Abstract
The paper is focused on the problem of estimating 3D structure and motion of nonrigid object from a monocular video sequence. Many previous methods on this problem utilize the extension technique of factorization based on rank constraint to the tracking matrix, where the 3D shape of nonrigid object is expressed as weighted combination of a set of shape bases. All these solutions are based on the assumption of affine camera model. This assumption will become invalid and cause large reconstruction errors when the object is close to the camera. The main contribution of this paper is that we extend these methods to the general perspective camera model. The proposed algorithm iteratively updates the shape and motion from weak perspective projection to fully perspective projection by refining the scalars corresponding to the projective depths. Extensive experiments on real sequences validate the effectiveness and improvements of the proposed method.
The work is partly supported by the National Natural Science Foundation of China.
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.
Similar content being viewed by others
References
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. IJCV 9(2), 137–154 (1992)
Poelman, C., Kanade, T.: A paraperspective factorization method for shape and motion recovery. IEEE T-PAMI 19(3), 206–218 (1997)
Christy, S., Horaud, R.: Euclidean shape and motion from multiple perspective views by affine iterations. IEEE T-PAMI 18(11), 1098–1104 (1996)
Triggs, B.: Factorization methods for projective structure and motion. In: Proc. CVPR (1996)
Heyden, R., Berthilsson, et al.: An iterative factorization method for projective structure and motion from image sequences. Image and Vision Computing 17(13) (1999)
Mahamud, S., Hebert, M.: Iterative projective reconstruction from multiple views. In: Proc. CVPR, vol. 2, pp. 430–437 (2000)
Costeira, J.P., Kanade, T.: A multibody factorization method for independently moving-objects. IJCV 29(3), 159–179 (1998)
Han, M., Kanade, T.: Reconstruction of a scene with multiple linearly moving objects. In: Proc. CVPR (2000)
Bascle, B., Blake, A.: Separability of pose and expression in facial tracing and animation. In: Proc. ICCV, pp. 323–328 (1998)
Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: Proc. CVPR (2000)
Torresani, L., Yang, D., et al.: Tracking and modeling non-rigid objects with rank constraints. In: Proc. CVPR (2001)
Brand, M.: Morphable 3D models from video. In: Proc. CVPR, vol. 2, pp. 456–463 (2001)
Xiao, J., Chai, J., Kanade, T.: A closed-form solution to non-rigid shape and motion recovery. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 573–587. Springer, Heidelberg (2004)
Xiao, J., Kanade, T.: Non-rigid shape and motion recovery: Degenerate deformations. In: Proc. CVPR, pp. 668–675 (2004)
Del Bue, A., Agapito, L.: Non-rigid 3D shape recovery using stereo factorization. In: Proc. ACCV (2004)
Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2000)
Pollefeys, M., Koch, R., Van Gool, L.: Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters. IJCV 32(1), 7–25 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, G., Tian, Y., Sun, G. (2005). Modelling Nonrigid Object from Video Sequence Under Perspective Projection. In: Tao, J., Tan, T., Picard, R.W. (eds) Affective Computing and Intelligent Interaction. ACII 2005. Lecture Notes in Computer Science, vol 3784. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11573548_9
Download citation
DOI: https://doi.org/10.1007/11573548_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29621-8
Online ISBN: 978-3-540-32273-3
eBook Packages: Computer ScienceComputer Science (R0)