软件导刊2024，Vol.23Issue(12)：206-212,7.DOI:10.11907/rjdk.232259
基于改进Yolov5s的路面裂缝病害检测与识别研究
Research on Detection and Identification of Pavement Crack Diseases Based on Improved Yolov5s
摘要
Abstract
Highway pavement cracks are an important influencing factor in asphalt pavement diseases,and pavement crack detection is an im-portant part of pavement maintenance.A pavement crack disease detection model based on improved Yolov5s is proposed to address the prob-lems of missed detections,false detections,and low recognition accuracy in detection algorithms for highway pavement cracks.Firstly,the at-tention mechanism module CBAM is adopted to learn target features and positional features,and to increase useful feature weights;Secondly,the Decoupled decoupling head method is proposed to separate the feature maps through different branches for processing,in order to improve training accuracy;Finally,an improved α DIoU loss function is proposed to replace the CIoU loss function in the original model,and α=3 is selected to enhance the loss gradient value of the high IoU object and the regression effect of the box.The experiment shows that the improved model has an average detection accuracy of 92.8%,a recall rate of 94.5%,and an mAP value of 96.5%,which is 1.8%higher than the origi-nal model.This proves that the improved model has a high improvement effect on detection accuracy and can meet the recognition and detec-tion tasks of highway pavement cracks.关键词
路面裂缝检测/Yolov5s/注意力机制/解耦头/损失函数Key words
road crack detection/Yolov5s/attention mechanism/decoupling head/loss function分类
信息技术与安全科学引用本文复制引用
陈修贤,高焕兵,杨志强,孔滕广,车仁海..基于改进Yolov5s的路面裂缝病害检测与识别研究[J].软件导刊,2024,23(12):206-212,7.基金项目
国家自然科学基金项目(61903227) （61903227）
山东省自然科学基金项目(ZR2022MF267) （ZR2022MF267）
