北京交通大学学报2025，Vol.49Issue(6)：147-155,9.DOI:10.11860/j.issn.1673-0291.20240134
基于改进YOLOv8的道路病害检测算法
Road defect detection algorithm based on improved YOLOv8
摘要
Abstract
To address the limitations of existing road defect detection algorithms,such as low accuracy in complex backgrounds,limited generalization capability,and frequent missed detections of small ob-jects,this study proposes an improved YOLOv8-based detection algorithm.First,a Coordinate Atten-tion(CA)mechanism is integrated into the backbone network layer to introduce positional informa-tion,enabling the model to better capture spatial dependencies and enhancing its feature discrimination ability under complex background conditions.Second,the Path Aggregation Network(PANet)in the neck network layer is replaced with a weighted Bi-directional Feature Pyramid Network(BiFPN).By incorporating bidirectional connections and learnable weights,the network facilitates bidirectional in-formation flow across different resolution levels,leading to more effective fusion of low-level posi-tional features with high-level semantic features and improving multi-scale feature representation.Fi-nally,small-object feature maps are introduced to more accurately capture the small-object characteris-tics and reduce missed detections,thereby improving detection precision.Experimental results show that on the RDD2022 road defect dataset,the improved algorithm increases mean Average Precision(mAP)by 3.1%compared to the original version,while reducing model parameters by 2.3%,achiev-ing more accurate and rapid road defect detection.关键词
道路病害检测/注意力机制/特征融合/小目标检测/YOLOv8Key words
road defect detection/attention mechanism/feature fusion/small-object detection/YOLOv8分类
信息技术与安全科学引用本文复制引用
郜潘栓,姬厚灵,徐明升,张乐,李刚,陈琳..基于改进YOLOv8的道路病害检测算法[J].北京交通大学学报,2025,49(6):147-155,9.基金项目
湖北省自然科学基金(2024AFB851) Natural Science Foundation of Hubei Province(2024AFB851) （2024AFB851）
