Defect detection in multimedia data plays a pivotal role in industrial manufacturing. However, existing methods are primarily designed for closed-world scenarios and can only identify defect classes in the training data, limiting their ability to effectively detect unknown class defects that arise during production. To address this critical limitation, we propose a novel approach by introducing industrial defect open set recognition (IDOSR), which overcomes the challenge of recognizing unknown defect classes. Furthermore, to tackle the issues of limited training samples and subtle inter-class differences in IDOSR, we present a high-frequency feature enhancement open set recognition (HFFE-OSR) method. Specifically, HFFE-OSR employs a high-frequency structural feature fusion enhancement strategy to meticulously extract and fuse defect-related high-frequency structural features. This enables the network to comprehensively learn defect target representations even under limited training samples, resulting in robust feature extraction for known classes, thereby improving the discriminability between known and unknown classes and addressing the difficulty of distinguishing between them. Additionally, a class mutual information constraint strategy is introduced to measure and reduce the mutual information among defect features from different classes. This ensures the independence of defect features across known classes, further enhancing their discriminability and significantly improving recognition performance for known classes. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art OSR methods on ID-OSD and MVTec datasets, achieving improvements of at least 7% in accuracy (ACC), 22% in F1 score, and 10% in AUROC, highlighting the effectiveness of our approach in industrial defect detection.

Anomaly detection for rail running bands, the pattern of wheel–rail contact area, is crucial to analyze composite rail irregularities. This paper presents an all-weather vision-based solution for running-band inspection. However, two major algorithmic challenges restrict inspection effectiveness: 1) the identification of high-quality features for diversified and imbalanced data subject to noise and outliers, and 2) inferring implicit anomaly co-occurrence patterns. We regard overall running-band anomaly detection as a multi-label classification problem and develop a novel deep multi-anomaly recognition network via recurrent attention graphs (RAGRN). The proposed RAGRN consists of two fundamental components, each directly addressing the two major challenges of this paper: 1) Class-specific features are extracted for fine-grained discrimination via split-channel and gradient-guided class-specific attention mechanisms; 2) We develop a multi-anomaly classifier, which effectively captures long-distance correlation features via a recurrent attention graph with visual and statistical guidance for graph propagation, containing prior statistical and image-specific information. The experiments and statistical analyses demonstrate that RAGRN outperforms all related state-of-the-art frameworks and has the potential to be applied to practical inspection.

Fastener pixel-level detection can provide a reliable basis for the assessment of fastener defects and requires only normal samples. Deep learning technology has been widely used for fastener detection due to its powerful ability in feature extraction and self-learning. However, the performance of many existing deep learning-based methods still requires further improvement as they fall short in producing the accurate pixel-level detection, especially for the fasteners in complicated backgrounds. To tackle this challenge, a novel dual-stream detection network (DSD-Net) based on encoder-decoder architecture is proposed for fastener pixel-level detection. In encoding stage, the enhanced and emphasized features of fastener foreground can be obtained by the dual-stream (i.e., raw image stream and mask image stream) encoder embedding designed feature enhancement module and cascade residual pooling module. In decoding stage, the decoder aggregates the features from dual-stream encoder by the feature enhancement module with skip-connection to improve the final fastener pixel-level detection results. Numerous experiments on the constructed dataset demonstrate that DSD-Net achieves more remarkable detection performance (Precision of 96.54%, Recall of 97.62%, Accuracy of 96.46% and IoU of 94.32%) for fasteners against other state-of-the-arts.

Fast detection of fasteners is important to improve the efficiency of railroad maintenance. However, this task remains challenging due to the limited computing resources of inspection system. To solve the challenge, a new lightweight detection network Op-YOLOv4-tiny is proposed in this paper. The proposed network firstly uses ResBlock-N modules to replace the CSPBlock modules in YOLOv4-tiny to reduce the computation complexity. Then, a large scale feature map ($52\times 52$) is added to obtain more features of fasteners to improve the detection accuracy. Extensive experiments are conducted on the captured railway and subway track images and the results show that Op-YOLOv4-tiny has good performance in terms of detection accuracy and speed. In detail, the detection speed and accuracy reach 408 FPS and 96.8%, respectively. In addition, compared with other detection networks and state-of-the-arts, it achieves the better performance. Thus, our proposed Op-YOLOv4-tiny is with some potential industrial application value for fast detection of fasteners.

Vision-based anomaly inspection plays a crucial role in the efficient maintenance of millions of kilometers of railway, with rail segmentation, a key step in such anomaly detection for providing localization prior. However multi-type rails, those involved in crossings and connections, have highly variable patterns, greatly restricting the performance of standard (straight) rail segmentation methods. Semantic segmentation helps to deal with complex railway scenes and variable patterns, however the noise sensitivity, intra-class differences, and inter-class similarities still challenge the segmentation. Superpixel segmentation can aggregate local similar pixels with precise boundaries, which can offer a weak prior for semantic segmentation for boundary information modeling, intra-class aggregation, and inter-class differentiation, however how to integrate superpixel-level guidance to advance rail segmentation is still challenging. This paper proposes a two-stage transformer-Convolutional Neural Network (CNN)-based segmentation framework. The first stage, Attention-Based Superpixel Segmentation Sub-Network via Boundary Calibration (BCASN), generates railway superpixels by the learning of intra-superpixel consistency and boundary calibration to effectively fit rail boundaries and guide the second-stage rail segmentation. The second stage, Superpixel-Guided Multi-Type Rail Segmentation Sub-Network via Contextual Information Aggregation (CIASSN), captures railway semantics via global and cross-scale context construction, aggregates rail features via directional guidance and structured prior, and makes comprehensive segmentation decisions at superpixel and pixel scales with the learning of superpixel-level context and classification. The experiments demonstrate that the proposed solution achieves 98.71% overall accuracy, 98.44% mIoU, and 87.33% boundary recall in multi-type rail segmentation, significantly extends applicable scenarios, and outperforms all related state-of-the-art methods in rail and road segmentation.

Rail surface defect inspection based on machine vision faces challenges against the complex background with interference and severe data imbalance. To meet these challenges, in this article, we regard defect detection as a key-point estimation problem and present the proposed attention neural network for rail surface defect detection via consistency of Intersection-over-Union(IoU)-guided center-point estimation (CCEANN). The CCEANN contains two crucial components. The two components are the stacked attention Hourglass backbone via cross-stage fusion of multiscale features (CSFA-Hourglass) and the CASIoU-guided center-point estimation head module (CASIoU-CEHM). Furthermore, the CASIoU-guided center-point estimation head module integrating the delicate coordinate compensation mechanism regresses detection boxes flexibly to adapt to defects’ large-scale variation, in which the proposed CASIoU loss, a loss regressing the consistency of intersection-over-union (IoU), central-point distance, area ratio, and scale ratio between the targeted defect and the predicted defect, achieves higher regression accuracy than state-of-the-art IoU-based losses. The experiments demonstrate that the CCEANN outperforms competitive deep learning-based methods in four surface defect datasets.

This article aims to improve the performance of deep learning-based defective fastener inspection method. Due to the defective fasteners are insufficient and far less than the defect-free ones in real railway, it is difficult to train a robust fastener inspection model on such imbalanced dataset. In view of this problem, a novel image generation method called four-discriminator cycle-consistent adversarial network (FD-Cycle-GAN) is proposed to generate the defect fastener images using a large number of defect-free ones. Extensive experiments are conducted on the real fastener images and generated images. Experimental results demonstrate that the defect fastener images generated by our proposed method have better quality and richer diversity than those generated by other state-of-the-art methods. In addition, compared with the CNN-only baseline, the performance of the fastener inspection model trained on the expanded dataset containing the defect fastener images generated by FD-Cycle-GAN is improved significantly. The detection accuracy and relative IMP reach 93.25% and 21.59% respectively.

Visual inspection techniques for rail surface defects have become prevalent approaches to obtain information on rail surface damage. However, uneven illumination leads to illegibility of local information, and the change of the wheel-rail area results in the changeful background of the rail surface, both of which pose challenges to the visual inspection. This paper proposes a novel algorithm that detects rail surface defects via partitioned edge features (PEF). PEF eliminates the effect of uneven illumination by effectively extracting edge features and building homogeneous background on the rail surface. In the process of edge feature extraction, the thresholding based on adaptive partition of rail surface (APRS) plays an indispensable role. In APRS, the rail surface is adaptively partitioned into three types of regions according to the wheel-rail contact degree. After that, the dynamic threshold is set adaptively for each region type on the basis of the prior information of defect proportion. Subsequently, based on neighborhood information and fuzzy decision, the spatial information of adjacent pixels and the direction information of fracture edges are utilized to realize the effective recovery of incomplete defect contours. In addition, defect contours are precisely filled via a flexible combination of morphological hole filling operation and defect region extraction based on improved background difference. The accuracy of this PEF algorithm was confirmed by experiments and comparisons with related algorithms. The experiment results show that PEF detects defects with 92.03% recall and 88.49% precision, which achieves higher accuracy than the established detection algorithms for rail surface defects.