aimed at tracking the traits of plants over time. The registration task involves finding data associations between measurements taken at different times while the plants grow and change their appearance, allowing 3D models taken at different points in time to be compared with each other. Registering plants over time is challenging due to its anisotropic growth, changing topology, and non-rigid motion in between the time of the measurements. Thus, we propose a novel approach that first extracts a compact representation of the plant in the form of a skeleton that encodes both topology and semantic information, and then use this skeletal structure to determine correspondences over time and drive the registration process. Through this approach, we can tackle the data association problem for the time-series point cloud data of plants effectively. We tested our approach on different datasets acquired over time and successfully registered the 3D plant point clouds recorded with a laser scanner. We demonstrate that our method allows for developing systems for automated temporal plant-trait analysis by tracking plant traits at an organ level.
Why it matches plant phenotyping methods植物の時系列3D点群を登録し、骨格表現に基づいて器官レベルの形質追跡を可能にする新規計算手法を開発・検証しており、フェノタイピング手法が中心である。
abstractIn this paper, we investigate the problem of registering 3D point clouds of the plants over time and space.
Reproduction assets foundThe paper's Data Availability Statement explicitly provides both the 4D plant point cloud datasets (maize and tomato laser-scanner time series used for the phenotyping/registration experiments) and the authors' implementation code, each with a public URL.Dataset · publicavailable at https://www.ipb.uni-bonn.de/data/4d- tems for automated temporal plant-trait analysis by tracking plant traits at an organ level.Open asset ↗pdf-page:1 lines:1-63Code · publicThe code for our approach is
available at https://github.com/PRBonn/4d_plant_
registration.Open asset ↗pdf-page:1 lines:1-63Plant phenotyping relevance match · UnverifiedEurope PMC · OpenAlex · checked 9 Sept 2026
Abstract BackgroundSurface roughness has a significant effect on leaf wettability, consequently influencing the efficiency and effectiveness of pesticide spraying application. Therefore, surface roughness measure of plant leaves is conducive to relevant researches. In order to characterize the surface roughness, present methods have to draw support from large apparatus, but they are generally high-cost and not portable enough for field measurement. Methods those instruments even have potentially inherent drawback such as absence of relation between pixel intensity and corresponding height for scanning electron microscope (SEM). ResultsAn imaging system with variable object distance is set up to capture images of plant leaves and a shape from focus (SFF) based method is proposed. These space-variantly blurred images are processed with the proposed algorithm to yield surface roughness of plant leaves. The algorithm mainly improves the current SFF method in image alignment, focus distortion correction, and NaN values introducing to make it applicative for precise 3d-reconstruction and surface roughness measure in small scale. ConclusionCompared with method via optical three-dimensional interference microscope, the proposed method preserves the overall topography of leaf surface and meanwhile achieves superior cost performance. Experiments on standard gauge blocks revealed the RMSE of step was approximately 4.44μm. Furthermore, the focus measure operator SML was supposed to perform best according to Friedman/Nemenyi test.
Why it matches plant phenotyping methods葉表面粗さという植物形質を画像ベースで推定するSFF法と撮像システムを開発し、既存手法との比較および精度検証を行っており、フェノタイピング手法が中心です。
This paper provides a practical procedure for fusing LiDAR and photogrammetric point clouds for the extraction of tree metrics. Aerial photogrammetric point clouds are first generated using the structure-from-motion and dense-matching methods. Registration of the LiDAR and photogrammetric point clouds is then performed using an onboard global positioning system and inertial measurement unit. However, due to systematic deviations, it is impossible to directly merge the two types of point cloud. Therefore, an urban street network obtained from the OpenStreetMap digital mapping system is utilized for point cloud segmentation. After segmentation, each chunk is finely registered and merged based on the iterative closest point algorithm, allowing the two types of data to be accurately co-registered and a fused point cloud obtained. Finally, we conducted experiments to extract stand and individual tree metrics from fused point clouds created for two study plots. The height distributions of the fused point clouds were highly consistent with LiDAR data, with the 5%, 10%, 25%, 50%, 75%, 90%, and 95% height percentiles showing acceptable similarities. The height distribution of individual trees was also consistent with that of field measurements. Furthermore, the fused point clouds contain a high point density and RGB color information, which allow shape delineation and estimation of tree health status. This comprehensive analysis demonstrates that this procedure provides a practical way to inventory tree stands and individuals in urban areas.
Why it matches plant phenotyping methodsLiDAR・写真測量点群の融合と樹木メトリクス抽出手順が中心で、個体・林分の樹高分布や樹形、健康状態を推定しており、植物フェノタイピング手法に該当する。
abstractThis paper provides a practical procedure for fusing LiDAR and photogrammetric point clouds for the extraction of tree metrics.
Abstract Grapevine ( Vitis vinifera L.) is an essential part of the oldest group of fruit trees around which horticulture evolved, currently includes thousands of cultivars, grown at numerous climatic conditions. Discrimination between these varieties has been traditionally conducted using ampelography, and in recent decades mostly by genetic analysis. However, when aiming to identify archaeobotanical remains, which are mostly charred- with extremely low genomic preservation, the application of the genomic approach is rarely successful. As a result, variety-level identification of most grape remains is currently prevented. Because grape pips are highly polymorphic, several attempts were made to utilize their morphological diversity as a classification tool, mostly using 2D image analysis technics, aiming to utilize these methods for the identification of fresh and archaeological specimens. Here, we present for the first time a highly accurate varietal classification tool, using an innovative and accessible approach for 3D seed scanning. The suggested classification methodology is machine-learning-based, using a complete set of 3D data obtained for each seed, applied with the Iterative Closest Point (ICP) registration algorithm and the Linear Discriminant Analysis (LDA) technique. This methodology achieved classification results of ca. 90-99% accuracy when trained by fresh seeds to test unknown fresh seeds. Moreover, the classification of charred seeds reached up to 100% accuracy when trained by charred seeds. Based on this approach, our long-term aim is to develop a computerized classification tool for the identification of grape and possibly other species and varieties. Such a tool can significantly improve the fields of archaeobotany, as well as general taxonomy.
Why it matches plant phenotyping methodsブドウ種子の3D形態画像を用いた機械学習による品種分類手法の開発・精度評価が中心であり、植物器官の形態表現型を抽出する方法研究に該当する。
abstractHere, we present for the first time a highly accurate varietal classification tool, using an innovative and accessible approach for 3D seed scanning.
Canopy thermal infrared imaging reflects the temperature change in the crop canopy, which is closely related to the stomatal conductance and water utilization characteristics of the crop. Thermal infrared imaging is an effective and nondestructive way to study the early detection of crop diseases. However, efficiently extracting the thermal infrared canopy region of the crops is an important factor restricting the study of canopy temperature changes. The grayscale distribution of the edges of the crop canopy thermal infrared image is uneven with strong noise and cannot be extracted effectively using the traditional image segmentation method. Thus, a recognition method for the thermal infrared images of plant canopies based on heterogeneous image characteristic registration was proposed to overcome the shortcomings above. First, the Gauss membership function was selected to construct the network recognition rules on the basis of the three-layer backward reasoning of the adaptive BP neural network to recognize the visible light reference images of the plant canopies. Second, the optimal registration parameters of the affine transformation were calculated for registering the canopy region of the reference image and that of the initial thermal infrared image. Third, a recognition model for the thermal infrared images of plant canopies was established based on bilinear mapping factors. Finally, information entropy and mutual information were used to evaluate the effectiveness of the recognition model. The results showed that the initial temperature range of the original thermal infrared image was 20.46–36.40 °C. After removing the background interference of the thermal infrared canopy of the crop, the temperature range of the target image was 20.46–26.65 °C, and the average temperature after extraction was 2.04 °C lower than that before extraction. In addition, the entropy difference between the canopy of the thermal infrared image identified by the proposed model in this study and the standard recognition method was within the range of 0.01–0.06, indicating the effectiveness of the recognition model for the plant canopy. Therefore, this study provided an efficient method for obtaining the canopy temperature characteristics of crops.
Why it matches plant phenotyping methods植物キャノピーの熱赤外画像から背景を除去し、キャノピー温度特性を抽出する認識・登録手法の開発が中心であり、植物表現型の取得方法に該当する。
abstractThus, a recognition method for the thermal infrared images of plant canopies based on heterogeneous image characteristic registration was proposed to overcome the shortcomings above.
Published6 Aug 2020The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesCited by 18 · OpenAlex ↗
Abstract. With the appearance of cost effective, easy to fly Unmanned Aerial Vehicles (UAV), a new type of data collection has been enabled: super high resolution multi-spectral, precisely georeferenced imagery and point clouds, collected over high value targets. The high spatial resolution and precise georeferencing accuracy makes information extraction and advanced analytics possible both in the spatial and temporal domain at scales simply not possible to collect from manned aircraft, and at much greater efficiency than can be collected from the ground. One example of this is plant phenotyping for experimental research where a high-accuracy spatial reference needs to be assigned to each plot entry to enable accurate and efficient plot level statistics of plant phenotypic attributes. This paper presents results from an integration of the Trimble APX-15-EI UAV Direct Georeferencing system with the Micasense Altum multi-spectral camera to produce a highly accurate and efficient UAV based mapping solution for advanced spatial and temporal analytics without the use of Ground Control Points (GCP’s). Results from a series of flights over a test range outfitted with GNSS surveyed check points show an orthomap accuracy at the level of 3 cm RMSx,y horizontal can be achieved. The same system flown over a test field operated by researchers at the University of Guelph containing plots of soybean demonstrated pixel-level alignment of the directly georeferenced orthomosaic to the cm-level plot boundaries previously surveyed by the researchers, thus meeting the requirements for automated phenotyping.
Why it matches plant phenotyping methodsUAVマルチスペクトル撮像と直接ジオリファレンス手法を開発・精度検証し、作物プロット単位の自動表現型解析に適用しているため、フェノタイピング手法が中心である。
abstractThis paper presents results from an integration of the Trimble APX-15-EI UAV Direct Georeferencing system with the Micasense Altum multi-spectral camera to produce a highly accurate and efficient UAV based mapping solution
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Premise Aerial imagery from small unmanned aerial vehicle systems is a promising approach for high‐throughput phenotyping and precision agriculture. A key requirement for both applications is to create a field‐scale mosaic of the aerial imagery sequence so that the same features are in registration, a very challenging problem for crop imagery. Methods We have developed an improved mosaicking pipeline, Video Mosaicking and summariZation (VMZ), which uses a novel two‐dimensional mosaicking algorithm that minimizes errors in estimating the transformations between successive frames during registration. The VMZ pipeline uses only the imagery, rather than relying on vehicle telemetry, ground control points, or global positioning system data, to estimate the frame‐to‐frame homographies. It exploits the spatiotemporal ordering of the image frames to reduce the computational complexity of finding corresponding features between frames using feature descriptors. We compared the performance of VMZ to a standard two‐dimensional mosaicking algorithm (AutoStitch) by mosaicking imagery of two maize (Zea mays) research nurseries freely flown with a variety of trajectories. Results The VMZ pipeline produces superior mosaics faster. Using the speeded up robust features (SURF) descriptor, VMZ produces the highest‐quality mosaics. Discussion Our results demonstrate the value of VMZ for the future automated extraction of plant phenotypes and dynamic scouting for crop management.
