This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Parametric Shape-from-Shading by Radial Basis Functions
April 1997 (vol. 19 no. 4)
pp. 353-365

Abstract—In this paper, we present a new method of shape from shading by using radial basis functions to parameterize the object depth. The radial basis functions are deformed by adjusting their centers, widths, and weights such that the intensity errors are minimized. The initial centers and widths are arranged hierarchically to speed up convergence and to stabilize the solution. Although the smoothness constraint is used, it can be eventually dropped out without causing instabilities in the solution. An important feature of our parametric shape-from-shading method is that it offers a unified framework for integration of multiple sensory information. We show that knowledge about surface depth and/or surface normals anywhere in the image can be easily incorporated into the shape from shading process. It is further demonstrated that even qualitative knowledge can be used in shape from shading to improve 3D reconstruction. Experimental comparisons of our method with several existing ones are made by using both synthetic and real images. Results show that our solution is more accurate than the others.

[1] M.J. Brooks and B.K.P. Horn, "The Variational Approach to Shape From Shading," Computer Vision, Graphics and Image Processing, vol. 33, pp. 174-208, 1986.
[2] M.J. Brooks and B.K.P. Horn, "Shape and Source From Shading," Proc. Int'l Joint Conf. Artificial Intelligence,Los Angeles, 1985, pp. 932-936.
[3] A.M. Bruckstein, "On Shape From Shading," Computer Vision, Graphics and Image Processsing, vol. 44, pp. 139-154, 1988.
[4] R. Courant and D. Hilbert, Methods of Mathematical Physics, vol. 1. New York: Interscience Publishers, 1953.
[5] P. Dupuis and J. Oliensis, Direct Method for Reconstructing Shape from Shading Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 453-458, June 1992.
[6] F.P. Ferrie and M.D. Levine, "Where and Why Local Shading Analysis Works," IEEE Trans. Pattern Analysis Machine Intelligence, vol. 11, no. 2, pp. 198-206, 1989.
[7] R.T. Frankot and R. Chellappa, “A Method for Enforcing Integrabilty in Shape from Shading Algorithms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no. 4, pp. 439-451, Apr. 1988.
[8] A. Goshtasby and W.D. O'Neill, "Curve Fitting by a Sum of Gaussians," CVGIP: Graphical Models and Image Processing, vol. 56, no. 4, pp. 281-288, 1994.
[9] J.W. Hsieh, H.Y.M. Liao, M.T. Ko, and K.C. Fan, "Wavelet-Based Shape From Shading," Graphical Models and Image Processing, vol. 57, no. 4, pp. 343-362, 1994.
[10] B.K.P. Horn, "Obtaining Shape From Shading Information," P.H. Winston, ed., The Psychology of Computer Vision.New York: McGraw Hill, 1975, pp. 115-155.
[11] B.K.P. Horn, "Height and Gradient From Shading," Int'l J. Computer Vision, vol. 5, no. 1, pp. 37-75, 1990.
[12] B.K.P. Horn and M.J. Brooks eds., Shape From Shading.Cambridge, Mass.: McGraw Hill, 1989
[13] K. Ikeuchi, and B.K.P. Horn, "Numerical Shape From Shading and Occluding Boundaries," Artificial Intelligence, vol. 17, pp. 141-184, 1981.
[14] A.G. Jones and C.J. Taylor, "Robust Shape From Shading," Image Vision Computing, vol. 12, no. 7, pp. 411-421, 1994.
[15] K. Kimmel and A.M. Bruckstein, "Tracking Level Sets by Level Sets: A Method for Solving the Shape From Shading Problem," Computer Vision and Image Understanding, vol. 62, no. 2, pp. 47-58, 1995.
[16] Y.G. Leclerc and A.F. Bobick, “The Direct Computation of Height from Shading,” IEEE Computer Vision and Pattern Recognition, pp. 552-558, 1991.
[17] C.-H. Lee and A. Rosenfeld, "Improved Methods of Estimating Shape From Shading Using the Light Source Coordinate System," Artificial Intelligence, vol. 26, pp. 125-143, 1985.
