Skip to main content
Log in

Recovering shape by purposive viewpoint adjustment

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

We present an approach for recovering surface shape from the occluding contour using an active (i.e., moving) observer. It is based on a relation between the geometries of a surface in a scene and its occluding contour: If the viewing direction of the observer is along a principal direction for a surface point whose projection is on the contour, surface shape (i.e., curvature) at the surface point can be recovered from the contour. Unlike previous approaches for recovering shape from the occluding contour, we use an observer thatpurposefully changes viewpoint in order to achieve a well-defined geometric relationship with respect to a 3-D shape prior to its recognition. We show that there is a simple and efficient viewing strategy that allows the observer to align the viewing direction with one of the two principal directions for a point on the surface. This strategy depends on only curvature measurements on the occluding contour and therefore demonstrates that recovering quantitative shape information from the contour does not require knowledge of the velocities or accelerations of the observer. Experimental results demonstrate that our method can be easily implemented and can provide reliable shape information from the occluding contour.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Aloimonos, Y. 1990. Purposive and qualitative active vision,Proc. 10th Intern. Conf. Patt. Recog., Atlantic City, NJ, pp. 346–360.

  • Aloimonos, Y., Weiss, I., and Bandyopadhyay, A. 1987. Active vision,Proc. 1st Intern. Conf. Comput. Vis., London, pp. 35–54.

  • Bajcsy, R. 1988. Active perception,Proc. IEEE 76(8): 996–1005.

    Google Scholar 

  • Ballard, D.H. 1989. Behavioural constraints on animate vision,Image Vis. Comput. 7(1):3–9.

    Google Scholar 

  • Ballard, D.H. 1989. Reference frames for animate vision,Proc. 11th Intern. Joint Conf. Artific. Intell., Detroit, pp. 1635–1641.

  • Ballard, D.H. 1991. Animate vision,Artificial Intelligence 48:57–86.

    Google Scholar 

  • Ballard, D.H., and Brown, C.M. 1992. Principles of animate vision,Comput. Vis. Graph., Image Process.: Image Understanding 56(1):3–21.

    Google Scholar 

  • Ballard, D.H., and Ozcandarli, A. 1988. Eye fixation and early vision: Kinetic depth,Proc. 2nd Intern. Conf. Comput. Vis., Tarpon Springs, FL, pp. 524–531.

  • Barrow, H.G., and Tenenbaum, J.M. 1981. Interpreting line drawings as three-dimensional images,Artificial Intelligence 17:75–116.

    Google Scholar 

  • Blake, A., Curwen, R., and Zisserman, A. 1993. A framework for spatio-temporal control in the tracking of visual contours,Intern. J. Comput. Vis., 11(2):127–145.

    Google Scholar 

  • Brady, M., and Yuille, A. 1984. An extremum principle for shape from contour,IEEE Trans. Patt. Anal. Mach. Intell. 6(3):288–301.

    Google Scholar 

  • Brady, M., Ponce, I, Yuille, A., and Asada, H. 1985. Describing surfaces,Comput. Graph. Image Process. 32:1–28.

    Google Scholar 

  • Brooks, R.A. 1986. A robust layered control system for a mobile robot,IEEE J. Robotics Automat. 2(1): 14–23.

    Google Scholar 

  • Brooks, R.A. 1989. A robot that walks: Emergent behaviors from a carefully evolved network,Proc. IEEE Robotics Automat. Conf., Scottsdale, AZ, pp. 692–696.

  • Cipolla, R., and Blake, A. 1992. Surface shape from the deformation of apparent contours,Intern. J. Comput. Vis. 9(2): 83–112.

    Google Scholar 

  • Come, S.D., and de Boor, C. 1972.Elementary Numerical Analysis. McGraw-Hill: New York.

    Google Scholar 

  • Coombs, D. and Brown, C. 1993. Real-time binocular smooth pursuit,Intern. J. Comput. Vis., 11(2): 147–164.

    Google Scholar 

  • doCarmo, M.P. 1976.Differential Geometry of Curves and Surfaces. Prentice-Hall: Englewood Cliffs, NJ.

    Google Scholar 

  • Giblin, P., and Weiss, R. 1987. Reconstruction of surfaces from profiles,Proc. 1st Intern. Conf. Comput. Vis., London, pp. 136–144.

  • Grosso, E., and Ballard, D.H. 1993. Head-centered orientation strategies in animate vision,Proc. 4th Intern. Conf. Comput. Vis., Berlin, pp. 395–402.

