Segmentation of Video Sequences using Volumetric Image Processing
This paper introduces an algorithm to detect cuts in a video sequence. The algorithm is based on volumetric processing of the video sequence, and uses techniques from differential geometry to classify the cut frames. The algorithm is very robust with respect to the presence of noise, and avoids the detection of “false cuts” in a video shot. We also describe an implementation of the algorithm that computes the video cut segmentation in real time.
KeywordsVideo Sequence Discriminant Function Hessian Matrix Editing Operation Video Shot
Unable to display preview. Download preview PDF.
- 1.Akihito Akutsu and Yoshinobu Tonomura. Video tomography: An efficient method for camerawork extraction and motion analysis. In Proceedings of ACM Multimedia Conference, pages 349–356, 1994.Google Scholar
- 2.Romildo J. da Silva. Geometric Processing of Volumetric Objects. PhD thesis, IMPA, Rio de Janeiro, Brazil, September 1998 (in Portuguese).Google Scholar
- 3.Romildo J. da Silva, J. Gomes, and L. Velho. Video cut detection using volumetric image sequence processing, 1999. (IMPA preprint).Google Scholar
- 4.Adam Finkelstein, Charles E. Jacobs, and David Salesin. Multiresolution video. SIG GRAPH ‘86 Conference Proceedings, pages 281–290, 1996.Google Scholar
- 5.Arun Hampapur, Ramesh Jain, and Terry Weymouth. Digital video segmentation. In Proceedings of ACM Multimedia Conference, pages 357–364, 1994.Google Scholar
- 6.Ira Konigsberg. The Complete Film Dictionary. Penguin Books, 1989.Google Scholar
- 7.A. Nagasaka and Y. Tanaka. Automatic video indexing and full-video search for object appearances. In Proc. of the IFIP Second Working Conference on Visual Database Systems, pages 119–133, 1991.Google Scholar
- 10.Yukinoby Taniguchi, Akihito Akutsu, and Yoshinobu Tonomura. Panoramaexcerpts: Extracting and packing panoramas for video brwosing. In Proceedings of ACM Multimedia Conference, pages 427–436, 1997.Google Scholar