Integrating Covariance Intersection into Bayesian multi-target tracking filters

Multi-target tracking systems typically provide sets of estimated target states as their output. It is challenging to be able integrate these outputs inputs other gain a better picture the area under surveillance since they do not conform standard observation model. Moreover, in cyclic distributed systems, there may common information between state estimates that would mean fused become overconfident and corrupt system. In this paper we develop Bayesian multi-target estimator based on covariance intersection algorithm for track-to-track data fusion. The approach integrated into demonstrated simulations. account missed tracks false produced by another