Estimating the Shape of Targets with a PHD Filter
2011 (English)In: Proceedings of the 14th International Conference on Information Fusion, 2011Conference paper (Refereed)
This paper presents a framework for tracking extended targets which give rise to a structured set of measurements per each scan. The concept of a measurement generating point (MGP) which is defined on the boundary of each target is introduced. The tracking framework contains an hybrid statespace where MGP:s and the measurements are modeled by random finite sets and target states by random vectors. The target states are assumed to be partitioned into linear and nonlinear components and a Rao-Blackwellized particle filter is used for their estimation. For each state particle, a probability hypothesis density (PHD) filter is utilized for estimating the conditional set of MGP:s given the target states. The PHD kept for each particle serves as a useful means to represent information in the set of measurements about the target states. The early results obtained show promising performance with stable target following capability and reasonable shape estimates.
Place, publisher, year, edition, pages
Tracking, Data association, Particle filter, Kalman filter, Estimation, PHD filter, Extended target, Rao-Blackwellized particle filter
Signal Processing Control Engineering
IdentifiersURN: urn:nbn:se:liu:diva-69945ISBN: 978-1-4577-0267-9OAI: oai:DiVA.org:liu-69945DiVA: diva2:433343
14th International Conference on Information Fusion, 5-8 July, Chicago, Illinois, USA