High level segmentation of instructional videos based on content density

ABSTRACT

Automatically partitioning instructional videos into topic sections is a challenging problem in e-learning environments for efficient content management and cataloging. This paper addresses this problem by proposing a novel density function to delineate sections underscored by changes in topics in instructional and training videos. The content density function draws guidance from the observation that topic boundaries coincide with the ebb and flow of the 'density' of content shown in these videos. Based on this function, we propose two methods for high-level segmentation by determining topic boundaries. We study the performance of the two methods on eight training videos, and our experimental results demonstrate the effectiveness and robustness of the two proposed high-level segmentation algorithms for learning media.

REFERENCES

• 1: Mediaware solution webflix professional v1.5.3. http://www.mediaware.com.au/webflix.html, 1999.
• 2: B. Adams, C. Dorai, and S. Venkatesh. Role of shot length in characterizing tempo and dramatic story sections in motion pictures. In IEEE Pacific Rim Conference on Multimedia 2000, pages 54--57, Sydney, Australia, December 2000.
• 3: S. Kobayashi. Color Image Scale. Kodansha International, 1990.
• 4: D. Q. Phung, C. Dorai, and S. Venkatesh. Narrative structure analysis with education and training videos for e-learning. In International Conference on Pattern Recognition, pages 835--839, Quibec, Canada, August 2002.
• 5: K. Shearer, C. Dorai, and S. Venkatesh. Incorporating domain knowlege with video and voice data analysis, 2000. MDM/KDD 2000, Workshop on Multimedia Data Minning, Aug 20--23, Boston, USA.
• 6: M. V. Srinivasan, S. Venkatesh, and R. Hoise. Qualitative estimation of camera motion parameters from video sequences. Pattern Recognition, 30(4):593--606, 1997.
• 7: H. Zettl. Sight, Sound, Motion: Applied Media Aesthetics. Wadsworth Publishing Company, 3rd edition, 1999.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing