Region and Edge-Aware Network for Rail Surface Defect Segmentation

Rail surface defect segmentation can provide a reliable basis for the severity evaluation of rail diseases. Deep learning technology has been widely applied to segment rail surface defects due to its powerful feature representation ability. However, most of the existing deep learning-based methods often produce inaccurate defect region boundaries and unsatisfactory segmentation results due to the inadequate integration of contextual information and insufficient edge features. To tackle this problem, a novel region and edge-aware network (REA-Net) is proposed for rail surface defect segmentation in this article. REA-Net adopts an encoder-decoder framework, where the encoder network incorporates three modules: feature pyramid edge (FPE) module, multitask learning (MTL) module, and cross-level fusion (CLF) module, to encode richer context information and finer-grained features at each stage. The decoder network aggregates the encoding features from each stage to obtain decoding features, and finally, these features are used to predict the defect segmentation results. Extensive experiments are conducted on the expanded public rail surface defect dataset (RSDD) and the results demonstrate our proposed REA-Net achieves good segmentation performance and outperforms the state-of-the-art in terms of F1-scores and intersection over union (IoU).