Abstract
This paper deals with generic 3D shape modelling for the purposes of object recognition. Common problems with many existing methods are that they either capture insufficient detailed structure or fail to provide sufficiently abstract descriptions (global vs. local representation). As a result, they tend have a limited field of application. The approach presented here attempts to address this problem by building a composite representation of the data in terms of a superquadric augmented with multi-scale surface models.
This is illustrated experimentally using laser range data. The superquadric that results in the best possible fit is expressed in terms of its position, size, shape and pose parameters. The residual of the fit is then modelled at several scales using multiple surface patches with uniform mean and Gaussian curvature. A hierarchical ranking of these patches is used to describe the residual based on geometric properties. These geometric properties are ranked according to criteria expressing their stability and utility. The most stable patches are selected as the description of the residual. The resulting representation can then be used for both pose estimation and object recognition.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Wassim Alami and Gregory Dudek. Multiscale object representation using surface patches. In Proc. of SPIE — The International Society for Optical Engineering, volume 2353, pages 108–119, Bellingham, WA USA, 1994.
T. Arbel, F. P. Ferrie, and P. Whaite. Recognizing volumetric objects in the presence of uncertainty. In International Conference on Pattern Recognition, volume 1, pages 470–476, Piscataway, NJ, USA, 1994. IEEE.
F. Attneave. Some informational aspects of visual perception. Psychological Review, (61):183–193, 1954.
Alan H. Barr. Superquadrics and angle preserving transformations. IEEE Computer Graphics and Applications, 1:11–23, Jan. 1981.
P. J. Besl and R. C. Jain. Segmentation through variable-order surface fitting. IEEE Trans. on Pattern Anal. Machine Intell., 10(2):167–192, March 1988.
Paul Besl. Invariant surface characteristics for three-dimensional object recognition in range images. IEEE Trans. Pattern Anal. Machine Intell., 33(1):33–80, January 1986.
Richard O. Duda and Peter E. Hart. Pattern Classification and Scene Analysis. John Wiley & Sons, New York, N.Y., 1973.
G. Dudek and J. K. Tsotsos. Shape representation and recognition from curvature. In Proc. of the 1991 Conference on Computer Vision and Pattern Recognition, pages 35–41, Maui, Hawaii, June 1991. IEEE.
F. P. Ferrie, J. Lagarde, and P. Whaite. Darboux frames, snakes and superquadrics: Geometry from the bottom up. IEEE Trans. Pattern Anal. Machine Intell., 15(8):771–783, Aug. 1993.
Dmitry B. Goldgof, Thomas S. Huang, and Hua Lee. Curvature-based approach to terrain recognition. IEEE Trans. Pattern Anal. Machine Intell., 11(11):1213–1217, Nov 1989.
W. Eric L. Grimson and Tomás Lozano-Pérez. Localizing overlapping parts by searching the interpretation tree. IEEE Trans. Pattern Anal. Machine Intell., 9(4):469–482, July 1987.
D. G. Lowe. Perceptual organization and visual recognition. Kluwer Academic Publishers, Boston, Mass., 1985.
David H. Marimont. A representation for image curves. AAAI, pages 237–242, 1984.
Art Matheny and Dmitry B. Goldgof. The use of three and four dimensional surface harmonics for rigid and nonrigid shape recovery and representation. IEEE Trans. Pattern Anal. Machine Intell., 17(10):967–981, Oct. 1995.
F Mokhtarian. Evolution properties of space curves. In International Conf. on Computer Vision, pages 100–105, Tarpon Springs, Fla., Dec. 1988. IEEE 2nd International Conf. on Computer Vision.
A. P. Pentland and S. Sclaroff. Closed-form solutions for physically based shape modelling and recognition. IEEE Trans. Pattern Anal. Machine Intell., 13(7):715–729, July 1991.
F. Solina and R. Bajcsy. Recovery of parametric models from range images: The case for superquadrics with global deformations. IEEE Trans. Pattern Anal. Machine Intell., 12(2):131–147, Feb. 1990.
D. Terzopoulos and D. Metaxas. Dynamic 3d models with local and global deformations: Deformable superquadrics. IEEE Trans. Pattern Anal. Machine Intell., 13(7):703–714, July 1991.
Peter Whaite and Frank P. Ferrie. From uncertainty to visual exploration. IEEE Trans. Pattern Anal. Machine Intell., 13(10):1038–1049, Oct 1991.
D. Wilkes and J. Tsotsos. Active object recognition. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pages 136–141, Urbana, Illinois, June 1992. IEEE Computer Society Press.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ayoung-Chee, N., Dudek, G., Ferrie, F.P. (1996). A hybrid approach to 3D representation. In: Ponce, J., Zisserman, A., Hebert, M. (eds) Object Representation in Computer Vision II. ORCV 1996. Lecture Notes in Computer Science, vol 1144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61750-7_35
Download citation
DOI: https://doi.org/10.1007/3-540-61750-7_35
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61750-1
Online ISBN: 978-3-540-70673-1
eBook Packages: Springer Book Archive