Random finite set multi-target trackers: stochastic geometry for space situational awareness

Abstract

This paper describes the recent development in the random finite set RFS paradigm in multi-target tracking. Over the last decade the Probability Hypothesis Density filter has become synonymous with the RFS approach. As result the PHD filter is often wrongly used as a performance benchmark for the RFS approach. Since there is a suite of RFS-based multi-target tracking algorithms, benchmarking tracking performance of the RFS approach by using the PHD filter, the cheapest of these, is misleading. Such benchmarking should be performed with more sophisticated RFS algorithms. In this paper we outline the high-performance RFS-based multi-target trackers such that the Generalized Labled Multi-Bernoulli filter, and a number of efficient approximations and discuss extensions and applications of these filters. Applications to space situational awareness are discussed.

Novel Multi-Object Filtering Approach for Space Situational Awareness

“…They maintain a collective description of the whole population of objects and avoid an explicit (and costly) data association step between objects and collected observations but do not maintain track continuity since they do not propagate specific information on any object (i.e., individual tracks). Recent developments [16] within the FISST framework, however, aim at augmenting the set representation with a unique labeling of targets in order to maintain individual information on objects; applications in the context of SSA can be found in [9,17,18]. This paper exploits the recent estimation framework for stochastic populations [19] for SSA applications.…”