Non-parametric patch based video matting
Sarim, M, Hilton, A and Guillemaut, J (2009) Non-parametric patch based video matting In: Proc. British Machine Vision Conference (BMVC 2009), 2009-09-07 - 2009-09-10, London, UK.
Available under License : See the attached licence file.
In computer vision, matting is the process of accurate foreground estimation in images and videos. In this paper we presents a novel patch based approach to video matting relying on non-parametric statistics to represent image variations in appearance. This overcomes the limitation of parametric algorithms which only rely on strong colour correlation between the nearby pixels. Initially we construct a clean background by utilising the foreground object’s movement across the background. For a given frame, a trimap is constructed using the background and the last frame’s trimap. A patch-based approach is used to estimate the foreground colour for every unknown pixel and finally the alpha matte is extracted. Quantitative evaluation shows that the technique performs better, in terms of the accuracy and the required user interaction, than the current state-of-the-art parametric approaches.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||Copyright the authors 2009. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.|
|Divisions:||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Depositing User:||Symplectic Elements|
|Date Deposited:||06 Feb 2012 11:25|
|Last Modified:||23 Sep 2013 19:00|
Actions (login required)
Downloads per month over past year