As a result of long‐term pressure from train operations and direct exposure to the natural environment, rails, fasteners, and other components of railway track lines inevitably produce defects, which have a direct impact on the safety of train operations. In this study, a multiobject detection method based on deep convolutional neural network that can achieve nondestructive detection of rail surface and fastener defects is proposed. First, rails and fasteners on the railway track image are localized by the improved YOLOv5 framework. Then, the defect detection model based on Mask R‐CNN is utilized to detect the surface defects of the rail and segment the defect area. Finally, the model based on ResNet framework is used to classify the state of the fasteners. To verify the robustness and effectiveness of our proposed method, we conduct experimental tests using the ballast and ballastless railway track images collected from Shijiazhuang‐Taiyuan high‐speed railway line. Through a variety of evaluation indexes to compare with other methods using deep learning algorithms, experimental results show that our method outperforms others in all stages and enables effective detection of rail surface and fasteners.

Rail surface defect detection is vital for railway safety. Traditional methods falter with varying defect sizes and complex backgrounds, while two-stage deep learning models, though accurate, lack real-time capabilities. To overcome these challenges, we propose an enhanced one-stage detection model based on CenterNet. We replace ResNet with ResNeXt and implement a multi-branch structure for better low-level feature extraction. Additionally, we integrate SKNet attention mechanism with the C2f structure from YOLOv8, improving the model’s focus on critical image regions and enhancing the detection of minor defects. We also introduce an elliptical Gaussian kernel for size regression loss, better representing the aspect ratio of rail defects. This approach enhances detection accuracy and speeds up training. Our model achieves a mean accuracy (mAP) of 0.952 on the rail defects dataset, outperforming other models with a 6.6% improvement over the original and a 35.5% increase in training speed. These results demonstrate the efficiency and reliability of our method for rail defect detection.

Loosening detection; cascade deep convolutional neural network; object localization; saliency detection problem of bolts on axlebox covers. Firstly, an SSD network based on ResNet50 and CBAM module by improving bolt image features is proposed for locating bolts on axlebox covers. And then, the A²-PFN is proposed according to the slender features of the marker lines for extracting more accurate marker lines regions of the bolts. Finally, a rectangular approximation method is proposed to regularize the marker line regions as a way to calculate the angle of the marker line and plot all the angle values into an angle table, according to which the criteria of the angle table can determine whether the bolt with the marker line is in danger of loosening. Meanwhile, our improved algorithm is compared with the pre-improved algorithm in the object localization stage. The results show that our proposed method has a significant improvement in both detection accuracy and detection speed, where our mAP (IoU = 0.75) reaches 0.77 and fps reaches 16.6. And in the saliency detection stage, after qualitative comparison and quantitative comparison, our method significantly outperforms other state-of-the-art methods, where our MAE reaches 0.092, F-measure reaches 0.948 and AUC reaches 0.943. Ultimately, according to the angle table, out of 676 bolt samples, a total of 60 bolts are loose, 69 bolts are at risk of loosening, and 547 bolts are tightened.

Regular fastener detection is necessary to ensure the safety of railways. However, the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways. Existing supervised inspection methods have insufficient detection ability in cases of imbalanced samples. To solve this problem, we propose an approach based on deep convolutional neural networks (DCNNs), which consists of three stages: fastener localization, abnormal fastener sample generation based on saliency detection, and fastener state inspection. First, a lightweight YOLOv5s is designed to achieve fast and precise localization of fastener regions. Then, the foreground clip region of a fastener image is extracted by the designed fastener saliency detection network (F-SDNet), combined with data augmentation to generate a large number of abnormal fastener samples and balance the number of abnormal and normal samples. Finally, a fastener inspection model called Fastener ResNet-8 is constructed by being trained with the augmented fastener dataset. Results show the effectiveness of our proposed method in solving the problem of sample imbalance in fastener detection. Qualitative and quantitative comparisons show that the proposed F-SDNet outperforms other state-of-the-art methods in clip region extraction, reaching MAE and max F-measure of 0.0215 and 0.9635, respectively. In addition, the FPS of the fastener state inspection model reached 86.2, and the average accuracy reached 98.7% on 614 augmented fastener test sets and 99.9% on 7505 real fastener datasets.

Rail-fastening components are essential for ensuring the safety of urban rail systems by securing rails to sleepers. Traditional inspection methods rely heavily on manual labor and are inefficient. This paper introduces a novel approach to address these inefficiencies and the challenges faced by computer vision-based inspections, such as missed detections due to imbalanced samples and limitations in conventional image segmentation techniques. Our approach transitions the industry’s focus from qualitative to a more precise quantitative analysis of rail-fastening components. We propose Mask-FRCN, an advanced image segmentation network that incorporates three key technological enhancements: the fully refined convolutional network module (FRCN),which refines the segmentation boundaries for SFC-type fasteners; the Channel-WiseKnowledge Distillation (CWD) algorithm, which boosts the model’s inference efficiency; and the FCRM methodology, which enhances the extraction capabilities for features specific to SFC-type fasteners. Furthermore, we introduce a fastener system inspection and quantization method based on the Mask FRCN method (FIQ), a novel technique for quantifying the condition of components by using image features, template matching with random forests, and a clustering calculation method derived from segmentation results. Experimental results validate that our method significantly surpasses existing techniques in accuracy, thereby offering a more efficient solution for inspecting rail-fastening components. The enhanced Mask-FRCN achieves a segmentation accuracy of 96.01% and a reduced network size of 36.1 M. Additionally, the FIQ method improves fault detection accuracy for SFC-type fasteners to 95.13%, demonstrating the efficacy and efficiency of our innovative approach.