作者: Chang Joo Lee , Jung Min Pak , Choon Ki Ahn , Kyung Min Min , Peng Shi
DOI: 10.1016/J.NEUCOM.2015.05.096
关键词: Computer science 、 Algorithm 、 Filter (signal processing) 、 Mahalanobis distance 、 Robustness (computer science) 、 Multi target 、 Markov jump linear systems 、 Kalman filter 、 Likelihood function 、 Finite impulse response 、 Control theory
摘要: Most existing multi-target tracking (MTT) algorithms are based on Kalman filters (KFs). However, KFs exhibit poor estimation performance or even diverge when system models have parameter uncertainties. To overcome this drawback, finite impulse response (FIR) been studied; these more robust against model uncertainty than KFs. In paper, we propose a novel MTT algorithm FIR filtering for Markov jump linear systems (MJLSs). The proposed is called the (MTFTA). MTFTA decision-making process to identify true-target's state among candidate states. true-target utilizes likelihood function and Mahalanobis distance. We show that exhibits better robustness uncertainties conventional KF-based algorithm.