A Unified Light Framework for Real-time Fault Detection of Freight Train Images

TL;DR

This paper introduces a lightweight, real-time fault detection framework for freight train images that significantly improves accuracy and efficiency using a novel backbone and multi-scale detection techniques.

Contribution

It proposes a unified, low-resource framework with a new lightweight backbone and multi-region proposal network for enhanced freight train fault detection.

Findings

Achieves over 38 frames per second in real-time detection.

Significantly improves detection accuracy over baseline models.

Requires less computation than state-of-the-art detectors.

Abstract

Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements. Despite the promising results for deep learning based approaches, the performance of these fault detectors on freight train images, are far from satisfactory in both accuracy and efficiency. This paper proposes a unified light framework to improve detection accuracy while supporting a real-time operation with a low resource requirement. We firstly design a novel lightweight backbone (RFDNet) to improve the accuracy and reduce computational cost. Then, we propose a multi region proposal network using multi-scale feature maps generated from RFDNet to improve the detection performance. Finally, we present multi level position-sensitive score maps and region of interest pooling to further improve accuracy with few redundant computations. Extensive experimental results on public benchmark datasets suggest that our RFDNet can significantly improve the performance of baseline network with higher accuracy and efficiency. Experiments on six fault datasets show that our method is capable of real-time detection at over 38 frames per second and achieves competitive accuracy and lower computation than the state-of-the-art detectors.