Dependent Multiple Cue Integration for Robust Tracking

We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearance and geometric object features and by their estimation using Bayesian filters, such as Kalman or particle filters. In particular, each filter estimates the state of a specific object feature, conditionally dependent on another feature estimated by a distinct filter. This dependence provides improved target representations, permitting us to segment it out from the background even in nonstationary sequences. Considering that the procedure of the Bayesian filters may be described by a "hypotheses generationhypotheses correction" strategy, the major novelty of our methodology compared to previous approaches is that the mutual dependence between filters is considered during the feature observation, that is, into the "hypoth...

• Type: Journal
• Year: 2008
• Where: PAMI
• Authors: Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris Samaras
• Keywords: Bayesian Filters, PAMI 2006, PAMI 2008, Specific Object Feature, Video Sequences