Growth chamberMultimodalStereoRootStem / branchTrackingGrowth / development / phenology
Understanding plant behaviour requires the integration of multiple phenotypic and physiological signals measured over time under controlled conditions. However, different plant signals are typically studied using separate experimental setups, limiting temporal alignment and integrative analyses.We present Mind(the)Plant, a modular experimental facility designed for the synchronized, long-term acquisition of multimodal plant data, including three-dimensional shoot kinematics, above- and below-ground volatile organic compounds (VOCs) and root imaging. Its modular architecture is designed to accommodate additional acquisition modules, such as electrophysiological signalling, as future extensions. The platform integrates a controlled growth environment with stereovision imaging, high-resolution time-of-flight mass spectrometry and custom rhizocameras. These components are connected through a unified network infrastructure that ensures synchronized acquisition and centralized data handling.We validate the performance of each acquisition module through multi-week recordings, demonstrating high-temporal stability, reliable stereovision synchronization, effective isolation of VOCs signals and robust operation of below-ground imaging. We further illustrate the analytical potential of the platform using a one-day continuous multimodal acquisition combining shoot kinematics, above-ground VOC emissions, rhizocameras observations and environmental data.Mind(the)Plant provides a novel methodological framework for studying plant behaviour, signalling and phenotypic plasticity in ecological and evolutionary research. By enabling coordinated measurements of multiple plant response modalities, the platform supports investigations of dynamic plant-environment and plant-plant interactions from a behavioural perspective.
Why it matches plant phenotyping methods植物の複数の表現型・生理シグナルを同期取得する施設を開発し、各取得モジュールの性能を検証しているため、表現型計測プラットフォームが研究の中心です。
abstractWe present Mind(the)Plant, a modular experimental facility designed for the synchronized, long-term acquisition of multimodal plant data, including three-dimensional shoot kinematics, above- and below-ground volatile organic compounds (VOCs) and root imaging.
Reproduction assets foundThe paper's data availability statement explicitly deposits data, code and processing pipelines (supporting the multimodal plant phenotyping measurements and analysis) in a public Zenodo archive with an authors' URL matching an allowed URL.Code · publicf Interest Statement
The authors have no conflicts of interest to declare.
Peer Review
The peer review history for this article is available at https://www.webofscience.com/api/gateway/wos/peer-review/10.1111/2041-210x.70411 .
Data availability Statement
Data, code and processing pipelines supporting this study are available at https://doi.org/10.5281/zenodo.22095454 ( Simonetti & Castiello, 2026 ).
References
Avesani S, Bonato B, Simonetti V, Guerra S, Ravazzolo L, Gjinaj G, Dadda M, Castiello U. Comparing proton transfer reaction (PTR) and adduct ionization mechanism (AIM) for the study of volatile organic compounds. Molecules. 2026;31(3):402. doi: 10.3390/molecules31030402.
Baluška F, LeOpen asset ↗zenodo · 10.5281/zenodo.22095454lines:482-508Code / dataset availability confirmedOpenAlex · Crossref · checked 6 Sept 2026
Automated three-dimensional plant phenotyping is an essential tool for non-destructive analysis of plant growth and structure. This paper presents a low-cost system based on stereo vision for depth estimation and morphological characterization of maize plants. The system incorporates an automatic detection stage for the object of interest using deep learning techniques to delimit the region of interest (ROI) corresponding to the plant. The Semi-Global Block Matching (SGBM) algorithm is applied to the detected region to compute the disparity map and generate a partial three-dimensional representation of the plant structure. The ROI delimitation restricts the disparity calculation to the plant area, reducing processing of the background and optimizing computational resource use. The deep learning-based detection stage maintains stable foliage identification even under varying lighting conditions and shadowing, ensuring consistent depth data across different experimental conditions. Overall, the proposed system integrates detection and disparity estimation into an efficient processing flow, providing an accessible alternative for automated three-dimensional phenotyping in agricultural environments.
Why it matches plant phenotyping methods植物の3次元形態を取得・特徴づけるステレオビジョンと深度推定システムの開発が中心であり、明確な植物フェノタイピング手法です。
abstractThis paper presents a low-cost system based on stereo vision for depth estimation and morphological characterization of maize plants.
Reproduction assets foundThe paper's Data Availability Statement openly deposits the original study data (the 544 stereo RGB maize images and related phenotyping data) on OSF at a DOI, which is a paper-specific, publicly actionable asset. No author analysis code repository is explicitly stated.Dataset · publicData Availability Statement: The original data presented in the study are openly available in OSF at
https://doi.org/10.17605/OSF.IO/MN6P9.Open asset ↗OSF · 10.17605/OSF.IO/MN6P9pdf-page:18 lines:1-59Code / dataset availability confirmedCrossref · OpenAlex · Europe PMC · checked 6 Sept 2026
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:278-306Code / dataset availability confirmedEurope PMC · OpenAlex · checked 6 Sept 2026
TomatoMultimodalStereoFruitObject detectionVisualization / data managementGrowth / development / phenologyFruit / seed / panicle traitsYield / yield components
Introduction The advancement of smart agriculture has witnessed increasing applications of computer vision in crop monitoring and management. However, existing approaches remain challenged by high computational complexity, limited real-time capability, and poor multi-task coordination in tomato cultivation scenarios. Methods To address these limitations, an intelligent tomato management system is proposed based on the Ghost-based Adaptive Efficient You Only Look Once (GAE-YOLO) algorithm. The lightweight architecture of the GAE-YOLO framework is achieved through the replacement of standard convolutional layers with Ghost Convolution (GhostConv) modules, while detection accuracy is significantly improved by the integration of both AReLU activation functions and Effective Intersection over Union (E-IoU) loss optimization. The system, implemented on a Jetson TX2 embedded platform, also incorporates ZED stereo vision for 3D localization and a PyQt6-based visualization platform. Results When implemented on Jetson TX2, the system achieving 93.5% mean Average Precision at 50% intersection over union (mAP@50) at 10.2 frames per second (FPS), which can be optimized to 27 FPS by employing TensorRT acceleration and 720p resolution for scenarios demanding higher throughput. Furthermore, it establishes standardized assessment systems for tomato maturity and yield prediction, and offers integrated modules for disease diagnosis and agricultural large language model consultation. Discussion This work establishes a new paradigm for edge computing in agriculture while providing critical technical support for smart farming development.
