AUTHOR=Mi Zengzhen , Chen Ren , Zhao Shanshan TITLE=Research on steel rail surface defects detection based on improved YOLOv4 network JOURNAL=Frontiers in Neurorobotics VOLUME=Volume 17 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2023.1119896 DOI=10.3389/fnbot.2023.1119896 ISSN=1662-5218 ABSTRACT=The surface images of steel rails are extremely difficult to detect and recognize due to the presence of interference such as light changes and texture background clutter during the acquisition process. To improve the accuracy of railway defects detection, a deep learning algorithm is proposed to detect the rail defects. Aiming at the problems of inconspicuous rail defects edges, small size and background texture interference, the rail region extraction, improved Retinex image enhancement, background modeling difference and threshold segmentation are performed sequentially to obtain the segmentation map of defects. For the classification of defects, Res2Net and CBAM attention mechanism are introduced to improve the receptive field and small target position weights. The bottom-up path enhancement structure is removed from the PANet structure to reduce the parameter redundancy and enhance the feature extraction of small targets. The results show the average accuracy of rail defects detection reaches 92.68%, the recall rate reaches 92.33%, and the detection speed reaches 0.068 per image. comparing the improved method with the mainstream target detection algorithms such as Faster RCNN, SSD, YOLOv3, and YOLOv4, the improved YOLOv4 model obviously better than several others in Pr, Rc, and F1 value, and can be well applied to rail defect detection projects.