Passive multi target tracking with GM-PHD filter

Dann Laneuville, Jeremie Houssineau

Abstract: This paper considers the challenging problem of multitarget tracking with passive data, obtained here by geographically distributed cameras. We use a Gaussian Mixture Probability Hypothesis Density filter approach to solve this difficult problem. As we make no spatial assumptions for the birth process, we use a slightly modified filter to obtain our results. We first describe the modified filter and detail our application before we present some results obtained on a realistic test scenario. Our simulations demonstrate that the proposed Probability Hypothesis Density filter is a promising candidate for three dimensional passive multi target tracking in clutter.