[18] K.M. Lee and C.C.J. Kuo, “Shape from Shading with a Linear Triangular Element Surface Model,” IEEE Pattern Analysis and Machine, vol. 15, no. 8, pp. 815-822, 1993.
[19] K.M. Lee and C.C.J. Kuo, "Shape From Shading With Perspective Projection," CVGIP: Image Understanding, vol. 59, no. 2, pp. 202-212, 1994.
[20] K.M. Lee and C.C.J. Kuo, "Surface Reconstruction From Photometric Stereo Images," J. Opt. Soc. Am. A, vol. 10, no. 5, pp. 855-868, 1993.
[21] S.Z. Li, "On Discontinuity-Adaptive Smoothness Priors in Computer Vision," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 6, pp. 576-586, June 1995.
[22] J. Moody and C.J. Darken, "Fast Learning in Networks of Locally-Tuned Processing Units," Neural Computation, vol. 1, pp. 281-294, 1989.
[23] S.K. Nayar, K. Ikeuchi, and T. Kanade, “Shape from Interreflections,” Proc. Int'l Conf. Computer Vision, pp. 1-11, 1990.
[24] J. Oliensis, "Uniqueness in Shape From Shading," Int'l J. Computer Vision, vol. 6, no. 2, pp. 75-104, 1991.
[25] J. Park and I.W. Sandberg, "Universal Approximation Using Radial-Basis-Function Networks," Neural Computation, vol. 3, pp. 246-257, 1991.
[26] A.P. Pentland, "Local Shading Analysis," IEEE Trans. Pattern Analysis Machine Intelligence, vol. 6, pp. 170-187, 1984.
[27] T. Poggio, V. Torre, and C. Koch, "Computational Vision and Regularization Theory," Nature, vol. 317, pp. 314-319, 1985.
[28] T. Poggio and F. Girosi, Networks for Approximation and Learning Proc. IEEE, vol. 78, pp. 1481-1497, 1990.
[29] M.J.D. Powell, "Radial Basis Functions for Multivariate Interpolation: A Review," Algorithms for Approximation, J.C. Mason and M.G. Cox, eds. Oxford, 1987, pp. 143-167.
[30] W.H. Press et al., Numerical Recipes in C: The Art of Scientific Computing, second edition. Cambridge University Press, 1992.
[31] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning Internal Representation by Error Propagation," D.E. Rumelhart and J.L. McClelland, eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318-362.Cambridge Mass.: MIT Press, 1986
[32] S.A. Shafer, "Using Color to Separate Reflection Components," Color Research and Applications, vol. 10, no. 2, pp. 210-218, 1985.
[33] M. Shao, R. Chellapa, and T. Simchony, "Reconstructing a 3D Depth Map From One or More Images," CVGIP: Image Understanding, vol. 53, no. 2, pp. 219-226, 1991.
[34] R. Szeliski, "Fast Shape From Shading," Computer Vision, Graphics and Image Processing: Image Understanding, vol. 53, no. 2, pp. 125-153, 1991.
[35] D. Terzopoulos, "Image Analysis Using Multigrid Relaxation Methods," IEEE Trans. Pattern Analysis Machine Intelligence, vol. 8, no. 2, pp. 129-139, 1986.
[36] D. Terzopoulos, "Regularization of Inverse Visual Problems Involving Discontinuities," IEEE Trans. Pattern Analysis Machine Intelligence, vol. 8, no. 4, pp. 129-424, 1986.
[37] L.B. Wolff and T.E. Boult, Constraining Object Features Using a Polarization Reflectance Model IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 635-657, July 1991.
[38] G.Q. Wei and G. Hirzinger, "Learning Shape From Shading by a Multilayer Network," IEEE Trans. Neural Networks, vol. 17, no. 4, pp. 985-995, July 1996.
[39] R. Zhang, P.S. Tsai, J.E. Cryer, and M. Shah, "Analysis of Shape From Shading Techniques," Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, pp. 377-384, 1994.
[40] Q. Zheng and R. Chellappa, Estimation of Illuminant Direction, Albedo, and Shape from Shading IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 680-702, July 1991.

Index Terms:
Shape from shading, radial basis functions, hierarchical structure, depth constraints, normals constraints, qualitative knowledge, stochastic gradient method.
Citation:
Guo-Qing Wei, Gerd Hirzinger, "Parametric Shape-from-Shading by Radial Basis Functions," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 4, pp. 353-365, April 1997, doi:10.1109/34.588016
Usage of this product signifies your acceptance of the Terms of Use.