Image based obstacle detection for automatic train supervision

Abstract

This paper focuses on the track obstacle detection based on image processing, analyzes and improves the Image gray-scale algorithm, Image binarization algorithm, Canny edge detection algorithm, and designs the detection window to rule out the useless information. As a result, we come up with three obstacle detection algorithms based on image feature extraction and feature analysis: Method based on Gray Level Histogram, Method based on the Proportion of Black and White Pixels, Method based on the integrity of the Rails and Sleepers. Finally, we take use of the server/client distributed model to design an automatically track detection system, which uses wireless communications. Through the experiment, the desired results have been obtained.

Comparison of Filtering Methods for Enhanced Reliability of a Train Axle Counter System

“…An efficient crack (broken rail) detection system is proposed by Kumar et al [4] for better diagnostics and inspection. Research is also carried out in the direction of using obstacle detections systems (study for image processing presented by Yao and colleagues [5]). Nowadays, such systems are commercially used for monitoring lines (e.g., distributed acoustic sensing based on fiber optic technology) and level crossings (e.g., radars).…”