Why it matches plant phenotyping methods植物表現型抽出を目的とする航空画像モザイク化パイプラインを開発し、既存手法と比較検証しており、画像取得・処理法が中心的です。
abstractWe have developed an improved mosaicking pipeline, Video Mosaicking and summariZation (VMZ), which uses a novel two‐dimensional mosaicking algorithm
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
Abstract Background Automated segmentation of large amount of image data is one of the major bottlenecks in high-throughput plant phenotyping. Dynamic optical appearance of developing plants, inhomogeneous scene illumination, shadows and reflections in plant and background regions complicate automated segmentation of unimodal plant images. To overcome the problem of ambiguous color information in unimodal data, images of different modalities can be combined to a virtual multispectral cube. However, due to motion artefacts caused by the relocation of plants between photochambers the alignment of multimodal images is often compromised by blurring artifacts. Results Here, we present an approach to automated segmentation of greenhouse plant images which is based on co-registration of fluorescence (FLU) and of visible light (VIS) camera images followed by subsequent separation of plant and marginal background regions using different species- and camera view-tailored classification models. Our experimental results including a direct comparison with manually segmented ground truth data show that images of different plant types acquired at different developmental stages from different camera views can be automatically segmented with the average accuracy of $$93\%$$ 93 % ( $$SD=5\%$$ S D = 5 % ) using our two-step registration-classification approach. Conclusion Automated segmentation of arbitrary greenhouse images exhibiting highly variable optical plant and background appearance represents a challenging task to data classification techniques that rely on detection of invariances. To overcome the limitation of unimodal image analysis, a two-step registration-classification approach to combined analysis of fluorescent and visible light images was developed. Our experimental results show that this algorithmic approach enables accurate segmentation of different FLU/VIS plant images suitable for application in fully automated high-throughput manner.
Why it matches plant phenotyping methods温室植物の蛍光・可視画像を用いた自動セグメンテーション手法を開発し、手動正解データとの比較で検証しており、植物表現型取得の中核的方法である。
abstractOur experimental results including a direct comparison with manually segmented ground truth data show that images of different plant types acquired at different developmental stages from different camera views can be automatically segmented with the average accuracy of $$93\%$$ 93 %
One of the major goals of tomorrow’s agriculture is to increase agricultural productivity but above all the quality of production while significantly reducing the use of inputs. Meeting this goal is a real scientific and technological challenge. Smart farming is among the promising approaches that can lead to interesting solutions for vineyard management and reduce the environmental impact. Automatic vine disease detection can increase efficiency and flexibility in managing vineyard crops, while reducing the chemical inputs. This is needed today more than ever, as the use of pesticides is coming under increasing scrutiny and control. The goal is to map diseased areas in the vineyard for fast and precise treatment, thus guaranteeing the maintenance of a healthy state of the vine which is very important for yield management. To tackle this problem, a method is proposed here for Mildew disease detection in vine field using a deep learning segmentation approach on Unmanned Aerial Vehicle (UAV) images. The method is based on the combination of the visible and infrared images obtained from two different sensors. A new image registration method was developed to align visible and infrared images, enabling fusion of the information from the two sensors. A fully convolutional neural network approach uses this information to classify each pixel according to different instances, namely, shadow, ground, healthy and symptom. The proposed method achieved more than 92% of detection at grapevine-level and 87%at leaf level, showing promising perspectives for computer aided disease detection in vineyards.
Why it matches plant phenotyping methodsブドウの病徴をUAVマルチスペクトル画像から推定する画像登録・セグメンテーション手法を開発し、検出性能も評価しており、植物表現型取得が中心的である。
abstractA new image registration method was developed to align visible and infrared images, enabling fusion of the information from the two sensors.
Automatic vision-based picking in orchards and fields is a highly challenging task. The orchard banana central stock, which is large in size, low in color contrast, and falls within a complex background, was taken as the subject in this research. A measurement framework based on multi-vision technology was established, and a set of general methods were utilized to improve the comprehensive performance of multi-view-geometry-based vision modules in orchard picking tasks. Multiple cameras at different angles were deployed to maximize the perception range. The global geometric parameters of the cameras were calibrated and a robust semantic segmentation network was trained to achieve effective image pre-processing. A novel adaptive stereo matching strategy was designed to ensure that the robot reliably completes 3D triangulation at various depths as it moves across the target area. Global calibration errors were corrected via a high-accuracy point cloud stitching algorithm. Experimental results indicated that the proposed adaptive stereo matching strategy was accurate to different sampling depths and showed stable performance, and the proposed point cloud stitching algorithm accurately stitched multi-view point clouds. This work provides theoretical and practical references for the 3D sensing of banana central stocks in complex environments. The proposed technique was designed for adaptability of the multi-vision system for field perception, so it can be easily transferred to similar applications such as the 3D reconstruction of agricultural targets, 3D positioning of fruit clusters, and 3D robotic arm obstacle avoidance.
Why it matches plant phenotyping methodsバナナ株の3次元形状を取得・再構成するマルチビジョン計測法が研究の中心であり、単なる収穫対象の位置検出を超えた植物器官の形態計測手法に該当する。
abstractA measurement framework based on multi-vision technology was established
In agriculture, information about the spatial distribution of plant growth is valuable for applications. Quantitative study of the characteristics of plants plays an important role in the plants' growth and development research, and non-destructive measurement of the height of plants based on machine vision technology is one of the difficulties. We propose a methodology for three-dimensional reconstruction under growing plants by Kinect v2.0 and explored the measure growth parameters based on three-dimensional (3D) point cloud in this paper. The strategy includes three steps-firstly, preprocessing 3D point cloud data, completing the 3D plant registration through point cloud outlier filtering and surface smooth method; secondly, using the locally convex connected patches method to segment the leaves and stem from the plant model; extracting the feature boundary points from the leaf point cloud, and using the contour extraction algorithm to get the feature boundary lines; finally, calculating the length, width of the leaf by Euclidean distance, and the area of the leaf by surface integral method, measuring the height of plant using the vertical distance technology. The results show that the automatic extraction scheme of plant information is effective and the measurement accuracy meets the need of measurement standard. The established 3D plant model is the key to study the whole plant information, which reduces the inaccuracy of occlusion to the description of leaf shape and conducive to the study of the real plant growth status.
Why it matches plant phenotyping methodsKinectによる3D点群再構成と葉・茎の分割、葉面積・葉長・葉幅・草丈の自動抽出を開発・評価しており、植物表現型取得が中心である。
abstractWe propose a methodology for three-dimensional reconstruction under growing plants by Kinect v2.0 and explored the measure growth parameters based on three-dimensional (3D) point cloud in this paper.
MaizeLaboratory / benchtopRoot2D/3D reconstructionImage / point-cloud registrationRoot system architecture
Complex plant-soil interactions can be visualized and quantified by combined application of different non-invasive imaging techniques. Oxygen, carbon dioxide and pH gradients in the rhizosphere can be observed with fluorescent planar optodes, while neutron radiography detects small-scale heterogeneities in soil moisture and its dynamics. Respiration and exudation rates can vary between roots of different types, such as primary and lateral roots, as well as along single roots among the same plant. The 3D root system architecture is therefore a key information when studying rhizosphere processes. It can be captured in detail with neutron tomography, but so far only for plants grown in small, cylindrical containers. Combined non-invasive imaging of biogeochemical dynamics, soil moisture distribution and 3D root system architecture is a technical challenge. Thin, slab-shaped rhizotrons with relatively large vertical and lateral extension are well suited for optical fluorescence imaging, allowing for spatially extended observation of biogeochemical patterns. This rhizotron geometry is, however, unfavorable for standard 3D tomography due to reconstruction artefacts triggered by insufficient neutron transmission when the long side of the sample is aligned parallel to the beam direction. We therefore applied neutron laminography, a method where the rotational axis is tilted, to measure the root systems of maize and lupine plants grown in slab-shaped glass rhizotrons (length = 150 mm, width = 150 mm, depth = 15 mm) in 3D. In parallel, we investigated rhizosphere oxygen dynamics and pH value via fluorescence imaging and assessed soil moisture distribution with neutron radiography. Neutron laminography enabled the 3D reconstruction of the root systems with a nominal spatial resolution of 100 µm/pixel. Reconstruction quality strongly depended on root-soil contrast and hence soil moisture level. After reconstruction of the root system and co-registration with the fluorescence images, first results indicate that observed oxygen concentrations and pH gradients depend on root type and individual distance of the roots from the planar optode. In conclusion, neutron laminography is a novel 3D imaging method for root-soil systems grown in slab-shaped rhizotrons. The method allows for determining the precise 3D position of individual roots within the rhizotron and can be combined with 2D imaging approaches. Following experiments will address X-ray laminography as a possible attractive further application.
Why it matches plant phenotyping methods根系アーキテクチャを3Dで取得する中性子ラミノグラフィーを開発・適用し、空間分解能や再構成品質も評価しているため、植物フェノタイピング手法が中心である。
abstractWe therefore applied neutron laminography, a method where the rotational axis is tilted, to measure the root systems of maize and lupine plants grown in slab-shaped glass rhizotrons
Measurement of plant nitrogen (N), phosphorus (P), and potassium (K) levels are important for determining precise fertilization management approaches for crops cultivated in greenhouses. To accurately, rapidly, stably, and nondestructively measure the NPK levels in tomato plants, a nondestructive determination method based on multispectral three-dimensional (3D) imaging was proposed. Multiview RGB-D images and multispectral images were synchronously collected, and the plant multispectral reflectance was registered to the depth coordinates according to Fourier transform principles. Based on the Kinect sensor pose estimation and self-calibration, the unified transformation of the multiview point cloud coordinate system was realized. Finally, the iterative closest point (ICP) algorithm was used for the precise registration of multiview point clouds and the reconstruction of plant multispectral 3D point cloud models. Using the normalized grayscale similarity coefficient, the degree of spectral overlap, and the Hausdorff distance set, the accuracy of the reconstructed multispectral 3D point clouds was quantitatively evaluated, the average value was 0.9116, 0.9343 and 0.41 cm, respectively. The results indicated that the multispectral reflectance could be registered to the Kinect depth coordinates accurately based on the Fourier transform principles, the reconstruction accuracy of the multispectral 3D point cloud model met the model reconstruction needs of tomato plants. Using back-propagation artificial neural network (BPANN), support vector machine regression (SVMR), and gaussian process regression (GPR) methods, determination models for the NPK contents in tomato plants based on the reflectance characteristics of plant multispectral 3D point cloud models were separately constructed. The relative error (RE) of the N content by BPANN, SVMR and GPR prediction models were 2.27%, 7.46% and 4.03%, respectively. The RE of the P content by BPANN, SVMR and GPR prediction models were 3.32%, 8.92% and 8.41%, respectively. The RE of the K content by BPANN, SVMR and GPR prediction models were 3.27%, 5.73% and 3.32%, respectively. These models provided highly efficient and accurate measurements of the NPK contents in tomato plants. The NPK contents determination performance of these models were more stable than those of single-view models.
Why it matches plant phenotyping methodsトマトのNPK含量という植物状態を、マルチスペクトル・3D画像、点群再構成、画像位置合わせ、回帰モデルで非破壊推定する方法を開発・定量評価しており、フェノタイピング手法が中心である。
abstracta nondestructive determination method based on multispectral three-dimensional (3D) imaging was proposed
Perception of the fruit tree canopy is a vital technology for the intelligent control of a modern standardized orchard. Due to the complex three-dimensional (3D) structure of the fruit tree canopy, morphological parameters extracted from two-dimensional (2D) or single-perspective 3D images are not comprehensive enough. Three-dimensional information from different perspectives must be combined in order to perceive the canopy information efficiently and accurately in complex orchard field environment. The algorithms used for the registration and fusion of data from different perspectives and the subsequent extraction of fruit tree canopy related parameters are the keys to the problem. This study proposed a 3D morphological measurement method for a fruit tree canopy based on Kinect sensor self-calibration, including 3D point cloud generation, point cloud registration and canopy information extraction of apple tree canopy. Using 32 apple trees (Yanfu 3 variety) morphological parameters of the height (H), maximum canopy width (W) and canopy thickness (D) were calculated. The accuracy and applicability of this method for extraction of morphological parameters were statistically analyzed. The results showed that, on both sides of the fruit trees, the average relative error (ARE) values of the morphological parameters including the fruit tree height (H), maximum tree width (W) and canopy thickness (D) between the calculated values and measured values were 3.8%, 12.7% and 5.0%, respectively, under the V1 mode; the ARE values under the V2 mode were 3.3%, 9.5% and 4.9%, respectively; and the ARE values under the V1 and V2 merged mode were 2.5%, 3.6% and 3.2%, respectively. The measurement accuracy of the tree width (W) under the double visual angle mode had a significant advantage over that under the single visual angle mode. The 3D point cloud reconstruction method based on Kinect self-calibration proposed in this study has high precision and stable performance, and the auxiliary calibration objects are readily portable and easy to install. It can be applied to different experimental scenes to extract 3D information of fruit tree canopies and has important implications to achieve the intelligent control of standardized orchards.
