Abstract
In video information retrieval, key frame extraction has been recognized as one of the important research issues. Although much progress has been made, the existing approaches are either computationally expensive or ineffective in capturing salient visual content. In this paper, we first discuss the importance of key frame extraction and then briefly review and evaluate the existing approaches. To overcome the shortcomings of the existing approaches, we introduce a new algorithm for key frame extraction based on unsupervised clustering. Meanwhile, we provide a feedback chain to adjust the granularity of the extraction result. The proposed algorithm is both computationally simple and able to capture the visual content. The efficiency and effectiveness are validated by large amount of real-world videos.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aigrain P, Zhang H, Petkovic D. Content-based representation and retrieval of visual media: A state-of-the-art review.Multimedia Tools and Applications, Nov. 1996, 3.
Voreczky J S, Rowe L A. Comparison of video shot boundary detection techniques., InProc. SPIE Conf. Vis. Commun. and Image Processing 1996.
Zhang H J, Wang J Y A, Altunbasak Y. Content-based video retrieval and compression: A unified solution. InProc. IEEE Int. Conf. Image Processing 1997.
Nagasaka A, Tanaka Y. Automatic video indexing and full-video search for object appearances. InVisual Database Systems II, 1992.
Zhang H, Wu J, Zhong D, Smoliar S W. An integrated system for content-based video retrieval and browsing.Pattern Recognition, 1997, 30(4): 643–658.
Wolf W. Key frame selection by motion analysis. InProc. IEEE Int. Conf. Acoust., Speech, and Signal Processing 1996.
Gresle P O, Huang T S. Gisting of video documents: A key frames selection algorithm using relative activity measure. InThe 2nd Int. Conf. Visual Information Systems, 1997.
Horn B K P, Schunck B G. Determining optical flow.Artificial Intelligence, 1981, 17: 185–203.
Duda R O, Hart P E. Pattern Classification and Scene Analysis. John Wiley and Sons, Inc., ch.6, pp.211–249.
Rabiner L, Juang B-H. Fundamentals of Speech Recognition. Englewood Cliffs, New Jersey: Prentice Hall, 1993, ch.5.
Zhuang Y, Rui Y, Huang T S, Mehrotra S. Adaptive key frame extraction using unsupervised clustering. InProc. IEEE Int. Conf. Image Processing (Chicago, USA), Oct. 1998.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the National Natural Science Foundation of China.
ZHUANG Yueting has been an Associate Professor of the Department of Computer Science, Zhejiang University since 1994. From Feb. 1997 to Aug. 1998, he studied at University of Illinois at Urbana-Champaign as a visiting scholar. His research interests are content-based video/image retrieval, multimedia information retrieval, intelligent CAD.
RUI Yong is a PhD candidate at ECE of University of Illinois at Urbana-Champaign. His research area is in content-based image/video indexing and retrieval, and multimedia database. He is a Research Assistant at Image Formation and Processing Group, the Beckman Institute.
Thomas S. Huang received his Sc.D. degree from MIT in 1963. He is a Professor in ECE and CSL at UIUC and a full-time Beckman Institute faculty member in the Image Formation and Processing and Artificial Intelligence groups. His fields of professional interest are computer vision, image compression and enhancement, pattern recognition, and sigual processing.
Rights and permissions
About this article
Cite this article
Zhuang, Y., Rui, Y. & Huang, T.S. Video key frame extraction by unsupervised clustering and feedback adjustment. J. of Comput. Sci. & Technol. 14, 283–287 (1999). https://doi.org/10.1007/BF02948517
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02948517