Abstract
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are represented using a non-linear generative model that explicitly encodes the orientation of the boundary, the velocities on either side, the motion of the occluding edge over time, and the appearance/disappearance of pixels at the boundary. We represent the posterior probability distribution over the model parameters given the image data using discrete samples. This distribution is propagated over time using a particle filtering algorithm. To efficiently represent such a high-dimensional space we initialize samples using the responses of a low-level motion discontinuity detector. The formulation and computational model provide a general probabilistic framework for motion estimation with multiple, non-linear, models.
Similar content being viewed by others
References
Ayer, S. and Sawhney, H. 1995. Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding. In Proc. IEEE International Conference on Computer Vision, Boston, MA, IEEE, pp. 777–784.
Bab-Hadiashar, A. and Suter, D. 1997. Optic flow calculation using robust statistics. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico, pp. 988–993.
Barron, J.L., Fleet, D.J., and Beauchemin, S.S. 1994. Performance of optical flowtechniques. International Journal of Computer Vision, 12(1):43–77.
Beauchemin, S.S. and Barron, J.L. 2000. The local frequency structure of 1d occluding image signals. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(2):200–206.
Bergen, J.R., Anandan, P., Hanna, K., and Hingorani, R. 1992. Hierarchical model-based motion estimation. In Proc. European Conference on Computer Vision, Springer-Verlag, pp. 237–252.
Black, M.J. 1999. Explaining optical flow events with parameterized spatiotemporal models. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, pp. 326–332.
Black, M.J. and Anandan, P. 1990. Constraints for the early detection of discontinuity from motion. In Proc. National Conference on Artificial Intelligence, AAAI-90, Boston, MA, pp. 1060–1066.
Black, M.J. and Anandan, P. 1996. The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding, 63(1):75–104.
Chou, G.T. 1995. A model of figure-ground segregation from kinetic occlusion. In IEEE International Conference on Computer Vision, Boston, MA, pp. 1050–1057.
Cornelius, N. and Kanade, T. 1983. Adapting optical flow to measure object motion in reflectance and X-ray image sequences. In Proc. ACM Siggraph/Sigart Interdisciplinary Workshop on Motion: Representation and Perception, Toronto, Ont., Canada, pp. 50–58.
Fleet, D.J. 1992. Measurement of Image Velocity. Kluwer: Boston.
Fleet, D.J. and Langley, K. 1994. Computational analysis of nonfourier motion. Vision Research, 22:3057–3079.
Fleet, D.J., Black, M.J., Yacoob, Y., and Jepson, A.D. 2000. Design and use of linear models for image motion analysis. International Journal of Computer Vision, 36(3):171–193.
Freeman, W. and Pasztor, E. 1999. Learning low-level vision. In Proc. IEEE International Conference on Computer Vision, Corfu, Greece, pp. 1182–1189.
Gordon, N.J., Salmond, D.J., and Smith, A.F.M. 1993. Novel approach to nonlinear/non-Gaussian Bayesian state estimation. In IEE Proceedings-F, Vol. 140, No 2, pp. 107–113.
Harris, J.G., Koch, C., Staats, E., and Luo, J. 1990. Analog hardware for detecting discontinuities in early vision. International Journal of Computer Vision, 4(3):211–223.
Heitz, F. and Bouthemy, P. 1993. Multimodal motion estimation of discontinuous optical flow using Markov random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(12):1217–1232.
Isard, M. and Blake, A. 1998a. Condensation-conditional density propagation for visual tracking. International Journal of Computer Vision, 29(1):2–28.
Isard, M. and Blake, A. 1998b. ICondensation: Unifying low-level and high-level tracking in a stochastic framework. In Proc. European Conf. on Computer Vision, ECCV-98, H. Burkhardt and B. Neumann (Eds.), Freiburg, Germany, Springer-Verlag, Vol. 1406, LNCS-Series, pp. 893–908.
Jepson, A. and Black, M.J. 1993. Mixture models for optical flow computation. In Partitioning Data Sets: With Applications to Psychology, Vision and Target Tracking, Ingmer Cox, Pierre Hansen, and Bela Julesz (Eds.), AMS Pub.: Providence, pp. 271–286. RI, DIMACS Workshop.
Konrad, J. and Dubois, E. 1988. Multigrid Bayesian estimation of image motion fields using stochastic relaxation. In Proc. IEEE International Conference on Computer Vision, Tampa, Florida, pp. 354–362.
Liu, J.S. and Chen, R. 1998. Sequential Monte Carlo methods for dynamic systems. Journal of the American Statistical Association, 93(443):1032–1044.
Murray, D.W. and Buxton, B.F. 1987. Scene segmentation from visual motion using global optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-9(2):220–228.
Mutch, K. and Thompson, W. 1985. Analysis of accretion and deletion at boundaries in dynamic scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7(2):133–138.
Nagel, H.H. and Enkelmann, W. 1986. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8(5):565–593.
Niyogi, S.A. 1995. Detecting kinetic occlusion. In Proc. IEEE International Conference on Computer Vision, Boston, MA, pp. 1044–1049.
Otte, M. and Nagel, H.H. 1994. Optical flow estimation: Advances and comparisons. In Proc. European Conference on Computer Vision, Stockholm, Sweden, J. Eklundh (Ed.), Springer-Verlag, Vol. 800, LNCS-Series, pp. 51–60.
Potter, J.L. 1980. Scene segmentation using motion information. IEEE Transactions S.M.C., 5:390–394.
Sawhney, H.S. and Ayer, S. 1996. Compact representations of videos through dominant and multiple motion estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8):814–831.
Schunck, B.G. 1989. Image flow segmentation and estimation by constraint line clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(10):1010–1027.
Shulman, D. and Hervé, J. 1989. Regularization of discontinuous flow fields. In Proc. IEEE Workshop on Visual Motion, Irvine, CA, pp. 81–85.
Spoerri, A. and Ullman, S. 1987. The early detection of motion boundaries. In Proc. IEEE International Conference on Computer Vision, London, UK, pp. 209–218.
Thompson, W.B., Mutch, K.M., and Berzins, V.A. 1985. Dynamic occlusion analysis in optical flow fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-7(4):374–383.
Weiss, Y. and Adelson, E.H. 1996. A unified mixture framework for motion segmentation: Incorporating spatial coherence and estimating the number of models. In Proc. IEEE Computer Vision and Pattern Recognition, San Francisco, pp. 321–326.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Black, M.J., Fleet, D.J. Probabilistic Detection and Tracking of Motion Boundaries. International Journal of Computer Vision 38, 231–245 (2000). https://doi.org/10.1023/A:1008195307933
Issue Date:
DOI: https://doi.org/10.1023/A:1008195307933