Random sets in data fusion: formalism to new algorithms

Abstract

Although a connection between multi-object tracking and random set theory was recognized during the course of the development of multi-hypothesis tracking algorithms, it was only recently that such a connection started to be discussed based on random set theory and to be related to several algorithms based on it. This paper describes a random set formalism of a general theory of multiple object tracking, and discusses recent developments in both theory and applications in an attempt to explore further applications of random set theory to data fusion.