Research on a new algorithm of target tracking

摘要

A new algorithm for the problem of tracking multiple maneuvering targets in the presence of clutter is proposed, through extending the IMM/Mscan-JPDA filtering algorithm, to the fixed-lag smoothing case. A suboptimal fixed-lag smoothing algorithm is developed by applying the IMM and the multiscan JPDA approaches to a state augmented system. The proposed algorithm is illustrated via a simulation example involving tracking of two maneuvering targets, a multiscan data window of length two, and a fixed-lag delayd = 1. It turns out that even a small time lag ofd samples results in a significant improvement in the track state estimation accuracy.