Road defect detection algorithm based on improved YOLOv8
GAO Panshuan
JI Houling
XU Mingsheng
ZHANG Le
LI Gang
CHEN Lin
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.
Keywords：road defect detectionattention mechanismfeature fusionsmall-object detectionYOLOv8
Publication Date：2025-12-30
Online Publishing Date：2026-02-02(First online date of this platform, not the publication date of the document)
Pages：9( 147-155 )