Abstract
This paper demonstrates how a new shape form shading scheme can be used to extract topographic information from 2D intensity imagery. The shape-from-shading scheme has two novel ingredients. Firstly, it uses a geometric update procedure which allows the image irradiance equation to be satisfied as a hard-constraint. This not only improves the data-closeness of the recovered needle-map, but also removes the necessity for extensive parameter tuning. Secondly, we use curvature information to impose topographic constraints on the recovered needlemap. The topographic information is captured using the shape-index of Koenderink and van Doorn [14] and consistency is imposed using a robust error function. We show that the new shape-from-shading scheme leads to a meaningful topographic labelling of 3D surface structures.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Belhumeur, P. N. and Kriegman, D. J. (1996) What is the Set of Images of an Object Under All Possible Lighting Conditions? Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 270–277.
Bichsel, M. and Pentland, A. P. (1992) A Simple Algorithm for Shape from Shading, Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 459–465.
Brooks, M. J. and Horn, B. K. P. (1986) Shape and Source from Shading, IJCAI, pp. 932–936, 1985.
Bruckstein, A. M. (1988) On Shape from Shading, CVGIP, Vol. 44, pp. 139–154.
Dorai C.and Jain A. K., “Shape Spectrum based View Grouping and Matching of 3D free-from objects”, IEEE PAMI, 19, pp. 1139–1146, 1997.
Ferrie, F. P. and Lagarde, J. (1990)Curvature Consistency Improves Local Shading Analysis, Proc. IEEE International Conference on Pattern Recognition, Vol. I, pp. 70–76.
Hoaglin, D. C., Mosteller, F. and Tukey, J. W. (eds.) (1983) Understanding robust and exploratory data analysis, Wiley, New York.
Horn, B. K. P. (1975) Obtaining Shape from Shading Information. In Winston, P.H. (ed.), The Psychology of Computer Vision, McGraw Hill, NY, pp.115–155.
Horn, B. K. P. and Brooks, M.J. (1986) The Variational Approach to Shape from Shading, CVGIP, Vol. 33, No. 2, pp. 174–208.
Horn, B. K. P. and Brooks, M. J. (eds.), Shape from Shading, MIT Press, Cambridge, MA, 1989.
Horn, B. K. P. (1990) Height and Gradient from Shading, IJCV, Vol. 5, No. 1, pp. 37–75.
Huber, P. (1981) Robust Statistics, Wiley, Chichester.
Ikeuchi, K. and Horn, B. K. P. (1981) Numerical Shape from Shading and Occluding Boundaries, Artificial Intelligence, Vol. 17, No. 3, pp. 141–184.
Koenderink, J. J. and van Doorn, A.J. (1992) Surface Shape and Curvature Scales, Image and Vision Computing, Vol. 10, pp. 557–565.
Koenderink, J. J., van Doorn, A.J., Christou, C. and Lappin, J.S. (1996) Perturbation study of shading in pictures, Perception, Vol. 25, No. 9, pp. 1009–1026.
Li, S. Z. (1995) Discontinuous MRF Prior and Robust Statistics: a Comparative Study, Image and Vision Computing, Vol. 13, No. 3, pp. 227–233.
Marr, D. C. (1982), Vision, Freeman, San Francisco.
Parent, P. and Zucker, S. W. (1985) Curvature Consistency and Curve Detection, J. Opt. Soc. America A, Vol. 2, No. 13, p. 5.
Pentland, A. P. (1984) Local Shading Analysis, IEEE PAMI, Vol. 6, pp. 170–187.
Sander P. and Zucker S. W., “Inferring Surface Structure and Differential Structure from 3D Images”, IEEE PAMI, 12, 833–854, 1990.
Szeliski, R. (1991) Fast Shape from Shading, CVGIP: Image Understanding, Vol. 53, pp. 129–153.
Worthington, P. L. and Hancock, E. R. (1997) Needle Map Recovery using Robust Regularizers, Proc. British Machine Vision Conference, BMVA Press, Vol. I, pp. 31–40.
Worthington, P. L. and Hancock, E. R. (1998) Needle Map Recovery using Robust Regularizers, Image and Vision Computing, to appear.
Worthington P. L., Huet B. and Hancock E. R., “Appearence based object recognition using shape-from-shading”, Proceedings of the 14th International Conference on Pattern Recongition, pp. 412–416, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Worthington, P.L., Hancock, E.R. (1999). Topographic Surface Structure from 2D Images Using Shape-from-Shading. In: Hancock, E.R., Pelillo, M. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1999. Lecture Notes in Computer Science, vol 1654. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48432-9_2
Download citation
DOI: https://doi.org/10.1007/3-540-48432-9_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66294-5
Online ISBN: 978-3-540-48432-5
eBook Packages: Springer Book Archive