Why it matches plant phenotyping methodsKinectによる3D点群の自己キャリブレーション、登録・融合、樹冠形態パラメータ抽出を開発し、実測値との精度検証まで行った植物フェノタイピング手法研究。
abstractThis study proposed a 3D morphological measurement method for a fruit tree canopy based on Kinect sensor self-calibration, including 3D point cloud generation, point cloud registration and canopy information extraction of apple tree canopy.
With the introduction of multi-camera systems in modern plant phenotyping new opportunities for combined multimodal image analysis emerge. Visible light (VIS), fluorescence (FLU) and near-infrared images enable scientists to study different plant traits based on optical appearance, biochemical composition and nutrition status. A straightforward analysis of high-throughput image data is hampered by a number of natural and technical factors including large variability of plant appearance, inhomogeneous illumination, shadows and reflections in the background regions. Consequently, automated segmentation of plant images represents a big challenge and often requires an extensive human-machine interaction. Combined analysis of different image modalities may enable automatisation of plant segmentation in "difficult" image modalities such as VIS images by utilising the results of segmentation of image modalities that exhibit higher contrast between plant and background, i.e. FLU images. For efficient segmentation and detection of diverse plant structures (i.e. leaf tips, flowers), image registration techniques based on feature point (FP) matching are of particular interest. However, finding reliable feature points and point pairs for differently structured plant species in multimodal images can be challenging. To address this task in a general manner, different feature point detectors should be considered. Here, a comparison of seven different feature point detectors for automated registration of VIS and FLU plant images is performed. Our experimental results show that straightforward image registration using FP detectors is prone to errors due to too large structural difference between FLU and VIS modalities. We show that structural image enhancement such as background filtering and edge image transformation significantly improves performance of FP algorithms. To overcome the limitations of single FP detectors, combination of different FP methods is suggested. We demonstrate application of our enhanced FP approach for automated registration of a large amount of FLU/VIS images of developing plant species acquired from high-throughput phenotyping experiments.
Why it matches plant phenotyping methods植物フェノタイピング用のVIS/FLU画像登録について、特徴点検出器を比較し、前処理と組合せ手法を評価する方法開発・検証研究であり、手法が中心的です。
abstractHere, a comparison of seven different feature point detectors for automated registration of VIS and FLU plant images is performed.
Reproduction assets foundThe authors publicly release example multimodal FLU/VIS plant images (original and manually segmented) together with a pre-compiled GUI demo tool implementing their FP registration analysis, via a dedicated IPK project page and a GitHub repository.Code · publicA precompilied GUI tool demonstrating the peformance of different FP algorithms can be downloaded along with examples of multimodal plant images from https://github.com/ba-ipk/fpRegOpen asset ↗ba-ipk/fpReglines:261-304Dataset · publicExamples of original (unfiltered) and manually segmented plant images along with the demo software are available from our project/paper dedicated page: http://ag-ba.ipk-gatersleben.de/fpreg.htmlOpen asset ↗lines:145-169Plant phenotyping relevance match · UnverifiedOpenAlex · checked 9 Sept 2026
Plant morphological data are an important basis for precision agriculture and plant phenomics. The three-dimensional (3D) geometric shape of plants is complex, and the 3D morphology of a plant changes relatively significantly during the full growth cycle. In order to make high-throughput measurements of the 3D morphological data of greenhouse plants, it is necessary to frequently adjust the relative position between the sensor and the plant. Therefore, it is necessary to frequently adjust the Kinect sensor position and consequently recalibrate the Kinect sensor during the full growth cycle of the plant, which significantly increases the tedium of the multiview 3D point cloud reconstruction process. A high-throughput 3D rapid greenhouse plant point cloud reconstruction method based on autonomous Kinect v2 sensor position calibration is proposed for 3D phenotyping greenhouse plants. Two red–green–blue–depth (RGB-D) images of the turntable surface are acquired by the Kinect v2 sensor. The central point and normal vector of the axis of rotation of the turntable are calculated automatically. The coordinate systems of RGB-D images captured at various view angles are unified based on the central point and normal vector of the axis of the turntable to achieve coarse registration. Then, the iterative closest point algorithm is used to perform multiview point cloud precise registration, thereby achieving rapid 3D point cloud reconstruction of the greenhouse plant. The greenhouse tomato plants were selected as measurement objects in this study. Research results show that the proposed 3D point cloud reconstruction method was highly accurate and stable in performance, and can be used to reconstruct 3D point clouds for high-throughput plant phenotyping analysis and to extract the morphological parameters of plants.
Why it matches plant phenotyping methodsKinect RGB-Dによる植物の3D点群再構成と形態パラメータ抽出を中心に、センサー自己校正と高スループット化を開発・評価しているため。
abstractA high-throughput 3D rapid greenhouse plant point cloud reconstruction method based on autonomous Kinect v2 sensor position calibration is proposed for 3D phenotyping greenhouse plants.
The accuracy of vertical position information can be degraded by various sources of error in digital aerial photogrammetry (DAP) based point clouds. To address this issue, we propose a relatively straightforward method for automated correction of such point clouds. This method can be used in conjunction with any 3D reconstruction method in which a point cloud is generated from a pair of aerial images. The crux of the method involves separately co-registering each DAP point cloud (formed by the overlap of two or more images) to a common airborne laser scanning (ALS) based digital terrain model. The proposed method has the following essential steps: (1) Ground surface patches are identified in the normalized DAP point clouds by selecting areas in which standard deviation of vertical height is low, (2) height differences between the DAP and ALS point clouds are calculated at these patches, and (3) a correction surface is interpolated from these height differences and is then used to rectify the entire DAP point cloud. The performance of the proposed method is verified using plot data (n = 250) from a forested study area in Eastern Finland. We observed that DAP data from the area corrected using our proposed method resulted in significant increases in prediction accuracy of key forest variables. Specifically, the root mean squared error (RMSE) values for dominant height predictions decreased by up to 23.2%, while the associated model R2 values increased by 16.9%. As for stem volume, RMSEs dropped by 20.6%, while the model R2 improved by 14.6%, respectively. Hence, prediction accuracies were almost as good as with ALS data. The results suggest that vertically misaligned DAP data, if rectified using an algorithm such as the one presented here, could deliver near ALS data quality at a fraction of the cost.
Why it matches plant phenotyping methods森林プロットの樹高・幹材積という植物形質を推定するため、DAP点群の自動補正手法を開発し、250プロットで性能検証している。形質取得精度の改善が中心であり、単なる森林測定ではない。
abstractwe propose a relatively straightforward method for automated correction of such point clouds
Nondestructive plant growth measurement is essential for researching plant growth and health. A nondestructive measurement system to retrieve plant information includes the measurement of morphological and physiological information, but most systems use two independent measurement systems for the two types of characteristics. In this study, a highly integrated, multispectral, three-dimensional (3D) nondestructive measurement system for greenhouse tomato plants was designed. The system used a Kinect sensor, an SOC710 hyperspectral imager, an electric rotary table, and other components. A heterogeneous sensing image registration technique based on the Fourier transform was proposed, which was used to register the SOC710 multispectral reflectance in the Kinect depth image coordinate system. Furthermore, a 3D multiview RGB-D image-reconstruction method based on the pose estimation and self-calibration of the Kinect sensor was developed to reconstruct a multispectral 3D point cloud model of the tomato plant. An experiment was conducted to measure plant canopy chlorophyll and the relative chlorophyll content was measured by the soil and plant analyzer development (SPAD) measurement model based on a 3D multispectral point cloud model and a single-view point cloud model and its performance was compared and analyzed. The results revealed that the measurement model established by using the characteristic variables from the multiview point cloud model was superior to the one established using the variables from the single-view point cloud model. Therefore, the multispectral 3D reconstruction approach is able to reconstruct the plant multispectral 3D point cloud model, which optimizes the traditional two-dimensional image-based SPAD measurement method and can obtain a precise and efficient high-throughput measurement of plant chlorophyll.
Why it matches plant phenotyping methods温室トマトのクロロフィル量を推定するための統合マルチスペクトル3D計測システム、画像登録、3D再構成、推定モデルを開発・比較しており、植物表現型取得が中心である。
abstractIn this study, a highly integrated, multispectral, three-dimensional (3D) nondestructive measurement system for greenhouse tomato plants was designed.
Unmanned aerial vehicles have an immense capacity for remote imaging of plants in agronomic field research trials. Traits extracted from the plots can explain development of the plants coverage, growth, flowering status, and related phenomenon. An important prerequisite step to obtain such information is to find the exact position of plots to extract them from an orthomosaic image. Extraction of plots using tools which assume a uniform spacing is often erroneous because the plots may neither be perfectly aligned nor equally distributed in a field. A novel approach is proposed which uses image-based optimization algorithm to find the alignment of plots. The method begins with a uniformly spaced grid of plots which is iteratively aligned with regions of high vegetation index, i.e., the underlying plots. The approach is validated and tested on two different orthomosaic images of fields containing wheat plots with simulated and real alignment problems, respectively. The result of alignment is compared to manually located ground truth position of plots and the errors are quantitatively analyzed. The effectiveness of the proposed method is confirmed in accurately estimating the phenotypic trait of canopy coverage compared to the common methods of extraction from uniform grids or trimmed grids. The software developed in this study is available from SourceForge, https://sourceforge.net/projects/phenalysis/.
Why it matches plant phenotyping methods圃場オルソモザイクから試験区を自動抽出し、キャノピー被覆率という植物形質を推定する画像解析手法を開発・検証しており、フェノタイピング手法が中心である。
abstractA novel approach is proposed which uses image-based optimization algorithm to find the alignment of plots.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe software developed in this study is available from SourceForge, https://sourceforge.net/projects/phenalysis/ .Open asset ↗phenalysislines:224-299Plant phenotyping relevance match · UnverifiedEurope PMC · Crossref · OpenAlex · checked 9 Sept 2026
With the rapid rising of global population, the demand for improving breeding techniques to greatly increase the worldwide crop production has become more and more urgent. Most researchers believe that the key to new breeding techniques lies in genetic improvement of crops, which leads to a large quantity of phenotyping spots. Unfortunately, current phenotyping solutions are not powerful enough to handle so many spots with satisfying speed and accuracy. As a result, high-throughput phenotyping is drawing more and more attention. In this paper, we propose a new field-based sensing solution to high-throughput phenotyping. We mount a LiDAR (Velodyne HDL64-S3) on a mobile robot, making the robot a "phenomobile." We develop software for data collection and analysis under Robotic Operating System using open source components and algorithm libraries. Different from conducting phenotyping observations with an in-row and one-by-one manner, our new solution allows the robot to move around the parcel to collect data. Thus, the 3D and 360° view laser scanner can collect phenotyping data for a large plant group at the same time, instead of one by one. Furthermore, no touching interference from the robot would be imposed onto the crops. We conduct experiments for maize plant on two parcels. We implement point cloud merging with landmarks and Iterative Closest Points to cut down the time consumption. We then recognize and compute the morphological phenotyping parameters (row spacing and plant height) of maize plant using depth-band histograms and horizontal point density. We analyze the cloud registration and merging performances, the row spacing detection accuracy, and the single plant height computation accuracy. Experimental results verify the feasibility of the proposed solution.
