Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination ($R^2$) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding.

Accurate and efficient soybean yield prediction is essential for ensuring food security and optimizing agricultural management. Remote-sensing approaches based on a single phenological stage or sensor may not fully capture the physiological and structural dynamics associated with soybean yield formation, thereby constraining prediction accuracy under field-level spatial heterogeneity. This study therefore developed and evaluated an integrated multi-source and multi-temporal UAV-based framework for plot-scale soybean yield prediction under production-field conditions. A UAV platform equipped with multispectral, RGB, and LiDAR sensors was used to extract multidimensional remote-sensing features at four key growth stages: beginning pod, full seed, beginning maturity, and full maturity. By integrating spectral indices, texture metrics, and three-dimensional canopy structural parameters, seven machine-learning algorithms—Ridge, LASSO, Random Forest, MLP, LightGBM, XGBoost, and CatBoost—were evaluated under single-temporal and multi-temporal scenarios. Nonlinear tree-based ensemble models generally achieved higher predictive accuracy than the linear models. On the independent test set, CatBoost performed best under the full multi-temporal, three-sensor fusion scenario, with an R² of 0.816 and an RMSE of 245 kg ha⁻¹. Among individual growth stages, the full seed stage (R6) produced the highest single-stage prediction accuracy. Three-sensor fusion improved prediction relative to the single-source multispectral scheme, and integrating features across phenological stages further improved performance by representing cumulative crop-growth dynamics. The proposed framework provides methodological support for UAV-based precision management and data-driven decision-making in soybean production.

Accurate estimation of the number of emerged soybean seedlings is critical for field production management. However, existing methods struggle to achieve rapid and precise counting due to several challenges: variation among varieties, differences in growth stage, large variations in object scale, and complex backgrounds. To address these challenges, we constructed a dataset of UAV images of multiple soybean varieties at the seedling stage and developed a lightweight detection model named SSDNet. The main innovations of this model include replacing the YOLOv11n backbone with StarNet to improve performance while maintaining efficiency; introducing a C3k2-PFDConv module to extract fine-grained features at multiple scales; incorporating a lightweight shared convolution detection head to reduce computational redundancy; and adopting slicing-aided inference to process high-resolution imagery. Experimental results show that SSDNet achieves 98.7% mAP@50 with only 1.57 M parameters and an inference time of 5.4 ms per image. When combined with SAHI, it completes detection in high-resolution imagery covering 675 breeding plots in 9.8 min. Across the 300 validation plots, the method achieved an absolute counting error of no more than 7 seedlings per plot relative to manual field counts. In summary, SSDNet enables accurate and efficient soybean seedling counting under the breeding field conditions and UAV image acquisition protocol tested in this study, providing technical support for emergence assessment in breeding fields.