Markov chain Monte Carlo data association for general multiple-target tracking problems
Songhwai Oh
Russell, S.
Sastry, S.
Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA;
This paper appears in: Decision and Control, 2004. CDC. 43rd IEEE Conference on
Publication Date: 17-17 Dec. 2004
Volume: 1,
On page(s): 735-742 Vol.1
Location: Nassau,
ISSN: 0191-2216
ISBN: 0-7803-8682-5
INSPEC Accession Number: 8359932
Digital Object Identifier: 10.1109/CDC.2004.1428740
Current Version Published: 2005-05-16
Abstract
In this paper, we consider the general multiple-target tracking problem in which an unknown number of targets appears and disappears at random times and the goal is to find the tracks of targets from noisy observations. We propose an efficient real-time algorithm that solves the data association problem and is capable of initiating and terminating a varying number of tracks. We take the data-oriented, combinatorial optimization approach to the data association problem but avoid the enumeration of tracks by applying a sampling method called Markov chain Monte Carlo (MCMC). The MCMC data association algorithm can be viewed as a "deferred logic" method since its decision about forming a track is based on both current and past observations. At the same time, it can be viewed as an approximation to the optimal Bayesian filter. The algorithm shows remarkable performance compared to the greedy algorithm and the multiple hypothesis tracker (MHT) under extreme conditions, such as a large number of targets in a dense environment, low detection probabilities, and high false alarm rates.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
