基于改进YOLOv8n的轻量化路面裂缝检测算法

打开文本图片集

中图分类号：TP391.4；U416 文献标志码：A

本文引用格式：，霈，峰.基于改进YOLOv8n的轻量化路面裂缝检测算法[J].华东交通大学学报，2025，42（3））：117-126.

Lightweight Road Crack Detection Algorithm Based on Improved YOLOv8n

Yang Ye¹²，Xu Pei²，Xu Feng²

（1.TheKeyLaboratoryofRoadandTraficEngineeing，MinistryofEducation，TongjiUniversityShanghai2804，Cina; 2.ChinaMerchantsChongqingCommunicationsTechnologyResearch&Design InstituteCo.，LTD.，Chongqing4067，China）

Abstract： To address the limitations in detection accuracy and inference speed in current road crack detection models，this paper proposes a novel YOLOv8-Crack network model. Based on YOLOv8n，this model incorporates multiple key structural optimizations，including the introduction of the NWD lossfunction to reduce dependency on aspect ratios of bounding boxes，thus improving detection capability for irregularly shaped cracks.The Slimneck lightweight structure is used to significantly reduce the number of parameters and computational complexity of the model，and accelerate the inference speed.The model also integrates a CA module to enhance the capture of critical feature information.Experimental results on the open-source dataset RDD202 demonstrate that the YOLOv8-Crack model achieves improvements over the original YOLOv8n，with precision，recalland mean average precision increased by 1.8% ， 3.7% ，and 2.6% ; respectively， while parameters and computation are reduced by 6.7% and 11.0% ：

Key Words： YOLOv8n; pavement cracks; attention mechanism; lightweight network; loss function

Citation format：YANG Y，XUP，XUF.Lightweight roadcrack detectionalgorithm based onimproved YOLOv8n[J]. Journal ofEast China JiaotongUniversity，2025，42（3）：117-126.

路面裂缝和坑槽等道路病害直接影响交通安全和道路的使用寿命。（剩余12497字）