Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Detection and tracking of objects with direct integration of perception and expectation

: Jüngling, K.; Arens, M.

Postprint urn:nbn:de:0011-n-1566612 (1.5 MByte PDF)
MD5 Fingerprint: 45f54c273a77f3ccee34ae6b2880ffc7
© 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 30.6.2011

Institute of Electrical and Electronics Engineers -IEEE-:
IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops. Proceedings. Vol.2 : Kyoto, Japan, 27 September - 4 October 2009
Piscataway, NJ: IEEE, 2009
ISBN: 978-1-4244-4442-7 (print)
ISBN: 978-1-4244-4441-0 (online)
International Conference on Computer Vision Workshops (ICCV Workshops) <12, 2009, Kyoto>
Conference Paper, Electronic Publication
Fraunhofer IITB ( IOSB) ()
feature extraction; object detection; target tracking; video signal processing

One of the main challenges in video-based multi-target tracking is the consistent maintenance of object identities over time. We present a novel approach to that challenge that integrates tracking and detection in a single process. We thereby inherently solve the identity problem and gain additional stability of the object detection performance. For that purpose, we extend a state-of-the-art local-feature based object detector by integrating expectations resulting from tracking directly into the detection procedure on the level of features. By that combination of newly gathered and expected local features we are able to directly integrate new data-evidence with object knowledge collected in the past without changing the detection approach itself. Since our tracking approach is solely based on local features, without employing other features like color or shape, it works independently of underlying video-data characteristics and preserves the general applicability independent of object-class specifics.