数字农科院2.0

PodNet: Pod real-time instance segmentation in pre-harvest soybean fields

文献类型： 外文期刊

作者： Shuo Zhou;Qixin Sun;Ning Zhang;Xiujuan Chai;Tan Sun

作者机构：

关键词： High-throughput field phenotyping;Instance segmentation;Pre-harvest dataset;Soybean pod

期刊名称： Plant Phenomics

ISSN： 2643-6515

年卷期： 2025 年 7 卷 2 期

页码：

收录情况： SCIE（2025版） ; ; EI（2025版） ; ; CSCD（2025-2026年度）

摘要： Noninvasive analysis of pod phenotypic traits under field conditions is crucial for soybean breeding research. However, previous pod phenotyping studies focused on postharvest materials or were limited to indoor scenarios, failing to generalize to real-field environments. To address these issues, this paper employs an instance segmentation approach for the precise extraction of the pod area from multiplant RGB images in preharvest soybean fields. We first introduce a cost-effective workflow for constructing datasets of densely planted crop images with a uniform backdrop. Starting with video recording, high-quality static frames are collected by automatic selection. Then, a large vision model is explored to facilitate dense annotation and build a large-scale soybean dataset comprising 20k pod masks. Second, the pod instance segmentation model PodNet is developed based on the YOLOv8 architecture. We propose a novel hierarchical prototype aggregation strategy to fuse multiscale semantic features and a U-EMA prototype generation network to improve the model's perception performance for small objects. Comprehensive experiments suggest that lightweight PodNet achieves a superior mean average accuracy of 0.786 in the custom pod segmentation dataset. PodNet also performs competitively on in-field images without a backdrop and enables real-time inference on the edge computing platform. To the best of our knowledge, PodNet is the first pod instance segmentation model for preharvest fields. The low-cost and high-precision extraction of pods is not only a prerequisite for phenotypic analysis of the pod organs but also constitutes an important foundation in conducting cross-scale phenotyping from whole-plant to seed levels.

分类号：

  • 相关文献

[1]Deep learning-based software and hardware framework for a noncontact inspection platform for aggregate grading. Jing Qin,Jiabao Wang,Tianjie Lei,Geng Sun,Jianwei Yue,Weiwei Wang,Jinping Chen,Guansheng Qian. 2023

[2]A synthetic datasets based instance segmentation network for High-throughput soybean pods phenotype investigation. Yang, Si,Zheng, Lihua,Yang, Huijun,Zhang, Man,Wu, Tingting,Sun, Shi,Tomasetto, Federico,Wang, Minjuan. 2022

[3]A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images. Ren Wei,Beilei Fan,Yuting Wang,Rongchao Yang. 2023

[4]Instance Segmentation and Number Counting of Grape Berry Images Based on Deep Learning. Yanmin Chen,Xiu Li,Mei Jia,Jiuliang Li,Tianyang Hu,Jun Luo. 2023

[5]Automatic grain unloading method for track-driven rice combine harvesters based on stereo vision. Cui Z.,Hu J.,Yu Y.,Cao G.,Zhang H.,Chai X.,Chen H.,Xu L.. 2024

[6]Multi-Scale Mixed Attention Tea Shoot Instance Segmentation Model. Chen, Dongmei,Cao, Peipei,Yan, Lijie,Chen, Huidong,Lin, Jia,Li, Xin,Yuan, Lin,Wu, Kaihua. 2024

[7]High-throughput soybean pods high-quality segmentation and seed-per-pod estimation for soybean plant breeding. Yang S.,Zheng L.,Wu T.,Sun S.,Zhang M.,Li M.,Wang M.. 2024

[8]Spatial-channel transformer network based on mask-RCNN for efficient mushroom instance segmentation. Wang, Jiaoling,Song, Weidong,Zheng, Wengang,Feng, Qingchun,Wang, Mingfei,Zhao, Chunjiang. 2024

作者其他论文 更多>>