Publication details

Range Video Segmentation

Conference Paper (international conference)

Haindl Michal, Žid Pavel, Holub Radek


serial: 10th International Conference on Information Sciences, Signal Processing and their Applications, p. 369-372

action: 10th International Conference on Information Sciences, Signal Processing and their Applications, (Kuala Lumpur, MY, 10.05.2010-13.05.2010)

research: CEZ:AV0Z10750506

project(s): 1M0572, GA MŠk, 2C06019, GA MŠk, GA102/08/0593, GA ČR

keywords: Range segmentation, Markov random fields

preview: Download

abstract (eng):

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.

RIV: BD