  • Hager, G., and Mintz, M. 1987. Searching for information,Proc. Workshop on Spatial Reasoning and Multi-Sensor Fusion, Charles, IL, pp. 313–322.

  • Horaud, R., and Brady, M. 1987. On the geometric interpretation of image contours,Proc. 1st Intern. Conf. Comput. Vis., London, pp. 374–382.

  • Horn, B.K.P. 1986.Robot Vision. MIT Press: Cambridge, MA.

    Google Scholar 

  • Kanade, T., 1981. Recovery of the three-dimensional shape of an object from a single view,Artificial Intelligence 17:409–460.

    Google Scholar 

  • Koenderink, J.J. 1984. What does the occluding contour tell us about solid shape?,Perception 13:321–330.

    Google Scholar 

  • Koenderink, J.J. 1990.Solid Shape. MIT Press: Cambridge, MA.

    Google Scholar 

  • Kriegman, D.J. 1993. Personal communication.

  • Krotkov, E. 1987. Focusing,Intern. J. Comput. Vis. 1 (3):223–237.

    Google Scholar 

  • Krotkov, E., and Bajcsy, R. 1993. Visual behaviors for reliable ranging: Cooperating focus, stereo, and vergence,Intern. J. Comput. Vis., 11(2):187–203.

    Google Scholar 

  • Kutulakos, K.M., and Dyer, C.R. 1993. Global surface reconstruction by purposive control of observer motion.Proc. Conf. Comput. Vis. Patt. Recog., Seattle, WA, to appear.

  • Leyton, M. 1988. A process grammar for shape,Artificial Intelligence 34:213–247.

    Google Scholar 

  • Malik, J. 1987. Interpreting line drawings of curved objects,Intern. J. Comput. Vis. 1(1):73–103.

    Google Scholar 

  • Marr, D., and Nishihara, H.K. 1978. Visual information processing: Artificial intelligence and the sensorium of sight,Technology Review 81:2–23.

    Google Scholar 

  • Nelson, R.C., and Aloimonos, Y. 1989. Obstacle avoidance using flow field divergence,IEEE Trans. Patt. Anal. Mach. Intell. 11(10): 1102–1106.

    Google Scholar 

  • Papanikolopoulos, N.P., Khosla, P.K. and Kanade, T. 1993. Visual tracking of a moving target by a camera mounted on a robot: A combination of control and vision,IEEE Trans. Robotics Automat. 9 (1):14–35.

    Google Scholar 

  • Ponce, J. and Chelberg, D. 1987. Finding the limbs and cusps of generalized cylinders,Intern. J. Comput. Vis. 1(3): 195–210.

    Google Scholar 

  • Ponce, J., Chelberg, D., and Mann, W.B. 1989. Invariant properties of straight homogeneous generalized cylinders and their contours,IEEE Trans. Patt. Anal. Mach. Intell. 11(9):951–966.

    Google Scholar 

  • Richards, W., Koenderink, J.J., and Hoffman, D.D. 1988. Inferring 3D shapes from 2D silhouettes. InNatural Computation, W. Richards, ed., pp. 125–136, MIT Press: Cambridge, MA.

    Google Scholar 

  • Richetin, M., Dhome, M., Lapreste, J.T., and Rives, G. 1991. Inverse perspective transform using zero-curvature contour points: Application to the localization of some generalized cylinders from a single view,IEEE Trans. Patt. Anal. Mach. Intell. 13(2):185–192.

    Google Scholar 

  • Rimey, R.D., and Brown, C.M. 1993. Control of selective perception using Bayes nets and decision theory,Intern. J. Comput. Vis., this issue.

  • Stevens, K.A. 1981. The visual interpretation of surface contours,Artificial Intelligence 17:47–73.

    Google Scholar 

  • Ulupinar, F., and Nevatia, R. 1988. Using symmetries for analysis of shape from contour,Proc. 2nd Intern. Conf. Comput. Vis., Tarpon Springs, FL, pp. 414–426.

  • Vaillant, R., and Faugeras, O.D. 1992. Using extremal boundaries for 3-D object modeling,IEEE Trans. Patt. Anal. Mach. Intell. 14(2):157–173.

    Google Scholar 

  • Wixson, L.E., and Ballard, D.H. 1993. Exploiting world structure to efficiently search for objects,Intern. J. Comput. Vis., this issue.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kutulakos, K.N., Dyer, C.R. Recovering shape by purposive viewpoint adjustment. Int J Comput Vision 12, 113–136 (1994). https://doi.org/10.1007/BF01421200

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01421200

Keywords

Navigation