Danilo Barbosa Coimbra
ABSTRACT
This paper proposes a new technique to segment digital video into semantic units called scenes. This technique is derived from the combined use of color histograms and silence detection, visual and aural features, respectively. The category of digital video used in this work is television news. The results show that the technique can identify more than 80% of the video scenes.
- }}A. Barla, F. Odone, and A. Verri. Histogram intersection kernel for image classification. In Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, volume 3, pages III-513--16 vol. 2, 2003.Google Scholar
Cross Ref
- }}J. Calic and E. Izquierdo. Temporal segmentation of mpeg video streams. EURASIP J. Appl. Signal Process., 2002(1):561--565, 2002. Google ScholarDigital Library
- }}J.-R. Cao. Algorithm of scene segmentation based on svm for scenery documentary. icnc, 3:95--98, 2007. Google ScholarDigital Library
- }}A. Dong and H. Li. Semantic segmentation of documentary video using music breaks. icme, 0:1825--1828, 2006.Google Scholar
- }}J. Han and K.-K. Ma. Fuzzy color histogram and its use in color image retrieval. Image Processing, IEEE Transactions on, 11(8):944--952, 2002. Google ScholarDigital Library
- }}A. Hanjalic. Content-Based Analysis of Digital Video. Kluwer Academic Publishers, 2004. 193 pags.Google ScholarDigital Library
- }}H. Jiang, T. Lin, and H.-J. Zhang. Video segmentation with the assistance of audio content analysis. In Proc. IEEE International Conference on Multimedia and Expo ICME 2000, volume 3, pages 1507--1510 vol. 3, 2000.Google ScholarCross Ref
- }}W. Lee, H. Kim, H. Kang, J. Lee, Y. Kim, and S. Jeon. Video cataloging system for real-time scene change detection of news video. pages 705--715. 2005.Google Scholar
- }}Y. Li, S. Narayanan, and C. Kuo. Content-based movie analysis and indexing based on audiovisual cues. 14(8):1073--1085, 2004. Google ScholarDigital Library
- }}Y. Li and D. Zhang, Tong anf Tretter. An overview of video abstraction techniques. Technical report, HP Image Systems Laboratory, Palo Alto, CA, 2001.Google Scholar
- }}L. Lu, H. Jiang, and H. Zhang. A robust audio classification and segmentation method. In MULTIMEDIA '01: Proceedings of the ninth ACM international conference on Multimedia, pages 203--211, 2001. Google ScholarDigital Library
- }}X. Shao, C. Xu, N. C. Maddage, Q. Tian, M. S. Kankanhalli, and J. S. Jin. Automatic summarization of music videos. ACM Trans. Multimedia Comput. Commun. Appl., 2(2):127--148, 2006. Google ScholarDigital Library
- }}T. Zhang and C.-C. Kuo. Hierarchical classification of audio data for archiving and retrieving. In Acoustics, Speech, and Signal Processing, 1999. ICASSP '99. Proceedings., 1999 IEEE International Conference on, volume 6, pages 3001--3004 vol. 6, Mar 1999. Google ScholarDigital Library
- }}L. Zhao, S.-Q. Yang, and B. Feng. Video scene detection using slide windows method based on temporal constrain shot similarity. In Proc. IEEE International Conference on Multimedia and Expo ICME 2001, pages 1171--1174, 2001.Google ScholarCross Ref
- }}S. Zhu and Y. Liu. A novel scheme for video scenes segmentation and semantic representation. In Proc. IEEE International Conference on Multimedia and Expo, pages 1289--1292, 2008.Google Scholar
Index Terms
- Digital video scenes identification using audiovisual features
Recommendations
Salient objects detection in dynamic scenes using color and texture features
Visual saliency is an important research topic in the field of computer vision due to its numerous possible applications. It helps to focus on regions of interest instead of processing the whole image or video data. Detecting visual saliency in still ...
Using the eyes to encode and recognize social scenes
ETRA '06: Proceedings of the 2006 symposium on Eye tracking research & applicationsIn a previous study, we found that observers look mostly at the eyes when viewing natural scenes containing one or more people (Birmingham et al. submitted). This prioritization of eye regions occurred regardless of the type of scene being viewed (e.g. ...
Robust TV news story identification via visual characteristics of anchorperson scenes
PSIVT'06: Proceedings of the First Pacific Rim conference on Advances in Image and Video TechnologyIn this paper, a new scheme for TV news segmentation via exploring the efficient visual features is proposed especially for TV news which contains lots of changeful background of anchorperson shots. The proposed scheme can be divided into two parts: ...
Comments