Data association for people tracking using multiple cameras

Author

Lee, Yeongseon ; Mersereau, Russell

Author_Institution

Georgia Inst. of Technol., Atlanta, GA

fYear

2008

fDate

March 31 2008-April 4 2008

Firstpage

2585

Lastpage

2588

Abstract

In this paper, we present a data association algorithm for people tracking in a 3D world using multiple cameras. Our approach expands an independent partitioned particle filter with a data association vector. For the association parameter, we propose a proposal function using likelihood functions based on color and distance. This proposed algorithm solves the data association problem without dramatically increasing the computational complexity even in the case of trajectories that cross.

Keywords

cameras; computational complexity; particle filtering (numerical methods); sensor fusion; target tracking; tracking filters; computational complexity; data association algorithm; independent partitioned particle filter; likelihood function; multiple cameras; people tracking; Bayesian methods; Cameras; Computational complexity; Particle filters; Particle measurements; Particle tracking; Partitioning algorithms; Probability; Proposals; Target tracking; IPPF; Particle filter; data association; proposal function; visual tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on

Conference_Location

Las Vegas, NV

ISSN

1520-6149

Print_ISBN

978-1-4244-1483-3

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2008.4518177

Filename

4518177