Real-time neighborhood based disparity estimation incorporating temporal evidence.

Bartczak, B., Jung, D. and Koch, Reinhard (2008) Real-time neighborhood based disparity estimation incorporating temporal evidence. Pattern Recognition, 5096 . pp. 153-162. DOI https://doi.org/10.1007/978-3-540-69321-5_16.

Full text not available from this repository.

Supplementary data:

Abstract

This paper presents a system for dense area based disparity estimation from binocular recti ed image sequences with the integration of temporal evidence. The system is using dense 2D optical ow elds and timely displaced disparity estimates to reason about the observed 3D scene ow. This scene ow is then exploited to strengthen timely consistent observations in the disparity estimation. Moreover a novel neighborhood assumption is presented, which allows to seamlessly im-plement the presented algorithm on the GPU. It is shown that by means of the presented approach the sensitivity to noise and ambiguities ob-served with plain real-time disparity estimations can be improved, even in fully dynamic scenarios with simultaneous movement of objects and cameras.

Document Type: Article
Keywords: Disparity Estimation, Disparity Level, Scene Flow, Shiftable Window, Cost Volume
Research affiliation: OceanRep > The Future Ocean - Cluster of Excellence
Kiel University
Refereed: Yes
Open Access Journal?: No
DOI etc.: https://doi.org/10.1007/978-3-540-69321-5_16
ISSN: 0031-3203
Projects: Future Ocean
Date Deposited: 15 Oct 2010 09:17
Last Modified: 26 Feb 2019 11:28
URI: http://oceanrep.geomar.de/id/eprint/8949

Actions (login required)

View Item View Item