Tabu Search Tracker for Multiple Target Tracking

Abstract

This paper presents a new method based on the tabu search algorithm for multiple target tracking. The data association problem formulated as an N-dimensional assignment problem is solved by using tabu search algorithm. A performance evaluation of the proposed tabu search tracker is presented using simulation studies. Six different tracking scenarios are considered for this evaluation. It was observed that the estimation results of the tabu search tracker are in very good agreement with the true tracks. Better accuracy with respect to the well known joint probabilistic data association algorithm is obtained.