Why it matches plant phenotyping methodsトマトの成熟度・収量予測および病害診断を含む画像・3Dビジョン基盤を開発し、エッジ環境で性能評価しているため、植物表現型取得が中心的な研究である。
abstractan intelligent tomato management system is proposed based on the Ghost-based Adaptive Efficient You Only Look Once (GAE-YOLO) algorithm
Reproduction assets foundThe paper's data availability statement explicitly states that the data and code supporting the study are publicly available on GitHub at the authors' repository (GAE-YOLO), which matches an allowed URL. This qualifies as a paper-specific public code asset for the tomato detection/phenotyping analysis.Code · publicThe data and code supporting this study are publicly available at GitHub under the following links: https://github.com/NSSCk/GAE-YOLO .Open asset ↗NSSCk/GAE-YOLOlines:756-834Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Abstract. Historical aerial images, captured by film cameras in the previous century, are valuable resources for quantifying Earth's surface and landscape changes over time. In the post-war period, these images were often acquired to create topographic maps, resulting in the acquisition of large-scale aerial photographs with stereo coverage. Photogrammetric techniques applied to these stereo images enable the extraction of 3D information to reconstruct digital surface models (DSMs) and orthoimages. Here, we present a highly automated photogrammetric approach for generating countrywide DSMs of Switzerland, at a 1 m resolution, from approximately 32 000 scanned aerial stereo images acquired between 1979 and 2006, with known exterior and interior orientation. We derived four countrywide DSMs for the epochs 1979–1985, 1985–1991, 1991–1998, and 1998–2006. From the DSMs, we generated corresponding countrywide vegetation height models (VHMs). We assessed the quality of the historical DSMs at the country scale and within six representative study sites, evaluating the vertical accuracy and the completeness of image matching across different land cover types. Mean completeness ranged from 64 % for “glacial and perpetual snow” to 98 % for “sealed surfaces”, with a value of 93 % for the “closed forest” class. Across Switzerland, the median elevation accuracy of the historical DSMs compared with a reference digital terrain model (DTM) on sealed surface points ranged from 0.08 to 0.16 m, with a normalized median absolute deviation (NMAD) of around 0.8 m and a maximum root mean square error (RMSE) of 1.20 m. Similar accuracies are obtained when comparing historical DSMs with measured geodetic points. The VHMs generated in this study enabled the detection of major changes in forest areas due to windstorm damage, forest dynamics, and growth. This work demonstrates the feasibility of generating accurate, very-high-resolution DSM time series (spanning three decades) and VHMs from historical aerial images of the entire surface of Switzerland in a highly automated manner. The VHMs are already being used to estimate countrywide biomass changes. The countrywide DSMs and VHMs for the four epochs, along with auxiliary data, are available online at https://doi.org/10.16904/envidat.528 (Marty et al., 2024) and can be used to quantify long-term elevation changes and related processes across different surfaces.
Why it matches plant phenotyping methods歴史的航空画像から植生高モデルを生成する自動写真測量法を開発・精度評価し、森林の高さ変化という植物キャノピー形質を抽出しているため、測定法が中心的である。
abstractFrom the DSMs, we generated corresponding countrywide vegetation height models (VHMs).
