A Gaussian-mixture PHD filter based on random hypersurface model for multiple extended targets

This paper presents an approach to track an unknown number of extended targets, in the presence of clutter measurements and missed detections, where the extensions of targets are modeled as random hypersurfaces. The random hypersurface model developed recently by Baum et al. is embedded into the extended target PHD framework. To do this, the pseudo-measurement and measurement likelihood function for extended target are constructed, and the update of PHD filter is derived based on the random hypersurface model under the necessary assumptions and approximations. The simulation results show that the proposed extended target filter could track the kinematic state and extension state of extended targets well.