We describe a probabilistic framework for detecting and tracking motion boundaries. It builds on previous work (M.J. Black and D.J. Fleet, 2000) that used a particle filter to compute a posterior distribution over multiple, local motion models, one of which was specific for motion boundaries. We extend that framework in two ways: 1) with an enhanced likelihood that combines motion and edge support, 2) with a spatiotemporal model that propagates beliefs between adjoining image neighborhoods to encourage boundary continuity and provide better temporal predictions for motion boundaries. Approximate inference is achieved with a combination of tools: sampled representations allow us to represent multimodal non-Gaussian distributions and to apply nonlinear dynamics, while mixture models are used to simplify the computation of joint prediction distributions.
Probabilistic tracking of motion boundaries with spatiotemporal predictions
01.01.2001
1773055 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions
British Library Conference Proceedings | 2001
|Probabilistic Detection and Tracking of Motion Boundaries
British Library Online Contents | 2000
|Probabilistic Tracking and Recognition of Non-Rigid Hand Motion
British Library Conference Proceedings | 2003
|