Tracking splitting targets in clutter using the CBMeMBer filter

Abstract

For splitting target tracking, the target may split into several such that estimating the states of all targets respon-sively and accurately becomes crucial. The standard formulation of the CBMeMBer filter assumes that the target birth intensity is known as a priori. In consideration of the fact that the target splitting event should be random and could happen at an arbitrary position, this assumption becomes unrealistic. In this paper we apply the adaptive birth distribution to solve the problem of tracking splitting targets. The adaptive birth method is turned out to be more suitable to the splitting target problem. The performance is evaluated by the Optimal Sub-pattern Assignment(OSPA) metric and cardinality estimate. Simulations show that the adaptive birth CBMeMBer is responsive to the changes in cardinality with small OSPA distance.