Reproduction assets foundThe paper's countrywide DSMs, VHMs, and auxiliary rasters (matching mask, vegetation mask, metadata shapefile) for four epochs are deposited publicly on EnviDat with an explicit DOI. These vegetation height models are the paper's plant/canopy phenotyping measurements. No author analysis code or trained models are namedDataset · publicDatasets can be accessed from EnviDat ( https://doi.org/10.16904/envidat.528 , Marty et al., 2024). The following files are available for the four epochs: countrywide digital surface model (DSM), hillshaded DSM, and vegetation height models (VHMs).Open asset ↗Envidat · 10.16904/envidat.528lines:249-256Code / dataset availability confirmedOpenAlex · checked 15 Sept 2026
Abstract. Historical aerial images, captured by film cameras in the previous century, are valuable resources for quantifying Earth’s surface and landscape changes over time. In the post-war period, these images were often acquired to create topographic maps, resulting in the acquisition of large-scale aerial photographs with stereo coverage. Photogrammetric techniques applied to these stereo images enable the extraction of 3D information to reconstruct digital surface models (DSMs) and orthoimages. Here, we present a highly automated photogrammetric approach for generating countrywide DSMs of Switzerland, at a 1 m resolution, from approximately 40,000 scanned aerial stereo images acquired between 1979 and 2006, with known exterior and interior orientation. We derived four countrywide DSMs for the epochs 1979–1985, 1985–1991, 1991–1998, and 1998–2006. From the DSMs, we generated corresponding countrywide vegetation height models (VHMs). We assessed the quality of the historical DSMs at the country scale and within six representative study sites, evaluating the vertical accuracy and the completeness of image-matching across different land cover types. Mean completeness ranged from 64 % for ‘glacial and perpetual snow’ to 98 % for ‘sealed surfaces’, with a value of 93 % for the ‘closed forest’ class. Across Switzerland, the median elevation accuracy of the historical DSMs compared with a reference digital terrain model (DTM) on sealed surface points ranged from 0.28 to 0.53 m, with a normalised median absolute deviation (NMAD) of around 1 m and a maximum root mean square error (RMSE) of 3.90 m. The same analysis between geodetic points and historical DSMs showed higher accuracies, with median values of ≤ 0.05 m and an NMAD < 1 m. The VHMs generated in this study enabled the detection of major changes in forest areas due to windstorm damage, forest dynamics, and growth. This work demonstrates the feasibility of generating accurate, very high-resolution DSM time series (spanning three decades) and VHMs from historical aerial images of the entire surface of Switzerland in a highly automated manner. The VHMs are already being used to estimate countrywide biomass changes. The countrywide DSMs and VHMs for the four epochs, along with auxiliary data, are available online at https://doi.org/10.16904/envidat.528 (Marty et al., 2024) and can be used to quantify long-term elevation changes and related processes across different surfaces.
Why it matches plant phenotyping methods歴史航空画像から植生高モデルを自動生成するフォトグラメトリ手法を開発・精度評価し、森林の高さ変化という植物状態を測定するデータセットも提供しているため、植物フェノタイピング手法が中心である。
abstractFrom the DSMs, we generated corresponding countrywide vegetation height models (VHMs).
Reproduction assets foundThe paper's own countrywide DSM and vegetation height model (VHM) rasters, plus masks and metadata, are publicly deposited on EnviDat with an explicit DOI, directly reproducing the paper's vegetation height measurements.Dataset · public22
5 Data availability
434
Datasets can be accessed from EnviDat (https://doi.org/10.16904/envidat.528, Marty et al., 2024). The following files are
435
available for the four epochs: countrywide digital surface model (DSM), hillshaded DSM, and vegetation height models
436
(VHMs). A metadata shapefile is provided with information about the acquisition year of the photographs used here; the
437
geometry corresponds to the 1:25,00Open asset ↗EnviDat · 10.16904/envidat.528pdf-raw-page:22 lines:1-63Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
In agriculture, the plant leaf angle influences light use efficiency and photosynthesis and, consequently, the overall crop performance. Leaf angle measurements are used in plant phenotyping, plant breeding, and remote sensing to study plant function and structure. Traditional manual leaf angle measurements have limited precision as they are labor- and time-intensive due to challenging environmental conditions and highly dynamic plant processes. To enable more detailed studies on leaf angles, we modified a well-established automated farming robot to obtain high-resolution 3D point clouds at customizable intervals of individual plants using stereo vision. We demonstrate the system's accuracy and reliability, with minimal deviation from reference values. The method can be utilized by other researchers to gather data on leaf angles and other structural plant traits at regular intervals to access the dynamics of leaves, plants, and canopies. The system's low cost and adaptability can enhance the efficiency of crop monitoring in plant breeding and phenotyping experiments. Detailed documentation and code are available on GitHub.•An open-source farming robot is retrofitted to function as an automatic data collection platform•Hard to access leaf angles can be retrieved with high accuracy•Leaf angle dynamics can be observed with high temporal resolution.
Why it matches plant phenotyping methodsステレオビジョンを用いて葉角度を高精度・高頻度に測定するロボット基盤を開発・改良し、精度と信頼性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 modified a well-established automated farming robot to obtain high-resolution 3D point clouds at customizable intervals of individual plants using stereo vision.
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 used codes and recorded data are available at: https://github.com/FrederikHennecke/PointCloudHarvest .Open asset ↗FrederikHennecke/PointCloudHarvestlines:218-236Code / dataset availability confirmedEurope PMC · OpenAlex · checked 7 Sept 2026
MaizeGrowth chamberStereoRoot2D/3D reconstructionGrowth / time-series analysisRoot system architecture
Background The root of a plant is a fundamental organ for the multisensory perception of the environment. Investigating root growth dynamics as a mean of their interaction with the environment is of key importance for improving knowledge in plant behaviour, plant biology and agriculture. To date, it is difficult to study roots movements from a dynamic perspective given that available technologies for root imaging focus mostly on static characterizations, lacking temporal and three-dimensional (3D) spatial information. This paper describes a new system based on time-lapse for the 3D reconstruction and analysis of roots growing in hydroponics. Results The system is based on infrared stereo-cameras acquiring time-lapse images of the roots for 3D reconstruction. The acquisition protocol guarantees the root growth in complete dark while the upper part of the plant grows in normal light conditions. The system extracts the 3D trajectory of the root tip and a set of descriptive features in both the temporal and frequency domains. The system has been used on Zea mays L. (B73) during the first week of growth and shows good inter-reliability between operators with an Intra Class Correlation Coefficient (ICC) > 0.9 for all features extracted. It also showed measurement accuracy with a median difference of Conclusions The system and the protocol presented in this study enable accurate 3D analysis of primary root growth in hydroponics. It can serve as a valuable tool for analysing real-time root responses to environmental stimuli thus improving knowledge on the processes contributing to roots physiological and phenotypic plasticity.
