Abstract
In this work, we propose a general method for computing distance between video frames or sequences. Unlike conventional appearance-based methods, we first extract motion fields from original videos. To avoid the huge memory requirement demanded by the previous approaches, we utilize the “bag of motion vectors” model, and select Gaussian mixture model as compact representation. Thus, estimating distance between two frames is equivalent to calculating the distance between their corresponding Gaussian mixture models, which is solved via earth mover distance (EMD) in this paper. On the basis of the inter-frame distance, we further develop the distance measures for both full video sequences.
Our main contribution is four-fold. Firstly, we operate on a tangent vector field of spatio-temporal 2D surface manifold generated by video motions, rather than the intensity gradient space. Here we argue that the former space is more fundamental. Secondly, the correlations between frames are explicitly exploited using a generative model named dynamic conditional random fields (DCRF). Under this framework, motion fields are estimated by Markov volumetric regression, which is more robust and may avoid the rank deficiency problem. Thirdly, our definition for video distance is in accord with human intuition and makes a better tradeoff between frame dissimilarity and chronological ordering. Lastly, our definition for frame distance allows for partial distance.
Similar content being viewed by others
References
Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: ICCV, pp. 1395–1402. IEEE Computer Society, Washington, DC (2005)
Boiman, O., Irani, M.: Similarity by composition. In: Schölkopf, B., Platt, J., Hoffman, T. (eds.) Advances in Neural Information Processing Systems 19. MIT Press, Cambridge, MA (2007)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley-Interscience Publication (2000)
Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: ICCV, pp. 726–733. IEEE Computer Society, Washington, DC (2003)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Comput. Vision 70(1), 41–54 (2006)
Greenspan, H., Dvir, G., Rubner, Y.: Context-dependent segmentation and matching in image databases. Comput. Vis. Image Underst. 93(1), 86–109 (2004)
Greenspan, H., Goldberger, J., Ridel, L.: A continuous probabilistic framework for image matching. Comput. Vis. Image Underst. 84(3), 384–406 (2001)
Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning. Springer (2001)
Ke, Y., Sukthankar, R., Hebert, M.: Efficient visual event detection using volumetric features. In: International Conference on Computer Vision, vol. 1, pp. 166–173. IEEE Computer Society, Washington, DC (2005)
Laptev, I., Lindeberg, T.: Space-time interest points. In: ICCV, pp. 432–439. IEEE Computer Society, Washington, DC (2003)
Li, S.Z.: Markov Random Field Modeling in Image Analysis (Computer Science Workbench). Springer (2001)
Rubner, Y., Guibas, L.J., Tomasi, C.: The earth movers distance, multi-dimensional scaling, and color-based image retrieval. In: APRA Image Understanding Workshop, pp. 661–668 (1997)
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vis. 40(2), 99–121 (2000)
Shechtman, E., Irani, M.: Space-time behavior based correlation. In: CVPR (1), pp. 405–412. IEEE Computer Society, Washington, DC (2005)
Sun, J., Yuan, L., Jia, J., Shum, H.Y.: Image completion with structure propagation. ACM Trans. Graph. 24(3), 861–868 (2005)
Trucco, E., Verri, A.: Introductory Techniques for 3-D Computer Vision. Prentice Hall PTR, Upper Saddle River, NJ (1998)
Wang, F., Zhang, C.: Label propagation through linear neighborhoods. In: ICML, pp. 985–992. ACM, New York, NY (2006)
Wang, Y., Ji, Q.: A dynamic conditional random field model for object segmentation in image sequences. In: CVPR (1), pp. 264–270. IEEE Computer Society, Washington, DC (2005)
Winnemöller, H., Olsen, S.C., Gooch, B.: Real-time video abstraction. ACM Trans. Graph. 25(3), 1221–1226 (2006)
Wu, M., Schoelkopf, B.: A local learning approach for clustering. In: Schölkopf, B., Platt, J., Hoffman, T. (eds.) Advances in Neural Information Processing Systems 19. MIT Press, Cambridge, MA (2007)
Yu, S.X., Shi, J.: Multiclass spectral clustering. In: ICCV, pp. 313–319. IEEE Computer Society, Washington, DC (2003)
Zelnik-Manor, L., Irani, M.: Event-based analysis of video. In: CVPR (2), pp. 123–130. IEEE Computer Society, Los Alamitos, CA (2001)
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Mu, Y., Yan, S., Huang, T. et al. Contextual motion field-based distance for video analysis . Visual Comput 24, 595–603 (2008). https://doi.org/10.1007/s00371-008-0240-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-008-0240-1