Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Feature-based probabilistic data association for video-based multi-object tracking

: Grinberg, Michael
: Beyerer, Jürgen

Fulltext urn:nbn:de:0072-814306 (15 MByte PDF)
MD5 Fingerprint: b2e48a76cb70477949b52594d9cf018d
(CC) by-nc-sa
Created on: 23.8.2018


Karlsruhe: KIT Scientific Publishing, 2018, XXII, 256 pp.
Zugl.: Karlsruhe, Inst. für Technologie (KIT), Diss., 2018
Karlsruher Schriften zur Anthropomatik, 35
ISBN: 978-3-7315-0781-9
Dissertation, Electronic Publication
Fraunhofer IOSB ()

This work proposes a feature-based probabilistic data association and tracking approach (FBPDATA) for multi-object tracking. FBPDATA is based on re-identification and tracking of individual video image points (feature points) and aims at solving the problems of partial, split (fragmented), bloated or missed detections, which are due to sensory or algorithmic restrictions, limited field of view of the sensors, as well as occlusion situations.