Joint Target Detection Tracking and Classification Based on Finite-Set Statistics Theory
Hong Wei Quan, Jun Hua Li, Xiao Juan Zhang · Applied Mechanics and Materials · 2014
In traditional target tracking methods, the target number, target states and target class can not be estimated in same time. This paper investigated the joint target detection, tracking and classification method which is based on finite-set statistics theory. First, the random set and finite-set statistics theory are introduced for theoretic analysis. Second, the finite-set model for target tracking is given to construct a generalized nonlinear fusion framework. Finally, the finite-set based Bayesian filter is developed to track the targets in surveillance region. By recursively calculating the probabilistic hypothesis density, the target number, target states and target class can be evaluated simultaneously.