{"title":"Key Frame Based Video Summarization via Dependency Optimization","authors":"Janya Sainui","volume":134,"journal":"International Journal of Computer and Information Engineering","pagesStart":128,"pagesEnd":135,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10008564","abstract":"As a rapid growth of digital videos and data
\r\ncommunications, video summarization that provides a shorter version
\r\nof the video for fast video browsing and retrieval is necessary.
\r\nKey frame extraction is one of the mechanisms to generate video
\r\nsummary. In general, the extracted key frames should both represent
\r\nthe entire video content and contain minimum redundancy. However,
\r\nmost of the existing approaches heuristically select key frames; hence,
\r\nthe selected key frames may not be the most different frames and\/or
\r\nnot cover the entire content of a video. In this paper, we propose
\r\na method of video summarization which provides the reasonable
\r\nobjective functions for selecting key frames. In particular, we apply
\r\na statistical dependency measure called quadratic mutual informaion
\r\nas our objective functions for maximizing the coverage of the
\r\nentire video content as well as minimizing the redundancy among
\r\nselected key frames. The proposed key frame extraction algorithm
\r\nfinds key frames as an optimization problem. Through experiments,
\r\nwe demonstrate the success of the proposed video summarization
\r\napproach that produces video summary with better coverage of
\r\nthe entire video content while less redundancy among key frames
\r\ncomparing to the state-of-the-art approaches.","references":"[1] A. G. Money, H. Agius, \u201cVideo summarization: a conceptual framework\r\nand survey of the state of the art,\u201d Journal of Visual Communication and\r\nImage Representation, Vol. 19, No. 2, pp. 121-143, 2008.\r\n[2] Ajmal, Muhammad and Ashraf, Muhammad Husnain and Shakir,\r\nMuhammad and Abbas, Yasir and Shah, Faiz Ali, \u201cVideo Summarization:\r\nTechniques and Classification,\u201d Proceedings of the 2012 International\r\nConference on Computer Vision and Graphics, pp. 1\u201313, 2012.\r\n[3] B. T. Troung, S. Venkatesh,\u201cVideo abstraction: a systematic review\r\nand classification,\u201d ACM Transactions Multimedia Computing,\r\nCommunications and Applications, Vol. 3, No. 1, 2007.\r\n[4] M. Furini, F. Geraci, and M. Montangero, \u201cVISTO: Visual STOryboard\r\nfor web video browsing,\u201d CIVR, pp.635-641, 2007.\r\n[5] Z. Li, G. M. Schuster, and A. K. Katsaggelos, \u201cMINMAX optimal video\r\nsummarization,\u201d IEEE Trans Circuits Syst. Video Technol., vol.15, no.10,\r\npp.1245-1256, 2005.\r\n[6] C. Panagiotakis, A. Doulamis, and G. Tziritas, \u201cEquivalent key frames\r\nselection based on iso-content principles,\u201d IEEE Trans. Circuits Syst.\r\nVideo Technol., vol.19, no.3, pp.447-451, 2009.\r\n[7] G. Guan, Z. Wang, S. Lu, J. D. Deng, and D. D. Feng, \u201cKeypoints-based\r\nkeyframe selection,\u201d IEEE Trans. Circuits Syst. Video Technol., vol.23,\r\nno.4, 2013.\r\n[8] S. E. D. Avila, A. B. P, Lopes, L. J. Antonio, and A. d. A. Araujo,\r\n\u201cVSUMM: a mechanism designed to produce static video summaries\r\nand novel evaluation method,\u201d Pattern Recognition Letter, vol.32 (1),\r\npp.56-68, 2011. [9] N. Ejaz, T. B. Tariq, and S. W. Balik, \u201cAdaptive key frame extraction for\r\nvideo summarization using an aggregating mechanism,\u201d Journal of Visual\r\nCommunication and Image Representation, vol.23, pp.1031-1040, 2012.\r\n[10] N. D. Doulamis, A. D. Doulamis, Y. Avrithis, and S. D. Kollias, \u201cA\r\nstochastic framework for optimal frame extraction from MPEG video\r\ndatabases,\u201d Comput. Visi. Image Understand., vol.75, no.1-2, pp.3-24,\r\n1999.