KIT | KIT-Bibliothek | Impressum | Datenschutz

Tracking a Minimum Bounding Rectangle based on Extreme Value Theory

Baum, Marcus; Hanebeck, Uwe D.


In this paper, a novel Bayesian estimator for the minimum bounding axis-aligned rectangle of a point set based on noisy measurements is derived. Each given measurement stems from an unknown point and is corrupted with additive Gaussian noise. Extreme value theory is applied in order to derive a linear measurement equation for the problem. The new estimator is applied to the problem of group target and extended object tracking. Instead of estimating each single group member or point feature explicitly, the basic idea is to track a summarizing shape, namely the minimum bounding rectangle, of the group. Simulation results demonstrate the feasibility of the estimator.

Volltext §
DOI: 10.5445/IR/1000035041
DOI: 10.1109/MFI.2010.5604456
Zitationen: 5
Cover der Publikation
Zugehörige Institution(en) am KIT Fakultät für Informatik – Institut für Anthropomatik (IFA)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2010
Sprache Englisch
Identifikator ISBN: 978-1-4244-5424-2
KITopen-ID: 1000035041
Erschienen in Proceedings of the 2010 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2010), Salt Lake City, Utah, USA, Sept. 5-7, 2010
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten 56-61
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page