Why it matches plant phenotyping methodsLiDAR搭載ロボットによる圃場高スループット表現型計測システムを開発し、トウモロコシの草高・条間を抽出して精度検証しているため、方法が研究の中心である。
abstractIn this paper, we propose a new field-based sensing solution to high-throughput phenotyping.
With the introduction of high-throughput multisensory imaging platforms, the automatization of multimodal image analysis has become the focus of quantitative plant research. Due to a number of natural and technical reasons (e.g., inhomogeneous scene illumination, shadows, and reflections), unsupervised identification of relevant plant structures (i.e., image segmentation) represents a nontrivial task that often requires extensive human-machine interaction. Registration of multimodal plant images enables the automatized segmentation of 'difficult' image modalities such as visible light or near-infrared images using the segmentation results of image modalities that exhibit higher contrast between plant and background regions (such as fluorescent images). Furthermore, registration of different image modalities is essential for assessment of a consistent multiparametric plant phenotype, where, for example, chlorophyll and water content as well as disease- and/or stress-related pigmentation can simultaneously be studied at a local scale. To automatically register thousands of images, efficient algorithmic solutions for the unsupervised alignment of two structurally similar but, in general, nonidentical images are required. For establishment of image correspondences, different algorithmic approaches based on different image features have been proposed. The particularity of plant image analysis consists, however, of a large variability of shapes and colors of different plants measured at different developmental stages from different views. While adult plant shoots typically have a unique structure, young shoots may have a nonspecific shape that can often be hardly distinguished from the background structures. Consequently, it is not clear a priori what image features and registration techniques are suitable for the alignment of various multimodal plant images. Furthermore, dynamically measured plants may exhibit nonuniform movements that require application of nonrigid registration techniques. Here, we investigate three common techniques for registration of visible light and fluorescence images that rely on finding correspondences between (i) feature-points, (ii) frequency domain features, and (iii) image intensity information. The performance of registration methods is validated in terms of robustness and accuracy measured by a direct comparison with manually segmented images of different plants. Our experimental results show that all three techniques are sensitive to structural image distortions and require additional preprocessing steps including structural enhancement and characteristic scale selection. To overcome the limitations of conventional approaches, we develop an iterative algorithmic scheme, which allows it to perform both rigid and slightly nonrigid registration of high-throughput plant images in a fully automated manner.
Why it matches plant phenotyping methods植物のマルチモーダル画像登録アルゴリズムを比較・検証し、高スループット画像から一貫した表現型解析を可能にする手法を開発しているため。
abstractHere, we investigate three common techniques for registration of visible light and fluorescence images
Reproduction assets foundThe authors provide a public GUI software tool (mPIR) implementing the paper's FP/PC/INT multimodal plant image registration algorithms, together with example FLU/VIS/NIR plant images from the study, downloadable from their homepage.Code · publica GUI software tool with examples of plant images is provided for direct download from our homepage; Footnote 1 a screen shot is shown in Fig. 10Open asset ↗lines:138-172Dataset · publicExamples of FLU, VIS and NIR plant images are included in our online file repository.Open asset ↗lines:138-172Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 10 Sept 2026
The ever-growing world population brings the challenge for food security in the current world. The gene modification tools have opened a new era for fast-paced research on new crop identification and development. However, the bottleneck in the plant phenotyping technology restricts the alignment in geno-pheno development as phenotyping is the key for the identification of potential crop for improved yield and resistance to the changing environment. Various attempts to making the plant phenotyping a "high-throughput" have been made while utilizing the existing sensors and technology. However, the demand for 'good' phenotypic information for linkage to the genome in understanding the gene-environment interactions is still a bottleneck in the plant phenotyping technologies. Moreover, the available technologies and instruments are inaccessible, expensive, and sometimes bulky. This work attempts to address some of the critical problems, such as exploration and development of a low-cost LiDAR-based platform for phenotyping the plants in-lab and in-field. A low-cost LiDAR-based system design, LiDARPheno, is introduced in this work to assess the feasibility of the inexpensive LiDAR sensor in the leaf trait (length, width, and area) extraction. A detailed design of the LiDARPheno, based on low-cost and off-the-shelf components and modules, is presented. Moreover, the design of the firmware to control the hardware setup of the system and the user-level python-based script for data acquisition is proposed. The software part of the system utilizes the publicly available libraries and Application Programming Interfaces (APIs), making it easy to implement the system by a non-technical user. The LiDAR data analysis methods are presented, and algorithms for processing the data and extracting the leaf traits are developed. The processing includes conversion, cleaning/filtering, segmentation and trait extraction from the LiDAR data. Experiments on indoor plants and canola plants were performed for the development and validation of the methods for estimation of the leaf traits. The results of the LiDARPheno based trait extraction are compared with the SICK LMS400 (a commercial 2D LiDAR) to assess the performance of the developed system.
Why it matches plant phenotyping methods低コストLiDARを用いた植物表現型取得システムを開発し、葉形質の抽出アルゴリズムを提示、実験と商用LiDAR比較で検証しており、方法が研究の中心である。
abstractA low-cost LiDAR-based system design, LiDARPheno, is introduced in this work to assess the feasibility of the inexpensive LiDAR sensor in the leaf trait (length, width, and area) extraction.
This paper presents an approach to estimating the plant or fruit size from objects on the digital images of natural scenes. Two images are taken from camera positions with a known distance between them. For a selected object and a pair of its boundary pixels in the first image, a corresponding pixel pair is found in the second image. The Euclidean distances within the two pairs compare in similar triangles and combine with the known distance between the camera positions to estimate the size of the object in metric units. A dense correspondence among images is first required. It can be determined by joint information of multiple 2D views of the same scene utilizing image registration techniques. These are used to align corresponding image points, without having to rely on distinct features, such as geometric properties. This is most advantageous for weak textured areas, e.g. uniform fruit shades, where many methods for corresponding point detection fail. The pixel neighbourhoods of candidate corresponding pairs are compared by template matching to verify their similarity and to select the most reliable correspondences. A stratified rigid-to-elastic registration approach generates a deformation matrix whose elements define translational vectors on a pixel basis. The accuracy of correspondence, checked by colour template matching, is assessed by mean absolute error, D, between corresponding pixel-pair intensities within the templates. By matching 26 random fruit image pairs, the proposed approach detected 1390.5 ± 1129.8 reliable corresponding points on the surface of the fruit with the accuracy of D≤5, on average. This means approximately 18% of all objects’ pixels and considerably exceeds the results of comparable methods for high-density correspondence detection, such as correlation-based correspondence, non-rigid dense correspondence (NRDC), and scale invariant feature transform (SIFT). The number and quality of corresponding points obtained by the proposed algorithm turned out to be reliable and sufficiently robust for an accurate estimation of distances between objects and camera positions (with an overall accuracy of 0.11 m ± 0.06 m) and height of plants (with an accuracy of 0.14 m ± 0.1 m) when taking two similar outdoor photographs of a scene.
Why it matches plant phenotyping methods画像登録による高密度対応点生成を開発し、果実サイズと植物高という明示的な植物形態形質を画像から推定する手法を評価しているため、植物フェノタイピング手法が中心である。
abstractThis paper presents an approach to estimating the plant or fruit size from objects on the digital images of natural scenes.
Remote sensing methods for forest monitoring are evolving rapidly thanks to recent advances in Unmanned Aerial Vehicle technology and digital photogrammetry. Photogrammetric point clouds allow the non-destructive derivation of individual tree parameters at a low cost. The fusion of aerial and terrestrial photogrammetry for creating full-tree point clouds is of utility for forest research, as tree volume could be assessed more economically and efficiently than by traditional methods. However, this is challenging to implement due to difficulties with co-registration and issues of occlusion. This study explores the possibility of using spherical targets typically used for Terrestrial Laser Scanning to accomplish the co-registration of UAV-based and terrestrial photogrammetric datasets. Results show a full-tree point cloud derived from UAV oblique imagery in combination with terrestrial imagery. Despite issues of noise produced from the sky in terrestrial imagery, the methodology is promising for aerial and terrestrial point cloud fusion.
Why it matches plant phenotyping methods航空・地上写真測量データの融合と点群作成が研究の中心で、個体樹木の体積など観測可能な形態形質を非破壊推定する手法を開発・検討しているため。
abstractPhotogrammetric point clouds allow the non-destructive derivation of individual tree parameters at a low cost.
Sclerotinia sclerotiorum , one of the major diseases infecting oilseed rape leaves, has seriously affected crop yield and quality. In this study, an indoor unmanned aerial vehicle (UAV) low-altitude remote sensing simulation platform was built for disease detection. Thermal, multispectral and RGB images were acquired before and after being artificially inoculated with Sclerotinia sclerotiorum on oilseed rape leaves. New image registration and fusion methods based on scale-invariant feature transform (SIFT) were presented to construct a fused database using multi-model images. The changes of temperature distribution in different sections of infected areas were analyzed by processing thermal images, the maximum temperature difference (MTD) on a single leaf reached 1.7 degrees Celsius 24 h after infection. Four machine learning models were established using thermal images and fused images respectively, including support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN) and naïve Bayes (NB). The results demonstrated that the classification accuracy was improved by 11.3% after image fusion, and the SVM model obtained a classification accuracy of 90.0% on the task of classifying disease severity. The overall results indicated the UAV low-altitude remote sensing simulation platform equipped with multi-sensors could be used to early detect Sclerotinia sclerotiorum on oilseed rape leaves.
Why it matches plant phenotyping methods油糧ナタネ葉の病害状態・重症度を、UAVマルチセンサー画像、画像融合、機械学習で取得・推定する方法が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractan indoor unmanned aerial vehicle (UAV) low-altitude remote sensing simulation platform was built for disease detection
The characterization of plant disease symptoms by hyperspectral imaging is often limited by the missing ability to investigate early, still invisible states. Automatically tracing the symptom position on the leaf back in time could be a promising approach to overcome this limitation. Therefore we present a method to spatially reference time series of close range hyperspectral images. Based on reference points, a robust method is presented to derive a suitable transformation model for each observation within a time series experiment. A non-linear 2D polynomial transformation model has been selected to cope with the specific structure and growth processes of wheat leaves. The potential of the method is outlined by an improved labeling procedure for very early symptoms and by extracting spectral characteristics of single symptoms represented by Vegetation Indices over time. The characteristics are extracted for brown rust and septoria tritici blotch on wheat, based on time series observations using a VISNIR (400–1000 nm) hyperspectral camera.
Why it matches plant phenotyping methods植物病害症状を追跡・抽出するためのハイパースペクトル画像の空間参照手法を開発しており、症状位置とスペクトル特性の取得が研究の中心である。
abstractTherefore we present a method to spatially reference time series of close range hyperspectral images.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 10 Sept 2026
Modern facilities for high-throughput phenotyping provide plant scientists with a large amount of multi-modal image data. Combination of different image modalities is advantageous for image segmentation, quantitative trait derivation, and assessment of a more accurate and extended plant phenotype. However, visible light (VIS), fluorescence (FLU), and near-infrared (NIR) images taken with different cameras from different view points in different spatial resolutions exhibit not only relative geometrical transformations but also considerable structural differences that hamper a straightforward alignment and combined analysis of multi-modal image data. Conventional techniques of image registration are predominantly tailored to detection of relative geometrical transformations between two otherwise identical images, and become less accurate when applied to partially similar optical scenes. Here, we focus on a relatively new technical problem of FLU/VIS plant image registration. We present a framework for automated alignment of FLU/VIS plant images which is based on extension of the phase correlation (PC) approach - a frequency domain technique for image alignment, which relies on detection of a phase shift between two Fourier-space transforms. Primarily tailored to detection of affine image transformations between two structurally identical images, PC is known to be sensitive to structural image distortions. We investigate effects of image preprocessing and scaling on accuracy of image registration and suggest an integrative algorithmic scheme which allows to overcome shortcomings of conventional single-step PC by application to non-identical multi-modal images. Our experimental tests with FLU/VIS images of different plant species taken on different phenotyping facilities at different developmental stages, including difficult cases such as small plant shoots of non-specific shape and non-uniformly moving leaves, demonstrate improved performance of our extended PC approach within the scope of high-throughput plant phenotyping.
