A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains

TL;DR

This paper introduces a lightweight, NMS-free vision-based fault detection system for freight trains that achieves real-time performance with high accuracy and low computational cost, enhancing railway safety.

Contribution

The authors propose a novel lightweight framework with a fault detection pyramid and loss functions that eliminate NMS, enabling faster and more efficient train fault detection.

Findings

Achieves over 83 FPS in real-time detection.

Smaller model size with higher accuracy than existing methods.

Low hardware resource requirements during training and testing.

Abstract

Real-time vision-based system of fault detection (RVBS-FD) for freight trains is an essential part of ensuring railway transportation safety. Most existing vision-based methods still have high computational costs based on convolutional neural networks. The computational cost is mainly reflected in the backbone, neck, and post-processing, i.e., non-maximum suppression (NMS). In this paper, we propose a lightweight NMS-free framework to achieve real-time detection and high accuracy simultaneously. First, we use a lightweight backbone for feature extraction and design a fault detection pyramid to process features. This fault detection pyramid includes three novel individual modules using attention mechanism, bottleneck, and dilated convolution for feature enhancement and computation reduction. Instead of using NMS, we calculate different loss functions, including classification and location costs in the detection head, to further reduce computation. Experimental results show that our framework achieves over 83 frames per second speed with a smaller model size and higher accuracy than the state-of-the-art detectors. Meanwhile, the hardware resource requirements of our method are low during the training and testing process.