Iterative joint integrated probabilistic data association filter for multiple-detection multiple-target tracking

Most classical target tracking algorithms assume that one target generates one measurement per scan. However, for situations where the target's physical size exceeds one sensor resolution cell or the transmission and received signals have multi-path propagations, one target generates multiple detections which terms the multiple-detection problem. The multiple-detection multiple-target tracking algorithms usually suffered from an intractable computational load and could not operate in real time when multiple targets are closely spaced or too many detections are generated. In addition, automatic track initialization technique in cluttered environments brings in the presences of both true and false tracks that false track discrimination is required. These two terms are critical for real tracking systems but largely neglected by the published papers for the multiple-detection problem. In this paper, the authors propose an algorithm, called the Multiple-detection Iterative Joint Integrated Probabilistic Data Association (MD-iJIPDA) filter, that iteratively adjusts the computational load as well the tracking performances so that desirable performances can be achieved within manageable time. By integrating the target existence probability as a track quality measure, the MD-iJIPDA becomes capable of false track discrimination. The MD-iJIPDA is obtained by utilizing the arithmetic structure of MD-JIPDA algorithm. Therefore, we first incorporate the target existence probability into the calculation of joint event probability in MD-JPDA to derive the MD-JIPDA algorithm, then followed by the derivation of MD-iJIPDA algorithm. Simulations for the scenarios of large number targets with multiple detections are investigated to validate the effectivenesses of the proposed algorithm in tracking performance and computational efficiency.