Title :
Real-time stereo vision for urban traffic scene understanding
Author :
Franke, U. ; Joos, A.
Author_Institution :
DaimlerChrysler AG, Stuttgart, Germany
Abstract :
This paper presents a precise correlation-based stereo vision approach that allows real-time interpretation of traffic scenes and autonomous Stop&Go on a standard PC. The high speed is achieved by means of a multiresolution analysis. It delivers the stereo disparities with sub-pixel accuracy and allows precise distance estimates. Traffic applications using this method are described
Keywords :
computer vision; correlation methods; microcomputer applications; real-time systems; road traffic; stereo image processing; traffic engineering computing; autonomous Stop&Go; correlation-based stereo vision; multiresolution analysis; precise distance estimates; real-time interpretation; real-time stereo vision; standard PC; stereo disparities; sub-pixel accuracy; urban traffic scene understanding; Cameras; Cities and towns; Hardware; Image edge detection; Intelligent vehicles; Layout; Motion detection; Motion estimation; Stereo vision; Visualization;
Conference_Titel :
Intelligent Vehicles Symposium, 2000. IV 2000. Proceedings of the IEEE
Conference_Location :
Dearborn, MI
Print_ISBN :
0-7803-6363-9
DOI :
10.1109/IVS.2000.898354
