JPDA Algorithm for Multi-Extended Target Tracking Based on PPP Model

A Joint Probabilistic Data Association (JPDA) Algorithm based on Poisson Point Process (PPP) Model is proposed for multiple extended target tracking issues. Firstly, we employ the PPP model for extended object measurement modeling. Secondly, a JPDA algorithm is proposed based on the “many-2-1” association model idea, and then marginal association probabilities can be calculated by the current effective measurement of the moving target. Thirdly, the kinematic and shape parameters of each extended target are updated separately in a probability data association (PDA) fashion of incorporating the marginal association probabilities. Finally, the simulation is used to achieve tracking when two targets whose trajectories cross and two spatially close trajectories. The simulation experiments show that the proposed algorithm has obvious advantages in computational time and tracking stability in high clutter environment.