Abstract
While there have been great strides in the development of systems to recognize 3D objects in images using viewpoint independent features, we have yet to develop algorithms for recognizing complex curved objects from large model databases; in part, the difficulty arises because image features are viewpoint dependent. Consequently, we must either develop viewer centered representations or have methods for directly relating viewpoint dependent features to 3D models. Aspect graphs, which enumerate all topologically distinct line drawings, may be too weak by themselves to support recognition. However, they can be used to control the search for image-model correspondences when coupled with the constraints afforded by viewpoint dependent features. When objects are represented by algebraic surfaces, these constraints can be expressed as systems of polynomial equations which can be solved using well established techniques. Alternatively, a new representation has been proposed called HOT Curves. Like representations based on geometric invariance, HOT Curves encode the relationship of image features for a particular 3D object. The representation can be constructed directly from a set of images, the features are viewpoint dependent, and indexing schemes are supported.
Preview
Unable to display preview. Download preview PDF.
References
R. Bajcsy and F. Solina. Three-dimensional object representation revisited. In Int. Conf. on Computer Vision, pages 231–240, London, U.K., June 1987.
T. O. Binford. Visual perception by computer. In IEEE Conf. on Systems and Control, 1971.
K. Bowyer and C. R. Dyer. Aspect graphs: An introduction and survey of recent results. Int. J. of Imaging Systems and Technology, 2:315–328, 1991.
M. Brady. Criteria for representations of shape. In J. Beck, B. Hope, and A. Rosenfeld, editors, Human and Machine Vision, pages 39–84. Academic Press, 1983.
B. Burns, R. Weiss, and E. Riseman. The non-existence of general-case view-invariants. In Geometric Invariance in Computer Vision, pages 120–131. MIT Press, 1992.
I. Chakravarty. The use of characteristic views as a basis for recognition of three-dimensional objects. Image Processing Laboratory IPL-TR-034, RensselaerPolytechnic Institute, October 1982.
C. Chen and A. Kak. A robot vision system for recognizing 3-d objects in low-order polynomial time. IEEE Systems, Man, and Cybernetics, 19:1535–1563, 1989.
R. Duda and P. Hart. Pattern Classification and Scene Analysis. Wiley, New York, 1973.
D. Eggert, K. Bowyer, C. Dyer, H. Christensen, and D. Goldgof. The scale space aspect graph. IEEE Trans. Pattern Anal. Mach. Intelligence, 15(11):1114–1131, 1993.
O. Faugeras and M. Hebert. The representation, recognition, and locating of 3-D objects. Int. J. Robot. Res., 5(3):27–52, Fall 1986.
F. Ferrie, J. Lagarde, and P. Whaite. Darboux frames, snakes, and super-quadrics: Geometry from the bottom-up. In Workshop on Interpretation of 3D Scenes, pages 170–176, 1989.
W. E. L. Grimson. Object Recognition by Computer: The Role of Geometric Constraints. MIT Press, 1990.
A. Gross and T. Boult. Error of fit measures for recovering parametric solids. In Int. Conf. on Computer Vision, pages 690–694, Tampa, Fl., December 1988.
P. Hallinan. A low-dimensional representation of human faces for arbitrary lighting conditions. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 995–999, 1994.
D. Huttenlocher and S. Ullman. Object recognition using alignment. In Int. Conf. on Computer Vision, pages 102–111, London, U.K., June 1987.
K. Ikeuchi and T. Kanade. Automatic generation of object recognition programs. Proceedings of the IEEE, 76(8):1016–35, August 1988.
D. W. Jacobs. Space efficient 3D model indexing. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 439–444, 1992.
T. Joshi, J. Ponce,B. Vijayakumar, and D. Kriegman. HOT curves for modelling and recognition of smooth curved 3D shapes. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., June 1994. In Press.
J. J. Koenderink. Solid Shape. MIT Press, Cambridge, MA, 1990.
J. J. Koenderink and A. J. Van Doom. The internal representation of solid shape with respect to vision. Biological Cybernetics, 32:211–216, 1979.
D. Kriegman and J. Ponce. On recognizing and positioning curved 3D objects from image contours. IEEE Trans. Pattern Anal. Mach. Intelligence, 12(12):1127–1137, 1990.
D. Kriegman, B. Vijayakumar, and J. Ponce. Constraints for recognizing and locating curved 3D objects from monocular image features. In European Conf. on Computer Vision, pages 829–833, 1992.