Why it matches plant phenotyping methods植物フェノタイピング用のマルチモーダル画像登録手法を開発し、複数施設・植物種の画像で性能を検証しているため、方法論が中心である。
abstractWe present a framework for automated alignment of FLU/VIS plant images which is based on extension of the phase correlation (PC) approach
ArabidopsisLaboratory / benchtopChlorophyll fluorescenceMicroscopyLiDAR / point cloudCell / cellular structureRootImage / point-cloud registrationTrackingGrowth / development / phenology
Background Particle-tracking in 3D is an indispensable computational tool to extract critical information on dynamical processes from raw time-lapse imaging. This is particularly true with in vivo time-lapse fluorescence imaging in cell and developmental biology, where complex dynamics are observed at high temporal resolution. Common tracking algorithms used with time-lapse data in fluorescence microscopy typically assume a continuous signal where background, recognisable keypoints and independently moving objects of interest are permanently visible. Under these conditions, simple registration and identity management algorithms can track the objects of interest over time. In contrast, here we consider the case of transient signals and objects whose movements are constrained within a tissue, where standard algorithms fail to provide robust tracking. Results To optimize 3D tracking in these conditions, we propose the merging of registration and tracking tasks into a fuzzy registration algorithm to solve the identity management problem. We describe the design and application of such an algorithm, illustrated in the domain of plant biology, and make it available as an open-source software implementation. The algorithm is tested on mitotic events in 4D data-sets obtained with light-sheet fluorescence microscopy on growing Arabidopsis thaliana roots expressing CYCB::GFP. We validate the method by comparing the algorithm performance against both surrogate data and manual tracking. Conclusion This method fills a gap in existing tracking techniques, following mitotic events in challenging data-sets using transient fluorescent markers in unregistered images.
Why it matches plant phenotyping methods植物組織の4D蛍光画像から一過性の有糸分裂イベントを追跡・抽出する計算手法を開発し、代理データおよび手動追跡で検証しているため、植物表現型取得・解析手法が中心です。
abstractTo optimize 3D tracking in these conditions, we propose the merging of registration and tracking tasks into a fuzzy registration algorithm to solve the identity management problem.
Citrus fruit detection is one of the most important and challenging steps in citrus yield mapping. The distinct color differences between the ripe fruit and leaves allowed previously-described imaging-based methods to achieve good results. However, immature green citrus fruit detection, which aims to provide valuable information for citrus yield mapping at earlier stages is much more difficult because the fruit and leaf colors are very similar. This study combines color and thermal images for immature green fruit detections. Experiments identified optimal conditions for thermal imaging. A multimodal imaging platform was built to integrate color and thermal cameras. A novel image registration method was developed for combining color and thermal images and matching fruit in both images which achieved pixel-level accuracy. A new Color-Thermal Combined Probability (CTCP) algorithm was created to effectively fuse information from the color and thermal images to classify potential image regions into fruit and non-fruit classes. Algorithms were also developed to integrate image registration, information fusion and fruit classification and detection into a single step for real-time processing. An increase in recall rate from 78.1% when using only color images to 90.4% after fusing the color and thermal images was obtained at similar precision rates, and an increase in precision rate from 86.6% to 95.5% was obtained at similar recall rates. The fusion of the color and thermal images effectively improved immature green citrus fruit detection.
Why it matches plant phenotyping methods未熟果実という植物器官の検出・計数に向けたマルチモーダル画像プラットフォーム、画像登録、情報融合、分類アルゴリズムを開発しており、植物フェノタイピング手法が中心である。
abstractThis study combines color and thermal images for immature green fruit detections.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
Published1 Jun 2018IEEE Transactions on Pattern Analysis and Machine IntelligenceCited by 53 · OpenAlex ↗
This paper proposes a novel framework for fluorescence plant video processing. The plant research community is interested in the leaf-level photosynthetic analysis within a plant. A prerequisite for such analysis is to segment all leaves, estimate their structures, and track them over time. We identify this as a joint multi-leaf segmentation, alignment, and tracking problem. First, leaf segmentation and alignment are applied on the last frame of a plant video to find a number of well-aligned leaf candidates. Second, leaf tracking is applied on the remaining frames with leaf candidate transformation from the previous frame. We form two optimization problems with shared terms in their objective functions for leaf alignment and tracking respectively. A quantitative evaluation framework is formulated to evaluate the performance of our algorithm with four metrics. Two models are learned to predict the alignment accuracy and detect tracking failure respectively in order to provide guidance for subsequent plant biology analysis. The limitation of our algorithm is also studied. Experimental results show the effectiveness, efficiency, and robustness of the proposed method.
Why it matches plant phenotyping methods植物蛍光動画から葉の分割・構造推定・追跡を行う画像解析手法を開発し、定量評価と失敗検出まで実施しており、植物表現型取得が中心です。
abstractA prerequisite for such analysis is to segment all leaves, estimate their structures, and track them over time.
Abstract. Hyperspectral and three-dimensional measurement can obtain the intrinsic physicochemical properties and external geometrical characteristics of objects, respectively. Currently, a variety of sensors are integrated into a system to collect spectral and morphological information in agriculture. However, previous experiments were usually performed with several commercial devices on a single platform. Inadequate registration and synchronization among instruments often resulted in mismatch between spectral and 3D information of the same target. And narrow field of view (FOV) extends the working hours in farms. Therefore, we propose a high throughput prototype that combines stereo vision and grating dispersion to simultaneously acquire hyperspectral and 3D information.
Why it matches plant phenotyping methods植物の高さを含む3D形態とハイパースペクトル情報を同時取得する高スループット計測システムの開発が中心であり、植物フェノタイピング手法に該当する。
titleHIGH THROUGHPUT SYSTEM FOR PLANT HEIGHT AND HYPERSPECTRAL MEASUREMENT
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 10 Sept 2026
Hyperspectral and three-dimensional measurements can obtain the intrinsic physicochemical properties and external geometrical characteristics of objects, respectively. The combination of these two kinds of data can provide new insights into objects, which has gained attention in the fields of agricultural management, plant phenotyping, cultural heritage conservation, and food production. Currently, a variety of sensors are integrated into a system to collect spectral and morphological information in agriculture. However, previous experiments were usually performed with several commercial devices on a single platform. Inadequate registration and synchronization among instruments often resulted in mismatch between spectral and 3D information of the same target. In addition, using slit-based spectrometers and point-based 3D sensors extends the working hours in farms due to the narrow field of view (FOV). Therefore, we propose a high throughput prototype that combines stereo vision and grating dispersion to simultaneously acquire hyperspectral and 3D information. Furthermore, fiber-reformatting imaging spectrometry (FRIS) is adopted to acquire the hyperspectral images. Test experiments are conducted for the verification of the system accuracy, and vegetation measurements are carried out to demonstrate its feasibility. The proposed system is an improvement in multiple data acquisition and has the potential to improve plant phenotyping.
Why it matches plant phenotyping methods植物フェノタイピング向けのハイパースペクトル・3D同時計測システムを開発し、精度検証と植生計測で実証しているため、計測手法が中心です。
abstractTherefore, we propose a high throughput prototype that combines stereo vision and grating dispersion to simultaneously acquire hyperspectral and 3D information.
Monitoring flower development can provide useful information for production management, estimating yield and selecting specific genotypes of crops. The main goal of this study was to develop a methodology to detect and count cotton flowers, or blooms, using color images acquired by an unmanned aerial system. The aerial images were collected from two test fields in 4 days. A convolutional neural network (CNN) was designed and trained to detect cotton blooms in raw images, and their 3D locations were calculated using the dense point cloud constructed from the aerial images with the structure from motion method. The quality of the dense point cloud was analyzed and plots with poor quality were excluded from data analysis. A constrained clustering algorithm was developed to register the same bloom detected from different images based on the 3D location of the bloom. The accuracy and incompleteness of the dense point cloud were analyzed because they affected the accuracy of the 3D location of the blooms and thus the accuracy of the bloom registration result. The constrained clustering algorithm was validated using simulated data, showing good efficiency and accuracy. The bloom count from the proposed method was comparable with the number counted manually with an error of -4 to 3 blooms for the field with a single plant per plot. However, more plots were underestimated in the field with multiple plants per plot due to hidden blooms that were not captured by the aerial images. The proposed methodology provides a high-throughput method to continuously monitor the flowering progress of cotton.
Why it matches plant phenotyping methods綿花の花数・開花進展を航空画像、CNN、3D再構成、クラスタリングで取得・推定する方法を開発し、手計数およびシミュレーションで検証しており、フェノタイピング手法が中心である。
abstractThe main goal of this study was to develop a methodology to detect and count cotton flowers, or blooms, using color images acquired by an unmanned aerial system.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Point cloud rigid registration and stitching for plants with complex architecture is a challenging task, however, it is an important process to take advantage of the full potential of 3-D cameras for plant phenotyping and agricultural automation for characterizing production environments in agriculture. A methodology for three-dimensional (3-D) reconstruction of maize crop rows was proposed in this research, using high resolution 3-D images that were mapped into the colour images using state-of-the art software. The point cloud registration methodology was based on the Iterative Closest Point (ICP) algorithm. The incoming point cloud was previously filtered using the Random Sample Consensus (RANSAC) algorithm, by reducing the number of soil points until a threshold value was reached. This threshold value was calculated based on the approximate number of plant points in a single 3-D image. After registration and stitching of the crop rows, a plant/soil segmentation process was done relying again on the RANSAC algorithm. A quantitative comparison showed that the number of points obtained with a time-of-flight (TOF) camera, compared with the ones from two light detection and ranging (LIDARs) from a previous research, was roughly 23 times larger. Finally, the reconstruction was validated by comparing the seedling positions as ground truth and the point cloud clusters, obtained using the k-means clustering, that represent the plant stem positions. The resulted maize positions from the proposed methodology closely agreed with the ground truth with an average mean and standard deviation of 3.4 cm and ±1.3 cm, respectively.
Why it matches plant phenotyping methodsTOFカメラによる植物の3-D再構成、点群処理、植物/土壌分割、位置推定を開発・検証しており、植物フェノタイピング手法が研究の中心である。
abstractA methodology for three-dimensional (3-D) reconstruction of maize crop rows was proposed in this research
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 10 Sept 2026
Water stress caused by water scarcity has a negative impact on the wine industry. Several strategies have been implemented for optimizing water application in vineyards. In this regard, midday stem water potential (SWP) and thermal infrared (TIR) imaging for crop water stress index (CWSI) have been used to assess plant water stress on a vine-by-vine basis without considering the spatial variability. Unmanned Aerial Vehicle (UAV)-borne TIR images are used to assess the canopy temperature variability within vineyards that can be related to the vine water status. Nevertheless, when aerial TIR images are captured over canopy, internal shadow canopy pixels cannot be detected, leading to mixed information that negatively impacts the relationship between CWSI and SWP. This study proposes a methodology for automatic coregistration of thermal and multispectral images (ranging between 490 and 900 nm) obtained from a UAV to remove shadow canopy pixels using a modified scale invariant feature transformation (SIFT) computer vision algorithm and Kmeans++ clustering. Our results indicate that our proposed methodology improves the relationship between CWSI and SWP when shadow canopy pixels are removed from a drip-irrigated Cabernet Sauvignon vineyard. In particular, the coefficient of determination (R2) increased from 0.64 to 0.77. In addition, values of the root mean square error (RMSE) and standard error (SE) decreased from 0.2 to 0.1 MPa and 0.24 to 0.16 MPa, respectively. Finally, this study shows that the negative effect of shadow canopy pixels was higher in those vines with water stress compared with well-watered vines.
