Integral-transform derivations of exact closed-form multitarget trackers
MetadataShow full item record
© 2016 ISIF. The generalized labeled multi-Bernoulli (GLMB) filter, introduced by B.-T. Vo and B.-N. Vo in 2013, is an exact closed-form solution of the multitarget recursive Bayes filter, based on the theory of labeled random finite sets (labeled RFS's). Vo and Vo's derivation was rather long and involved. The purpose of this paper is twofold. First, to provide a more streamlined derivation of the GLMB filter using probability generating functional (p.g.fl.) methods. Second, to use p.g.fl. methods to derive another tractable, exact closed-form multitarget tracker, the labeled multi-Bernoulli mixture (LMBM) filter. This filter may be of some utility, since LMB mixtures are computationally simpler than GLMB distributions.
Showing items related by title, author, creator and subject.
Bryant, D.; Vo, Ba Tuong; Vo, Ba-Ngu; Jones, B. (2017)© 2017 IEEE. Previous labeled random finite set filter developments use a target motion model that only accounts for survival and birth. While such a model provides the means for a multi-target tracking filter such as the ...
Vo, Ba-Ngu; Vo, Ba Tuong; Phung, D. (2014)An analytic solution to the multi-target Bayes recursion known as the δ-Generalized Labeled Multi-Bernoulli ( δ-GLMB) filter has been recently proposed by Vo and Vo in [“Labeled Random Finite Sets and Multi-Object Conjugate ...
Reuter, S.; Vo, Ba Tuong; Vo, Ba-Ngu; Dietmayer, K. (2014)In this paper, we propose the labeled multi-Bernoulli filter which explicitly estimates target tracks and provides a more accurate approximation of the multi-object Bayes update than the multi-Bernoulli filter. In particular, ...