ABSTRACT
We present improved algorithms for cut, fade, and dissolve detection which are fundamental steps in digital video analysis. In particular, we propose a new adaptive threshold determination method that is shown to reduce artifacts created by noise and motion in scene cut detection. We also describe new two-step algorithms for fade and dissolve detection, and introduce a method for eliminating false positives from a list of detected candidate transitions. In our detailed study of these gradual shot transitions, our objective has been to accurately classify the type of transitions (fade-in, fade-out, and dissolve) and to precisely locate the boundary of the transitions. This distinguishes our work from other early work in scene change detection which tends to focus primarily on identifying the existence of a transition rather than its precise temporal extent. We evaluate our improved algorithms against two other commonly used shot detection techniques on a comprehensive data set, and demonstrate the improved performance due to our enhancements.
- 1.A. M. Alattar. Detecting and compressing dissolve regions in video sequences with a DVI multimedia image compression algorithm. In Proceedings of 1993 IEEE International Symposium on Circuit and Systems, pages 13-16, 1993.Google ScholarCross Ref
- 2.A. M. Alattar. Detecting fade regions in uncompressed video sequences. In Proceedings of 1997 IEEE International Conference on Acoustics Speech and Signal Processing, pages 3025-3028, 1997. Google ScholarDigital Library
- 3.M. Ardebilian, X. Tu, and L. Chen. Improvement of shot detection methods based on dynamic threshold selection. In Proceedings of SPIE Conference on Multimedia Storage and Archiving Systems, volume 3229, DBllas, USA, Nov. 1997.Google ScholarCross Ref
- 4.F. Arman, A. Hsu, and M.-Y. Chiu. Image processing on compressed data for large video databases. In ACM Multimedia '9$, pages 267-272, California, July 1993. Google ScholarDigital Library
- 5.B. Furht, S. W. SingUlar, and H. Zhang. Video and Image Processing in Multimedia Systems. Kluwer Academic Publishers, 1995. Google ScholarDigital Library
- 6.L. Gu, K. Tsui, and D. Keightley. Dissolve detection in MPEG compressed video. In Proceedings of IBBE International Conference on Intelligent Processing Systems, volume 2, pages 1692-1696, 1997.Google Scholar
- 7.A. Hampapur, R. Jain, and T. Weymouth. Digital video segmentation. In Proceedings of the Second ACM International Conference on Multimedia (MULTIMEDIA '94), pages 357-364, New York, Oct. 1994. ACM Press. Google ScholarDigital Library
- 8.A. Hanjedic, R. L. Lagendijk, and J. Biemond. A novel video parsing method with improved thresholding. In Third Annual Conference of the Advanced School for Computing and Imaging, ASCI'97, Neitherland, 1996.Google Scholar
- 9.H. Kim, S.-F. Park, J. Lee, W. M. Kimg, and S. M.-H. Song. Processing of partial video data for detection of wipes. In Proceedings of SPIE, 1999.Google Scholar
- 10.V. Kobla, D. DeMenthon, and D. Doermann. Special effect edit detection using Video Trails: a comparison with existing techniques. In Proceedings of SPIE conference on Storage and Retrieval for Image and Video Databases VII, Jan. 1999.Google Scholar
- 11.T. C. Kuo, Y. Lin, A. L.P.Chen, S.-C. Chen, and C. Ni. Efficient shot change detection on compressed video. In Proceedings of International Workshop on Multimedia Database Management Systems, pages 101-108, 1996. Google ScholarDigital Library
- 12.R. Lienhart. Comparison of automatic shot boundary detection algorithms. In Proceedings of SPIE, Image and Video Processing VII, volume SPIE 3656-29, 1999.Google Scholar
- 13.G. Lupatini, C. Saraceno, and R. Leonardi. Scene break detection: a comparison. In Proceedings of 8th Workshop on Continuous-Media Databases and Applications, pages 34--41, 1998. Google ScholarDigital Library
- 14.J. Meng, Y. Juan, and S.-F. Chang. Scene change detection in a MPEG compressed video sequence. In IS&AT/SPIE Symposium Proceedings Vol 2419, Feb. 1995.Google Scholar
- 15.A. Nagasnlm and Y. Tanaka. Automatic video indexing and full-motion search for object appea rance. In Proceedings of Second Working Conference on Visual Databases Sys terns, pages 113-127. Elsevier Science Publishers B.V., 1992. Google ScholarDigital Library
- 16.N. V. Patel and I. K. Sethi. Compressed video processing for cut detection. In IEE Proceedings: Vision, Image and Signal Processing, volume 134, pages 315-322, Oct. 1996.Google ScholarCross Ref
- 17.B. T. Truong. Video genre classification based on shot segmentation. Honours Thesis, Curtis University of Technology, Western Australia, November 1999.Google Scholar
- 18.I. H. Witten, A. Moffat, and T. C. Bell. Managing Gigabytes; Compressing and Indezing Documents and Images. Van Nostrand Reinhold, New York, 1994. Google ScholarDigital Library
- 19.B.-L. Yeo and B. Liu. Rapid scene analysis on compressed video. IEBE Transaction on Circuits and Systems for Video Technology, 2:533-544, 1995. Google ScholarDigital Library
- 20.R. Zabih, J. Miller, and K. Mai. A feature-based algorithm for detecting and classifying production effects. Multimedia Systems, 7(2):119-128, 1999. Google ScholarDigital Library
- 21.H. Zhang, A. Kankanlmlli, and S. Smoliar. Automatic partitioning of full-motion video. Multimedia System, 1:10-28, 1993. Google ScholarDigital Library
Index Terms
- New enhancements to cut, fade, and dissolve detection processes in video segmentation
Recommendations
Dissolve transition detection algorithm using spatio-temporal distribution of MPEG macro-block types (poster session)
MULTIMEDIA '00: Proceedings of the eighth ACM international conference on MultimediaAlmost every shot change detection algorithm detects abrupt transition (hard cut) without difficulty, but gradual transitions such as fades, dissolves, wipes are left as hard-to-detect problems. Dissolve effect, among the various gradual transition ...
A motion-tolerant dissolve detection algorithm
Gradual shot change detection is one of the most important research issues in the field of video indexing/retrieval. Among the numerous types of gradual transitions, the dissolve-type gradual transition is considered the most common one, but it is also ...
Information theory-based shot cut/fade detection and video summarization
New methods for detecting shot boundaries in video sequences and for extracting key frames using metrics based on information theory are proposed. The method for shot boundary detection relies on the mutual information (MI) and the joint entropy (JE) ...
Comments