Abstract
We describe a 2.5D layered representation for visual motion analysis. The representation provides a global interpretation of image motion in terms of several spatially localized foreground regions along with a background region. Each of these regions comprises a parametric shape model and a parametric motion model. The representation also contains depth ordering so visibility and occlusion are rightly included in the estimation of the model parameters. Finally, because the number of objects, their positions, shapes and sizes, and their relative depths are all unknown, initial models are drawn from a proposal distribution, and then compared using a penalized likelihood criterion. This allows us to automatically initialize new models, and to compare different depth orderings.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
M. J. Black and A. D. Jepson. EigenTracking: Robust matching and tracking of articulated objects using a view-based representation. IJCV, 26:63–84, 1998.
C. Bregler and J. Malik. Tracking people with twists and exponential maps. Proc. IEEE CVPR, pp. 8–15, Santa Barbara, 1998.
T. Cham and J.M. Rehg. A multiple hypothesis approach to figure tracking. Proc. IEEE CVPR, vol. II, pp. 239–245, Fort Collins, 1998.
T. Darrell and A. Pentland. Cooperative robust estimation using layers of support. IEEE PAMI, 17:474–487, 1995.
J.S. de Bonet and P. Viola. Roxels: Responsibility weighted 3d volume reconstruction. Proc. IEEE ICCV, vol. I, pp. 418–425, Corfu, 1999.
A.P. Dempster, N.M. Laird, and D.B. Rubin. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Stat. Soc. B, 39:1–38, 1977.
J. Deutscher, A. Blake, and I. Reid. Articulated body motion capture by annealed particle filtering. Proc. IEEE CVPR, vol. II, pp. 126–133, Hilton Head, 2000.
G. D. Hager and P. N. Belhumeur. Efficient region tracking with parametric models of geometry and llumination. IEEE PAMI, 27:1025–1039, 1998.
S.S. Intille and A.F. Bobick. Recognizing planned, multi-person action. CVIU, 81:1077–3142, 2001.
M. Irani, B. Rousso, and S. Peleg. Computing occluding and transparent motions. IJCV, 12:5–16, 1994.
M. Isard and A. Blake. Condensation-conditional density propagation for visual tracking. IJCV, 29:2–28, 1998.
A. Jepson and M. J. Black. Mixture models for optical flow computation. Proc. IEEE CVPR, pp. 760–761, New York, 1993.
A.D. Jepson, D.J. Fleet and T.F. El-Maraghi. Robust on-line appearance models for visual tracking. Proc. IEEE CVPR, Vol. 1, pp. 415–422, Kauai, 2001.
D. Koller, K. Daniilidis, T. Thorhallson, and H.-H. Nagel. Model-based object tracking in traffic scenes. Proc. ECCV, pp. 437–452. Springer-Verlag, Santa Marguerita, 1992.
J. Listgarten. Exploring qualitative probabilities for image understanding. MSc. Thesis, Dept. Computer Science, Univ. Toronto, October 2000.
J. MacCormick and A. Blake. A probabilistic exclusion principle for tracking multiple objects. Proc IEEE ICCV, vol. I, pp. 572–578, Corfu, 1999.
J. MacCormick and M. Isard. Partitioned sampling, articulated objects, and interface-quality hand tracking. Proc. ECCV, vol. II, pp. 3–19, Dublin, 2000.
F.G. Meyer and P. Bouthemy. Region-based tracking using affine motion models in long image sequences. CVGIP: Image Understanding, 60:119–140, 1994.
C. Rasmussen and G.D. Hager. Probabilistic data association methods for tracking complex visual objects. IEEE PAMI, 23:560–576, 2001.
H. S. Sawhney and S. Ayer. Compact representations of videos through dominant and multiple motion estimation. IEEE PAMI, 18:814–831, 1996.
H. Sidenbladh, M.J. Black, and D.J. Fleet. Stochastic tracking of 3d human figures using 2d image motion. Proc. ECCV, vol. II, pp. 702–718. Springer-Verlag, Dublin 2000.
R. Szeliski and P. Golland. Stereo matching with transparency and matting. IJCV, 32:45–61, 1999.
H. Tao, H.S. Sawhney, and R. Kumar. Dynamic layer representation with applications to tracking. Proc. IEEE CVPR, vol. 2, pp. 134–141, Hilton Head, 2000.
P.H.S. Torr, A.R. Dick, and R. Cipolla. Layer extraction with a Bayesian model of shapes. Proc. ECCV, vol. II, pp. 273–289, Dublin, 2000.
N. Vasconcelos and A. Lippman. Empirical Bayesian motion segmentation. IEEE PAMI, 23:217–221, 2001.
J. Y. A. Wang and E. H. Adelson. Representing moving images with layers. IEEE Trans. Im. Proc., 3:625–638, 1994.
Y. Weiss. Smoothness in layers: Motion segmentation using nonparametric mixture estimation. Proc. IEEE CVPR, pp. 520–526, Puerto Rico, 1997.
Y. Weiss and E. H. Adelson. A unified mixture framework for motion segmentation: Incorporating spatial coherence and estimating the number of models. Proc. IEEE CVPR, pp. 321–326, San Francisco, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jepson, A.D., Fleet, D.J., Black, M.J. (2002). A Layered Motion Representation with Occlusion and Compact Spatial Support. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2350. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47969-4_46
Download citation
DOI: https://doi.org/10.1007/3-540-47969-4_46
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43745-1
Online ISBN: 978-3-540-47969-7
eBook Packages: Springer Book Archive