Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Association of motion verbs with vehicle movements extracted from dense optical flow fields

: Kollnig, H.; Nagel, H.-H.; Otte, M.


Eklundh, J.-O.:
Computer Vision. ECCV '94. Proceedings. Vol.2
Berlin: Springer, 1994 (Lecture Notes in Computer Science 801)
ISBN: 3-540-57957-5
ISSN: 0302-9743
pp.338-347 : Abb.,Tab.,Lit.
European Conference on Computer Vision (ECCV) <3, 1994, Stockholm>
Conference Paper
Fraunhofer IITB ( IOSB) ()
image evaluation; image sequence; moving object; natural language; optical flow; traffic scene

This contribution addresses the problem of detection and tracking of moving vehicles in image sequences from traffic scenes recorded by a stationary camera. By replacing the low level vision system component for the estimation of displacement vectors by an optical flow estimation module we are able to detect all moving vehicles in our test image sequence. By replacing the edge detector and by doubling the sampling rate we improve the model-based object tracking system significantly compared to an earlier system. The trajectories of vehicles are characterized by motion verbs and verb phrases. Results from various experiments with real world traffic scenes are presented.