Distributed interacting multipattern data association for multiplatform target tracking

• Published in: Signal processing Vol. 82; no. 7; pp. 1007 - 1021
• Main Author: Hong, Lang
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.07.2002; Elsevier Science
• Subjects: Applied sciences; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Image processing; Information, signal and communications theory; Signal and communications theory; Signal processing; Signal, noise; Telecommunications and information theory; Performance evaluation; Target tracking; Probabilistic approach; Distributed algorithm; Data fusion; Multiple target; Target detection
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/S0165-1684(02)00204-9

A distributed interacting multipattern data association tracking algorithm is developed in this paper. Multipattern data association is based on a novel approach for tracking multiple targets using multiple patterns extracted from measurement sequences. A Markov chain controls the switching behavior of multipatterns, which allows an interacting operation of multipatterns. To save the communication bandwidth, the distributed interacting multipattern data association tracking algorithm is based on exchanges of combined target tracks, which creates a unique difficulty in developing an optimal fusion algorithm. The difficulty is overcome by developing equivalent platform and global models which then propagate the fused tracks needed for the distributed fusion algorithm.