Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

3D pose estimation by fitting image gradients directly to polyhedral models

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


Massachusetts Institute of Technology -MIT-, Cambridge/Mass.:
Fifth International Conference on Computer Vision 1995. Proceedings
Cambridge/Mass., 1995
ISBN: 0-8186-7042-8
S.569-574 : Abb.,Lit.
International Conference on Computer Vision (ICCV) <5, 1995, Cambridge>
Fraunhofer IITB ( IOSB) ()
Bildauswertung; Bildfolgenauswertung; IEKF; iteraktive extended Kalman filter; Iterativer erweiterter Kalman-Filter; Lageschätzung; model-based image sequence evaluation; modellgestützte Bildauswertung; Objekt; objekt tracking; Objektverfolgung; partial occlusion; partielle Verdeckung; pose estimation; road traffic; road vehicle model; Straßenfahrzeug; Straßenverkehr

This contribution addresses the problem of pose estimation and tracking of vehicles in image sequences from traffic scenes recorded by a stationary camera. In a new algorithm, the vehicle pose is estimated by directly fitting image gradients to polyhedral vehicle models without an edge segment extraction process. The new approach is significantly more robust than approaches that rely on feature extraction because the new approach exploits more information from the image data. We can track vehicles that are partially occluded by textured objects, e.g. foliage, where classical approaches based on edge segmentation extraction fail. Results from various experiments with real world traffic scenes are presented.