In this presentation, we focus on techniques for video object segmentation and the subsequent combination of the extracted object(s) with another video scene (`video compositing´) from a computer vision point of view. We present results obtained by state-of-the art stereo and motion segmentation algorithms and discuss the special requirements of video compositing tasks on the segmentation algorithm. In this context, we also address special problems arising along object boundaries and related occlusions and demonstrate the need for boundary matting techniques.
M. Gelautz, M. Bleyer, C. Rhemann, D. Markovic, E. Stavrakis: "Video Object Segmentation and Compositing"; Talk: Winter Augmented Reality Meeting 2005, Graz; 12-19-2005.
Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.