Dependent multiple cue integration for robust tracking

We propose a new technique for fusing multiple cues to robustly segment an object from itsbackground in video sequences that suffer from abrupt changes of both illumination and position ofthe target. Robustness is achieved by the integration of appearance and geometric object features andby their estimation using Bayesian filters, such as Kalman or particle filters. In particular, each filterestimates the state of a specific object feature, conditionally dependent on another feature estimatedby a distinct filter. This dependence provides improved target representations, permitting to segmentit out from the background even in non-stationary sequences. Considering that the procedure of the Bayesian filters may be described by a 'hypotheses generation - hypotheses correction- strategy, themajor novelty of our methodology compared to previous approaches is that the mutual dependence between filters is considered during the feature observation, i.e, into the 'hypotheses correction' stage,instead of considering it when generating the hypotheses. This proves to be much more effective interms of accuracy and reliability. The proposed method is analytically justified and applied to developa robust tracking system that adapts online and simultaneously the color space where the image points are represented, the color distributions, the contour of the object and its bounding box. Results withsynthetic data and real video sequences demonstrate the robustness and versatility of our method.