Imposing Integrability in Geometric Shape-from-Shading

  • Mario Castelán
  • Edwin R. Hancock
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)

Abstract

This paper describes a Fourier domain algorithm for surface height recovery using shape from shading. The algorithm constrains surface normals to fall on an irradiance cone. The axis of the cone points in the light source direction. The opening angle of the cone varies with iteration number, and is such that the surface normal minimizes brightness error and satisfies the integrability constraint. The results show that the method recovers needle maps that are both smooth and integrable, with improved surface stability.

Keywords

Machine Intelligence Height Function Hard Constraint Apex Angle Integrability Constraint 
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

  1. 1.
    Bors, A.G., Hancock, E.R., Wilson, R.C.: Terrain Analysis Using Radar Shape from-Shading. IEEE Trans, on Pattern Analysis and Machine Intelligence 25(5) (2003)Google Scholar
  2. 2.
    Erens, R.G.F., Kappers, A.M.L., Koenderink, J.J.: Perception of Local Shape from Shading. Perception and Psychophysics 54(2), 145–156 (1993)CrossRefGoogle Scholar
  3. 3.
    Erens, R.G.F., Kappers, A.M.L., Koenderink, J.J.: Estimating Local Shape from Shading in the Presence of Global Shading. Perception and Psychophysics 54(3), 334–342 (1993)CrossRefGoogle Scholar
  4. 4.
    Frankot, R.T., Chellapa, R.: A Method for Enforcing Integrability in Shape from Shading Algorithms. IEEE Trans. Pattern Analysis and Machine Intelligence 10(4), 438–451 (1988)CrossRefGoogle Scholar
  5. 5.
    Horn, B.K.P., Brooks, M.J.: Shape from Shading. MIT Press, Cambridge (1989)Google Scholar
  6. 6.
    Horn, B.K.P.: Understanding Image Intensities. Artificial Intelligence 8, 201–231 (1977)MATHCrossRefGoogle Scholar
  7. 7.
    Klette, R., SChluns, K.: Height Data from Gradient Fields. In: Proc. Machine Vision Applications, Architectures and Systems Integration, vol. 5, pp. 204–215 (1996)Google Scholar
  8. 8.
    Klette, R., Schluns, K., Koschan, A.: Computer Vision: Three-dimensional Data From Images. Springer, Singapore (1998)MATHGoogle Scholar
  9. 9.
    Koenderink, J.J., Van Doorn, A.J., Kappers, A.M.L.: Surface Perception in Pictures. Perception and Psychophysics 52(5), 487–496 (1992)CrossRefGoogle Scholar
  10. 10.
    Marr, D.: Vision. W.H. Freeman & Co., San Francisco (1982)Google Scholar
  11. 11.
    Nene, S.A., Nayar, S.K., Murase, H.: Columbia Object Image Library: COIL-100. Technical Report CUCS-006-96, Department of Computer Science, Columbia University (February 1996)Google Scholar
  12. 12.
    Robles-Kelly, A., Hancock, E.R.: A Graph-Spectral Method for Surface Height Recovery from Needle-maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Los Alamitos (2001)Google Scholar
  13. 13.
    Worthington, P.L., Hancock, E.R.: Needle Map Recovery Using Robust Regularizers. Image and Vision Computing 17(8), 545–559 (1998)CrossRefGoogle Scholar
  14. 14.
    Worthington, P.L., Hancock, E.R.: New Constraints on Data-closeness and Needle Map Consistency for Shape-from-shading. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(12), 1250–1267 (1999)CrossRefGoogle Scholar
  15. 15.
    Worthington, P.L., Hancock, E.R.: Object Recognition Using Shape-from-Shading. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(5), 535–542 (2001)CrossRefGoogle Scholar
  16. 16.
    Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape from Shading: A Survey. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(8), 690–706 (1999)CrossRefGoogle Scholar
  17. 17.
    Signal Analysis and Machine Perception Laboratory, Department of Electrical Engineering, The Ohio State University, http://sampl.eng.ohio-state.edu/sampl/data/3DDB/RID/index.htm

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Mario Castelán
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Dept. of Computer ScienceUniversity of YorkYorkUnited Kingdom

Personalised recommendations