DATA ASSOCIATION AND TRACKING FROM DISTRIBUTED SENSORS USING HIDDEN MARKOV MODELS AND DYNAMIC PROGRAMMING: THE DIAMANT ALGORITHM

The problem of target tracking from distributed sensors in a cluttered environment is addressed. We introduce here a new algorithm, which achieves target tracking and target motion analysis. This technique uses the formalism of HMMs, and is based on two successive steps: the first one consists in a spatial fusion of the measurements obtained at a given time, and the second achieves temporal association, thus leading to the target trajectory. This approach basically differs from classic ones, because it requires no initialization and no a priori hypothesis for target motion. It is based on the discretization of the targets state space, and theoretically valid in the single target case, but extented to multiple targets in simulations. Simulation results are shown, in which the multiple targets and maneuvering target cases are given particular attention.