Abstract
Pavement crack serves as a crucial indicator of road condition, directly associated with subsequent pavement deterioration. To address the demand for large-scale real-time pavement damage assessment, this study proposes a lightweight pavement damage detection model based on YOLOv5s (LPDD-YOLO). Initially, a lightweight feature extraction network, FasterNet, is adopted to reduce the number of parameters and computational complexity. Secondly, to mitigate the reduction in accuracy resulting from the usage of lightweight network, the attention-based downsampling module and the neural network cognitive module are introduced. These modules aim to enhance the feature extraction robustness and to eliminate interference from irrelevant features. In addition, considering the significant variation in aspect ratios and diverse morphologies of pavement damages, K-Means clustering and the deformable convolution module are employed. These mechanisms ensure dynamic anchor feature selection and extend the scope of deformation ability, respectively. According to the ablation experiment on a self-built dataset, LPDD-YOLO demonstrates notable improvements in both accuracy and efficiency compared to the original model. Specifically, the mAP increases by 4.1%, and the F1 score rises by 5.3%. Moreover, LPDD-YOLO can obtain a 47.3% reduction in parameters and a 54.4% decrease in GFLOPs. It is noteworthy that LPDD-YOLO achieves real-time and accurate damage detection, with a speed of up to 85 FPS. The effectiveness and superiority of LPDD-YOLO are further substantiated through comparisons with other state-of-the-art algorithms.