Why it matches plant phenotyping methods根の3D動態を取得・解析する画像計測システムを開発し、特徴量の信頼性と精度を検証しており、植物表現型取得が中心である。
abstractThis paper describes a new system based on time-lapse for the 3D reconstruction and analysis of roots growing in hydroponics.
Reproduction assets foundThe paper's 3D root tip trajectory data (phenotyping measurements from maize root imaging) are publicly deposited on Zenodo. The analysis software and scripts are only available upon request, so they qualify as request_only.Dataset · publicData describing 3D trajectories used in this paper are available here: https://zenodo.org/record/8422242 . Software and scripts are available for research purposes upon request through the email address: mindtheplantlab@gmail.com.Open asset ↗Zenodo · 8422242lines:141-172Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Forests are a vital source of food, fuel, and medicine and play a crucial role in climate change mitigation. Strategic and policy decisions on forest management and conservation require accurate and up-to-date information on available forest resources. Forest inventory data such as tree parameters, heights, and crown diameters must be collected and analysed to monitor forests effectively. Traditional manual techniques are slow and labour-intensive, requiring additional personnel, while existing non-contact methods are costly, computationally intensive, or less accurate. Kenya plans to increase its forest cover to 30% by 2032 and establish a national forest monitoring system. Building capacity in forest monitoring through innovative field data collection technologies is encouraged to match the pace of increase in forest cover. This study explored the applicability of low-cost, non-contact tree inventory based on stereoscopic photogrammetry in a recently reforested stand in Kieni Forest, Kenya. A custom-built stereo camera was used to capture images of 251 trees in the study area from which the tree heights and crown diameters were successfully extracted quickly and with high accuracy. The results imply that stereoscopic photogrammetry is an accurate and reliable method that can support the national forest monitoring system and REDD+ implementation.
Why it matches plant phenotyping methodsステレオ写真測量を用いて樹高と樹冠径を非接触で抽出し、精度と信頼性を評価しているため、植物形質取得手法が研究の中心です。
abstractThis study explored the applicability of low-cost, non-contact tree inventory based on stereoscopic photogrammetry
Reproduction assets foundThe paper's Data Availability Statement explicitly states that the supporting data and software code for the stereoscopic photogrammetry tree inventory (tree height, crown diameter, DBH extraction from stereo images of 251 trees in Kieni Forest) are publicly available on the authors' GitHub repository DeKUT-DSAIL/TreeVCode · publicData Availability Statement: The data that support the findings of this study, as well as the software
code, are publicly available on GitHub: https://github.com/DeKUT-DSAIL/TreeVision (accessed on
11 August 2023).Open asset ↗DeKUT-DSAIL/TreeVisionpdf-page:11 lines:1-61Code / dataset availability confirmedEurope PMC · OpenAlex · Crossref · checked 7 Sept 2026
MaizeLaboratory / benchtopStereoRootMorphology / geometry measurement2D/3D reconstructionGrowth / time-series analysisGrowth / development / phenologyRoot system architecture
Background: The root of a plant is a fundamental organ for the multisensory perception of the environment. Investigating root growth dynamics as a mean of their interaction with the environment is of key importance for improving knowledge in plant behaviour, plant biology and agriculture. To date, it is difficult to study roots movements from a dynamic perspective given that available technologies for root imaging focus mostly on static characterizations, lacking of temporal and three-dimensional (3D) spatial information. This paper describes a new system based on timelapse for the 3D reconstruction and analysis of roots growing in hydroponics. Results The system is based on infrared stereo-cameras acquiring time-lapse images of the roots for 3D reconstruction. The acquisition protocol guarantees the root growth in complete dark while the upper part of the plant grows in normal light conditions. The system extracts the 3D trajectory of the root tip and a set of descriptive features in both the temporal and frequency domains. The system has been used on Zea mays L. (B73) during the first week of growth and shows good inter-reliability between operators with an Intra Class Correlation Coefficient (ICC) > 0.9 for all features extracted. It also showed measurement accuracy with a median difference of < 1 mm between computed and manually measured root length. Conclusions The system and the protocol presented in this study enable accurate 3D analysis of primary root growth in hydroponics. It can serve as a valuable tool for analyzing real-time root responses to environmental stimuli thus improving knowledge on the processes contributing to roots physiological and phenotypic plasticity.
Why it matches plant phenotyping methods根の3D動態を画像から再構成・解析するシステムを開発し、特徴量の信頼性と測定精度を検証しており、植物表現型取得法が中心である。
abstractThis paper describes a new system based on timelapse for the 3D reconstruction and analysis of roots growing in hydroponics.
