Research on steel rail surface defects detection based on improved YOLOv4 network

Abstract

IntroductionThe 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.MethodsTo 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.ResultsThe results show the average accuracy of rail defects detection reaches 92.68%, the recall rate reaches 92.33%, and the average detection time reaches an average of 0.068 s per image, which can meet the real-time of rail defects detection.DiscussionComparing the improved method with the mainstream target detection algorithms such as Faster RCNN, SSD, YOLOv3 and other algorithms, the improved YOLOv4 has excellent comprehensive performance for rail defects detection, 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.

Imbalanced Anomaly Detection Using Augmented Deeper FCDDs for Wooden Sleeper Deterioration Prognostics

“…2 depicts several railway inspection applications that utilize deep learning models for the detection of defective classes of railway components. These applications are often based on supervised deep learning approaches such as classification (Alvarenga et al, 2021;Chandran, Asber, Thiery, Odelius, & Rantatalo, 2021) and object detection (Mi, Chen, & Zhao, 2023;Hsieh et al, 2020;Hsieh, Hsu, & Huang, 2022). In supervised learning studies, the authors assigned class labels by annotating whole images and bounding boxes that enclosed defective regions.…”

Strip steel surface defect detection based on lightweight YOLOv5

“…Li et al ( 2020 ) improved YOLOv3 by employing a weighted K-means clustering algorithm and introducing a large-scale detection layer, achieving an 80% increase in detection accuracy. Mi et al ( 2023 ) proposed a novel data augmentation method based on YOLOv4 to enhance the robustness and accuracy of the algorithm's detection capabilities. Liu et al ( 2023 ) designed the MSC-DNet model, which excels in pinpointing defects and significantly contributes to the accurate detection of medium and large-scale defects.…”

Editorial: Recent advances in image fusion and quality improvement for cyber-physical systems, volume II

“…Hence, studies in this field can be divided into two aspects: new end-to-end neural network models for merging constituent parts during the image fusion process and the embodiment of artificial neural networks for image processing systems. In addition, current booming techniques, including deep neural systems and embodied artificial intelligence systems, are considered potential future trends for reinforcing image fusion performance and quality improvement (Wang W. et al, 2022 ; Yang et al, 2022 ; Zhang et al, 2022 , 2023 ; Jin et al, 2023b ; Liu et al, 2023 ; Mi et al, 2023 ).…”