Motion Recognition Using Nonparametric Image Motion Models Estimated from Temporal and Multiscale Cooccurrence Statistics
|
Abstract—A new approach for motion characterization in image sequences is presented. It relies on the probabilistic modeling of temporal and scale cooccurrence distributions of local motion-related measurements directly computed over image sequences. Temporal multiscale Gibbs models allow us to handle both spatial and temporal aspects of image motion content within a unified statistical framework. Since this modeling mainly involves the scalar product between cooccurrence values and Gibbs potentials, we can formulate and address several fundamental issues: model estimation according to the ML criterion (hence, model training and learning) and motion classification. We have conducted motion recognition experiments over a large set of real image sequences comprising various motion types such as temporal texture samples, human motion examples, and rigid motion situations.
[1] 1619 E. Ardizzone and M. La Cascia, "Video Indexing Using Optical Flow Field," Proc. IEEE Int'l Conf. Image Processing (ICIP), IEEE Press, Piscataway, N.J., 1996, pp. 831-834.
[2] J.S. De Bonet and P. Viola, “Texture Recognition Using a Non-Parametric Multi-Scale Statistical Model,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1998.
[3] Y. Deng and B.S. Manjunath, Content-Based Search of Video Using Color, Texture and Motion Proc. Fourth IEEE Int'l Conf. Image Processing, pp. 543-547, Oct. 1997.
[4] R. Fablet, Modélisation Statistique non Paramétrique et Reconnaissance du Mouvement dans des Sequences d'Images; Applicationàl'Indexation Vidéo PhD thesis, Univ. of Rennes 1, Irisa no. 2526, July 2001.
[5] R. Fablet and P. Bouthemy, Motion-Based Feature Extraction and Ascendant Hierarchical Classification for Video Indexing and Retrieval Proc. Third Int'l Conf. Visual Information Systems, pp 221-228, June 1999.
[6] R. Fablet, P. Bouthemy, and P. Perez, Non Parametric Motion Characterization Using Causal Probabilistic Models for Video Indexing and Retrieval IEEE Trans. Image Processing, vol. 11, no. 4, pp. 393-407, 2002.
[7] A. Fitzgibbon, Stochastic Rigidity: Image Registration for Nowhere-Static Scenes Proc. Seventh IEEE Int'l Conf. Computer Vision, pp. 662-670, July 2001.
[8] F. Heitz and P. Bouthemy, Multimodal Estimation of Discontinuous Optical Flow Using Markov Random Fields IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 12, pp. 1217-1232, Dec. 1993.
[9] B. Horn and B. Schunck, Determining Optical Flow Artificial Intelligence, vol. 17, nos. 1-3, pp. 185-203, 1981.
[10] P. Huber, Robust Statistics. John Wiley&Sons, 1981.
[11] G. Johansonn, Visual Perception of Biological Motion and a Model for Its Analysis Perception and Physics, vol. 14, pp. 201-211, 1973.
[12] R. Nelson and R. Polana, Qualitative Recognition of Motion Using Temporal Texture Computer Vision, Graphics, and Image Processing, vol. 56, no. 1, pp. 78-99, 1992.
[13] J.M. Odobez and P. Bouthemy, Separation of Moving Regions from Background in an Image Sequence Acquired with a Mobile Camera Video Data Compression for Multimedia Computing, H.H. Li, S. Sun, and H. Derin, eds., chapter 8, pp. 295-311, Kluwer, 1997.
[14] C.-H. Peh and L.-F. Cheong, Exploring Video Content in Extended Spatio-Temporal Textures Proc. Workshop Content-Based Multimedia Indexing, pp. 147-153, Oct. 1999.
[15] J. Portilla and E.P. Simoncelli, "A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients," Int'l J. of Computer Vision, 2000, to appear; currently available on the Web at.
[16] P. Saisan, G. Doretto, Y. Wu, and S. Soatto, Dynamic Texture Recognition Proc. IEEE Conf. Computer Vision and Pattern Recognition, Dec. 2001.
[17] M. Szummer and R.W. Picard, “Temporal Texture Modeling,” Proc. IEEE Int'l Conf. Image Processing (ICIP 1996), 1996, also appeared as MIT Media Lab Perceptual Computing TR #381.
[18] R.P. Wildes and J.R. Bergen, Qualitative Spatiotemporal Analysis Using an Oriented Energy Representation Proc. Sixth European Conf. Computer Vision, pp. 768-784, June 2000.
[19] L. Zelnik-Manor and M. Irani, Event-Based Analysis of Video Proc. IEEE Conf. Computer Vision and Pattern Recognition, Dec. 2001.
[20] S.C. Zhu, Y. Wu, and D. Mumford, “Filters Random Fields and Maximum Entropy(Frame)—Towards a Unified Theory for Texture Modeling,” Int'l J. Computer Vision, vol. 27, no. 2, pp. 107-126, 1998.
Index Terms:
Nonparametric motion analysis, motion recognition, multiscale analysis, Gibbs models, cooccurrences, ML criterion.
Citation:
R. Fablet, P. Bouthemy, "Motion Recognition Using Nonparametric Image Motion Models Estimated from Temporal and Multiscale Cooccurrence Statistics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 12, pp. 1619-1624, Dec. 2003, doi:10.1109/TPAMI.2003.1251155
PURCHASE ARTICLE: $19
IEEE Xplore Subscribers
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb