Railway intrusion seriously threatens railway safety and can cause enormous loss of life and property. Therefore, railway intrusion detection is crucial for the safety of railway operation. Among the current methods of intrusion detection, machine vision-based methods have been widely used in railways, and have attracted close attention because of their great benefits. This paper proposes a comprehensive review of railway intrusion detection based on machine vision, covering ground monitoring, on-board inspection, and unmanned aerial vehicle (UAV) inspection. First, this paper systematically reviews most of the studies over the past two decades and presents the survey in three parts. Second, by analyzing these studies and the requirements for railway monitoring, we summarize the major challenges that hinder railway intrusion detection based on machine vision. Finally, we propose several promising perspectives for railway intrusion detection based on machine vision by comprehensively considering the development of machine vision, sensors, and pattern recognition together with the needs of railway scenes.

With the widespread use of face masks due to the COVID-19 pandemic, accurate masked face recognition has become more crucial than ever. While several studies have investigated masked face recognition using convolutional neural networks (CNNs), there is a paucity of research exploring the use of plain Vision Transformers (ViTs) for this task. Unlike ViT models used in image classification, object detection, and semantic segmentation, the model trained by modern face recognition losses struggles to converge when trained from scratch. To this end, this paper initializes the model parameters via a proxy task of patch reconstruction and observes that the ViT backbone exhibits improved training stability with satisfactory performance for face recognition. Beyond the training stability, two strategies based on prompts are proposed to integrate holistic and masked face recognition in a single framework, namely FaceT. Along with popular holistic face recognition benchmarks, several open-sourced masked face recognition benchmarks are collected for evaluation. Our extensive experiments demonstrate that the proposed FaceT performs on par or better than state-of-the-art CNNs on both holistic and masked face recognition benchmarks. Codes will be made available at https://github.com/zyainfal/Joint-Holistic-and-Masked-Face-Recognition.

Convolutional neural networks trained on large datasets can generalize various down-streaming tasks, including industrial anomaly detection and localization, which is critical in modern large-scale industrial manufacturing. Whereas previous methods have demonstrated that the feature fusion strategy across multiple layers is effective for better performance on industrial anomaly detection and localization, they lack flexibility in intervening and manipulating the local and global information composition process. Through experiments, we demonstrate that the brute-force feature fusion strategy used in previous methods leads to sub-optimal performance in most industrial anomaly detection scenarios. To this end, we propose a novel feature factorization and reversion framework based on invertible neural networks, enabling the selective emphasis or suppression of distinct information in a continuous space by request to fit various preferences for detecting different abnormalities. The preferred local and global info-combination for detecting different defects on 15 objects is studied by experiments exhaustively on the popular benchmark MVTec-AD. Based on feature factorization and reversion, our method is able to outperform previous state-of-the-art methods by a noticeable margin, achieving an image-level anomaly detection AUROC score of up to 99.67% (previously 99.4%), pixel-level anomaly localization AUROC score of 98.61% (previously 98.5%), and AUPRO of 95.15% (previously 94.6%), which validates the effectiveness of the proposed method for industrial anomaly detection and localization.

The transmission bandwidth of a vehicle–ground connection is low when an EMU (electric multiple unit) is running in a high-speed scenario. To this end, this paper focuses on the need to solve the problem of the poor bandwidth of the vehicle–ground integration information network, and proposes a vehicle–ground integration information network scheme for EMUs based on small base stations. Based on the existing wi-fi system of the EMU, in order to realize the coverage of the 5G signal in the carriage, this paper—through the deployment of the technical characteristics of 5G—sinks the customized UPF (user plane function) and MEC (mobile edge computing) to the train carriage, and expands the internet channels of the train carriage. Relying on the technologies of MEC and CDN (content delivery network) for high-speed railways, network extension service products can satisfy passengers’ needs around network rate and delay. On the one hand, this can relieve the pressure of the network backhaul and save the bandwidth resources of the vehicle–ground integration information network. On the other hand, it can help operators to reduce the investment of network construction, operation, and maintenance. As a result, the proposed scheme can inspire the products that match the extended service needs of the passenger, realize the technical and innovation value of the 5G mobile network, and achieve business model innovation in high-speed mobile scenarios.

The deformation monitoring system of railway infrastructure comes with many non-Gaussian behaviors. These behaviors are the typical fractional order characteristics which are hard to analyze by traditional methods. This paper presents a detail fractional order statistical theory to capture the key deformation feature and further achieve active warning of railway infrastructure. Initially, α-stable distribution is applied to reveal the non-Gaussian features hidden in the monitored time series. Then, long-range correlation and multifractal properties are extracted by the fractional order statistical method. After that, a novel fractional Bi-long short term memory model (F-BiLSTM) capture long-term trends characteristic and simulate stochastic process of the monitoring system. The proposed method is used to predict the deformation of railway infrastructure and obtained the superior prediction performances.

In this paper, the classification for kinds and levels of accidents in Chinese railway is deeply analyzed, and a model of security and emergency management in Chinese railway is proposed. Then the system architecture, which includes net layer, hardware layer, data resource layer, information-processing layer, interface layer, business application layer, and access layer, is given.