Digital video segmentation

ABSTRACT

The data driven, bottom up approach to video segmentation has ignored the inherent structure that exists in video. This work uses the model driven approach to digital video segmentation. Mathematical models of video based on video production techniques are formulated. These models are used to classify the edit effects used in video and film production. The classes and models are used to systematically design the feature detectors for detecting edit effects in digital video. Digital video segmentation is formulated as a feature based classification problem. Experimental results from segmenting cable television programming with cuts, fades, dissolves and page translate edits are presented.

REFERENCES

• 1: Farshid Arman , Arding Hsu , Ming-Yee Chiu, Image processing on compressed data for large video databases, Proceedings of the first ACM international conference on Multimedia, p.267-272, August 02-06, 1993, Anaheim, California, United States [doi>10.1145/166266.166297]
• 2: David BordweU and Thompson Kristin. Film Art: An Introduction. Addison-Wesley Publishing Company, 1980.
• 3: Glorianna Davenport , Thomas Aguirre Smith , Natalio Pincever, Cinematic Primitives for Multimedia, IEEE Computer Graphics and Applications, v.11 n.4, p.67-74, July 1991 [doi>10.1109/38.126883]
• 4: Richard O Dud~ and Peter E Hart. Pattern Classification and Scene Analysis. A Wiley-Interscience Publication. John Wiley and Sons, 1973.
• 5: Claude L Fenema and William B Thompson. Velocity determination in scenes containing several moving objects. Computer Graphics and image Pwcessing, 9:301- 315, 1979.
• 6: Arun Hampapur, Ramesh Ja/n, and Terry Weymouth. Production model hazed digital video segmentation. Technical report, The University of Michigan, Ann Atbor, 1994.
• 7: Berthold K. P. Horn aad Brian G. Schunck. Determining optical flow. Artificial Intelligence, 17:185-203, 1981.
• 8: R J~in. Difference and accumulative difference pictures in dynamic scene analysis. Image and ViJion Comput. ing, Vol 2(No 2):99-108, May 1984.
• 9: R Ja/n and H H Navel. On the a~a~ys/s of accumulative difference pic%ures/tom image sequences of zeal world scenes. IE~E Transactions on Pattern Analysis and Machine Intelligence, Vol 1(No 2):206-214, April 1/)79.
• 10: It& Koni~sberg. The Complete Film Dictionary. Pengxtia Books, 1989.
• 11: J O Limb and J A Murphy. Estimating the velocity of moving images in television signals. Computer Graphics and Image Processing, 4:311-327, 1975.
• 12: Akio Na~a~aka and Yuzuru Tanaka. Aurora&tic video indexing and full-video search for object appeazances. In ~nd Working Conference on Visual Database Systerns, pages 119-133, Budapest, Hungary, October 1991. iFIP WG 2.6.
• 13: George Wolberg, Digital Image Warping, IEEE Computer Society Press, Los Alamitos, CA, 1994
• 14: HongJinag Zhan$, Atreyi Kanka~halli, and Stephen W. Smoliaz. Automatic partitioning of animate video. Technical report, Institute of Systems Science, National University of Singapore * Heng Mui Keng Terrace * Kent Ridge * Singapore 0511, 1992.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems
          Subjects: Video (e.g., tape, disk, DVI)

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation
          Subjects: Pixel classification

General Terms:
Algorithms, Design, Experimentation