重庆大学学报2024，Vol.47Issue(9)：91-100,10.DOI:10.11835/j.issn.1000-582X.2023.101
改进YOLOv5s的桥梁表观病害检测方法
Apparent disease detection of bridges using improved YOLOv5s
摘要
Abstract
To solve the problems of low accuracy,high false detection rate,and high missed detection rate in current target detection methods for apparent diseases in concrete bridges,an improved YOLOv5s method is proposed. To achieve more effective fusion of features at different scales and increase receptive fields,an improved spatial pyramid pooling module is added to the YOLOv5s network to enhance feature extraction capabilities and reduce computational cost;a light-weight attention module is incorporated into the YOLOv5s network to tackle the high false detection and missed detection rates caused by the cross-distribution of different defect features in disease images;and a loss function considering vector angles is adopted to solve the problems related to varying defect sizes,classification difficulties and small dataset-induced boundary box regression mismatches. Experimental results show that the improved YOLOv5s detector significantly improves accuracy while reducing false detection and missed detection rates in the task of detecting apparent diseases in bridges.关键词
病害检测/YOLOv5s/特征融合/平均精度Key words
disease detection/YOLOv5s/feature fusion/mean average accuracy分类
信息技术与安全科学引用本文复制引用
董绍江,谭浩,刘超,胡小林..改进YOLOv5s的桥梁表观病害检测方法[J].重庆大学学报,2024,47(9):91-100,10.基金项目
国家自然科学基金资助项目(51775072) （51775072）
重庆市科技创新领军人才支持计划项目(CSTCCCXLJRC201920) （CSTCCCXLJRC201920）
重庆市高校创新研究群体(CXQT20019).Supported by National Natural Science Foundation of China(51775072),the Chongqing Science and Technology Innovation Leading Talents Support Program(CSTCCCXLJRC201920),and the Chongqing University Innovation Research Group(CXQT20019). （CXQT20019）
