Title :
Discrimination of the road condition toward understanding of vehicle driving environments
Author :
Yamada, Muneo ; Ueda, Koji ; Horiba, Isao ; Sugie, Noboru
Author_Institution :
Nagoya Electr. Works Co. Ltd., Aichi, Japan
fDate :
6/21/1905 12:00:00 AM
Abstract :
Detection of vehicle driving environments is necessary to secure transport facilities safe from accidents and to keep the performance smooth. Road condition is one of the most important factors toward the detection of vehicle driving environments. Conventional road condition discrimination methods involved the use of optical or ultrasonic sensors. However, since these sensors could only provide spot information, detected results do not always reflect the spacious condition. To deal with this problem, a new algorithm that employs image analysis technology for discrimination of the road condition is proposed in this paper. In this algorithm, for discrimination of the road condition, we focused on features related to water and snow on the road and we extracted these features by image analysis. Features related to water were extracted by the ratio of horizontal polarization image intensity to vertical polarization image intensity for each pixel. Features related to snow were extracted by texture analysis using the co-occurrence matrix. We employ a multivariate analysis to discriminate five kinds of the road conditions
Keywords :
accidents; computer vision; feature extraction; road vehicles; safety; traffic engineering computing; accidents; co-occurrence matrix; feature extraction; horizontal polarization image intensity; image analysis; multivariate analysis; pixel; road condition discrimination; safety; snow; texture analysis; vehicle driving environments; vertical polarization image intensity; water; Ice surface; Image texture analysis; Intelligent vehicles; Optical sensors; Road accidents; Road vehicles; Snow; Vehicle detection; Vehicle driving; Vehicle safety;
Conference_Titel :
Intelligent Transportation Systems, 1999. Proceedings. 1999 IEEE/IEEJ/JSAI International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-4975-X
DOI :
10.1109/ITSC.1999.821021