Joint Multiple Group Target Center and Component Tracking Using Random Finite Set

Abstract

Multiple group target tracking, when group target birth, group target death and track cross events occur, has been an extremely challenging task. The group target tracking includes two implications: group target center tracking and group component (targets inside the group target)tracking. In this paper, by modeling the multiple group targets as a hierarchical point processes, a joint multiple group target center and component tracking algorithm in the random finite set framework is proposed, which is able to jointly estimate the motion states and number of the multiple group centers, the motion states and number of the group components, and obtain the tracks of the group centers. The main innovations of this paper are as follows. The labeled particle unresolved target probability hypothesis density (L-P-UT-PHD)filter is used for multiple group center tracking. Based on the estimated group center states, a measurement set partition algorithm is proposed. Each cell in the obtained partition is assigned to the corresponding single-group particle PHD filter for each group target. The single-group particle PHD filter estimates the component states and the component number.