Since the appearance changes of the target jeopardize visual measurements and often lead to tracking failure in practice, trackers need to be adaptive to non-stationary appearances or to dynamically select features to track. However, this idea is threatened by the risk of adaptation drift that roots in its ill-posed nature, unless good constraints are imposed. Different from most existing adaptation schemes, we enforce three novel constraints for the optimal adaptation: (1) negative data, (2) bottom-up pair-wise data constraints, and (3) adaptation dynamics. Substantializing the general adaptation problem as a subspace adaptation problem, this paper gives a closed-form solution as well as a practical iterative algorithm. Extensive experiments have shown that the proposed approach can largely alleviate adaptation drift and achieve better tracking results.
Tracking non-stationary appearances and dynamic feature selection
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) ; 2 ; 1059-1066 vol. 2
2005-01-01
911359 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Tracking Appearances with Occlusions
British Library Conference Proceedings | 2003
|Tracking appearances with occlusions
IEEE | 2003
|Corresponding dynamic appearances
British Library Online Contents | 2002
|Factorized appearances for object detection
British Library Online Contents | 2015
|