A rail defect detection framework under class-imbalanced conditions based on improved you only look once network

In real rail operations, defects that can lead to serious accidents occur at very low frequencies, resulting in sample scarcity and class imbalances in rail defect datasets. Under imbalanced conditions, rail defect detection models tend to be biased toward majority classes and ignore minority classes, which further leads to inaccurate defect detection results. Therefore, a two-stage rail defect detection framework based on a latent diffusion model (LDM) and an improved You Only Look Once (YOLO) network operating under imbalanced conditions is proposed. This framework aims to enhance the detection performance achieved on imbalanced defect datasets through data augmentation and model improvements. First, the LDM is used to generate many defects with extremely small sample sizes and provide high-quality generated samples to expand the original imbalanced dataset. Furthermore, a coordinate attention module and a feature fusion module are integrated into the original YOLO version 8 (YOLOv8) model to improve its detection capabilities on imbalanced datasets. The coordinate attention mechanism enhances its focus on the positional information of various defects, whereas the feature fusion module enhances its ability to fuse the multiscale features of different defects. The results of the case study demonstrate that sample generation and filtration can provide high-quality samples for dataset augmentation purposes, alleviating the impact of minority defects on the overall detection accuracy. The results of the comparison and ablation experiments show that the improved YOLOv8 model has better detection performance than that of the comparison methods due to its introduction of coordinate attention and feature fusion modules.