A Multi-Camera Image Processing and Visualization System for Train Safety Assessment

TL;DR

This paper introduces a multi-camera machine vision system designed to monitor trains for safety by automatically analyzing imagery for wagon ID, temperature, and pantograph detection, aiding operators in fault detection.

Contribution

The paper presents a novel multi-camera system integrating high-rate visible and thermal cameras with advanced algorithms for train safety assessment, including wagon ID, temperature, and pantograph detection.

Findings

Effective wagon identification and temperature monitoring demonstrated.

System successfully detects and visualizes pantographs in real-time.

Potential to improve railway safety through automated visual analysis.

Abstract

In this paper we present a machine vision system to efficiently monitor, analyze and present visual data acquired with a railway overhead gantry equipped with multiple cameras. This solution aims to improve the safety of daily life railway transportation in a two- fold manner: (1) by providing automatic algorithms that can process large imagery of trains (2) by helping train operators to keep attention on any possible malfunction. The system is designed with the latest cutting edge, high-rate visible and thermal cameras that ob- serve a train passing under an railway overhead gantry. The machine vision system is composed of three principal modules: (1) an automatic wagon identification system, recognizing the wagon ID according to the UIC classification of railway coaches; (2) a temperature monitoring system; (3) a system for the detection, localization and visualization of the pantograph of the train. These three machine vision modules process batch trains sequences and their resulting analysis are presented to an operator using a multitouch user interface. We detail all technical aspects of our multi-camera portal: the hardware requirements, the software developed to deal with the high-frame rate cameras and ensure reliable acquisition, the algorithms proposed to solve each computer vision task, and the multitouch interaction and visualization interface. We evaluate each component of our system on a dataset recorded in an ad-hoc railway test-bed, showing the potential of our proposed portal for train safety assessment.