Reproduction assets foundThe preprint explicitly states that the 3D root tip trajectory data underlying its phenotyping analysis are publicly deposited on Zenodo (record 8422242), making this a paper-specific, publicly accessible phenotype dataset. No author analysis code with a public URL is stated (SPROUTS is proprietary third-party softwareDataset · publicData describing 3D trajectories used in this paper are available here: https://zenodo.org/record/8422242Open asset ↗Zenodo · 8422242lines:119-156Code / dataset availability confirmedCrossref · OpenAlex · checked 15 Sept 2026
Buckwheat plant height is an important indicator for producers. Due to the decline in agricultural labor, the automatic and real-time acquisition of crop growth information will become a prominent issue for farms in the future. To address this problem, we focused on stereo vision and a regression convolutional neural network (CNN) in order to estimate buckwheat plant height. MobileNet V3 Small, NasNet Mobile, RegNet Y002, EfficientNet V2 B0, MobileNet V3 Large, NasNet Large, RegNet Y008, and EfficientNet V2 L were modified into regression CNNs. Through a five-fold cross-validation of the modeling data, the modified RegNet Y008 was selected as the optimal estimation model. Based on the depth and contour information of buckwheat depth image, the mean absolute error (MAE), root mean square error (RMSE), mean square error (MSE), and mean relative error (MRE) when estimating plant height were 0.56 cm, 0.73 cm, 0.54 cm, and 1.7%, respectively. The coefficient of determination (R2) value between the estimated and measured results was 0.9994. Combined with the LabVIEW software development platform, this method can estimate buckwheat accurately, quickly, and automatically. This work contributes to the automatic management of farms.
Why it matches plant phenotyping methodsステレオビジョンと回帰CNNにより、圃場でのソバ草丈を自動推定する手法を開発・検証しており、植物表現型の取得方法が研究の中心です。
abstractwe focused on stereo vision and a regression convolutional neural network (CNN) in order to estimate buckwheat plant height.
Reproduction assets foundThe paper's buckwheat height estimation model code (modified regression CNNs with training results) is publicly available via an authors' GitHub repository explicitly stated in the text. The phenotype dataset (depth images with height labels) is only available by contacting the authors, so it is not a public asset.Code · publicndows 11 (64 bit), and an
Nvidia GeForce RTX 3090 24 GB graphics card with Nvidia Ampere architecture. All of
the models used the processed grayscale images of 224 × 224 pixels as the input and the
estimated buckwheat height as the output. The codes of the models with training results
are available at the following GitHub link: https://github.com/18801389568/Buckwheat-height-estimation (accessed on 26 July 2023).
Figure 5. Construction method of the buckwheat crop height estimation models.
Training the models was essentially a process of continually updating the trainable
parameters of each model in order to make the crop height estimation results increasingly
accurate. Considering the quantOpen asset ↗18801389568/Buckwheat-height-estimationpdf-raw-page:6 lines:1-60Code / dataset availability confirmedEurope PMC · OpenAlex · checked 7 Sept 2026
Crop yield potential is intrinsically related to canopy photosynthesis; therefore, improving canopy photosynthetic efficiency is a major focus of current efforts to enhance crop yield. Canopy photosynthesis rate ( A c ) is influenced by several factors, including plant architecture, leaf chlorophyll content, and leaf photosynthetic properties, which interact with each other. Identifying factors that restrict canopy photosynthesis and target adjustments to improve canopy photosynthesis in a specific crop cultivar pose an important challenge for the breeding community. To address this challenge, we developed a novel pipeline that utilizes factorial analysis, canopy photosynthesis modeling, and phenomics data collected using a 64-camera multi-view stereo system, enabling the dissection of the contributions of different factors to differences in canopy photosynthesis between maize cultivars. We applied this method to 2 maize varieties, W64A and A619, and found that leaf photosynthetic efficiency is the primary determinant (17.5% to 29.2%) of the difference in A c between 2 maize varieties at all stages, and plant architecture at early stages also contribute to the difference in A c (5.3% to 6.7%). Additionally, the contributions of each leaf photosynthetic parameter and plant architectural trait were dissected. We also found that the leaf photosynthetic parameters were linearly correlated with A c and plant architecture traits were non-linearly related to A c . This study developed a novel pipeline that provides a method for dissecting the relationship among individual phenotypes controlling the complex trait of canopy photosynthesis.
Why it matches plant phenotyping methods64台カメラのマルチビュー・ステレオ計測によるフェノミクスデータと、キャノピー光合成モデル・因子分析を統合した新規パイプラインの開発が中心であり、植物形態形質とキャノピー光合成の関係を定量化している。
titleDevelopment of a Novel 3D Canopy Modeling Pipeline
Reproduction assets foundThe paper's Data Availability section explicitly deposits the authors' 3D canopy modeling pipeline source code and the FastTracer ray tracing software used for the canopy photosynthesis simulations, both on public GitHub repositories. No phenotype/image datasets are explicitly deposited.Code · publicThe source code used in this study is available for non-commercial use and the code can be downloaded from https://github.com/PlantSystemsBiology/3DCanopyModelOpen asset ↗PlantSystemsBiology/3DCanopyModellines:224-402Code · publicThe FastTracer software is available from https://github.com/PlantSystemsBiology/fastTracerPublicOpen asset ↗PlantSystemsBiology/fastTracerPubliclines:224-402Code / dataset availability confirmedEurope PMC · OpenAlex · checked 15 Sept 2026
Smart farming (SF) applications rely on robust and accurate computer vision systems. An important computer vision task in agriculture is semantic segmentation, which aims to classify each pixel of an image and can be used for selective weed removal. State-of-the-art implementations use convolutional neural networks (CNN) that are trained on large image datasets. In agriculture, publicly available RGB image datasets are scarce and often lack detailed ground-truth information. In contrast to agriculture, other research areas feature RGB-D datasets that combine color (RGB) with additional distance (D) information. Such results show that including distance as an additional modality can improve model performance further. Therefore, we introduce WE3DS as the first RGB-D image dataset for multi-class plant species semantic segmentation in crop farming. It contains 2568 RGB-D images (color image and distance map) and corresponding hand-annotated ground-truth masks. Images were taken under natural light conditions using an RGB-D sensor consisting of two RGB cameras in a stereo setup. Further, we provide a benchmark for RGB-D semantic segmentation on the WE3DS dataset and compare it with a solely RGB-based model. Our trained models achieve up to 70.7% mean Intersection over Union (mIoU) for discriminating between soil, seven crop species, and ten weed species. Finally, our work confirms the finding that additional distance information improves segmentation quality.
