In this paper, two novel angle tracking algorithms are proposed for tracking multiple targets using an array of sensors with known locations. First, we present an extended Kalman particle filter (EKPF) which is capable of determining the direction-of-arrival (DOA) angles using a single snapshot of data during the interval between each time step. The proposed EKPF algorithm combines particle filtering with the extended Kalman filter (EKF) in order to prevent sample impoverishment during its resampling process. Next, we present a robust Kalman filter (RKF) tracking algorithm intended to improve tracking success rates of other existing algorithms for the case of multiple snapshots of data within each time increment. In the proposed RKF algorithm, a robust decision mechanism is proposed and incorporated into the Kalman filter (KF), leading to a much better tracking success rate. Because KF (or EKF) is able to offer the predictability of DOA angles, the proposed EKPF and RKF algorithms can avoid the data association problem that usually occurs in multitarget tracking. The effectiveness of the proposed algorithms are demonstrated via computer simulations in scenarios involving targets with crossing trajectories.
Hou, Sheng-Yun; Hung, Hsien-Sen; Chang, Shun-Hsyung; and Liu, Jeng-Cheng
"NOVEL ALGORITHMS FOR TRACKING MULTIPLE TARGETS,"
Journal of Marine Science and Technology: Vol. 18:
2, Article 12.
Available at: https://jmstt.ntou.edu.tw/journal/vol18/iss2/12