Title :
Image based obstacle detection for automatic train supervision
Author :
Yao, Tingting ; Dai, Shenghua ; Wang, Pei ; He, Yue
Author_Institution :
School of Electronics and Information Engineering, Beijing Jiaotong University, China
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.
Keywords :
Automatic Train Supervision; Canny operator; binary image; detection window; gray histogram; machine vision; obstacle detection; wireless communication;
Conference_Titel :
Image and Signal Processing (CISP), 2012 5th International Congress on
Conference_Location :
Chongqing, Sichuan, China
Print_ISBN :
978-1-4673-0965-3
DOI :
10.1109/CISP.2012.6469703