Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Dynamic-occlusion likelihood incorporation in a PHD filter based range-only tracking system

: Jovanoska, Snezhana; Govaers, Felix; Thomae, Reiner; Koch, Wolfgang

International Society of Information Fusion -ISIF-:
18th International Conference on Information Fusion, Fusion 2015 : July 6-9, 2015, Washington D.C., USA
Sunnyvale: ISIF, 2015
ISBN: 978-0-9964527-1-7
ISBN: 978-0-9824-4386-6
International Conference on Information Fusion (FUSION) <18, 2015, Washington/DC>
Fraunhofer FKIE

In multiple target tracking target occlusion or shadowing is a common occurrence. A target may be occluded by an existing structure, or in many cases, by another moving target in the environment. In this paper we consider a UWB-based range-only person tracking system. Occlusion regions induced by moving targets in the scenario are defined followed by a derivation of an occlusion likelihood function. The occlusion likelihood is then incorporated within a person localization and tracking framework based on the PHD filter by influencing the probability of target detection. Numerical and experimental results demonstrate that the incorporation of `negative information' leads to a more complete belief of the scenario and can result in use of fewer sensors for covering the area of interest.