YOLOv8-PCD: a pavement crack detection method based on enhanced feature fusion

With deep learning prevailing in intelligent transportation systems, pavement crack detection using object detection has aroused wide attentions in both academic research and engineering application. Unfortunately, it still a challenge to focus on pavement critical areas and perceive crack at different scales due to the complexity in traffic background. To improve feature extraction and fusion capabilities, a pavement crack detection method named YOLOv8-PCD is proposed in this paper based on enhanced feature fusion. Firstly, the Biformer attention mechanism is incorporated into the network to enhance its performance in handling pavement objects at varying scales. Secondly, the Neck network is upgraded to BiFPN to better integrate crack features from different levels, thereby improving the detection capabilities. Finally, the experiments verify the proposed method could accomplish satisfactory result in both robustness and accuracy.