Why it matches plant phenotyping methodsUAV熱画像とマルチスペクトル画像の自動コレジストレーションおよび影画素除去手法を開発し、ブドウ樹の水ストレス表現型（CWSI）推定性能をSWPとの関係で検証しているため、方法が中心的である。
abstractThis study proposes a methodology for automatic coregistration of thermal and multispectral images
The technologies and applications of aerial photography have exponentially evolved in the past two decades. The adventof purpose specific micro sensors and unmanned aerial vehicles (UAVs)havegone a long way in revolutionizingthe applications ofaerial imagesfrom crop monitoring to hazard assessment.The use of UAVs has become widespread due to its operational flexibility,ultra-high spatial resolution acquisition, and inexpensiveness. However, the application of multitemporal seriesof multispectral UAV imagery still suffers a setback ofsignificantmisregistration errors,and therefore becoming a concern forapplications such as precision agriculture. In addition, the micro sensors have different spectral properties thus an integration and/or comparative analysis is inevitable. Researchers have widely studied the application of UAV imagery; topical issues range from spectral and spatial properties to image registration and multi-sensor integration. In crop monitoring, accurate co-registration of images acquired within and in different epochs remains to be exhaustively researched on; spectral band-to-band alignment is fundamental to precise crop sensing. Although the application of UAV-based sensors is widespread, direct image georeferencing and co-registration is done using GCP; this is usually costly and time consuming. This research proposes a novel approach for automatic co-registration of multitemporal UAV imagery using intensity-based keypoints. The approach is based on multispectral orthophoto alignment. However,photogrammetric products such as Digital Surface Models (DSM) present an interesting challenge to automatically co-register a multitemporal seriesof such productsincluding the several spectral channels, fromthree to twelve, captured by the UAV-based micro sensors.This research makes an effort to investigateinherent intra-epoch and inter-epochco-registration errors inmultispectral imagery, and the spatial data quality of photogrammetric products of two UAV-based cameras (Parrot Sequoia and Micro MCA Tetracam).A successful image registration involves four major stages, feature detection, feature description or descriptor extraction, feature matching, and geometric transformation. Estimation of geometric transformation from matched point pairs yields a 2D transformation matrix, in this case a similarity transformation matrix, which maps the inlying matched pairs. The inliers are selected randomly iteratively until sufficient pairs fitting the transformation model is reached. In this study, existing keypoints detection algorithms wereassessed to identify the most viable algorithm to be implemented for co-registration of multi-spectral and multitemporal UAVimages.Intensity-based registration algorithms (SURF, BRISK, MSER and KAZE) were tested and optimally parameterized. A detailed comparison on the performance of these algorithms was done and an informed decision was reached to pursue further experiments with only SURF and KAZE. The co-registration error analysisshows that optimally parametrized SURF and KAZE algorithmscan obtain co-registration accuracies of 0.1 and 0.3pixelsfor intra-epoch and inter-epoch imagesrespectively.To obtain better intra-epoch co-registration accuracy, collective band processing is advised. On the other hand, the quality of the DSM per band is evaluated and the results show that the red band is best fit for DSM extraction.In addition, the spatial variability of the UAV-based spectral features and that of Sentinel2Bsatellite imageryarecompared; the results show that regardless of the differences in spectral bandwidths, and spatial resolution, they are highly correlated.A positive correlation of 0.93 and 0.77 was obtained for the maize field and non-vegetated area respectively.However, the UAVs take pride in the spatial resolution advantage to reveal intrinsic intra-farm variability.On the other hand, a comparison ofspectral response of vegetation using Parrot Sequoia and Micro MCA Tetracam show that although both cameras are able to correctly sense active and declining photosynthetic activity in crops, spectral and radiometric calibration is key to achieving optimalresponse for the Micro MCA camera. In light of the results obtained in this study, descriptor-based methods are fit for co-registration of multispectral imagery for crop monitoring. In addition, UAV based multispectral cameras have different specifications and thus differ in the quality of their respective photogrammetric outputs; using the same system for monitoring purposes is advised.
Why it matches plant phenotyping methodsマルチスペクトルUAV画像の自動コレジストレーション手法を開発し、複数アルゴリズムの性能比較と精度評価を行っており、植物センシングの取得・解析手法が研究の中心である。
abstractThis research proposes a novel approach for automatic co-registration of multitemporal UAV imagery using intensity-based keypoints.
The 3D reconstruction of plant based on LiDAR is the main way to obtain the spatial structure of plant rapidly, nondestructive and all-weather. However, the influence of LiDAR instrument performance and field operation environment, the point cloud data obtained will lose the details of plant and reduce the accuracy of the model. In this study, the three-dimensional point cloud of plants generated based on multi-view sequence images was taken as a reference. The optimized Iterative Closest Point registration was adopted to calibrate the point cloud data from the LiDAR scanning to improve the detailed characteristics of the plants and establish a 3D model of plant. At the same time, according to the measured plant phenotype parameters (leaf length, leaf width, leaf area, plant height), the accuracy of 3D model was evaluated. The results showed that high accuracy of 3D reconstruction was obtained based on LiDAR and multi-view image sequence method. There was a good agreement between measured and calculated leaf area, leaf length, leaf width and plant height with R 2 >0.8 for leaf area, RMSE 0.85 for leaf length, R 2 >0.95 for leaf width. There was no significant difference for each phenotypic parameter between measured and calculated data (ANOVA, P <0.05). This method provides a technical reference for the research and application of LiDAR in fine modeling of field crops. Keywords: LiDAR, multi-view sequence images, plant 3D reconstruction, accuracy evaluatione DOI: 10.33440/j.ijpaa.20180101.0007 Citation: Wu J W, Xue X Y, Zhang S C, Qin W C, Chen C, Sun T. Plant 3D reconstruction based on LiDAR and multi-view sequence images. Int J Precis Agric Aviat, 2018; 1(1): 37–43.
Why it matches plant phenotyping methodsLiDARと多視点画像による植物3D再構成手法を開発し、葉形質や草丈との一致で精度検証しており、植物表現型取得が研究の中心である。
abstractThe optimized Iterative Closest Point registration was adopted to calibrate the point cloud data from the LiDAR scanning to improve the detailed characteristics of the plants and establish a 3D model of plant.
A low-cost three-dimensional (3D) plant reconstruction and morphological traits characterization system was developed. Corn plant seedlings were used as research objects for development and validation of the 3D reconstruction and point cloud data analysis algorithms. In this application, precise alignment of multiple 3D views generated by a 3D time-of-flight (ToF) sensor is critical to the 3D reconstruction of a plant. Previous research indicated that there is strong need for high-throughput, high-accuracy, and low-cost 3D plant reconstruction and trait characterization phenotyping systems. This research produced a 3D reconstruction system for indoor plant phenotyping by innovatively integrating a low-cost 2D camera, a low-cost 3D ToF camera, and a chessboard pattern beacon array to track the position and attitude of the 3D ToF sensor and, thus, accomplished precise 3D point cloud registration over multiple views. Specifically, algorithms for beacon target detection, camera pose tracking, and spatial relationship calibration between 2D and 3D cameras were developed for such a low-cost but high-performance 3D reconstruction solution. A plant analysis algorithm in a 3D space was developed to extract the morphological trait parameters of the plants by analyzing their 3D point cloud data. The phenotypical data obtained by this novel and low-cost 3D reconstruction based phenotyping system were validated by the experimental data generated by instrument and manual measurement. The results demonstrated that the developed phenotyping system has achieved promising measurement accuracy, fast processing speed while offering a low hardware cost, lending itself to a practical means of acquiring detailed 3D morphological traits for automated indoor plant phenotyping.
Why it matches plant phenotyping methods低コスト3Dセンサー、再構成・点群解析アルゴリズムによる植物形態形質取得システムの開発と、機器・手計測による検証が研究の中心であるため。
abstractA low-cost three-dimensional (3D) plant reconstruction and morphological traits characterization system was developed.
