Research on tunnel defect detection based on YOLOv8 model

To enhance tunnel maintenance and traffic safety, this study implements automatic detection and identification of tunnel defects using the YOLOv8 model. By collecting defect image data from various tunnel environments and performing data preprocessing and annotation, the YOLOv8 model was constructed for defect detection. The results demonstrate that the YOLOv8 model achieves a precision of 0.87, a recall of 0.89, and an mAP50 of 0.87 on the test set, indicating excellent detection capabilities and accuracy. The model accurately identifies and locates defect types such as cracks, damage, and spalling. Visual analysis of the model's detection results confirms its ability to precisely locate and recognize various internal tunnel defects, further validating the model's stability and practicality. This research provides significant technical support for intelligent transportation and tunnel safety management, highlighting the importance of early identification and effective treatment of tunnel defects. It contributes to improving the safety and efficiency of tunnel operations.