Unmanned surface vehicle target tracking based on marine radar

To solve the target tracking problem of Unmanned Surface Vehicle (USV), this paper is concerned with the study on dynamic target tracking in marine radar images by using Gaussian particle filter (GPF). GPF is asymptotically optimal with the Gaussianity assumption and a certain number of particles. Compared with the particle filter (PF), it avoids the resampling step and the particle degeneracy phenomenon. Here we complete the target matching in the image sequence by selecting the moment invariant of the target. The experimental results demonstrate that the proposed algorithm can efficiently complete the target tracking, and the performance of GPF is superior to that of the PF.