An adaptive fusion architecture for target tracking

Author

Loy, Gareth ; Fletcher, Luke ; Apostoloff, Nicholas ; Zelinsky, Alexander

Author_Institution

Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia

fYear

2002

Firstpage

261

Lastpage

266

Abstract

A vision system is demonstrated that adaptively allocates computational resources over multiple cues to robustly track a target in 3D. The system uses a particle filter to maintain multiple hypotheses of the target location. Bayesian probability theory provides the framework for sensor fusion, and resource scheduling is used to intelligently allocate the limited computational resources available across the suite of cues. The system is shown to track a person in 3D space moving in a cluttered environment.

Keywords

Bayes methods; computer vision; image motion analysis; probability; resource allocation; scheduling; sensor fusion; tracking; 3D target tracking; Bayesian probability theory; adaptive fusion architecture; cluttered environment; computational resource allocation; computer vision system; multiple cues; particle filter; person tracking; resource scheduling; sensor fusion; Bayesian methods; Computer architecture; Computer vision; Machine vision; Particle filters; Processor scheduling; Resource management; Robustness; Sensor fusion; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on

Conference_Location

Washington, DC, USA

Print_ISBN

0-7695-1602-5

Type

conf

DOI

10.1109/AFGR.2002.1004164

Filename

1004164