Amodal Segmentation and Trait Extraction of On-Branch Soybean Pods with a Synthetic Dual-Mask Dataset.

Abstract

We address the challenge that occlusions in on-branch soybean images impede accurate pod-level phenotyping. We propose a lab on-branch pipeline that couples a prior-guided synthetic data generator (producing synchronized visible and amodal labels) with an amodal instance segmentation framework based on an improved Swin Transformer backbone with a Simple Attention Module (SimAM) and dual heads, trained via three-stage transfer (synthetic excised → synthetic on-branch → few-shot real). Guided by complete (amodal) masks, a morphology-driven module performs pose normalization, axial geometric modeling, multi-scale fused density mapping, marker-controlled watershed, and topological consistency refinement to extract seed per pod (SPP) and geometric traits. On real on-branch data, the model attains Visible Average Precision (AP) 50/75 of 91.6/77.6 and amodal AP50/75 of 90.1/74.7, and incorporating synthetic data yields consistent gains across models, indicating effective occlusion reasoning. On excised pod tests, SPP achieves a mean absolute error (MAE) of 0.07 and a root mean square error (RMSE) of 0.26; pod length/width achieves an MAE of 2.87/3.18 px with high agreement (R 2 up to 0.94). Overall, the co-designed data-model-task pipeline recovers complete pod geometry under heavy occlusion and enables non-destructive, high-precision, and low-annotation-cost extraction of key traits, providing a practical basis for standardized laboratory phenotyping and downstream breeding applications.

Plant phenotyping relevance

大豆莢の遮蔽下形状を画像から復元し、種子数や幾何形質を抽出する画像解析パイプラインを開発・評価しており、植物表現型取得が中心である。

Code and data availability

The supplied blocks describe a synthetic dual-mask soybean pod dataset, an amodal segmentation model, and a trait-extraction pipeline, but contain no data availability statement, no public dataset/model/code deposit, and no author-provided URLs beyond ORCID profiles and the CC BY license link. The only URLs present (OR

No evidence-backed public reproduction asset is currently recorded.