Abstract
Most past work on video summarization has been based on selecting key frames from videos. We propose a model of video summarization based on three important parameters: Priority (of frames), Continuity (of the summary), and non-Repetition (of the summary). In short, a summary must include high priority frames and must be continuous and non-repetitive. An optimal summary is one that maximizes an objective function based on these three parameters. We show examples of how CPR parameters can be computed and provide algorithms to find optimal summaries based on the CPR approach. Finally, we briefly report on the performance of these algorithms.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
S. Adali, K.S. Candan, S.-S. Chen, K. Erol, and V.S. Subrahmanian, “Advanced video information systems,” ACM Multimedia Systems Journal, Vol. 4, pp. 172–186, 1996.
T.H. Cormen, C.E. Leiserson, R.L. Rivest, and C. Stein, Introduction to Algorithms, 2nd Edition MIT Press, 2001.
D. DeMenthon, D.S. Doermann, and V. Kobla, “Video summarization by curve simplification,” in Proc. ACM Multimedia, Bristol, England, 1998, pp. 211–218.
L. He, E. Sanocki, A. Gupta, and J. Grudin, “Auto-summarization of audio-video presentations,” in ACM Proc. on Multimedia, 1999, pp. 489–498.
S. Ju, M. Black, S. Minneman, and D. Kimber, “Summarization of videotaped presentations: Automatic analysis of motion and gesture,” IEEE Trans. on Circuits and Systems for Video Technology, Vol. 8, No. 5, pp. 686–696, 1998.
Y.P. Ma, L. Lu, H.J. Zhang, and M. Li, “A user attention model for video summarization,” in Proc. ACM Multimedia, 2002.
H. Martin and R. Lozano, “Dynamic generation of video abstracts using an object oriented video DBMS,” Networking and Information Systems Journal, Vol. 3, No. 1, pp. 53–75, 2000.
H.R. Naphide and T.S. Huang, “A probabilistic framework for semantic video indexing, filtering, and retrieval,” IEEE Transactions on Multimedia, Vol. 3, No. 1, pp. 141–151, 2001.
E. Oomoto and K. Tanaka, “OVID: Design and implementation of a video-object database system,” IEEE TKDE (Multimedia Information Systems), Vol. 5, No. 4, pp. 629–643, 1993.
C. Stauffer and E. Grimson, “Learning patterns of activity using real-time tracking,” IEEE Trans. on pattern analysis and machine intelligence, Vol. 22, No. 8, pp. 747–757, 2000.
V.S. Subrahmanian, Principles of Multimedia Database Systems, Morgan Kaufmann, 1998.
D. Zhong and S.F. Chang, “Video object model and segmentation for content-based video indexing,” in IEEE Intern. Conf. on Circuits and Systems, Hong Kong, June, 1997.
W. Zhou, A. Vellaikal, and C.C. Jay Kuo, “Rule-based video classification system for basketball video indexing,” in Proc. ACM Multimedia Workshop, 2000, pp. 213–216.
Author information
Authors and Affiliations
Additional information
Marat Fayzullin has received his PhD degree in Computer Science from the University of Maryland, College Park, in 2004. He has done research in Distributed Simulation Environments, Multimedia Database Algebras, and Automated Content Summarization. His topics of interest also include Mobile Agent Networks and Reasoning with Semantic Networks.
V.S. Subrahmanian received his Ph.D. in Computer Science from Syracuse University in 1989. Since then, he has been on the faculty of the Computer Science Department at the University of Maryland, College Park, where he currently holds the rank of Professor. He also serves as Director of the University of Maryland’s Institute for Advanced Computer Studies (UMIACS) established by the State of Maryland in the mid-1980s to pursue interdisciplinary research involving IT. He received the NSF Young Investigator Award in 1993 and the Distinguished Young Scientist Award from the Maryland Academy of Science/Maryland Science Center in 1997. Prof. Subrahmanian is recognized for his work on nonmonotonic and probabilistic logics, inconsistency management in databases, database models views and inference, rule bases, heterogeneous databases, multimedia databases, and probabilistic databases. More recently, he has developed techniques to “agentize” legacy software, allowing multiple software modules to dynamically collaborate with each other to solve complex problems. He has edited two books, one on nonmonotonic reasoning (MIT Press) and one on multimedia databases (Springer). He has co-authored an advanced database textbook (Morgan Kaufman, 1997) and a book on heterogeneous software agents. He is the sole author of the best known textbook on multimedia databases (Morgan Kaufmann)—a second edition of this book is under preparation. Prof. Subrahmanian has given invited talks at numerous national and international conferences—in addition, he has served on numerous conference and funding panels, as well as on the program committees of numerous conferences. He has also chaired several conferences. Prof. Subrahmanian is or has previously been on the editorial board of IEEE Transactions on Knowledge and Data Engineering, Artificial Intelligence Communications, Multimedia Tools and Applications, Journal of Logic Programming, Annals of Mathematics and Artificial Intelligence, Distributed and Parallel Database Journal, and Theory and Practice of Logic Programming.
Prof. Subrahmanian has served on DARPA’s (Defense Advanced Research Projects Agency) Executive Advisory Council on Advanced Logistics and as an ad-hoc member of the US Air Force Science Advisory Board (2001).
Antonio Picariello received the Laurea degree in Electronics Engineering from the University of Napoli, Italy, in 1991. In 1993 he joined the Istituto Ricerca Sui Sistimi Informatici Paralleli, The National Research Council, Napoli, Italy. He received a Ph.D. degree in Computer Science and Engineering in 1998 from the University of Naples “Federico II”. In 1999, he joined the Dipartimento di Informatica e Sistemistica, University of Napoli “Federico II”, Italy, and is currently an Associate Professor of Data Base. He has been active in the field of Computer Vision, Medical Image Processing and Pattern Recognition, Object-Oriented models for image processing, Multimedia Data Base and Information Retrieval. His current research interests lie in Knowledge Extraction and Management, Multimedia Integration and Image and Video databases. He is a member of the International Association of Pattern Recognition.
Maria Luisa Sapino has got her master degree and Ph.D. in Computer Science at the University of Torino, where she’s currently Associate Professor. She initially worked in the area of logic programming and artificial intelligence, specifically interested in the semantics of negation in logic programming, and in the abductive extensions of logic programs. Her current research interests include heterogeneous and multimedia databases, in particular similarity based information retrieval, and modeling and querying multimedia presentations. She has been serving as a reviewer for several international conferences and journals.
Rights and permissions
About this article
Cite this article
Fayzullin, M., Subrahmanian, V.S., Picariello, A. et al. The CPR Model for Summarizing Video. Multimed Tools Appl 26, 153–173 (2005). https://doi.org/10.1007/s11042-005-0451-7
Issue Date:
DOI: https://doi.org/10.1007/s11042-005-0451-7