Liu Fei, Liu Hang, Wu Qiong, Han Zhongzhi, Pang Shanchen, Wang Shudong, Zhao Longgang
Qingdao Agricultural University, Qingdao, 266109, China.
China University of Petroleum (East China), Qingdao, 266400, China.
Plant Methods. 2025 Jun 9;21(1):82. doi: 10.1186/s13007-025-01399-0.
Phenotypic characterization of mature soybean pods is a crucial aspect of breeding programs, yet efficiently obtaining accurate pod phenotypic parameters remains a major challenge. Recent advances in deep learning, particularly in keypoint detection models, have introduced innovative methods for pod phenotype extraction. However, precise identification and analysis of fine-scale phenotypic traits in soybean pods remain challenging in current research.
We propose Pod-pose, an innovative top-down keypoint detection model for precise soybean pod phenotyping that adapts human pose estimation techniques to plant phenotyping. Specifically, Pod-pose integrates the architectural strengths of various advanced YOLO (You Only Look Once) models through bottleneck structure optimization and positional feature enhancement to achieve superior detection accuracy. Furthermore, we implemented a two-stage detection method augmented with transfer learning, which not only reduces training complexity but also significantly enhances the model's performance. Extensive evaluation of our custom-built dataset demonstrated Pod-Pose's superior performance, with the X variant achieving an Average Precision of 0.912 at an IoU threshold of 0.5 (AP@IoU = 0.5). Notably, four critical pod-related phenotypic traits were successfully quantified: pod length, bending length, curvature, and inflection point width.
This study establishes Pod-Pose as a viable solution for pod phenotyping, with potential applications in soybean breeding optimization.
成熟大豆豆荚的表型特征描述是育种计划的关键方面，但有效地获取准确的豆荚表型参数仍然是一项重大挑战。深度学习的最新进展，特别是在关键点检测模型方面，为豆荚表型提取引入了创新方法。然而，在当前研究中，大豆豆荚中精细尺度表型特征的精确识别和分析仍然具有挑战性。
我们提出了Pod-pose，这是一种创新的自上而下的关键点检测模型，用于精确的大豆豆荚表型分析，它将人体姿态估计技术应用于植物表型分析。具体而言，Pod-pose通过瓶颈结构优化和位置特征增强，整合了各种先进YOLO（You Only Look Once）模型的架构优势，以实现卓越的检测精度。此外，我们实施了一种结合迁移学习的两阶段检测方法，这不仅降低了训练复杂度，还显著提高了模型的性能。对我们定制数据集的广泛评估证明了Pod-Pose的卓越性能，X变体在交并比阈值为0.5（AP@IoU = 0.5）时的平均精度达到0.912。值得注意的是，成功量化了四个与豆荚相关的关键表型特征：豆荚长度、弯曲长度、曲率和拐点宽度。
本研究将Pod-Pose确立为豆荚表型分析的可行解决方案，在大豆育种优化中具有潜在应用。
