Multi-frame scene-flow estimation using a patch model and smooth motion prior
Popham, T. J., Bhalerao, Abhir and Wilson, Roland (2010) Multi-frame scene-flow estimation using a patch model and smooth motion prior. In: British Machine Vision Conference Workshop, Aberystwyth, UK, 31 Aug - 3 Sept 2010. Published in: Proceedings of the BMVC 2010 UK postgraduate workshop 2.1-2.11.
WRAP_Popham_bmvc_2010.pdf - Published Version - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1852Kb) | Preview
Official URL: http://www.bmva.org/bmvc/2010/workshop/paper2/inde...
This paper addresses the problem of estimating the dense 3D motion of a scene over several frames using a set of calibrated cameras. Most current 3D motion estimation techniques are limited to estimating the motion over a single frame, unless a strong prior model of the scene (such as a skeleton) is introduced. Estimating the 3D motion of a general scene is difficult due to untextured surfaces, complex movements and occlusions. In this paper, we show that it is possible to track the surfaces of a scene over several frames, by introducing an effective prior on the scene motion. Experimental results show that the proposed method estimates the dense scene-flow over multiple frames, without the need for multiple-view reconstructions at every frame. Furthermore, the accuracy of the proposed method is demonstrated by comparing the estimated motion against a ground truth.
|Item Type:||Conference Item (Paper)|
|Subjects:||Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
T Technology > TA Engineering (General). Civil engineering (General)
|Divisions:||Faculty of Science > Computer Science|
|Library of Congress Subject Headings (LCSH):||Three-dimensional imaging, Image processing, Estimation theory|
|Journal or Publication Title:||Proceedings of the BMVC 2010 UK postgraduate workshop|
|Official Date:||September 2010|
|Status:||Not Peer Reviewed|
|Access rights to Published version:||Open Access|
|Conference Paper Type:||Paper|
|Title of Event:||British Machine Vision Conference Workshop|
|Type of Event:||Workshop|
|Location of Event:||Aberystwyth, UK|
|Date(s) of Event:||31 Aug - 3 Sept 2010|
 S. Baker, D. Scharstein, JP Lewis, S. Roth, M.J. Black, and R. Szeliski. A database and evaluation methodology for optical flow. In IEEE International Conference on
Actions (login required)
Downloads per month over past year