Abstract
For automated analysis of video contents and efficient browsing, it is essential to extract the internal structure of the video contents. For this purpose, three technologies (a robust shot boundary detection algorithm, an R-frame selection algorithm, an editor that allows manual edition of the structure of the video contents to complement the first two automated processes) are needed. This paper addresses the first two problems.
For shot boundary detection, a new algorithm including dual detectors for the two types of boundaries, cuts and gradual boundaries, is proposed. Also, some peculiar shot boundaries that are reported from each detector could be eliminated by adopting a delayed decision mechanism rather than immediate decision at each detector level. Therefore, the proposed algorithm produces high accuracy of 0.974 in recall and 0.942 in precision, which are far better results than those of the existing algorithms compared.
For R-frame selection, the changing pattern of the pixel differences is investigated. The existing algorithms mainly adopt simple mechanical approaches such as a fixed period sampling. By contrast, the proposed approach considers the motion in contents by using pixel differences, and thus, can select more meaningful frames. Furthermore, since the proposed algorithm reuses the pixel differences which is already calculated for the shot boundary detection, the total processing time is not much increased.
Chapter PDF
References
Huang, L., Lee, J. C., Li, Q. and Xiong, W. (1996) An Experimental Video Database Management System Based On Advanced Object-Oriented Techniques: Proc. SPIE, Vol. 2670, pp. 158–169.
Zhong, D., Zhang, H. J. and Chang, S. (1996) Clustering Methods for Video Browsing and Annotation: Proc. SPIE, Vol. 2670, pp. 239–246.
Zhang., H. J., Low, C. Y., Smoliar, S. W. and Wu, J. H. (1995) Video Parsing, Retrieval and Browsing: An Integrated and Content-Based Solution: Proc. ACM Multimedia ‘85, pp. 15–24.
Ahanger, G and Little, T. (1996) A Survey of Technologies for Parsing and Indexing Digital Video: Journal of Visual Communication and Image Representation, Special Issue on Digital Libraries, Vol. 7, No. 1, pp. 28–43.
Boreczky, J. S. and Rowe, L. A. (1996) Comparison of Video Shot Boundary Detection Techniques: ISandT/SPIE, Vol. 2670, pp. 170–179.
Zhang, H. J. and Smoliar, S. W. (1994) Developing Power Tools for Video Indexing and Retrieval: Proc. SPIE, Vol. 2185, pp. 140–149.
Ardizzone, E., Cascia, M. and Molinelli, D. (1996) Motion and Color Based Video Indexing and Retrieval: Int. Conf. on Pattern Recognition, ICPR, Wien, Austria.
Liu, H. and Zick, G. L. (1995) Scene Decomposition of MPEG Compressed Video: Proc. SPIE, Vol. 2419, pp. 26–37.
Meng, J. and Chang, S. (1996) Tools for Compressed-Domain Video Indexing and Editing: Proc. SPIE, Vol. 2670, pp. 180–191.
Zhang, A. and Multani, S. (1996) Implementation of Video Presentation in Database Systems: Proc. SPIE, Vol. 2670, pp. 228–238.
Cascia, M. and Ardizzone, E. (1996) JACOB: Just a Content-Based Query System for Video Database: Proc. ICASSP-96, pp. 1–4
Picard, R. W. (1995) A Video Browser that Learns by Example: MIT Media Laboratory Technical Report #383
Tou, J. T. and Gonzalez, R. C. (1974) Pattern Recognition Principles: Addition-Wesley Publishing Company, Inc. pp. 113–114.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media New York
About this chapter
Cite this chapter
Lee, J.Y., Jeong, S.Y., Chun, B.T., Bae, Y.J. (1998). A Method for Shot Boundary Detection and R-Frame Selection of Digital Video. In: Ioannidis, Y., Klas, W. (eds) Visual Database Systems 4 (VDB4). VDB 1998. IFIP — The International Federation for Information Processing. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-35372-2_27
Download citation
DOI: https://doi.org/10.1007/978-0-387-35372-2_27
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4757-6939-5
Online ISBN: 978-0-387-35372-2
eBook Packages: Springer Book Archive