This contribution presents an algorithm for visual detection and tracking of multiple extended targets which is capable of coping with merged, split, incomplete and missed detections. Informations will be utilized about the measurements composition gained by tracking dedicated feature points in the image and in 3D space which allows to reconstruct the desired object characteristics from the data even in the case of detection errors due to limited field of view, occlusions and sensor malfunction. The proposed feature-based probabilistic data association approach resolves data association ambiguities in a soft threshold-free decision based not only on target state prediction but also on the existence and observability estimation modelled as two additional Markov chains. This process is assisted by a grid based object representation, which offers a higher abstraction level of targets extents and is used for detailed occlusion analysis.
Data association for visual multi-target tracking under splits, merges and occlusions
Datenzuordnung für eine visuelle Verfolgung von Mehrzielen bei fehlerhafter, vermengter und unvollständiger Information
2009
8 Seiten, 8 Quellen
Aufsatz (Konferenz)
Englisch
Tracking Cell Splits and Merges
British Library Conference Proceedings | 1996
|Systems and methods for navigating lane merges and lane splits
Europäisches Patentamt | 2020
|SYSTEMS AND METHODS FOR NAVIGATING LANE MERGES AND LANE SPLITS
Europäisches Patentamt | 2022
|SYSTEMS AND METHODS FOR NAVIGATING LANE MERGES AND LANE SPLITS
Europäisches Patentamt | 2021
|SYSTEMS AND METHODS FOR NAVIGATING LANE MERGES AND LANE SPLITS
Europäisches Patentamt | 2020
|