The ongoing development of imaging systems continuously brings novel possibilities for the exploration of plant anatomy at different scales. However, increasing resolution often results in a smaller field of view, limiting the scope for wider conclusions. Staedler et al. (2018) got round this problem by making use of 3D images acquired at two different scales to estimate the number of pollen grains within flowers. It is a powerful approach, providing much more information than with a single scale. An understanding of the biological functions, development, or evolution of plants requires an accurate description of their anatomy at various scales: the whole organism, its organs, tissues within each organ, cells within a tissue, the cell walls, or the organelles within a cell. Depending on the representative scale of the structures of interest, various image acquisition devices can be employed to investigate their morphology, chemical composition, or spatial organization (Rousseau et al., 2015) (see Box 1). The anatomical structure of plants can be assessed at different scales. At the largest scale, the whole plant can be imaged using digital photography. The structure is commonly quantified by phenotypic feature related to the size (e.g. length, volume, thickness) of the different organs. The spatial localization of the organs (e.g. position of leaves or fruits on the stem) or their organization may also be relevant. When focusing on a specific organ, a common question is how the different compartments are organized relative to each other. Imaging modalities such as tomography (A) or magnetic resonance imaging (MRI) allow for non-destructive investigation of the global organ geometry (e.g. size, shape, curvature) and organization of different compartments (computed tomography image, A, courtesy of C. Girousse, INRA Clermont-Ferrand). The slicing and staining of samples, followed by macroscopy or microscopy imaging, provides more precise information on the spatial organization of the tissues within an organ (B). When the resolution is sufficient, the size and shape of the cells within tissues may also be assessed (C). At a larger magnification, the use of electron microscopy (D) gives access to more detailed information, such as the morphology of cell walls (e.g. thickness, curvature). Using adequate staining or immuno-labelling also makes it possible to identify specific chemicals, and to describe their spatial localization. Historically, microscopy has been the usual technique for investigating plant anatomy at the cellular or tissue scale, and the rise of confocal microscopy has allowed us to perceive the 3D structure of tissues or organs with a resolution at the micron level (Truernit et al., 2008). But new technologies – such as the recent development of super-resolution techniques (e.g. PALM or STORM) or the introduction of optical coherence tomography (OCT) (Lee et al., 2006) – continuously bring novel imaging possibilities. For imaging cell walls or organelles within the cells, electron microscopy has often been the method of choice, reaching resolutions at the nanometre scale. The 3D structure can also be assessed, either by combining scanning electron microscopy with serial sectioning of the specimen (Bhawana et al., 2014), or by adapting tomography algorithms to transmission electron microscopy. Magnetic resonance imaging (MRI) and X-ray computed tomography are popular methods for the non-destructive investigation of the 3D architecture of biological specimens, without the need for staining, sectioning or inclusion. The high resolution reached by computed tomography (below the micron) often makes it the best method for the investigation of plant organs (Stuppy et al., 2003; Cloetens et al., 2006; Dhondt et al., 2010; Staedler et al., 2013). Staedler et al. (2018) took advantage of this resolution to quantify the 3D anatomy of orchid inflorescences, and through this showed differences in reproductive investment between inflorescences of rewarding and deceiving orchids. The physical properties of image acquisition devices limit the total quantity of information that can be gained, and so there is a compromise between a high resolution and a large field of view. When the spatial resolution is too low, the smallest structures are difficult to identify. On the other hand, the smaller the field of view, the more difficult it is to cover the totality of the organ of interest with a reasonable acquisition time. The increase in resolution of reconstructed images therefore often corresponds to a reduction in the size of the field of view. This difficulty was encountered in the work of Staedler et al. (2018): the structures of interest (pollen grains) could not be imaged with a resolution that allowed their identification while taking into account the whole reference structure (the pollinium, an aggregate of pollen grains). The strategy adopted to circumvent this difficulty was to acquire images at two different resolutions. Images acquired at finer resolution were used for segmentation and counting the pollen grains; images at a coarser resolution were used for assessing the size and shape of the reference structure. The total number of pollen grains was then estimated by combining their numerical density with the volume of the pollinium. It is an approach which exemplifies how data obtained at different resolutions may be used together to provide much more information than data at a single resolution. The multi-scale investigation of plant tissues is undoubtedly a promising strategy for a better description and understanding of plant anatomy. However, investigation and integration of images, obtained both at different scales and using different imaging modalities (see below), raise new methodological questions (Rousseau et al., 2015). Investigating plant anatomy at different scales often relies on different imaging modalities. A common approach in microscopy for combining these modalities is correlative microscopy, in particular correlative light and electron microscopy (CLEM) (Bell et al., 2013), and this correlative approach can also be performed with other modalities. For example, the joint analysis of 3D modalities allows the investigation of both anatomy and physiology (Jahnke et al., 2009). Similarly, hyperspectral images obtained from different spectroscopic techniques can be coupled (Allouche et al., 2012). Quantification of the cellular morphology of tomato pericarp was also performed from images obtained using both macroscopy and microscopy imaging, applying a statistical integration approach (Legland et al., 2012). Finally, the multi-scale strategy can be employed for modelling purposes (Mendoza et al., 2007). In many cases, for example to evaluate the quality of acquisitions, it is of interest to visualize, simultaneously, all the images obtained at different scales on the same sample. Unfortunately, the management and visualization of multiple images obtained with different resolution and/or different orientation still remain complicated. The spatial alignment of two different views of the same object is performed by applying image registration algorithms, which automatically identify the geometric transformation mapping one image onto another (Zitova and Flusser, 2003). Many algorithms have been developed, mostly in the context of medical imaging. The registration of images at similar scales is possible, but is difficult to apply in an automated way when differences in scales are large. Few user-friendly software solutions take into account spatial positioning of images for visualization. Using high-resolution 2D and 3D imaging at the tissue level makes it possible to quantify the 2D and 3D morphology and/or spatial organization of whole biological structures. However, contrary to conventional 2D imaging and except for simple tasks such as counting objects, performing manual measurements on 3D images is challenging – the quantification of anatomical structures therefore strongly relies on adequate image processing and analysis pipelines. The 3D raw images are usually converted into 3D reconstructions of the structures as binary images or geometrical models, and the reconstructed geometry then quantified using adequate descriptors. In the simpler case, structures or structural sections can just be counted. When the structures of interest can be delimited, either manually or by the use of segmentation methods, their geometry can be quantified (e.g. volume, surface area, thickness). When the structure of interest consists of a collection of elements that can be ‘individualized’ (e.g. cells, pores), its geometry can also be described by the shape or size distribution of its elements. In some cases, more complicated descriptors may be envisioned, for example based on skeletization of the microstructure (Mendoza et al., 2007). Estimating a global quantity from quantifications performed in fields of view with limited size requires a statistical approach. As in Staedler et al. (2018), the field of view may be assumed to be representative of the whole organ or tissue under investigation. For some plants, however, tissues may present large variability in morphology depending on their position in the organs. For example, the morphology of cells in fleshy fruit pericarps varies significantly depending on the distance to the outer epidermis. In such cases, an adequate sampling strategy has to be performed, either to integrate the biological variability or to quantify position-dependent variations in morphology. Another methodological question relates to the differences in resolution of 3D images, which affect the precision and accuracy of measurements taken from them (Arganda-Carreras and Andrey, 2017). When measuring the volume of a biological structure, the estimated values converge when the resolution increases. Increasing the resolution increases the number of details which can be detected and quantified, as well as how many small objects can be distinguished. Contrary to measurement of volume, the measurement of surface area from 3D images thus increases with image resolution, as smaller surface variations are detected. This effect was observed, for example, by Chevallier et al. (2014) on food products, with micro-tomography using two different scales. A larger quantity of fine structures (within the overall distribution of structure size) was observed with a smaller voxel size. In plant sciences, a similar effect was observed by Legland et al. (2012) in quantifying the morphology of cells in tomato pericarp using two different imaging modalities. The average cell size estimated from macroscopy images was larger than the one obtained after estimation from 3D confocal microscopy (see Box 2). Digital images may be processed and analysed to provide quantitative information. However, comparison and integration of quantitative information measured on images obtained at different scales are not always straightforward. In the example shown, images of tomato pericarp have been produced using two acquisition devices. The macroscopy imaging of a pericarp slice allows different tissues to be distinguished (e.g. epidermis, vascular bundles, parenchyma) as well as variations of cell morphology dependent on their location. However, it is difficult to individualize cells due to sampling resolution and the superposition of cell layers. The cellular morphology within images was quantified using texture analysis tools, measuring variations in shades of grey, and enabling an assessment of mean size variation dependent on the distance to the outer epidermis. A set of 3D confocal laser scanning microscopy images was also acquired along the pericarp and stitched together. The cellular morphology was then quantified by estimating specific cell wall surface area. Assuming that cells are spherical, a typical cell diameter can be estimated, as well as its variation dependent on the distance to the outer epidermis. A comparison of estimated cell diameter obtained from both imaging methods reveals that relative variations are very similar, but that absolute values differ with a scaling factor equal to two or three. The imaging modality at larger scale (here the macroscopy) provides more integrated data, resulting in smoother profiles. The imaging modality with better resolution (here the microscopy) exhibits stronger variability, due to the smaller size of the field of view. The scaling difference between the two profiles can be interpreted as the difference in the resolutions: finer imaging resolves more details, resulting in a smaller estimation of typical cell size. The management of image data obtained at different scales also leads to new computational issues, many of which are reviewed in Walter et al. (2010). A first issue is access to data. The large amount of image data, especially when multi-dimensional (3D, time-lapse, multi-channel), is not always well managed by current image-processing software (although specific software and file formats have been developed for accessing high-resolution images produced by slide scanners, using a pyramidal approach). The heterogeneity of specific or proprietary file formats may also restrict accessibility to the data or its reusability. With the increase in amount of image data, visualization becomes more complicated. Many different projection or rendering methods can be used for exploring multi-dimensional data sets, but the superposition of images obtained from different modalities increases the complexity of the task. In the case of multi- or hyperspectral images, vector spectral data are associated with an image element. Statistical methods such as principal components analyses are therefore necessary to be able to extract relevant information, and to represent its spatial variations within the plant or organ (Geladi and Grahn, 1996). Quantitative image analysis usually requires the processing of large collections of images to identify relevant factors related to changes in morphology or organization. The proper management of meta-data associated with images obtained on different individuals, with different imaging modalities or at different scales, requires organization and a rigorous approach. Nevertheless, new software solutions such as OMERO (Goldberg et al., 2005) have emerged for the management of large image collections. To conclude, while modern imaging techniques allow the investigation of plant anatomy at different scales, many challenges still exist for the quantification of data from complex imaging modalities and the fusion of data obtained from different scales, modalities, or datasets.
Why it matches plant phenotyping methods植物解剖のマルチスケール画像取得・画像処理・形態計測を中心に扱う方法論レビューであり、植物形質の抽出と画像統合が主題である。
titleQuantitative imaging of plants: multi-scale data for better plant anatomy
Machine vision technologies have shown advantages for efficient and accurate plant inspection in precision agriculture. Regarding the balance between accuracy of inspection and compactness for infield applications, multispectral imaging systems would be more suitable than RGB colour cameras or hyperspectral imaging systems. Multispectral image registration (MIR) is a key issue for multispectral imaging systems, however, this task is challenging. First of all, in many cases, two images needing registration do not have a one-to-one linear mapping in 2D space and therefore they cannot be aligned in 2D images. Furthermore, the general MIR algorithms are limited to images with uniform intensity and are incapable of registering images with rich features. This study developed a machine vision system (MVS) and a MIR method which replaces 2D-2D image registration by 3D-3D point cloud registration. The system can register 3D point clouds of ultraviolet (UV), blue, green, red and near-infrared (NIR) spectra in 3D space. It was found that the point clouds of general plants created by images of different spectral bands have a complementary property, and therefore a combined point cloud, called multispectral 3D point cloud, is denser than any cloud created by a single spectral band. Intensity information of each spectral band is available in a multispectral 3D point cloud and therefore image fusion and 3D morphological analysis can be conducted in the cloud. The MVS could be used as a sensor of a robotic system to fulfil on-the-go infield plant inspection tasks.
Why it matches plant phenotyping methods植物の多波長3D点群登録を開発し、画像融合と3D形態解析による圃場植物検査を可能にする手法・システムが研究の中心であるため。
abstractThis study developed a machine vision system (MVS) and a MIR method which replaces 2D-2D image registration by 3D-3D point cloud registration.
Crop breeding plays an important role in modern agriculture, improving plant performance, and increasing yield. Identifying the genes that are responsible for beneficial traits greatly facilitates plant breeding efforts for increasing crop production. However, associating genes and their functions with agronomic traits requires researchers to observe, measure, record, and analyze phenotypes of large numbers of plants, a repetitive and error-prone job if performed manually. An automated seedling phenotyping system aimed at replacing manual measurement, reducing sampling time, and increasing the allowable work time is thus highly valuable. Toward this goal, we developed an automated corn seedling phenotyping platform based on a time-of-flight of light (ToF) camera and an industrial robot arm. A ToF camera is mounted on the end effector of the robot arm. The arm positions the ToF camera at different viewpoints for acquiring 3D point cloud data. A camera-to-arm transformation matrix was calculated using a hand-eye calibration procedure and applied to transfer different viewpoints into an arm-based coordinate frame. Point cloud data filters were developed to remove the noise in the background and in the merged seedling point clouds. A 3D-to-2D projection and an x -axis pixel density distribution method were used to segment the stem and leaves. Finally, separated leaves were fitted with 3D curves for morphological traits characterization. This platform was tested on a sample of 60 corn plants at their early growth stages with between two to five leaves. The error ratios of the stem height and leave length measurements are 13.7% and 13.1%, respectively, demonstrating the feasibility of this robotic system for automated corn seedling phenotyping.
Why it matches plant phenotyping methodsロボットアームとToFカメラを用いた3D画像取得、セグメンテーション、形態形質推定によるトウモロコシ幼苗フェノタイピング基盤を開発・検証しており、方法が研究の中心です。
abstractwe developed an automated corn seedling phenotyping platform based on a time-of-flight of light (ToF) camera and an industrial robot arm.
