Variational Optical Flow from Alternate Exposure Images

Zitieren

Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

SELLENT, Anita, Martin EISEMANN, Bastian GOLDLÜCKE, Thomas POCK, Daniel CREMERS, Marcus MAGNOR, 2009. Variational Optical Flow from Alternate Exposure Images. VMV 09 : Vision, Modeling and Visualization Workshop in Braunschweig, Germany. Braunschweig, 16. Nov 2009 - 18. Nov 2009. In: MARCUS MAGNOR ..., , ed.. Proceedings of the Vision, Modeling, and Visualization Workshop 2009 : November 16 - 18, 2009, Braunschweig, Germany. VMV 09 : Vision, Modeling and Visualization Workshop in Braunschweig, Germany. Braunschweig, 16. Nov 2009 - 18. Nov 2009. Magdeburg:Eurographics Association, pp. 135-143. ISBN 978-3-9804874-8-1

@inproceedings{Sellent2009Varia-29122, title={Variational Optical Flow from Alternate Exposure Images}, year={2009}, isbn={978-3-9804874-8-1}, address={Magdeburg}, publisher={Eurographics Association}, booktitle={Proceedings of the Vision, Modeling, and Visualization Workshop 2009 : November 16 - 18, 2009, Braunschweig, Germany}, pages={135--143}, editor={Marcus Magnor ...}, author={Sellent, Anita and Eisemann, Martin and Goldlücke, Bastian and Pock, Thomas and Cremers, Daniel and Magnor, Marcus} }

Pock, Thomas Variational Optical Flow from Alternate Exposure Images 2014-10-15T09:23:20Z Goldlücke, Bastian Pock, Thomas Magnor, Marcus Eisemann, Martin Magnor, Marcus Cremers, Daniel Sellent, Anita Sellent, Anita Traditional optic flow algorithms rely on consecutive short-exposure images. In contrast, longexposed images contain integrated motion information directly in form of motion blur. In this paper, we show how the additional information provided by a long exposure image can be used to improve robustness and accuracy of motion field estimation. Recently, an image formation model was introduced [23] that relates a long-exposure image to preceding and succeeding short-exposure images in terms of dense 2D motion and occlusion. We formulate the original two-step problem for motion and occlusion timings as a joint minimization problem and derive a global TV-L<sup>1</sup> energy functional that can be minimized efficiently and accurately. The approach is able to calculate highly accurate motion fields, assigning motion to occluded and disoccluded image regions in one joint optimization procedure. Cremers, Daniel eng Eisemann, Martin 2009 Goldlücke, Bastian 2014-10-15T09:23:20Z

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto