Jia Youdong, Zhang Yuhang, Yang Rui, Li Xinzhi, Li Zhengfang, Yao Sibo, Zeng Jiaxing, Zhu Ziyue, Zhang Yuanxin
Faculty of Mechanical and Electrical Engineering, Kunming University, Kunming, 650214, People's Republic of China.
Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, 650500, People's Republic of China.
Sci Rep. 2025 Jul 2;15(1):23170. doi: 10.1038/s41598-025-02683-8.
In recent years, the detection of non-ferrous metals in end-of-life vehicles (ELVs) has become essential for improving recycling in the circular economy. Traditional methods struggle with accurate detection due to the variety of metals and challenging industrial environments. This study proposes a Hybrid-YOLOv5-based algorithm for efficiently detecting copper, aluminum, and stainless steel in ELVs. The goal is to enhance detection accuracy and computational efficiency in metal sorting. By integrating the Coarse-to-Fine (C2F) module, Squeeze-and-Excitation (SE) module, and MobileNetV3 backbone, we significantly improve performance and speed. On a dataset of 2,500 infrared images, Hybrid-YOLOv5 achieves 84.2% mAP@0.5 and 60 FPS inference speed, outperforming YOLOv3, YOLOv5, YOLOv7, and YOLOv11 by 22.2%, 12.4%, 11.1%, and 36.2% in mAP@0.5, respectively. This work provides an efficient solution for industrial metal sorting and intelligent recycling in the circular economy.
近年来，报废汽车（ELV）中有色金属的检测对于改善循环经济中的回收利用至关重要。由于金属种类繁多且工业环境具有挑战性，传统方法在准确检测方面面临困难。本研究提出了一种基于混合YOLOv5的算法，用于高效检测报废汽车中的铜、铝和不锈钢。目标是提高金属分选的检测精度和计算效率。通过集成粗到细（C2F）模块、挤压与激励（SE）模块和MobileNetV3主干，我们显著提高了性能和速度。在一个包含2500张红外图像的数据集上，混合YOLOv5实现了84.2%的mAP@0.5和60 FPS的推理速度，在mAP@0.5方面分别比YOLOv3、YOLOv5、YOLOv7和YOLOv11高出22.2%、12.4%、11.1%和36.2%。这项工作为循环经济中的工业金属分选和智能回收提供了一种有效的解决方案。
