| Dependent multiple cue integration for robust tracking (2008) | |||||||||||||||
Abstract | |||||||||||||||
|
16 pages, 13 figures..
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 generation-hypotheses 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 "hypotheses-correction" stage, instead of considering it when generating the hypotheses. This proves to be much more effective in terms of accuracy and reliability. The proposed method is analytically justified and applied to develop a 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 with synthetic data and real video sequences demonstrate the robustness and versatility of our method..
This research was conducted at the Institut de Robòtica i Informàtica Industrial of the Technical University of Catalonia and Consejo Superior de Investigaciones Científicas. It was partially supported by Consolider Ingenio 2010, project CSD2007-00018, CICYT project DPI2007-614452, and IST-045062 of the European Community Union, by a fellowship from the Spanish Ministry of Science and Technology, and by grants from theUSDepartment of Justice (2004-DD-BX-1224), Department of Energy (MO-068), and US National Science Foundation (ACI-0313184 and IIS-0527585)..
http://hdl.handle.net/2117/2705 Peer reviewed |
|||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||