Variational Bayesian adaptation of noise covariances in multiple target tracking problems

Multiple Target Tracking (MTT) is the process of computing the number of targets present in a surveillance area. MTT requires estimation of state variables and data association. New measurements are associated with existing tracks, clutter or new tracks. MTT generally involves unknown number of targets. Mostly because of computational complexity faced by MTT algorithms, it is a difficult and challenging problem. Computational load, underlying assumptions of known number of targets, and high cluttered environment are the main reasons, which available methods cannot address properly. Rao-Blackwellized has been used for multiple target tracking. It uses Kalman filter for state estimation and particle filter for data association. Our objective is to extend Rao-Blackwellized Monte Carlo Data Association (RBMCDA) that estimates number of targets and maintains track continuity enabling persistent tracking of targets. RBMCDA has been tested with seven different resampling methods in an effort to obtain the best resampling method. Gating validation and Variational Bayesian have been incorporated for multi target tracking problem. The modified RBMCDAs are applied to different case studies for its performance evaluation.