This Article 
 Bibliographic References 
 Add to: 
Acquiring 3-D Models from Sequences of Contours
February 1994 (vol. 16 no. 2)
pp. 163-178

This paper explores shape from contour for acquiring 3-D graphics models. In this method, a continuous sequence of images is taken as an object rotates. A smooth convex shape can be estimated instantaneously from its contour and by the first derivative of contour movement (trace of contour, or contour distribution with time). We also analyze shapes that do not satisfy the conditions of smoothness and visibility, which are indispensable for modeling an object. A region that does not expose as contour yields a nonsmoothness in the tracked contour movement. We can thus detect such a region by contour distribution filtering and extract its accurate location by computing the left and right derivatives of the distribution. This has not been studied previously. These unknown regions are obtained for further investigation using other visual cues. A general approach for building a geometrical object model using contours is then described. The entire process from silhouettes to a 3-D model is based local computation; this is promising for producing shapes in real time. Our direct goal is to establish 3-D graphics models of human faces for the growing needs of visual communications. We have obtained some good results.

[1] P. Giblin and R. Weiss, "Reconstruction of surface from profiles," inProc. 1st ICCV, pp. 136-144, 1987.
[2] H. Baker and R. Belles, "Generalizing epipolar-plane image analysis on the spatiotemporal surface," inProc. CVPR-88, pp. 2-9, 1988.
[3] D. Terzopoulos, A. Witkin, and M. Kass, "Constraints on deformable models: Recovering 3D shape and nonrigid motion,"Artificial Intell., vol. 36, pp. 91-123, 1988.
[4] A. Blake and G. Brelstaff, "Geometry from specularities," inProc. 2nd ICCV, pp. 394-403, 1988.
[5] J. J. Koenderink,Solid Shape. Cambridge, MA: MIT Press, 1989.
[6] N. Takagi, T. Asada, and S. Yajima, "Redundant CORDIC methods with a constant scale factor for sine and cosine computation,"IEEE Trans. Comput., to be published.
[7] J.Y. Zheng and S. Tsuji, "Panoramic representation of scenes for route understanding," inProc. 10th Int. Conf. Patt. Recogn., 1990, pp. 161-167.
[8] A. Pentland, "Automatic extraction of deformable part models,"Int. J. Comput. Vision, vol. 4, pp. 107-126, 1990.
[9] L. Williams, "Performance-driven facial animation,"Comput. Graphics, vol. 24, no. 4, pp. 235-242.
[10] C. Tomasi and T. Kanade, "Shape without depth," inProc. 3rd ICCV, pp. 91-95, Dec. 1990.
[11] R. Cipolla and A. Blake, "The dynamic analysis of apparent contours," inProc. Third Int. Conf. Comput. Vision, 1990.
[12] D. Terzopoulos and K. Waters, "Analysis of dynamic facial images using physical and anatomical models," inProc. Third Int. Conf. Comput. Vision(Osaka, Japan), 1990, pp. 306-331.
[13] H. Harajima and F. Kishino, "Intelligent image coding and communications with realistic sensations,"IEICE Trans., vol. E 74, no. 6, pp. 1582-1592, June 1991.
[14] J. Y. Zheng, M. Nagashima, and F. Kishino, "Construct a 3-D face model from rotational images,"EIC Technique Rep., IE91-87, pp. 45-50, Nov. 1991.
[15] R. Vaillant and O. D. Faugeras, "Using extremal boundaries for 3-D object modeling,"IEEE Trans. Patt. Anal. Machine Intell., vol. 14, no. 2, pp. 157-173, Feb. 1992.
[16] J. Y. Zheng and F. Kishino, "Verifying and combining different visual cues into a complete 3-D model," inProc. CVPR92, pp. 777-780, June 1992.
[17] J. Y. Zheng and F. Kishino, "3-D model from contours: Further identification of unexposed areas," inProc. 11th ICPR, vol. 1, pp. 349-353, Sept. 1992.
[18] J. Y. Zheng and S. Tsuji, "Panoramic representation of scenes for route recognition by a mobile robot,"Int. J. Comput. Vision, vol. 9, no. 1, pp. 55-77, 1992.
[19] R. P. Bianchini, Jr. and R. Buskens, "An adaptive distributed system-level diagnosis algorithm and its implementation," inProc. Twenty-First Int. Symp. Fault-Tolerant Comput., IEEE, June 1991.
[20] R. Cipolla and A. Blake, "Surface shape from the deformation of apparent contours,"Int. J. Comput. Vision, vol. 9, no. 2, pp. 83-112, 1992.
[21] M. P. Carmo,Differential geometry of curves and surfacesEnglewood Cliffs, NJ: Prentice-Hall, 1976.

Index Terms:
image sequences; filtering and prediction theory; 3-D graphics models acquisition; contour sequences; shape from contour; image sequence; smooth convex shape; tracked contour movement; contour distribution filtering; geometrical object
J.Y. Zheng, "Acquiring 3-D Models from Sequences of Contours," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 2, pp. 163-178, Feb. 1994, doi:10.1109/34.273734
Usage of this product signifies your acceptance of the Terms of Use.