HCC-YOLO: A Lightweight Multilevel Feature Fusion Algorithm for Road Damage Detection

Abstract

Abstract In order to overcome the limitation of traditional road damage detection algorithms such as single detection type, real-time, and lightweight scenarios, a lightweight multilevel feature fusion algorithm HCC-You Only Look Once (HCC-YOLO) is proposed in this paper. First, improved HGNetv2 is adopted as a backbone network; a lightweight spatial attention module is integrated; activation function is optimized to enhance damage area location and spatial expression, and a very low-cost innovative module (SiGE) replaces C2PSA to improve feature enhancement efficiency. Secondly, a lightweight neck network CHP with deep optimization is designed to reduce redundancy through feature screening and cross-scale interaction and improve adaptability to complex scenes. Thirdly, a multitask lightweight task dynamic alignment detection head (LTADH) is proposed to enhance multiscale damage feature extraction by combining task decoupling and dynamic alignment. Experiments on RDD2022 data set show that the HCC-YOLO model reduces 61.82% in size, 44.44% in computation, and 66.67% in parameters (less than 1 M), while mAP@0.5 reaches 88.2%. (1.6% higher than the baseline module YOLOv11n). The algorithm model can be deployed on edge computing devices carried by drones to quickly detect cracks, potholes, and other damages on road surfaces, so as to repair roads in time, ensure road driving safety, and realize green, intelligent, and efficient operation and maintenance.