\r\n[11] A. Nagasaka and Y. Tanaka, \u201cAutomatic video indexing and full-video\r\nsearch for object appearances,\u201d in Visual Database Systems II, 1992.\r\n[12] Y. Zhuang, Y. Rui, T. Huang, and S. Mehrotra, \u201cAdaptive key frame\r\nextraction using unsupervised clustering,\u201d in Proc. IEEE Int. Image\r\nProcess., pp.866-870, 1998.\r\n[13] P. Mundur, Y. Rao, and Y. Yesha, \u201cKeyframe-based video summarization\r\nusing Delaunay clustering,\u201d International Journal on Digital Libraries\r\n(IJDL) 6(2), pp.219-232, 2006.\r\n[14] M. Furini, F. Geraci, M. Montangero, and M. Pellegrini, \u201cSTIMO: STIll\r\nand MOving video storyboard for the web scenario,\u201d Multimedia Tools\r\nand Applications, vol.46, no.1, pp.47-69, 2010.\r\n[15] J. Almeida, N. J. Leite, and Ricardo da S. Torres, \u201cVISON: VIdeo\r\nSummarization for ONline applications,\u201d Pattern Recogn. Lett. 33, 4\r\n(March 2012), pp. 397-409, 2012.\r\n[16] Z. Zhao and A. Elgammal, \u201cInformation theoretic key frame selection\r\nfor action recognition,\u201d in Proc. Of British machine vision, pp.1-10, 2008.\r\n[17] T. Liu, H. J. Zhang, and F. Qi, \u201cA novel video key-frame-extraction\r\nalgorithm based on perceived motion energy model,\u201d IEEE Trans. Circuits\r\nSyst. Video Technol., vol.13, no.10, pp.1006-1013, 2013.\r\n[18] B. Fauvet, P. Bouthemy, P. Gros, and F. Spindler, \u201cA geometrical\r\nkey-frame selection method exploiting dominant motion estimation in\r\nvideo,\u201d in Proc. CIVR, 2004.\r\n[19] W. Wolf, \u201cKey frame selection by motion analysis,\u201d in Proc. IEEE Int.\r\nConf. Acoust., Speech, and Signal Proc., 1996.\r\n[20] W. Barhoumi and E. Zagrouba, \u201cOn-the-fly extraction of key frames for\r\nefficient video summarization,\u201d AASRI Conference on Intelligent Systems\r\nand Control, vol.4, pp.78-84, 2013.\r\n[21] N. Ejaz, I. Mehmood, and S. W. Baik, \u201cEfficient visual attention based\r\nframework for extracting key frames from videos,\u201d Signal Processing:\r\nImage Communication, vol.28(1), pp.34-44, 2013.\r\n[22] H. Zhang, J.Wu, D. Zhong, and S. W. Smoliar, \u201cAn integrated system for\r\ncontent-based video retrieval and browsing,\u201d Pattern Recognition, vol.30,\r\nno.4, pp.643-658, 1997.\r\n[23] K. Torkkoa, \u201cFeature extraction by non-parametric mutual information,\u201d\r\nJ. Machine Learning Research, vol.3, pp.1415-1438, 2003.\r\n[24] J. Sainui and M. Sugiyama, \u201cDirect approximation of quadratic mutual\r\ninformation and its application to dependence-maximization clustering,\u201d\r\nIEICE Trans. Inf. & Syst., vol.E96-D, no.10, pp.2282-2285, 2013.\r\n[25] J. Sainui and M. Sugiyama, \u201cMinimum dependency key frames selection\r\nvia quadratic mutual information \u201d, The 10th International Conference on\r\nDigital Information Management (ICDIM2015), pp. 148-153, 2015.\r\n[26] M.J. Swain and D.H. Ballard, \u201cColor indexing\u201d, International Journal\r\nof Computer Vision, 7 (11), pp. 11-32, 1991.\r\n[27] The Open Video Project (Online). Available: http:\/\/www.open-video.org\r\n(Accessed on 27\/10\/2015).\r\n[28] Video SUMMarization (Online). Available:\r\nhttps:\/\/sites.google.com\/site\/vsummsite\/download (Accessed on\r\n27\/10\/2015).\r\n[29] (Online). Available: http:\/\/www.liv.ic.unicamp.br\/ jurandy\/vison\/VISON\r\nSummary.zip (Accessed on 16\/05\/2016).\r\n[30] (Online). Available: http:\/\/www.liv.ic.unicamp.br\/\u223cjurandy\/summaries\r\n(Accessed on 16\/05\/2016).","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 134, 2018"}