Feature aided tracking algorithm based on Generalized Probability Data Association

In traditional multi-target tracking algorithm, only target kinematic information has been used for data association. A new association algorithm is presented in this paper-Feature Aided Tracking (FAT) algorithm, which is based on the Generalized Probability Data Association (GPDA) algorithm. FAT algorithm combines target feature information with traditional kinematic information in a probabilistic way, which preferably resolves closely spaced targets in dense clutter environment. This idea is demonstrated via an example where the target ID range profile measurement is incorporated into data association. Simulation results verified that the FAT algorithm outperforms the conventional probability data association algorithm.