Combining graph connectivity & dominant set clustering for video summarization
The paper presents an automatic video summarization technique based on graph theory methodology and the dominant sets clustering algorithm. The large size of the video data set is handled by exploiting the connectivity information of prototype frames that are extracted from a down-sampled version of the original video sequence. The connectivity information for the prototypes which is obtained from the whole set of data improves video representation and reveals its structure. Automatic selection of the optimal number of clusters and hereafter keyframes is accomplished at a next step through the dominant set clustering algorithm. The method is free of user-specified modeling parameters and is evaluated in terms of several metrics that quantify its content representational ability. Comparison of the proposed summarization technique to the Open Video storyboard, the Adaptive clustering algorithm and the Delaunay clustering approach, is provided.
KeywordsVideo summary Prototype set Connectivity graph Dominant set
This work was financed by the European Social Fund (ESF), Operational Program for Educational and Vocational Training II (EPEAEK II), and particularly the Program “New graduate programs of University of Patras”.
- 1.Behzard S, Gibbon DS (1995) Automatic generation of pictorial transcripts of video programs. Proc SPIE Multimedia Computer Networking 2417:512–518Google Scholar
- 2.Boreczky JS, Rowe LA (1996) Comparison of video shot boundary detection techniques. Proc Int Conf Storage Retr Still Image Video Databases 5(2):170–179Google Scholar
- 3.Bovic AC (2000) Handbook of image and video processing. Bovic Academic Press 2000 9(2):705–715Google Scholar
- 5.Cooper M, Foote J (2005) Discriminative techniques for keyframe selection. IEEE Int. Conf Multimedia and Expo (ICME) 502–505Google Scholar
- 6.DeMenthon D, Doermann DS, Kobla V (1998) Video summarization by curve simplification. Proc. ACM Multimedia 211–218Google Scholar
- 7.Divakaran A, Radhakrishnanp R, Peker KA (2002) Motion activity-based extraction of key-frames from video shots. Int Conf Image Process 1:932–935Google Scholar
- 8.Dufaux F (2000) Key frame selection to represent a video. Proc ICIP Conf 2:275–278Google Scholar
- 9.Gibson DNC, Thomas B (2002) Visual abstraction of wildlife footage using Gaussian mixture models. Proc. 15th Int. Conf Vision InterfaceGoogle Scholar
- 13.He L, Sanocki E, Gupta A, Grudin J (1999) Auto-Summarization of audio-video presentations. Proc. ACM Multimedia Conf. (ACMMM) 489–498Google Scholar
- 15.Latecki LJ, Widldt DD, Hu J (2001) Extraction of key frames from videos by optimal color composition matching and polygon simplification. Proc. Multimedia Signal Process Conf. (France)Google Scholar
- 16.Liu T, Kender JR (2002) An efficient error-minimizing algorithm for variable-rate temporal video sampling. Proc. Int. Conf. Multimedia Expo (ICME)Google Scholar
- 19.Marchionini G, Geisler G (2002) The open video digital library. D-Lib 8(12). doi: 10.1045/december2002-marchionini
- 23.Ueda H, Miyatake T, Yoshizawa S (1991) Impact: an interactive natural picture dedicated multimedia authoring systems. Proc. SIGCHI Conf Human factors Computer Systems 343–350Google Scholar
- 24.Weibull JW (1995) Evolutionary game theory. MIT PressGoogle Scholar
- 26.The Open Video Project http://www.open-video.org/
- 27.The MPEG Software Simulation Group http://www.mpeg.org/MPEG/MSSG/.
- 28.Yahiaoui I, Merialdo B, Huet B (2001) Automatic video summarization. Proc. CBMIR ConfGoogle Scholar
- 30.Yu X D, Wang L, Tian Q, Xue P (2004) Multi-level video representation with application to keyframe extraction. Proc. Int. Conf. Multimedia Modelling (MMM) 117–121Google Scholar
- 32.Zhuang Y, Rui Y, Huang TS, Mehrotra S (1998) Adaptive key frame extraction using unsupervised clustering. Proc Int Conf Image Process 1:866–870Google Scholar