DocumentCode :
3319757
Title :
Vision-based vehicle detection in the nighttime
Author :
Kuo, Ying-Che ; Chen, Hsuan-Wen
Author_Institution :
Dept. of Electr. Eng., Nat. Chin-Yi Univ. of Technol., Taiping, Taiwan
Volume :
2
fYear :
2010
fDate :
5-7 May 2010
Firstpage :
361
Lastpage :
364
Abstract :
In this paper, we present a vision-based vehicle detection method for collision warning of driver assistance system on highway in the nighttime. The major function of our work is to find preceding vehicles in the dynamic background. The system captures the image of road environment by a camera mounted on the windshield of the test car and uses multi-level image processing algorithms to extract taillights of preceding vehicles and identify the proceeding vehicles by taillight clustering processing. At the same time, it estimates the related distance between the test car and the preceding vehicle for collision warning. In our experiments, the system is implemented on an embedded system with Linux operation system, open source codes and limited hardware resources. With the results of our experiments, it shows that the system can correctly verify the proceeding vehicles in the nighttime under the real-time requirement.
Keywords :
automobiles; driver information systems; embedded systems; feature extraction; object detection; vision; Linux operation system; driver assistance system; embedded system; highway; multilevel image processing; open source codes; taillight clustering processing; taillight extraction; vehicle collision warning; vision based vehicle detection; Automotive components; Cameras; Clustering algorithms; Image processing; Road accidents; Road transportation; Road vehicles; System testing; Vehicle detection; Vehicle dynamics; Driver Assistance; Night Vision; Vehicle Detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Communication Control and Automation (3CA), 2010 International Symposium on
Conference_Location :
Tainan
Print_ISBN :
978-1-4244-5565-2
Type :
conf
DOI :
10.1109/3CA.2010.5533451
Filename :
5533451
Link To Document :
بازگشت