Summarization scheme based on near-duplicate analysis

ABSTRACT

This paper presents our approach to select relevant sequences from raw videos in order to generate summaries to Trecvid 2008 BBC Rush Task. Our system is composed of two major steps: First, the system detects "semantic" shot boundaries and keeps only non-redundant shots; then, the system estimates average motion for each shot, as a criterion of amount of information, to better share out the duration of the summary between remaining shots. The first step is based on a fast near-duplicate retrieval using Locality Sensitive Hashing (LSH) which provides results in few seconds (if we do not take into account decoding and encoding processes). The evaluation of Trecvid shows very promising results, since we ranked 17^th over 43 runs, regarding redundancy measure (RE), and 18^th for object and event inclusion (IN). These balanced results (most of best teams for the first criterion are among the latest for the second one) show that our method offers a quite good trade-off between false negatives (IN) and false positives (RE).

REFERENCES

• 1: A. Andoni. E2lsh. http://www.mit.edu/~andoni/LSH/.
• 2: G. Camara-Chavez, M. Cord, S. Philipp-Foliguet, F. Precioso, and A. de Araujo Albuquerque. Robust scene cut detection by supervised learning. EUSIPCO, 2006.
• 3: Ba Tu Truong , Svetha Venkatesh, Generating comprehensible summaries of rushes sequences based on robust feature matching, Proceedings of the international workshop on TRECVID video summarization, p.30-34, September 28-28, 2007, Augsburg, Bavaria, Germany [doi>10.1145/1290031.1290036]
• 4: Ondřej Chum , James Philbin , Michael Isard , Andrew Zisserman, Scalable near identical image and shot detection, Proceedings of the 6th ACM international conference on Image and video retrieval, p.549-556, July 09-11, 2007, Amsterdam, The Netherlands [doi>10.1145/1282280.1282359]
• 5: Mayur Datar , Nicole Immorlica , Piotr Indyk , Vahab S. Mirrokni, Locality-sensitive hashing scheme based on p-stable distributions, Proceedings of the twentieth annual symposium on Computational geometry, June 08-11, 2004, Brooklyn, New York, USA [doi>10.1145/997817.997857]
• 6: A. M. Ferman. Two-stage hierarchical video summary extraction to match low-level user browsing preerences. IEEE Trans. on Multimedia, 5(2):244--256, 2003.
• 7: Y. Gong and X. Liu. Summarizing video by minimizing visual content redundancies. IEEE ICME, 2001.
• 8: Yihong Gong, Summarizing audiovisual contents of a video program, EURASIP Journal on Applied Signal Processing, v.2003 n.1, p.160-169, January 2003 [doi>10.1155/S1110865703211082]
• 9: R. L. A. Hanjalic and J. Biemond. Automated high-level movie segmentation for advanced video retrieval systems. IEEE Trans. CSVT, 9(4):580--588, 1999.
• 10: Piotr Indyk , Rajeev Motwani, Approximate nearest neighbors: towards removing the curse of dimensionality, Proceedings of the thirtieth annual ACM symposium on Theory of computing, p.604-613, May 24-26, 1998, Dallas, Texas, United States [doi>10.1145/276698.276876]
• 11: Ba Tu Truong , Svetha Venkatesh, Generating comprehensible summaries of rushes sequences based on robust feature matching, Proceedings of the international workshop on TRECVID video summarization, p.30-34, September 28-28, 2007, Augsburg, Bavaria, Germany [doi>10.1145/1290031.1290036]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.3 Clustering
          Subjects: Algorithms

General Terms:
Algorithms, Experimentation, Performance

Keywords:
lsh, near-duplicate, video summarization