Wisdom of the Crowd in Egocentric Video Curation

Videos recorded by wearable egocentric cameras often suffer from quality degradations that cannot be corrected. When several wearable video cameras are viewing the same scene, it is possible to combine their multiple videos into a single high-quality video. Existing techniques select for each point in time the video having highest quality, but the highest quality video may not be relevant. E.g. the best quality video can come from a person that happens to look sideways from the main attraction. We propose the curation of a single video stream from multiple egocentric videos by requiring that the selected video will also view the most interesting region in the scene. Importance of a region is determined by the “wisdom of the crowd”, i.e. the number of cameras looking at a region. The resulting video is more interesting and of a higher quality than any individual video streams can possibly obtain. Sev-eral examples are presented demonstrating the effectiveness of this technique. 1