Loopy sum-product algorithm based joint detection, tracking and classification of extended objects with analytic implementations

Abstract

This paper addresses the problem of joint detection, tracking and classification (JDTC) of multiple extended objects (EOs), where each EO is restricted to be an ellipse modeled as a random matrix, and the classification of an EO is obtained on the basis of its size information. In order to reduce the computational complexity of data association and calculating the marginal posterior probability density function (PDF), the loopy sum-product algorithm (LSPA) is carried out based on a suitably devised factor graph. The goal of LSPA-based JDTC is achieved by iteratively computing the belief of each EO which is used to approximate the marginal posterior. Furthermore, in order to get a closed-form implementation, the belief of each EO is modeled via a sum of belief of each class, which is further modeled as the class probability multiplied by a mixture Gamma-Gaussian-inverse-Wishart (GGIW) distribution conditional on the class. The details of implementation are discussed in this paper and, finally, the effectiveness of the proposed approach is assessed via simulation experiments.