Abstract
A new representation called Harmonic Shape Images for 3D free-form surfaces is proposed in this paper. This representation is based on the well-studied theory of Harmonic Maps which studies the mapping between different metric manifolds from the energyminimization point of view. The basic idea of Harmonic Shape Images is to map a 3D surface patch with disc topology to a 2D domain and encode the shape information of the surface patch into the 2D image. Due to the application of harmonic maps in generating Harmonic Shape Images, Harmonic Shape Images have the following advantages: they preserve both the shape and the continuity of the underlying surfaces, they are robust to occlusion and they are independent of surface sampling strategy. The proposed representation is applied to solve the surface-registration problem. Experiments have been conducted on real data and results are presented in the paper.
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
Y. Xin: Geometry of Harmonic Maps. Birkhauser, 1996
J. Eells and L.H, Sampson: Harmonic Mappings of Riemannian Manifords. Amer. J. Math., 86:109–160, 1964
B. O’Neill: Elementary differential geometry. Academic Press, Inc., 1996
M. Eck, T. DeRose, T. Duchamp, H. Hoppe, M. Lounsbery, and W. Stuetzle,: Multi-resolution Analysis of Arbitrary Meshes. Proc. SIGGRAPH.96, 325–334
B. K. P. Horn: Extended Gaussian Image. Proc. IEEE, vol. 72, pp. 1671–1686, 1984
M. Hebert, K. Ikeuchi and H. Delingette,: A Spherical Representation for Recognition of Free-form Surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, No.7, pp. 681–689, 1995
K. Higuchi, M. Hebert and K. Ikeuchi: Building 3D Models from Unregistered Range Images. CVGIP-Image Understanding, vol. 57, No.4, 1995
D. Zhang, M. Hebert: Multi-scale Classification of 3D Objects. Proc. CVPR’97, pp. 864–869
D. Zhang, M. Hebert, A. Johnson and Y. Liu: On Generating Multi-resolution Representations of Polygonal Meshes. Proc. ICCV’98 Workshop on Modelbased 3-D Image Analysis, Jan. 3, 1998, Bombay, India
O. D. Faugeras and M. Hebert: The Representation, Recognition And Locating of 3-D Objects. Int’l J. of Robotics Research, vol. 5, No. 3, pp. 27–52, 1986.
C. Dorai, A. Jain: COSMOS-A Representation Scheme for 3D Free-form Objects. IEEE Transaction Pattern on Pattern Analysis and Machine Intelligence, vol. 19, No. 10: pp.1115–1130, 1997.
P. J. Besl: Triangles as A Primary Representation. Object Representation in Computer Vision, M. Hebert, J. Ponce, T. Boult and A. Gross, eds., Berlin, Springer-Verlag, pp.191–206, 1995.
T. Joshi, J. Ponce, B. Vijayakumar and D.J. Kriegman: HOT Curves for Modeling and Recognition of Smooth Curved 3D Objects. Proc. CVPR.94, pp.876–880, 1994
F. Stein and G. Medioni: Structural Indexing: Efficient 3-D Object Recognition, IEEE Transactions Pattern on Pattern Analysis and Machine Intelligence, vol. 14, No. 2: pp.125–145, 1992.
D. Keren, K. Cooper and J. Subrahmonia: Describing Complicated Objects by Implicit Polynomials. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, No.1, pp. 38–53, 1994
A. Johnson and M. Hebert: Efficient Multiple Model Recognition in Cluttered 3-D Scenes. CVPR’ 98, pp. 671–677
C. S. Chua and R. Jarvis: 3D Free-form Surface Registration and Object Recognition. Int’l J. of Computer Vision, vol. 17, pp.77-99, 1996
P. J. Besl: The Free-form Surface Matching Problem. Machine Vision for Threedimensional Scenes. H. Freeman, ed., Academic Press, pp.25–71, 1990
P. J. Besl and N.D. Mckay: A Method for Registration of 3-D Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, No. 2, pp.239–256, 1992
Y. Chen and G. Medioni: Object Modeling by Registration of Multiple Range Images. Image Vision Computing, vol. 10, No. 3, pp.145–155, 1992
R. Bergevin, D. Laurendeau and D. Poussart: Estimating The 3D Rigid Transformation between Two Range Views of A Complex Object. Proc. 11th IAPR, Int’l Conf. Patt. Recog., The Hague, The Netherlands, pp. 478–482, Aug. 30-Sep. 3, 1992
J. Deovre: Probability and statistics for engineering and science. Brooks/Cole, Belmont, CA, 1987
D. Zhang and M. Hebert: Harmonic Maps and Their Applications in Surface Matching. To appear in CVPR.99
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
Zhang, D., Hebert, M. (1999). Harmonic Shape Images: A Representation for 3D Free-Form Surfaces Based on Energy Minimization. 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_3
Download citation
DOI: https://doi.org/10.1007/3-540-48432-9_3
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