Dense Long-term Motion Estimation via Statistical Multi-step Flow
Pierre-Henri Conze, Philippe Robert, Tomás Crivelli, Luce Morin
2014
Abstract
We present statistical multi-step flow, a new approach for dense motion estimation in long video sequences. Towards this goal, we propose a two-step framework including an initial dense motion candidates generation and a new iterative motion refinement stage. The first step performs a combinatorial integration of elementary optical flows combined with a statistical candidate displacement fields selection and focuses especially on reducing motion inconsistency. In the second step, the initial estimates are iteratively refined considering several motion candidates including candidates obtained from neighboring frames. For this refinement task, we introduce a new energy formulation which relies on strong temporal smoothness constraints. Experiments compare the proposed statistical multi-step flow approach to state-of-the-art methods through both quantitative assessment using the Flag benchmark dataset and qualitative assessment in the context of video editing.
DownloadPaper Citation
in Harvard Style
Conze P., Robert P., Crivelli T. and Morin L. (2014). Dense Long-term Motion Estimation via Statistical Multi-step Flow . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 545-554. DOI: 10.5220/0004683005450554
in Bibtex Style
@conference{visapp14,
author={Pierre-Henri Conze and Philippe Robert and Tomás Crivelli and Luce Morin},
title={Dense Long-term Motion Estimation via Statistical Multi-step Flow},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={545-554},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004683005450554},
isbn={978-989-758-009-3},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Dense Long-term Motion Estimation via Statistical Multi-step Flow
SN - 978-989-758-009-3
AU - Conze P.
AU - Robert P.
AU - Crivelli T.
AU - Morin L.
PY - 2014
SP - 545
EP - 554
DO - 10.5220/0004683005450554