Abstract
In this paper, we propose a novel approach of video segmentation into scenes based on the technique of conditional random fields (CRFs). This approach is built upon the design in which scene segmentation is transformed into a label identification problem by defining three types of shots. To implement our algorithm, three middle-level features including shot difference signal, scene transition graph and audio type are extracted to depict the label properties of each shot, and then CRFs model is employed to identify the labels sequence. The advantage of CRFs model lies in its facility in integrating context information of neighboring shots, which produces accurate results in scene segmentation. The proposed approach is verified by seven types of data covering the most major genres of TV program. Experiments on testing data set yield average 0.88 F-measure, which illustrates that the proposed method can accurately detect most scenes in different genres of programs.
This work was supported by the National Natural Science Foundation of China (Grant No.61202326).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Petersohn, C.: Logical unit and scene detection: a comparative survey. In: Multimedia Content Access: Algorithms and Systems II, vol. 6820, pp. 2–17 (2008)
Yeung, M., Yeo, B.L., Liu, B.: Segmentation of video by clustering and graph analysis. Computer Vision and Image Understanding 71, 94–109 (1998)
Chong-Wah, N., Yu-Fei, M., Hong-Jiang, Z.: Video summarization and scene detection by graph modeling. IEEE Transactions on Circuits and Systems for Video Technology 15, 296–305 (2005)
Jianbo, S., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 888–905 (2000)
Rasheed, Z., Shah, M.: Detection and representation of scenes in videos. IEEE Transactions on Multimedia 7, 1097–1105 (2005)
Yun, Z., Shah, M.: Video scene segmentation using markov chain monte carlo. IEEE Transactions on Multimedia 8, 686–697 (2006)
Chasanis, V.T., Likas, A.C., Galatsanos, N.P.: Scene detection in videos using shot clustering and sequence alignment. IEEE Transactions on Multimedia 11, 89–100 (2009)
Sakarya, U., Telatar, Z.: Video scene detection using graph-based representations. Signal Processing: Image Communication 25, 774–783 (2010)
Jinhui, Y., Huiyi, W., Lan, X., Wujie, Z., Jianmin, L., Fuzong, L., Bo, Z.: A formal study of shot boundary detection. IEEE Transactions on Circuits and Systems for Video Technology 17, 168–186 (2007)
Xinbo, G., Xiaoou, T.: Unsupervised video-shot segmentation and model-free anchorperson detection for news video story parsing. IEEE Transactions on Circuits and Systems for Video Technology 12, 765–776 (2002)
Kudo, T.: Crf++: Yet another crf toolkit (2005)
Li, Y., Dorai, C.: Svm-based audio classification for instructional video analysis. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2004), vol. 5, pp. 897–900 (2004)
Sutton, C., McCallum, A.: An Introduction to Conditional Random Fields. ArXiv e-prints (2010)
Klinger, R., Tomanek, K., Klinger, R.: Classical probabilistic models and conditional random fields (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, S., Feng, B., Xu, B. (2013). Temporal Video Segmentation to Scene Based on Conditional Random Fileds. In: Li, S., et al. Advances in Multimedia Modeling. Lecture Notes in Computer Science, vol 7733. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35728-2_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-35728-2_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35727-5
Online ISBN: 978-3-642-35728-2
eBook Packages: Computer ScienceComputer Science (R0)