An improved algorithm for maximum-likelihood based approach for a multitarget tracking problem
暂无分享,去创建一个
It has been shown that the optimal solution for the matching problem in multi-target tracking, when both estimated measuring bearing data and actual measuring data are known, can be found from among N different matchings. This paper shows by experiment that the costs of the N different possible solutions constitute a bimodal sequence, which suggests an algorithm of O(N-logN) complexity for the matching, lower than most known algorithms. An improved algorithm for the whole process of the multi-target tracking problem is obtained, and an improved performance is shown.
[1] Y. Bar-Shalom,et al. A new relaxation algorithm and passive sensor data association , 1992 .
[2] Ronald A. Iltis,et al. Multitarget motion analysis in a DSN , 1991, IEEE Trans. Syst. Man Cybern..
[3] Rangasami L. Kashyap,et al. Multiple target tracking using maximum likelihood principle , 1995, IEEE Trans. Signal Process..
[4] Liang Chen,et al. An Improved Solution to ML-Based Multitarget Motion Tracking with Bearings-Only Measurements , 2002, Int. J. Comput. Eng. Sci..