Genetic Algorithm-based Data Association and Multiple Filter Bank-based Target Tracking in Infrared Image Sequences

Abstract

Simultaneous tracking of multiple maneuvering and nonmaneuvering point targets in the presence of dense clutter and in the absence of any a priori information about target dynamics is a challenging problem. Moreover, a successful solution to this problem requires to assign an observation to track for state update, i.e. data association. In this paper, we investigate a tracking algorithm based on multiple Alter bank to track an arbitrary trajectory in the presence of dense clutter. The novelty about the proposed tracking algorithm is the use of genetic algorithm for data association, i.e. observation to track fusion. Extensive simulation results demonstrate the effectiveness of the proposed approach for real-time tracking in infrared image sequences.