Video Puzzle: Descriptive One-Shot Video Composition
Seetha Mahesh,  P Sai Prasad
A large amount of short, single-shot videos are created by personal camcorder every day, such as the small video clips in family albums. Thus, a solution for presenting and managing these video clips is highly desired. From the perspective of professionalism and artistry, long-take/shot video, also termed one shot video, is able to present events, persons or scenic spots in an informative manner. In this project a novel video composition system “Video Puzzle” is proposed which generates aesthetically enhanced long-shot videos from short video clips. Automatic composition of several related single shots into a virtual long-take video is done. A novel framework is designed to compose descriptive long-take video with content-consistent shots retrieved from a video pool . For each video, frame-by-frame search is performed over the entire pool to find start-end content correspondences through a coarse-to-fine partial matching process. The content correspondence here is general and can refer to the matched regions or objects, such as human body and face. The content consistency of these correspondences enables us to design several shot transition schemes to seamlessly stitch one shot to another in a spatially and temporally consistent manner. The entire long-take video thus comprises several single shots with consistent contents and fluent transitions. Meanwhile, with the generated matching graph of videos, the proposed system can also provide an efficient video browsing mode.
Keywords- Image retrieval, one-shot video, video authoring, and video transition
Cite this Article
Seetha Mahesh,  P Sai Prasad,   "Video Puzzle: Descriptive One-Shot Video Composition"
, International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.2, Issue 3, pp.3228-3238, Sept 2014, Available at :http://www.ijedr.org/papers/IJEDR1403068.pdf