Abstract
We propose a new framework that allows simultaneous modelling and tracking of articulated objects in real time. We introduce a non-probabilistic graphical model and a new type of message that propagates explicit motion information for realignment of feature constellations across frames. These messages are weighted according to the rigidity of the relations between the source and destination features. We also present a method for learning these weights as well as the spatial relations between connected feature points, automatically identifying deformable and rigid object parts. Our method is extremely fast and allows simultaneous learning and tracking of nonrigid models containing hundreds of feature points with negligible computational overhead.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sudderth, E.B., Mandel, M.I., Freeman, W.T., Willsky, A.S.: Visual hand tracking using nonparametric belief propagation. In: CVPRW 2004, Washington, DC, USA, vol. 12. IEEE Computer Society, Los Alamitos (2004)
Wu, Y., Hua, G., Yu, T.: Tracking articulated body by dynamic markov network. In: ICCV 2003, Washington, DC, USA, p. 1094. IEEE Computer Society, Los Alamitos (2003)
Ross, D.A., Tarlow, D., Zemel, R.S.: Unsupervised learning of skeletons from motion. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 560–573. Springer, Heidelberg (2008)
Yan, J., Pollefeys, M.: Automatic kinematic chain building from feature trajectories of articulated objects. In: CVPR 2006, Washington, DC, USA, pp. 712–719. IEEE Computer Society, Los Alamitos (2006)
Ramanan, D., Forsyth, D.A., Barnard, K.: Building models of animals from video. In: PAMI 2006, vol. 28, pp. 1319–1334 (2006)
Krahnstoever, N., Yeasin, M., Sharma, R.: Automatic acquisition and initialization of articulated models. Mach. Vision Appl. 14, 218–228 (2003)
Declercq, A., Piater, J.H.: On-line simultaneous learning and tracking of visual feature graphs. In: Online Learning for Classification Workshop, CVPRW 2007 (2007)
Yedidia, J.S., Freeman, W.T., Weiss, Y.: Understanding belief propagation and its generalizations, pp. 239–269 (2003)
Sudderth, E.B., Ihler, A.T., Freeman, W.T., Willsky, A.S.: Nonparametric belief propagation. In: CVPR 2003, vol. 1, pp. I–605–I–612 (2003)
Leordeanu, M., Collins, R.: Unsupervised learning of object features from video sequences. In: CVPR 2005, vol. 1, pp. 1142–1149. IEEE Computer Society, Los Alamitos (2005)
Yin, Z., Collins, R.: On-the-fly object modeling while tracking. In: CVPR 2007, pp. 1–8. IEEE Computer Society, Los Alamitos (2007)
Drouin, S., Hébert, P., Parizeau, M.: Incremental discovery of object parts in video sequences. Comput. Vis. Image Underst. 110, 60–74 (2008)
Briers, M., Doucet, A., Singh, S.S.: Sequential auxiliary particle belief propagation. In: 8th Int. Conf. on. Information Fusion, 2005, vol. 1, p. 8 (2005)
Hua, G., Wu, Y.: Multi-scale visual tracking by sequential belief propagation. In: CVPR 2004, vol. 1, pp. 826–833 (2004)
Baker, S., Matthews, I.: Lucas-kanade 20 years on: A unifying framework. Int. J. Comput. Vision 56, 221–255 (2004)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI 1981, pp. 674–679 (1981)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Declercq, A., Piater, J. (2011). Affine Warp Propagation for Fast Simultaneous Modelling and Tracking of Articulated Objects. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6494. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19318-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-19318-7_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19317-0
Online ISBN: 978-3-642-19318-7
eBook Packages: Computer ScienceComputer Science (R0)