Why it matches plant phenotyping methods植物種の画素単位セグメンテーション用RGB-Dデータセットとベンチマークを構築し、植物識別・分離という表現型取得ワークフローを中心的に評価しているため。
abstractwe introduce WE3DS as the first RGB-D image dataset for multi-class plant species semantic segmentation in crop farming.
Reproduction assets foundThe paper's WE3DS RGB-D image dataset (2568 annotated images) and the authors' modified ESANet analysis code are publicly deposited on Zenodo (DOI 10.5281/zenodo.7457983), as stated in the experiments section. The MDPI supplementary file contains only tables (species list, depth accuracy, confusion matrices), not the影像Dataset · public024 × 512
20.6
27.0
37.7 †
34.2
11.5
RGB
1024 × 512
52.4
22.2
39.2 †
38.4
11.5
RGB-D
1024 × 512
59.1
19.2
85.8
55.3
18.5
D
1280 × 960
48.5
11.3
154.1
37.0
27.1
RGB
1280 × 960
70.1
11.0
156.1
46.8
27.1
RGB-D
1280 × 960
70.7
8.6
240.3
66.6
43.4
Information on the dataset and modified code of the ESANet can be found on our website https://doi.org/10.5281/zenodo.7457983 (accessed on 18 December 2022).
4.4. ResultsOpen asset ↗Zenodo · 10.5281/zenodo.7457983lines:69-146Code / dataset availability confirmedarXiv · OpenAlex · checked 15 Sept 2026
In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10 - 20 meters) is arguably needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map over the "Landes de Gascogne" forest in France, a large maritime pine plantation of 13,000 km$^2$ with flat terrain and intensive management. This area is characterized by even-aged and mono-specific stands, of a typical length of a few hundred meters, harvested every 35 to 50 years. Our deep learning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 with composite time averages as input to predict tree height derived from GEDI waveforms. The evaluation is performed with external validation data from forest inventory plots and a stereo 3D reconstruction model based on Skysat imagery available at specific locations. We trained seven different U-net models based on a combination of Sentinel-1 and Sentinel-2 bands to evaluate the importance of each instrument in the dominant height retrieval. The model outputs allow us to generate a 10 m resolution canopy height map of the whole "Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 m on the Test dataset. The best predictions were obtained using all available satellite layers from Sentinel-1 and Sentinel-2 but using only one satellite source also provided good predictions. For all validation datasets in coniferous forests, our model showed better metrics than previous canopy height models available in the same region.
Why it matches plant phenotyping methodsSentinel/GEDI等のリモートセンシング画像から樹冠高を推定する深層学習手法を開発し、外部データで検証しているため、植物形質取得法が中心である。
abstractwe developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map
Reproduction assets foundThe paper's primary phenotyping-relevant input is the GEDI L2A canopy height dataset (526,449 footprints over the Landes forest, 2020), explicitly downloaded from NASA's EarthDataSearch. This is a public, paper-specific sensor dataset directly used for the study's canopy height measurements and model training. No code,Dataset · publicwater bodies (Beck et al., 2020). Indeed, these
surfaces mirror the transmitted waveforms that have a pulse width of ~ 15 ns which
corresponds to a ~ 2.25 m wide waveform (Dubayah et al., 2020).
In total, 526,449 footprints from the GEDIv002 L2A product (Dubayah et al., 2021) were
downloaded from NASA’s EarthDataSearch website
(https://search.earthdata.nasa.gov/search) for this study, covering the entire area of interest
for 2020. Due to atmospheric perturbations, some waveforms could not be used to give
information on the vertical forest structure. Therefore, several filtering criteria were applied to
remove unusable waveforms: (1) When the quality_flag provided in the GEDI data was set toOpen asset ↗GEDIv002 L2Apdf-raw-page:6 lines:1-45Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Intelligent detection and localization of mature citrus fruits is a critical challenge in developing an automatic harvesting robot. Variable illumination conditions and different occlusion states are some of the essential issues that must be addressed for the accurate detection and localization of citrus in the orchard environment. In this paper, a novel method for the detection and localization of mature citrus using improved You Only Look Once (YOLO) v5s with binocular vision is proposed. First, a new loss function (polarity binary cross-entropy with logit loss) for YOLO v5s is designed to calculate the loss value of class probability and objectness score, so that a large penalty for false and missing detection is applied during the training process. Second, to recover the missing depth information caused by randomly overlapping background participants, Cr-Cb chromatic mapping, the Otsu thresholding algorithm, and morphological processing are successively used to extract the complete shape of the citrus, and the kriging method is applied to obtain the best linear unbiased estimator for the missing depth value. Finally, the citrus spatial position and posture information are obtained according to the camera imaging model and the geometric features of the citrus. The experimental results show that the recall rates of citrus detection under non-uniform illumination conditions, weak illumination, and well illumination are 99.55%, 98.47%, and 98.48%, respectively, approximately 2-9% higher than those of the original YOLO v5s network. The average error of the distance between the citrus fruit and the camera is 3.98 mm, and the average errors of the citrus diameters in the 3D direction are less than 2.75 mm. The average detection time per frame is 78.96 ms. The results indicate that our method can detect and localize citrus fruits in the complex environment of orchards with high accuracy and speed. Our dataset and codes are available at https://github.com/AshesBen/citrus-detection-localization.
