Railway Track Surface Defect Detection Based on Wavelet Convolution and Scale Dynamic Loss

To address the challenges in multi-scale defect detection on railway track surfaces—such as the high likelihood of missing tiny defects, weak anti-interference capability in complex environments, and poor scale adaptability—this paper proposes a WTConv-YOLOv11 detection model based on wavelet convolution and scale dynamic loss, specifically tailored for embedded scenarios in intelligent inspection robots. By embedding a wavelet convolution module, the model leverages multi-frequency decomposition characteristics to enhance multi-scale defect feature extraction, effectively compensating for the shortcomings of traditional convolution in detail extraction and limited receptive fields. Meanwhile, a Scale Dynamic Loss (SD Loss) function is introduced to adaptively adjust regression weights according to defect scales, significantly reducing multi-scale target localization deviations and Intersection over Union (IoU) fluctuations. Experiments conducted on a real-world railway dataset comprising 2396 track defect images demonstrate that the proposed model achieves mean Average Precision (mAP)@0.5 of 82.56%, which is 12.16 percentage points higher than the original YOLOv11. With an inference speed of 99 FPS, the model balances high accuracy with real-time performance. Real-world testing further verifies the model’s robustness under strong light, shadows, and water stains, providing effective technical support for intelligent unmanned railway inspection.