Lightweight decoder U-net crack segmentation network based on depthwise separable convolution

Cracks are a common type of damage found on the surfaces of concrete buildings and roads. Accurately identifying the width and direction of these cracks is critical for maintaining and evaluating such structures. However, challenges such as irregular crack shapes and complex background interference persist in the crack identification task. To address these challenges, we propose a semantic segmentation network for cracks (DSU-Net) based on U-Net. A lightweight decoder is built through depthwise separable convolution to reduce model complexity and better retain the high-level features extracted by the encoder. Three modules are designed to improve the performance of the model. First, a feature enhancement module (DCM) that combines CBAM and squeeze excitation (cSE) is constructed to further enhance and optimize the intermediate features extracted by the encoder. Secondly, a neighboring layer information fusion module (NIF) is constructed to enrich the semantic information of extracted features. Finally, a feature refinement module (FRM) is constructed using multi-layer convolutional skip connections to make the final refinement of the features extracted by the model. Experiments were conducted using three datasets: DeepCrack, Crack500, and CCSS. The segmentation effect was tested, and nine models were used for comparative experiments. The test results showed an average improvement of 1.29% and 1.89% in the three datasets compared to the suboptimal models MIoU and F1, respectively.