Why it matches plant phenotyping methods収穫ロボット向けの位置検出が主目的だが、果実形状・姿勢・3D直径を画像から抽出し、精度を検証する技術開発が中心であり、再利用可能な植物器官形質の推定に該当する。
abstracta novel method for the detection and localization of mature citrus using improved You Only Look Once (YOLO) v5s with binocular vision is proposed.
Reproduction assets foundThe authors explicitly state that their citrus image dataset (4855 binocular image groups with depth maps) and analysis code are publicly available on GitHub, matching the allowed URL.Dataset · publicnt occlusion conditions in natural orchards. Future work will focus on few-shot learning and reduce the number of citrus fruits in the training dataset to improve citrus detection and localization.
Data availability statement
The original contributions presented in this study are publicly available. This data can be found here: https://github.com/AshesBen/citrus-detection-localization .
Author contributions
All authors contributed to the method and result of the study, dataset generation, model training and testing, analysis of results, and the drafting, revising, and approving of the contents of the manuscript.
Funding
We acknowledged support from the Natural Science Foundation of GuangdongOpen asset ↗AshesBen/citrus-detection-localizationlines:335-356Code · public98 mm, and the average errors of the citrus diameters in the 3D direction are less than 2.75 mm. The average detection time per frame is 78.96 ms. The results indicate that our method can detect and localize citrus fruits in the complex environment of orchards with high accuracy and speed. Our dataset and codes are available at https://github.com/AshesBen/citrus-detection-localization .
Keywords: citrus detection, citrus localization, binocular vision, YOLO v5s, loss function
status released display-pdf yes is-olf no is-manuscript no is-preprint no is-journal-matter no is-scanned no is-retracted no
Received 2022 Jun 18; Accepted 2022 Jul 12; Collection date 2022.
IntroductionOpen asset ↗AshesBen/citrus-detection-localizationlines:1-28Code / dataset availability confirmedEurope PMC · OpenAlex · checked 8 Sept 2026
This work focuses on the problem of non-contact measurement for vegetables in agricultural automation. The application of computer vision in assisted agricultural production significantly improves work efficiency due to the rapid development of information technology and artificial intelligence. Based on object detection and stereo cameras, this paper proposes an intelligent method for vegetable recognition and size estimation. The method obtains colorful images and depth maps with a binocular stereo camera. Then detection networks classify four kinds of common vegetables (cucumber, eggplant, tomato and pepper) and locate six points for each object. Finally, the size of vegetables is calculated using the pixel position and depth of keypoints. Experimental results show that the proposed method can classify four kinds of common vegetables within 60 cm and accurately estimate their diameter and length. The work provides an innovative idea for solving the vegetable's non-contact measurement problems and can promote the application of computer vision in agricultural automation.
Why it matches plant phenotyping methods野菜の長さ・直径という植物器官形質を、ステレオカメラ、深度画像、キーポイント検出で非接触推定する手法が研究の中心であるため。
abstractThis work focuses on the problem of non-contact measurement for vegetables in agricultural automation.
Reproduction assets foundThe authors publicly released both the vegetable keypoint dataset (1600 COCO-format images with ROI boxes and six keypoints) and the implementation code for their size estimation method on GitHub. Labelme is a generic third-party annotation tool and is excluded.Code · publicThe implementation code of our size estimation method can be accessed on https://github.com/BourneZ130/VegetableDetection , accessed on 15 February 2022.Open asset ↗BourneZ130/VegetableDetectionlines:76-141Code / dataset availability confirmedOpenAlex · Europe PMC · checked 10 Sept 2026
Recent advances in high throughput phenotyping have made it possible to collect large datasets following plant growth and development over time, and those in machine learning have made inferring phenotypic plant traits from such datasets possible. However, there remains a dirth of datasets following plant growth under stress conditions along with methods for inferring them using only remotely sensed data, especially under a combination of multiple stress factors such as drought, weeds and nutrient deficiency. Such stress factors and their combinations are commonly encountered during crop production and being able to accurately detect and treat such stress conditions in an automated and timely manner can provide a major boost to farm yields with minimal resource input. We present a generic framework for remote plant stress phenotyping that consists of a dataset with spatio-temporal-spectral data following sugarbeet crop growth under optimal, drought, low and surplus nitrogen fertilization, and weed stress conditions, along with a machine learning based methodology for systematically inferring these stress conditions from the remotely measured data. The dataset contains biweekly color images, infra-red stereo image pairs and hyperspectral camera images along with applied treatment parameters and environmental factors like temperature and humidity, collected over two months. We present a plant agnostic methodology for deriving plant trait indicators such as canopy cover, height, hyperspectral reflectance and vegetation indices along with a spectral 3D reconstruction of the plants from the raw data to serve as a benchmark. Additionally, we provide fresh and dry weight measurements for both the above (canopy) and below (beet) ground biomass at the end of the growing period to serve as indicators of expected yield. We further describe a data driven, machine learning based method to infer water, Nitrogen and weed stress using the derived plant trait indicators. We use the plant trait indicators to evaluate 8 different classification approaches from which the best classifier achieved a mean cross validation accuracy of $$\approx$$ 93, 76 and 83% for drought, nitrogen and weed stress severity classification respectively. We also show that our multi-modal approach significantly improves classifier performance over using any single modality. The presented framework and dataset can serve as a valuable reference for creating and comparing processing pipelines which extract plant trait indicators and infer prevalent stress factors from remote sensing data under a variety of environments and cropping conditions. These techniques can then be deployed on farm machinery or robots enabling automated, precise and timely corrective interventions for maximising yield.
