YOLO-ROC: a high-precision and ultra-lightweight model for real-time road damage detection
Zicheng Lin, Weichao Pan
Abstract
Abstract Road damage detection is a critical task for ensuring traffic safety and maintaining infrastructure integrity. While deep learning-based detection methods are now widely adopted, they still face two core challenges: first, the inadequate multi-scale feature extraction capabilities of existing networks for diverse targets like cracks and potholes, leading to high miss rates for small-scale damage; and second, the substantial parameter counts and computational demands of mainstream models, which hinder their deployment for efficient, real-time detection in practical applications. To address these issues, this paper proposes a high-precision and lightweight model, Y ou O nly L ook O nce- R oad O rthogonal C ompact ( YOLO-ROC ). We designed a B idirectional M ulti- s cale S patial P yramid P ooling F ast (BMS-SPPF) module to enhance multi-scale feature extraction and implemented a hierarchical channel compression strategy to reduce computational complexity. The BMS-SPPF module leverages a bidirectional spatial-channel attention mechanism to improve the detection of small targets. Concurrently, the channel compression strategy reduces the parameter count from 3.01 M to 0.89 M and giga floating-point operations per second (GFLOPs) from 8.1 to 2.6. Experiments on the RDD2022-China Drone dataset demonstrate that YOLO-ROC achieves a mAP50 of 67.6%, surpassing the baseline YOLOv8n by 1.4%. Notably, the recall rate for the small-target D40 category improved by 19%, and the final model size is only 2.0 MB. Furthermore, the model exhibits excellent generalization performance on the RDD2022-China Motorbike dataset.