Field / plotPhotogrammetry / SfM / MVSLiDAR / point cloudWhole plant / canopy / plot / fieldImage / point-cloud registration
Some point-cloud holes usually exist in the point-cloud data of trees acquired by a terrestrial 3D laser scanner. Such holes can affect the integrity of point-cloud data and subsequent 3D reconstruction work. In order to solve the problems such as point-cloud holes or incomplete point-cloud data caused by the shield of obstacles or unable setup of 3D laser scanner, this study focuses on the registration of point-cloud data and repairing the point-cloud holes aided by photogrammetry after analyzing the point-cloud data, and discusses the precise registration of point-cloud data based on ICP (Iterative Closest Point) algorithm and the fusion of scanned point-clouds with point-clouds generated by images.The purpose of this study lies on the registration of the target point clouds acquired by a terrestrial laser scanner with the point clouds generated from the entity image data, so as to ensure the integrity of the entity point-cloud data.Firstly, a terrestrial 3D laser scanner is used to acquire the point-cloud data of two Chinese pine (Pinus tabulaeformis) trees in the scanning region, and at the same time the algorithm of ICP is used to register the scanned point clouds.Then, in order to make up the pointcloud data holes caused by external objective factors, a digital camera is used to take pictures of the Chinese pine trees and acquire the image data that has high degree of overlap.The pairwise matching of homonymy feature points of the adjacent images taken on site is completed by using SIFT (Scale Invariant Feature Transform) image stitching algorithm, and then PMVS (patch-based multi-view stereo) algorithm is used to generate the 3D point set of the two target Chinese pine trees.Finally, in the VC++ environment the ICP algorithm is used to fuse the point-cloud data obtained by 3D laser scanner with the 3D point set generated by PMVS algorithm.The results show that the mean square error for point-cloud registration and fusion are 0.0353733 and 0.0009226364, respectively, which indicate that the effects of the registration and fusion are satisfied.This research can accurately and quickly finish the registration of the point-cloud data obtained in different ways, solve the defects of point-cloud holes caused by objective factors in complex forest environments such as trees blocked or site settings and other factors, and realize the acquirement of complete three-dimensional point cloud of trees, which has played a key role for subsequent three-dimensional reconstruction and parameters extraction of the trees.
Why it matches plant phenotyping methods樹木の3D点群取得・登録・融合・欠損修復を中心に開発および精度評価しており、完全な樹体形状の再構築と形質抽出に用いる植物フェノタイピング手法である。
abstractthis study focuses on the registration of point-cloud data and repairing the point-cloud holes aided by photogrammetry
Background Smarthouses capable of non-destructive, high-throughput plant phenotyping collect large amounts of data that can be used to understand plant growth and productivity in extreme environments. The challenge is to apply the statistical tool that best analyzes the data to study plant traits, such as salinity tolerance, or plant-growth-related traits. Results We derive family-wise salinity sensitivity (FSS) growth curves and use registration techniques to summarize growth patterns of HEB-25 barley families and the commercial variety, Navigator. We account for the spatial variation in smarthouse microclimates and in temporal variation across phenotyping runs using a functional ANOVA model to derive corrected FSS curves. From FSS, we derive corrected values for family-wise salinity tolerance, which are strongly negatively correlated with Na but not significantly with K, indicating that Na content is an important factor affecting salinity tolerance in these families, at least for plants of this age and grown in these conditions. Conclusions Our family-wise methodology is suitable for analyzing the growth curves of a large number of plants from multiple families. The corrected curves accurately account for the spatial and temporal variations among plants that are inherent to high-throughput experiments.
Why it matches plant phenotyping methods大規模植物フェノタイピングで得た成長曲線を補正・登録し、塩耐性形質を推定する統計的方法が研究の中心である。
abstractWe derive family-wise salinity sensitivity (FSS) growth curves and use registration techniques to summarize growth patterns of HEB-25 barley families and the commercial variety, Navigator.
In recent years, there has been significant progress in Computer Vision based plant phenotyping (quantitative analysis of biological properties of plants) technologies. Traditional methods of plant phenotyping are destructive, manual and error prone. Due to non-invasiveness and non-contact properties as well as increased accuracy, imaging techniques are becoming state-of-the-art in plant phenotyping. Among several parameters of plant phenotyping, growth analysis is very important for biological inference. Automating the growth analysis can result in accelerating the throughput in crop production. This thesis contributes to the automation of plant growth analysis.\nFirst, we present a novel system for automated and non-invasive/non-contact plant growth measurement. We exploit the recent advancements of sophisticated robotic technologies and near infrared laser scanners to build a 3D imaging system and use state-of-the-art Computer Vision algorithms to fully automate growth measurement. We have set up a gantry robot system having 7 degrees of freedom hanging from the roof of a growth chamber. The payload is a range scanner, which can measure dense depth maps (raw 3D coordinate points in mm) on the surface of an object (the plant). The scanner can be moved around the plant to scan from different viewpoints by programming the robot with a specific trajectory. The sequence of overlapping images can be aligned to obtain a full 3D structure of the plant in raw point cloud format, which can be triangulated to obtain a smooth surface (triangular mesh), enclosing the original plant. We show the capability of the system to capture the well known diurnal pattern of plant growth computed from the surface area and volume of the plant meshes for a number of plant species.\nSecond, we propose a technique to detect branch junctions in plant point cloud data. We demonstrate that using these junctions as feature points, the correspondence estimation can be formulated as a subgraph matching problem, and better matching results than state-of-the-art can be achieved. Also, this idea removes the requirement of a priori knowledge about rotational angles between adjacent scanning viewpoints imposed by the original registration algorithm for complex plant data. Before, this angle information had to be approximately known.\nThird, we present an algorithm to classify partially occluded leaves by their contours. In general, partial contour matching is a NP-hard problem. We propose a suboptimal matching solution and show that our method outperforms state-of-the-art on 3 public leaf datasets. We anticipate using this algorithm to track growing segmented leaves in our plant range data, even when a leaf becomes partially occluded by other plant matter over time.\nFinally, we perform some experiments to demonstrate the capability and limitations of the system and highlight the future research directions for Computer Vision based plant phenotyping.
Why it matches plant phenotyping methods植物の3D画像取得、コンピュータビジョン、ロボットスキャンによる成長形質の自動計測システムを開発しており、フェノタイピング手法が研究の中心である。
abstractThis thesis contributes to the automation of plant growth analysis.
The thermal behaviour of an orchard is intrinsically related to the plant physiological status and it is commonly observed using thermal imagery, in most cases, provided by a drone or by a satellite. Such remote sensing methods are currently popular since they allow to analyse large amounts of land data with few sensor readings. However, they are restricted by the spatial resolution of the images, which always correspond to top views of the canopies. The latter does not allow for a side recording or analysis of the orchard. In this work, we design and evaluate a portable ground-based system for a manual thermal and geometrical characterisation of an orchard, merging thermal images with LiDAR-based range readings in order to obtain a 3D thermal reconstruction of the crop to overcome the previously mentioned issues. The proposed system can work in Global Navigation Satellite System (GNSS) denied environments and delivers multiple views of the orchard, offering the user a three-dimensional view of the thermal behaviour of the grove. Further, the implemented algorithm classifies points from the LiDAR measurements which correspond to the canopy using a supervised classifier. Later, a matching procedure is performed between such points and the thermal information provided by the thermal camera. In order to reconstruct the entire orchard or only a section of the grove, several frames are registered using the Iterative Closest Point algorithm. The system was tested in two conditions: in laboratory and in field within a plantation of Hass avocado, which is one of the main fruit trees growing in Chile, and its performance is compared with an LI-6400 Infra-red Gas Analyser (IRGA) portable photosynthesis system (LI-COR, Lincoln, NE).
Why it matches plant phenotyping methodsLiDARと熱画像を融合し、果樹の樹冠形状と熱的・生理的状態を3D再構成する地上型計測システムを設計・評価しており、植物フェノタイピング手法が中心である。
abstractwe design and evaluate a portable ground-based system for a manual thermal and geometrical characterisation of an orchard
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
Abstract. Understanding the genetic basis of complex plant traits requires connecting genotype to phenotype information, known as the “G2P question.” In the last three decades, genotyping methods have become highly developed. Much less innovation has occurred for measuring plant traits (phenotyping), particularly under field conditions. This imbalance has stimulated research to develop methods for field-based high-throughput plant phenotyping (HTPP). Sensors installed on ground vehicles can provide a huge amount of potentially transformative phenotypic measurements, orders of magnitude larger than provided by traditional phenotyping practice, but their utility requires accurate mapping. Using geospatial processing techniques, sensor data must be consistently matched to their corresponding field plots to establish links between breeding lines and measured phenotypes. This article examines problems and solutions for georeferencing sensor measurements from ground vehicle platforms for field-based HTPP. Using three case studies, the importance of vehicle heading for sensor positioning is examined. Three corresponding approaches for georeferencing are introduced based on different methods to estimate vehicle heading. For two of the cases, approaches to develop a field map of plot areas are addressed, where the issue is to ensure that sensor positions are correctly assigned to plots. Two solutions are proposed. One uses a geographic information system to design a field map before planting, while the other adopts an algorithm that calculates plot boundaries from the georeferenced sensor measurements. An advantage of the latter approach is the accommodation of irregular planting patterns. Using the algorithm to calculate the plot boundaries of a winter wheat field in Kansas, 98.4% of the calculated plot centers were within 0.4 m of the surveyed plot centers, and all of the calculated plot centers were within 0.6 m of the surveyed plot centers. While multiple options and software tools are available for geospatial processing of field-based HTPP data, they share common problems with sensor positioning and plot delineation. The options and tools presented in this study are distinguished by their practicality, accessibility, and ability to rapidly map phenotypic data.
Why it matches plant phenotyping methods圃場型高スループット植物フェノタイピングにおけるセンサー測定値の地理参照、圃場区画割当、ソフトウェア処理を中心に開発・検証しており、フェノタイプ取得ワークフローの技術的貢献が明確である。
abstractThis article examines problems and solutions for georeferencing sensor measurements from ground vehicle platforms for field-based HTPP.
KEY MESSAGE : Low-cost methodology to obtain CHMs integrating terrain data from LiDAR into photogrammetric point clouds with greater spatial, radiometric and temporal resolution due to a correction model. This study focuses on developing a methodology to generate a Dense Canopy Height Model based on the registration of point clouds from LiDAR open data and the photogrammetric output from a low-cost flight. To minimise georeferencing errors from dataset registration, terrain data from LiDAR were refined to be included in the photogrammetric point cloud through a correction model supported by a statistical analysis of heights. As a result, a fusion point cloud was obtained, which applies LiDAR to characterize the terrain in areas with high vegetation and utilizes the greater spatial, radiometric and temporal resolution of photogrammetry. The obtained results have been successfully validated: the accuracy of the fusion cloud is statistically consistent with the accuracies of both clouds based on the principles of classical photogrammetry and LiDAR processing. The resulting point cloud, through a radiometric and geometric segmentation process, allows a Dense Canopy Height Model to be obtained.
Why it matches plant phenotyping methods低コスト写真測量とLiDARを融合し、植生の高さを表すDense Canopy Height Modelを生成・検証する手法開発が研究の中心であるため、植物形態計測として収載する。
abstractLow-cost methodology to obtain CHMs integrating terrain data from LiDAR into photogrammetric point clouds
Technologically advanced imaging techniques have allowed us to generate and study the internal part of a tissue over time by capturing serial optical images that contain spatio-temporal slices of hundreds of tightly packed cells. Image registration of such live-imaging datasets of developing multicelluar tissues is one of the essential components of all image analysis pipelines. In this paper, we present a fully automated 4D(X-Y-Z-T) registration method of live imaging stacks that takes care of both temporal and spatial misalignments. We present a novel landmark selection methodology where the shape features of individual cells are not of high quality and highly distinguishable. The proposed registration method finds the best image slice correspondence from consecutive image stacks to account for vertical growth in the tissue and the discrepancy in the choice of the starting focal point. Then, it uses local graph-based approach to automatically find corresponding landmark pairs, and finally the registration parameters are used to register the entire image stack. The proposed registration algorithm combined with an existing tracking method is tested on multiple image stacks of tightly packed cells of Arabidopsis shoot apical meristem and the results show that it significantly improves the accuracy of cell lineages and division statistics.
Why it matches plant phenotyping methodsシロイヌナズナの4Dライブイメージング画像を対象に、細胞対応付けと画像登録を自動化する手法を開発しており、植物組織の形態・発生状態を抽出する解析基盤が中心である。
abstractIn this paper, we present a fully automated 4D(X-Y-Z-T) registration method of live imaging stacks that takes care of both temporal and spatial misalignments.