K. Kutulakos and C. Dyer. Occluding contour detection using affine invariants and purposive viewpoint adjustment. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 323–329, 1994.
D. G. Lowe. The viewpoint consistency constraint. Int. J. Computer Vision, 1(1):57–72, 1987.
D. Marr and K. Nishihara. Representation and recognition of the spatial organization of three-dimensional shapes. Proc. Royal Society, London, B-200:269–294, 1978.
A. Morgan. Solving Polynomial Systems using Continuation for Engineering and Scientific Problems. Prentice Hall, Englewood Cliffs, 1987.
J. Mundy and A. Zisserman. Geometric Invariance in Computer Vision. MIT Press, Cambridge, Mass., 1992.
H. Murase and S. Nayar. Illumination planning for object recognition in structured environments. In IEEE Conference on Computer Vision and Pattern Recognition, pages 31–38, Seattle, WA, 1994.
R. Nevatia and T. Binford. Description and recognition of complex curved objects. Artificial Intelligence, 8:77–98, 1977.
A. Pentland. Perceptual organization and the representation of natural form. Artificial Intelligence, 28:293–331, 1986.
R. Peterson. A Field Guide to Western Birds. Houghton-Mifflin, Boston, 1990.
S. Petitjean, J. Ponce, and D. Kriegman. Computing exact aspect graphs of curved objects: Algebraic surfaces. Int. J. Computer Vision, 9(3):231–255, 1992.
J. Ponce, A. Hoogs, and D. Kriegman. On using CAD models to compute the pose of curved 3D objects. Computer Vision, Graphics, and Image Processing: Image Understanding, 55(2):184–197, Mar 1992.
J. Ponce, D. Kriegman, S. Petitjean, S. Sullivan, G. Taubin, and B. Vijayakumar. Representations and algorithms for 3D curved object recognition. In 3D Object Recognition Systems, pages 327–352. Elsevier Press, 1992.
M. Seibert and A. Waxman. Adaptive 3-D object recognitin from multiple views. IEEE Trans. Pattern Anal. Mach. Intelligence, 14(2):107–124, Feb. 1992.
S. Shafer. Shadows and Silhouettes in Computer Vision. Kluwer Academic Publishers, 1985.
I. Shimshoni and J. Ponce. Finite resolution aspect graphs of polyhedral objects. In IEEE Workshop on Qualitative Vision, June 1993.
L. Stark, D. Eggert, and K. Bowyer. Aspect graphs and non-linear optimization. In Int. Conf. on Computer Vision, pages 501–507, 1988.
J. Subrahmonia, D. Cooper, and D. Keren. Reliable object recognition using high-dimensional implicit polynomials for 2D curves and 3D surfaces. Technical Report LEMS-94, Brown University, 1991.
G. Taubin. Estimation of planar curves, surfaces and nonplanar space curves defined by implicit equations, with applications to edge and range image segmentation. IEEE Trans. Pattern Anal. Mach. Intelligence, 13(11):1115–1138, 1991.
G. Taubin, F. Cukierman, S. Sullivan, J. Ponce, and D. Kriegman. Parameterized families of polynomials for bounded algebraic curve and surface fitting. IEEE Trans. Pattern Anal. Mach. Intelligence, 16(3):287–303, 1994.
M. Turk and A. Pentland. Face recognition using eigenfaces. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 586–591, 1991.
B. Vijayakumar, D. Kriegman, T. Joshi, and J. Ponce. Towards invariant-based recognition of complex 3D curved objects in images. In Yale Workshop on Adaptive and Learning, June 1994.
B. Vijayakumar, D. Kriegman, and J. Ponce. Invariant-based recognition of complex 3D curved objects. In Int. Conf. on Computer Vision, 1995. Submitted.
R. Walker. Algebraic Curves. Princeton University Press, 1950.
A. Zisserman, D. Forsyth, J. Mundy, and C. Rothwell. Recognizing general curved objects efficiently. In Mundy and Zisserman, editors, Geometric Invariance in Computer Vision, pages 228–251. MIT Press, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kriegman, D.J., Ponce, J. (1995). Representations for recognizing complex curved 3D objects. In: Hebert, M., Ponce, J., Boult, T., Gross, A. (eds) Object Representation in Computer Vision. ORCV 1994. Lecture Notes in Computer Science, vol 994. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60477-4_9
Download citation
DOI: https://doi.org/10.1007/3-540-60477-4_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60477-8
Online ISBN: 978-3-540-47526-2
eBook Packages: Springer Book Archive