In concrete structures, surface cracks are an important indicator for assessing the durability and serviceability of the structure. Existing convolutional neural networks for concrete crack identification are inefficient and computationally costly. Therefore, a new Cross Swin transformer-skip (CSW-S) is proposed to classify concrete cracks. The method is optimized by adding residual links to the existing Cross Swin transformer network and then trained and tested using a dataset with 17,000 images. The experimental results show that the improved CSW-S network has an extended range of extracted image features, which improves the accuracy of crack recognition. A detection accuracy of 96.92% is obtained using the trained CSW-S without pretraining. The improved transformer model has higher recognition efficiency and accuracy than the traditional transformer model and the classical CNN model.

Cracks that occur in concrete surfaces are numerous and diverse, and different cracks will affect road safety in different degrees. Accurately identifying pavement cracks is crucial for assessing road conditions and formulating maintenance strategies. This study improves the original U-shaped convolutional network (U-Net) model through the introduction of two innovations, thereby modifying its structure, reducing the number of parameters, enhancing its ability to distinguish between background and cracks, and improving its speed and accuracy in crack detection tasks. Additionally, datasets with different exposure levels and noise conditions are used to train the network, broadening its predictive ability. A custom dataset of 960 road crack images was added to the public dataset to train and evaluate the model. The test results demonstrate that the proposed U-Net-FML model achieves high accuracy and detection speed in complex environments, with MIoU, F₁ score, precision, and recall values of 76.4%, 74.2%, 84.2%, and 66.4%, respectively, significantly surpassing those of the other models. Among the seven comparison models, U-Net-FML has the strongest overall performance, highlighting its engineering value for precise detection and efficient analysis of cracks.

An improved YOLOv8 model, YOLOv8‐NETC, is proposed in this study for fine‐grained crack recognition through instance segmentation. YOLOv8‐NETC is designed and enhanced with four self‐developed modules. First, ablation studies were conducted to assess the effectiveness of each module. The model’s accuracy and speed were evaluated based on parameters such as mean average precision (mAP50) and model weight (MW). The experimental results show significant improvements in accuracy, storage efficiency, and processing speed. Compared to the original network, YOLOv8‐NETC achieved a 6.5% increase in mAP50, a 6.1% average reduction in MW and parameters, and an 8.5% improvement in FPS. Subsequently, YOLOv8‐NETC was compared with other state‐of‐the‐art models across three datasets, including the crack type dataset, crack trueness dataset, and the public Crack500 dataset. The experimental results demonstrate that the proposed model achieved the best recognition performance on all datasets. Furthermore, YOLOv8‐NETC showed superior robustness against interference and computational efficiency compared to other benchmark models.