Comparison of Nearest Neighbor and Probabilistic Data Association Filters for Target Tracking in Cluttered Environment

Abstract

Target tracking is having of great importance as it is one of the developing areas which has various applications in the military as well as civilian applications. Detection of target and data association in presence of false alarms are the two main difficult situations faced during tracking a maneuvering target. A survey has been done on the number of algorithms developed so far to solve the difficulties in target tracking. This paper gives a brief review of the need for data association and the algorithms and techniques proposed so far to resolve the problem due to data correlation in target tracking. In this paper, a simulation has been carried out to analyze the filter performance using nearest neighbor (NN) and probabilistic data association (PDA) as data association techniques. A comparison has been done between these two algorithms based on the variation in the values of the sampling time, clutter rate, standard deviation in noise covariances. The results fosters the use of PDA as the better data association algorithm for tracking process especially in high cluttered environment.