Video segmentation combining similarity analysis and classification

ABSTRACT

In this paper, we compare several recent approaches to video segmentation using pairwise similarity. We first review and contrast the approaches within the common framework of similarity analysis and kernel correlation. We then combine these approaches with non-parametric supervised classification for shot boundary detection. Finally, we discuss comparative experimental results using the 2002 TRECVID shot boundary detection test collection.

REFERENCES

• 1: A. Smeaton and P. Over. The TREC 2002 Video Track Report. Proc. TREC Video Track, 2002.
• 2: B. Gunsel, M. Ferman, and A. M. Tekalp, Temporal video segmentation using unsupervised clustering and semantic object tracking, J. Electronic Imaging 7(3):592--604, July 1998.
• 3: M. Cooper and J. Foote. Scene Boundary Detection Via Video Self-Similarity Analysis. Proc. IEEE Intl. Conf. on Image Processing, 2001.
• 4: J. Boreczky and L. Rowe. Comparison of video shot boundary detection techniques. Proc. SPIE Storage and Retrieval for Image and Video Databases, 1996.
• 5: A. Witkin. Scale-space Filtering: A New Approach to Multi-scale Description. Proc. IEEE ICASSP, 1984.
• 6: Malcolm Slaney , Dulce Ponceleon , James Kaufman, Multimedia edges: finding hierarchy in all dimensions, Proceedings of the ninth ACM international conference on Multimedia, September 30-October 05, 2001, Ottawa, Canada [doi>10.1145/500141.500149]
• 7: D. Pye, N. Hollinghurst, T. Mills, and K. Wood. Audio-visual Segmentation for Content-Based Retrieval. Proc. Intl. Conf on Spoken Language Processing, 1998.
• 8: M. Pickering, D. Heesch, et al.. Video Retrieval using Global Features in Keyframes. Proc. TREC Video Track, 2002.
• 9: Y. Qi, A. Hauptman, and T. Liu. Supervised Classification for Video Shot Segmentation. Proc. IEEE Intl. Conf. on Multimedia & Expo, 2003.
• 10: T. Liu, A. Moore, and A. Gray. Efficient Exact k-NN and Nonparametric Classification in High Dimensions. Proc. Neural Information Processing Systems, 2003.

INDEX TERMS

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

General Terms:
Algorithms, Management

Keywords:
temporal media indexing and segmentation