Extended Target Tracking using a Gaussian-Mixture PHD filter, Report no. LiTH-ISY-R-3028

This paper presents a Gaussian-mixture implementation of the PHD lter for tracking extended targets. The exact lter requires processing of all possible measurement set partitions, which is generally infeasible to implement. A method is proposed for limiting the number of considered partitions and possible alternatives are discussed. The implementation is used on simulated data and in experiments with real laser data, and the advantage of the lter is illustrated. Suitable remedies are given to handle spatially close targets and target occlusion.