DocumentCode
3310415
Title
Fast obstacle detection using flow/depth constraint
Author
Heinrich, S.
Author_Institution
DaimlerChrysler AG, Ulm, Germany
Volume
2
fYear
2002
fDate
17-21 June 2002
Firstpage
658
Abstract
The early recognition of potentially harmful traffic situations is an important goal of vision based driver assistance systems. Pedestrians, in particular children, are highly endangered in inner city traffic. Within the DaimlerChrysler UTA (Urban Traffic Assistance) project, we are using stereo vision and motion analysis in order to manage those situations. The flow/depth constraint combines both methods in an elegant way and leads to a robust and powerful detection scheme.
Keywords
automotive electronics; computer vision; image motion analysis; object detection; stereo image processing; DaimlerChrysler UTA project; Urban Traffic Assistance project; children; fast obstacle detection; flow/depth constraint; inner city traffic; motion analysis; pedestrians; stereo vision; vision based driver assistance systems; Cities and towns; Image motion analysis; Motion analysis; Motion detection; Motion estimation; Object detection; Road accidents; Robustness; Stereo vision; Vehicles;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Vehicle Symposium, 2002. IEEE
Print_ISBN
0-7803-7346-4
Type
conf
DOI
10.1109/IVS.2002.1188026
Filename
1188026
Link To Document