Abstract
The efficiency and the effectiveness of railway intrusion detection are crucial to the safety of railway transportation. Most current methods of railway intrusion detection or obstacle detection are inappropriate for large-scale applications due to their high cost or limited coverage. In this study, we present a fast and low-cost solution to intrusion detection of high-speed railways. As the solution to heavy computational burdens in the current convolutional-neural-network-based detection methods, the proposed method is mainly a novel neural network based on the SSD framework, which includes a feature extractor using an improved MobileNet and a lightweight and efficient feature fusion module. In addition, aiming to improve the detection accuracy of small objects, the feature map weights are introduced through convolution operation to fuse features at different scales. TensorRT is employed to optimize and deploy the proposed network in the low-cost embedded GPU platform, NVIDIA Jetson TX2, to enhance the efficiency. The experimental results show that the proposed methods achieved 89% mAP on the railway intrusion detection dataset, and the average processing time for a single frame was 38.6 ms on the Jetson TX2 module, which satisfies the need of real-time processing.
Highlights
The rapid development of railway transportation has led to more and more attention to railway safety
The experimental results show that the proposed methods achieved 89% mAP on the railway intrusion detection dataset, and the average processing time for a single frame was 38.6 ms on the Jetson TX2 module, which satisfies the need of real-time processing
To study the performance of the proposed method, the criterion of average precision (AP) was introduced, which depends on precision and recall
Summary
The rapid development of railway transportation has led to more and more attention to railway safety. Any obstacles or pedestrians intruding the railway track area are the major hazards to the safety and the security of the railway operations. The machine-vision-based intrusion detection methods have been increasingly popular, benefiting from the rapid development of deep learning [2,3,4,5,6,7,8,9,10,11]. Most early vision-based methods detect intruding objects with background subtraction methods, which have very poor detection effects due to lighting conditions or bad weather. The convolutional neural networks (CNNs) have achieved promising results in visual tasks such as image classification, image segmentation, and object detection for its benefits of strong comprehensiveness, activeness, and its capability of detecting and identifying multiple types of objects simultaneously
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
