This Article 
 Bibliographic References 
 Add to: 
Invariant Properties of Straight Homogeneous Generalized Cylinders and Their Contours
September 1989 (vol. 11 no. 9)
pp. 951-966

A fundamental group in computer vision is the recovery of three-dimensional shape from image data. While this problem is in general underconstrained, the authors show that it can be simplified in the case where the objects being viewed are generalized cylinders. They consider the class of straight homogeneous generalized cylinders (SHGCs), without any further assumption on the viewing direction or the precise shape of these objects. They present a rigorous mathematical study of the geometry of SHGCs and characterize their Gaussian curvature and occluding contours, and use these results to prove several new invariant properties of the contours of SHGCs. These properties are, in turn, used in two implemented algorithms for recovering SHGC descriptions from image contours. Several examples of segmentation of real images are given. Other applications are also discussed.

[1] G. J. Agin, "Representation and description of curved objects," Ph.D. dissertation, Stanford Artificial Intelligence Lab., Rep. AIM- 273, Oct. 1972.
[2] N. Ayache and O. D. Faugeras, "HYPER: A new approach for the recognition and positioning of two-dimensional objects,"IEEE Trans. Patt. Anal. Machine Intell., vol. 8, no. 1, pp. 44-54, 1986.
[3] D. H. Ballard, "Generalizing the Hough transform to detect arbitrary shapes,"Pattern Recognition, vol. 13, no. 2, pp. 111-122, 1981.
[4] H. G. Barrow and J. M. Tenenbaum, "Recovering intrinsic scene characteristics from images," inComputer Vision Systems, A. R. Hanson and E. M. Riseman, Eds. New York: Academic, 1978, pp. 3-26.
[5] T. O. Binford, "Visual perception by computer," inProc. IEEE Conf. Systems and Control, Miami, FL, Dec. 1971.
[6] T. O. Binford, "Generic surface interpretation: Observability model," inProc. 4th Int. Symp. Robotics Research, Santa Cruz, CA, Aug. 1987.
[7] T. O. Binford, T. Levitt, and W. Mann, "Bayesian inference in model-based machine vision," inProc. Workshop Uncertainty in Artificial Intelligence, 1987.
[8] J. M. Brady and H. Asada, "Smooth local symmetries and their implementation,"Int. J. Robotics Res., vol. 3, no. 3, 1984.
[9] J. M. Brady, J. Ponce, A. Yuille, and H. Asada, "Describing surfaces," inProc. 2nd Int. Symp. Robotics Research, Harasuja and Inoue, Eds. Cambridge, MA: MIT Press, 1985.
[10] R. A. Brooks, "Symbolics reasoning among 3D models and 2D images,"Artificial Intell., vol. 17, pp. 285-348, 1981.
[11] M. P. do Carmo,Differential Geometry of Curves and Surfaces. Englewood Cliffs, NJ: Prentice-Hall, 1976.
[12] W. E. L. Grimson and T. Lozano-Perez, "Localizing overlapping parts by searching the interpretation tree,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, no. 4, July 1987.
[13] R. Horaud, "New methods for matching 3-D objects with single perspective views,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, pp. 401-412, May 1987.
[14] R. Horaud and J. M. Brady, "On the geometric interpretation of image contours," inProc. First Int. Conf. Computer Vision, London, UK, June 1987.
[15] P. V. C. Hough, "Method and means for recognizing complex patterns," U.S. Patent 3,069,654, 1962.
[16] T. Kanade, "Recovery of the 3-D shape of an object from a single view,"Artificial Intell., vol. 17, no. 1-3, 1981.
[17] J. J. Koenderink, "What does the occluding contour tell us about solid shape?"Perception, vol. 13, 1984.
[18] D. G. Lowe, "The viewpoint consistency constraint,"Int. J. Comput. Vision, vol. 1, no. 1, pp. 57-72, 1987.
[19] J. Malik, "Interpreting line drawings of curved objects,"Int. J. Comput. Vision, vol. 1, no. 1, pp. 73-103, 1987.
[20] D. H. Marimont, "A representation for image curves," inProc. AAAI-84, Austin, TX, 1984.
[21] D. Marr, "Analysis of occluding contour,"Proc. Roy. Soc. London, vol. B-197, pp. 441-475, 1977.
[22] D. Marr and K. Nishihara, "Representation and recognition of the spatial organization of three dimensional shapes,"Proc. Roy. Society London, vol. B-200, pp. 269-294, 1978.
[23] R. Nevatia and T. O. Binford, "Description and recognition of complex curved objects,"Artificial Intell., vol. 8, pp. 77-98, 1977.
[24] R. Nevatia,Machine Perception. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[25] J. Ponce and J. M. Brady, "Toward a surface primal sketch," inThree-Dimensional Machine Vision, T. Kanade, Ed. New York: Kluwer Academic, 1987.
[26] J. Ponce and D. Chelberg, "Finding the limbs and cusps of generalized cylinders,"Int. J. Comput. Vision, vol. 1, no. 3, Oct. 1987.
[27] J. Ponce, D. Chelberg, and W. Mann, "Invariant properties of the projections of straight homogeneous generalized cylinders," inProc. First Int. Conf. Computer Vision, London, UK, June 1987.
[28] J. Ponce, D. Chelberg, D. J. Kriegman, and W. Mann, "Geometric modeling with generalized cylinders," inProc. 1987 IEEE Workshop Computer Vision, Miami, FL, Dec. 1987.
[29] J. Ponce, D. Chelberg, and W. Mann, "Invariant properties of straight homogeneous generalized cylinders and their projections," Stanford Univ., to appear as CS Tech. Rep., 1988.
[30] J. Ponce, "Straight homogeneous generalized cylinders: Differential geometry and uniqueness results," inProc. IEEE Comput. Soc. Conf. Comput. Vision Patt. Recogn.(Ann Arbor, MI), June 5-9, 1988, pp. 327-334.
[31] J. Ponce, "Ribbons, symmetries, and skewed symmetries," inProc. Image Understanding Workshop, 1988.
[32] K. Rao and R. Nevatia, "From sparse 3-D data directly to volumetric shape description," inProc. Image Understanding Workshop, Los Angeles, CA, Feb. 1987.
[33] K. R. Roberts, "Equivalent descriptions of generalized cylinders," inProc. Image Understanding Workshop, Miami, FL, Dec. 1985.
[34] S. A. Shafer,Shadows and Silhouettes in Computer Vision. New York: Kluwer Academic, 1985.
[35] T. Sumanaweera, G. Healey, B. Lee, T. O. Binford, and J. Ponce, "Image segmentation using geometric and physical constraints," inProc. Image Understanding Workshop, 1988.
[36] A. Verri and A. Yuille, "Perspective projection invariants," MIT Artificial Intell. Lab., Rep. AIM-832, 1986.
[37] R. E. Williamson and H. F. Trotter,Multivariable Mathematics. Englewood Cliffs, NJ: Prentice-Hall, 1979.

Index Terms:
3D shape recovery; invariant property; computerised picture processing; straight homogeneous generalized cylinders; computer vision; Gaussian curvature; image contours; segmentation; computer vision; computerised pattern recognition; computerised picture processing
J. Ponce, D. Chelberg, W.B. Mann, "Invariant Properties of Straight Homogeneous Generalized Cylinders and Their Contours," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 9, pp. 951-966, Sept. 1989, doi:10.1109/34.35498
Usage of this product signifies your acceptance of the Terms of Use.