Ma Baojian, Wu Zhenghao, Ge Yun, Chen Bangbang, Zhang He, Xia Hao, Wang Dongyun
Department of Mechanical and Electrical Engineering, Xinjiang Institute of Technology, Aksu 843100, China.
College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, China.
Sensors (Basel). 2025 Aug 5;25(15):4820. doi: 10.3390/s25154820.
Accurate identification of picking points remains a critical challenge for automated marigold harvesting, primarily due to complex backgrounds and significant pose variations of the flowers. To overcome this challenge, this study proposes SCS-YOLO-Seg, a novel method based on a lightweight segmentation model. The approach enhances the baseline YOLOv8n-seg architecture by replacing its backbone with StarNet and introducing C2f-Star, a novel lightweight feature extraction module. These modifications achieve substantial model compression, significantly reducing the model size, parameter count, and computational complexity (GFLOPs). Segmentation efficiency is further optimized through a dual-path collaborative architecture (Seg-Marigold head). Following mask extraction, picking points are determined by intersecting the optimized elliptical mask fitting results with the stem skeleton. Experimental results demonstrate that SCS-YOLO-Seg effectively balances model compression with segmentation performance. Compared to YOLOv8n-seg, it maintains high accuracy while significantly reducing resource requirements, achieving a picking point identification accuracy of 93.36% with an average inference time of 28.66 ms per image. This work provides a robust and efficient solution for vision systems in automated marigold harvesting.
准确识别采摘点仍然是自动万寿菊采摘面临的一项关键挑战，主要原因在于背景复杂以及花朵姿态变化显著。为克服这一挑战，本研究提出了SCS-YOLO-Seg，这是一种基于轻量级分割模型的新方法。该方法通过用StarNet替换其主干并引入新型轻量级特征提取模块C2f-Star来增强基线YOLOv8n-seg架构。这些改进实现了模型的大幅压缩，显著减小了模型大小、参数数量和计算复杂度（GFLOPs）。通过双路径协作架构（Seg-Marigold头）进一步优化了分割效率。在提取掩码后，通过将优化后的椭圆掩码拟合结果与茎干骨架相交来确定采摘点。实验结果表明，SCS-YOLO-Seg有效地平衡了模型压缩与分割性能。与YOLOv8n-seg相比，它在显著降低资源需求的同时保持了高精度，实现了93.36%的采摘点识别准确率，平均每张图像的推理时间为28.66毫秒。这项工作为自动万寿菊采摘中的视觉系统提供了一个强大而高效的解决方案。
