Computational Video

By this we mean the set of principles and associated algorithms that make explicit the relationship between the analysis and synthesis of visual data. Examples include video editing/manipulation, tele-immersion and virtual reality, three-dimensional video, synthetic worlds and the synergistic mixture of graphics with vision. In video manipulation one needs to alter the video's content by inserting or deleting particular objects; it amounts, for the most part, to recovering and maintaining relationships between different coordinate systems. Video x1 contains an original sequence. Having recovered the structure of the scene, we can insert any object for which a model is available with that object having any desired relationship with the structure of the original scene. Having recovered the camera's motion, we can view the "new" video. Video x2 shows an insertion of donuts in various places. Video x3 shows an original sequence with a fence in front of the scene. A new video can be made with the fence taken out. See this figure for a mosaic made out of the video with the fence removed. Using our motion segmentation technology we can delete objects from videos. See, for example, Video x5 and Video x6.
Return to the front page

Revised 1999/04/15
Send questions about these Web pages to