Multiple Group Targets Tracking Using the Generalized Labeled Multi-Bernoulli Filter

In multi-target tracking field, conventional algorithms supposed that target is a point source and produces at most one measurement. While with the development of modern sensor technology, the group target tracking has been widespread concern in recent years. This paper considers group target tracking with uncertain number of targets and groups under cluttered environment. The proposed tracking algorithm involves follow stages, i.e., dynamic model established and group target tracking. In the first stage, by borrowing some conceptions of graph theory, we use adjacent matrix to build group dynamic models. In the second stage, on the base of given group dynamic models, we derive the target estimated state set and the number of targets by using the Generalized Labeled Multi-Bernoulli (GLMB) Filter which based on the random finite set (RFS) with the assumption of independence of all targets. Finally, we use adjacent matrix to estimate the number of groups. To verify the proposed algorithm, the final experiment proposes three group targets, with different shapes and distributions, moving in a 2-dimension plane with constant velocity (CV).