Models and Algorithms for Detection and Tracking of Coordinated Groups

Abstract

In this paper, we describe a set of models and algorithms for detection and tracking of group and individual targets. We develop a novel group dynamical model within a continuous time setting and a group structure transition model. This is combined with an interaction model using Markov Random Fields (MRF) to create a realistic group model. We use a Markov Chain Monte Carlo (MCMC)-Particle Algorithm to perform the sequential inference. Computer simulations demonstrate the ability of the algorithm to detect and track targets, as well as infer the correct group structure.