Relevance Ranking of Video Data Using Hidden Markov Model Distances and Polygon Simplification
A video can be mapped into a multidimensional signal in a non-Euclidean space, in a way that translates the more predictable passages of the video into linear sections of the signal. These linear sections can befiltered out by techniques similar to those used for simplifying planar curves. Different degrees of simplification can be selected. We have refined such a technique so that it can make use of probabilistic distances between statistical image models of the video frames. These models are obtained by applying hidden Markov model techniques to random walks across the images. Using our techniques, a viewer can browse a video at the level of summarization that suits his patience level. Applications include the creation of a smart fast-forward function for digital VCRs, and the automatic creation of short summaries that can be used as previews before videos are downloaded from the web.
KeywordsHide Markov Model Video Data Video Summarization Video Player Image Stream
Unable to display preview. Download preview PDF.
- 1.Anders, J.,Java MPEG page,http://rnvs.informatik.tu-chemnitz.de/_ja/MPEG/MPEG Play.html
- 3.DeMenthon, D.F., Kobla, V., M., and Doermann, D., “Video Summarization by Curve Simplification”, Technical Report LAMP-TR-018, CAR-TR-889, July 1998; also ACM Multimedia 98, Bristol, England, pp. 211–218, 1998.Google Scholar
- 4.DeMenthon, D.F., Vuilleumier Stückelberg, M., and Doermann, D., “Hidden Markov Models for Images”, Int. Conf. on Pattern Recognition, Barcelona, Spain, 2000.Google Scholar
- 5.Foote, J., Boreczky, J., Girgensohn, A., and Wilcox, L. (1998), “An Intelligent Media Browser using Automatic Multimodal Analysis”, ACM Multimedia 98, Bristol,England, pp. 375–380, 1998.Google Scholar
- 7.Hershberger, J., and Snoeyink, J. “Speeding up the Douglas-Peucker Line-Simplification Algorithm”, http://www.cs.ubc.ca/cgi-bin/tr/1992/TR-92-07.
- 8.Huang, J., Kumar, S.R., Mitra, M., Zhu, W-J., and Zabih, R., “Image Indexing Using Color Correlograms”, IEEE Conf. on Computer Vision and Pattern Recognition, pp. 762–768, 1997.Google Scholar
- 11.Latecki, L.J. and LakÄmper, R., “Shape Similarity Measure Based on Correspondence of Visual Parts”, IEEE Trans. on Pattern Analysis and Machine Intelligence,to appear.Google Scholar
- 12.Rabiner, L.R., and Juang, B.-H., “Fundamentals of Speech Processing”, Prentice Hall, pp. 321–389, 1993.Google Scholar
- 14.Smith, M.A., and Kanade, T., “Video Skimming for Quick Browsing Based on Audio and Image Characterization”, IEEE Conf. on Computer Vision and Pattern Recognition, 1997.Google Scholar
- 15.Yeung, M.M., Yeo, B-L., Wolf, W. and Liu, B.,“Video Browsing using Clustering and Scene Transitions on Compressed Sequences”, SPIE Conf. on MultimediaComputing and Networking, vol. 2417, pp. 399–413, 1995.Google Scholar
- 16.Yoon, K., DeMenthon, D.F., and Doermann, D., “Event Detection from MPEG Video in the Compressed Domain”, Int. Conf. on Pattern Recognition, Barcelona, Spain, 2000.Google Scholar
- 17.Zhang, H.J., Low, C.Y., Smoliar, S.W., and Wu, J.H., “Video Parsing, Retrieval and Browsing: An Integrated and Content-Based Solution”, ACM Multimedia, 1995.Google Scholar