Number of the records: 1
Range Video Segmentation
- 1.0343251 - ÚTIA 2011 RIV US eng C - Conference Paper (international conference)
Haindl, Michal - Žid, Pavel - Holub, Radek
Range Video Segmentation.
10th International Conference on Information Sciences, Signal Processing and their Applications. Los Alamitos: IEEE, 2010, s. 369-372. ISBN 978-1-4244-7166-9.
[10th International Conference on Information Sciences, Signal Processing and their Applications. Kuala Lumpur (MY), 10.05.2010-13.05.2010]
R&D Projects: GA MŠMT 1M0572; GA ČR GA102/08/0593
Grant - others:GA MŠk(CZ) 2C06019
Institutional research plan: CEZ:AV0Z10750506
Keywords : Range segmentation * Markov random fields
Subject RIV: BD - Theory of Information
http://library.utia.cas.cz/separaty/2010/RO/haindl-range video segmentation.pdf
An unsupervised range video segmentation method based on a spatial probabilistic model for intended vehicle-based safety and warning system applications is introduced. Statistical range data discontinuities are represented by a wide-sense Markov model which guides the subsequent line-based region growing process. Single frame segmentations are mutually corrected using the continuity constraint. The resulting segmentation allows tracking moving objects and estimating their distance and velocity. The method is illustrated on synthetic range video data.
Permanent Link: http://hdl.handle.net/11104/0185769
Number of the records: 1