A Novel Data association algorithm for single target tracking in cluttered environment

Abstract

In this paper a novel data association algorithm based on density-based spatial clustering of applications with noise (DBSCAN) and maximum entropy fuzzy clustering (MEFC) algorithm is proposed for single target tracking in cluttered environments. A modified version of DBSCAN clustering approach is used to eliminate unlikely measurement to overcome the problem of clutter or false alarm. Then, the association weights between validate measurements and track of target are determined according to the MEFC principle. The efficiency and the characteristic of the proposed algorithm in comparison with Nearest-Neighbor (NN) and Probabilistic data association (PDA) filters are demonstrated. The results show the performance of the proposed algorithm in cluttered environments.