Sciweavers

ECCV
2002
Springer

Towards Improved Observation Models for Visual Tracking: Selective Adaptation

14 years 6 months ago
Towards Improved Observation Models for Visual Tracking: Selective Adaptation
Abstract. An important issue in tracking is how to incorporate an appropriate degree of adaptivity into the observation model. Without any adaptivity, tracking fails when object properties change, for example when illumination changes affect surface colour. Conversely, if an observation model adapts too readily then, during some transient failure of tracking, it is liable to adapt erroneously to some part of the background. The approach proposed here is to adapt selectively, allowing adaptation only during periods when two particular conditions are met: that the object should be both present and in motion. The proposed mechanism for adaptivity is tested here with a foreground colour and motion model. The experimental setting itself is novel in that it uses combined colour and motion observations from a fixed filter bank, with motion used also for initialisation via a Monte Carlo proposal distribution. Adaptation is performed using a stochastic EM algorithm, during periods that meet the...
Andrew Blake, Jaco Vermaak, Michel Gangnet, Patric
Added 16 Oct 2009
Updated 16 Oct 2009
Type Conference
Year 2002
Where ECCV
Authors Andrew Blake, Jaco Vermaak, Michel Gangnet, Patrick Pérez
Comments (0)