Research on crack detection method for pavement based on improved YOLOv8

Abstract

Pavement crack detection plays a fundamental role in ensuring the safety, durability, and sustainable operation of urban transportation infrastructure. These factors often lead to missed detections and false detections in existing deep learning models. To address these challenges, this paper proposes an improved YOLOv8-based crack detection framework termed SCD-YOLO. The proposed method introduces two key improvements. First, ConvNeXt V2 is employed as the backbone network to enhance feature extraction capability, enabling more accurate representation of fine cracks and weak structural features. Second, an Efficient Multi-scale Attention (EMA) mechanism is integrated to suppress background interference and improve feature discrimination. Experiments conducted on the public dataset demonstrate that SCD-YOLO achieves a mAP@0.5 of 89.7%, precision of 90.3%, and recall of 90.3%, outperforming other methods. The proposed method achieves superior detection accuracy while maintaining real-time performance, providing a reliable and scalable solution for intelligent pavement inspection within city infrastructure systems.