Deep learning-based 3D morphological segmentation and quantitative growth analysis of field-grown cabbage across the full cycle.

Abstract

Monitoring the growth dynamics in field-grown cabbage is critically important for ensuring stable vegetable production and advancing precision agricultural management. However, conventional two-dimensional (2D) image-based monitoring approaches are limited to planar projection information and lack representations of spatial structural characteristics, rendering them inadequate for supporting high-precision, full-cycle phenotypic monitoring of cabbage under open-field conditions. In this study, a high-precision three-dimensional (3D) point cloud dataset covering the period from the seedling stage to maturity was constructed using depth cameras in conjunction with multi-view spatial registration techniques. Building on this dataset, an adaptive point cloud segmentation network designed for the whole-cycle growth monitoring was proposed, incorporating a Head Refinement Module (HRM), a Leaf Instance Segmentation Module (LISM), and Cross Module Interaction (CMI) to address leaf adhesion and head boundary delineation. Experimental results demonstrated that the proposed method consistently outperformed state-of-the-art models in both semantic and instance segmentation tasks. For semantic segmentation, the mean Intersection over Union (mIoU) reached 0.767, with a point classification accuracy of 94.8%. The model comprises 54.25 million parameters and achieves an average response time of 0.76 s. For instance segmentation, the Average Precision (AP) improved by 2.3% for cabbage heads and 3.8% for leaves, while the Average Recall (AR) increased by 6.9%. Growth parameters, including plant height and canopy spread, extracted from the segmentation results showed strong agreement with ground-truth measurements, with correlation of coefficients (R 2 ) exceeding 0.9 for plant height, canopy length, and canopy width. Leveraging these multidimensional phenotypic descriptors, the temporal dynamics of cabbage growth throughout the entire growth cycle were systematically characterized. Overall, this study enables dynamic monitoring of cabbage phenotypes across the full growth cycle, providing a novel technical pathway for extending 3D phenotyping from controlled environments to open-field applications and offering important support for precise crop monitoring and the development of digital twin agriculture.

Plant phenotyping relevance

3D点群データセット、セグメンテーションネットワーク、形質抽出を開発・検証し、圃場キャベツの草高や冠幅を定量化する植物フェノタイピング手法が研究の中心である。

Code and data availability

The paper's authors publicly release their improved OneFormer3D point cloud segmentation code on GitHub; the cabbage 3D point cloud dataset is only available upon request.