Marginal multi-bernoulli filters: RFS derivation of MHT, JIPDA, and association-based member

Abstract

Recent developments in random finite sets (RFSs) have yielded a variety of tracking methods that avoid data association. This paper derives a form of the full Bayes RFS filter and observes that data association is implicitly present, in a data structure similar to multiple hypothesis tracking (MHT). Subsequently, algorithms are obtained by approximating the distribution of associations. Two algorithms result: one nearly identical to joint integrated probabilistic data association (JIPDA), and another related to the multiple target multi-Bernoulli (MeMBer) filter. Both improve performance in challenging environments.