Abstract
Road cracks pose a significant safety hazard to transportation, making timely detection crucial for traffic safety. Traditional crack segmentation methods face three main issues: (1) Tree shadow background affects crack recognition in real-world environments. (2) Conventional convolutional neural networks fail to detect complete cracks. (3) Direct deconvolution during upsampling results in unclear crack details. To address these challenges, this paper proposes the WFU-Unet model for road crack detection and segmentation. First, the WCM module, constructed with wavelet transform, ConvNext, and MobileNet, reduces shadow interference, enabling the network to distinguish between cracks and tree shadows. Second, the Fuse module replaces traditional convolutional blocks, enhancing the network's ability to extract crack features. Finally, the Up module substitutes conventional upsampling techniques to minimize spatial information loss of cracks. Experimental results show that the WFU-Unet model achieves a Miou of 81.68%, precision of 91.43%, recall of 86.63%, and F1-Score of 88.93%. Compared to other models, WFU-Unet demonstrates superior generalization ability and segmentation accuracy, making it more suitable for crack detection in shadowed environments.