Why it matches plant phenotyping methods植物ストレス表現型を推定するデータセット、マルチモーダル画像・分光計測、形質抽出、機械学習推定を一体化した汎用フレームワークであり、表現型取得・解析手法が研究の中心である。
abstractWe present a generic framework for remote plant stress phenotyping that consists of a dataset with spatio-temporal-spectral data
Reproduction assets foundThe paper releases its own plant stress phenotyping dataset (RGB, stereo IR, hyperspectral imagery, reference measurements) and accompanying pre-processing/classification software, both publicly available at author-provided URLs.Dataset · publicThe images and reference data that support the findings of this study are available from ETH Zürich ASL Datasets Repository, “ https://projects.asl.ethz.ch/datasets/doku.php?id=2018plantstressphenotyping ”.Open asset ↗ETH Zürich ASL Datasets Repository · 2018plantstressphenotypinglines:367-481Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 14 Sept 2026
In this paper we report on an automated procedure to capture and characterize the detailed structure of a crop canopy by means of stereo imaging. We focus attention specifically on the detailed characteristic of canopy height distribution-canopy shoot area as a function of height-which can provide an elaborate picture of canopy growth and health under a given set of conditions. We apply the method to a wheat field trial involving ten Australian wheat varieties that were subjected to two different fertilizer treatments. A novel camera self-calibration approach is proposed which allows the determination of quantitative plant canopy height data (as well as other valuable phenotypic information) by stereo matching. Utilizing the canopy height distribution to provide a measure of canopy height, the results compare favourably with manual measurements of canopy height (resulting in an R2 value of 0.92), and are indeed shown to be more consistent. By comparing canopy height distributions of different varieties and different treatments, the methodology shows that different varieties subjected to the same treatment, and the same variety subjected to different treatments can respond in much more distinctive and quantifiable ways within their respective canopies than can be captured by a simple trait measure such as overall canopy height.
Why it matches plant phenotyping methodsステレオ画像による作物キャノピー構造・高さ分布の自動取得法を開発し、手動測定と比較検証しているため、植物表現型取得が中心である。
abstractwe report on an automated procedure to capture and characterize the detailed structure of a crop canopy by means of stereo imaging
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。Dataset · publicThe sub-dataset for land-based crop phenotyping using stereo images can be downloaded from https://sourceforge.net/projects/land-based-crop-phenotyping/ , which includes images of all 60 plots and their depth maps on 23 Sept 2016 and 11 Oct 2016. These data are sufficient to validate the results presented in this paper.Open asset ↗sourceforge · land-based-crop-phenotypinglines:135-142Code / dataset availability confirmedEurope PMC · Crossref · checked 14 Sept 2026
The arrangement of leaf material is critical in determining the light environment, and subsequently the photosynthetic productivity of complex crop canopies. However, links between specific canopy architectural traits and photosynthetic productivity across a wide genetic background are poorly understood for field grown crops. The architecture of five genetically diverse rice varieties-four parental founders of a multi-parent advanced generation intercross (MAGIC) population plus a high yielding Philippine variety (IR64)-was captured at two different growth stages using a method for digital plant reconstruction based on stereocameras. Ray tracing was employed to explore the effects of canopy architecture on the resulting light environment in high-resolution, whilst gas exchange measurements were combined with an empirical model of photosynthesis to calculate an estimated carbon gain and total light interception. To further test the impact of different dynamic light patterns on photosynthetic properties, an empirical model of photosynthetic acclimation was employed to predict the optimal light-saturated photosynthesis rate ( P max ) throughout canopy depth, hypothesizing that light is the sole determinant of productivity in these conditions. First, we show that a plant type with steeper leaf angles allows more efficient penetration of light into lower canopy layers and this, in turn, leads to a greater photosynthetic potential. Second the predicted optimal P max responds in a manner that is consistent with fractional interception and leaf area index across this germplasm. However, measured P max , especially in lower layers, was consistently higher than the optimal P max indicating factors other than light determine photosynthesis profiles. Lastly, varieties with more upright architecture exhibit higher maximum quantum yield of photosynthesis indicating a canopy-level impact on photosynthetic efficiency.
Why it matches plant phenotyping methodsステレオカメラによる3D植物再構成を用いてイネの群落構造形質を取得し、光環境・光合成との関係を解析しており、表現型取得ワークフローが研究の中心である。
abstractRay tracing was employed to explore the effects of canopy architecture on the resulting light environment in high-resolution
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。Supplement · publicSupplementary Table S2
Physiological characteristics of the 15 parental MAGIC lines + IR64 used in the initial screening . All measurements, apart from harvest dry weight and seed dry weight, were taken 55–60 days after transplanting (DAT), corresponding to the vegetative growth stage.Open asset ↗lines:538-570