Skip to main content
SpringerLink
Log in

Constructing object models from multiple images

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

Abstract

Methods for constructing face-edge-vertex models of objects directly from image data are presented. These methods, applicable to both range and intensity data, produce refined models using multiple images. Each model bounds the actual positions of surfaces on the object. The techniques rely on topologically significant image features to generate bounding volumes for the object surfaces. Potentially occupied volumes obtained from the multiple image viewpoints are intersected to form a cumulative description of potential surface positions. In conjunction with certain coherence and visibility assumptions, a model can be produced with little or no ambiguity. Typically, several well-chosen views will produce a good approximation to the object under consideration. Illustrative examples of building models from multiple range and intensity images are provided.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Agin, G.J., and Binford, T.O., 1973. Computer description of curved objects,3rd Intern. Joint Conf. Artif. Intell., Stanford, CA, p. 629–635. August.

  • Allen, P.K., 1986. Sensing and describing 3-d surfaces,Proc. 1986 Conf. Robot. Autom. IEEE, San Francisco, April.

  • Arkin, R.C., 1987. Toward cosmopolitan robots: Intelligent navigation in extended man-made environments, Tech. Rept. 87-80, COINS Department, University of Massachusetts, September.

  • Asada, H., and Brady, J.M., 1985. The curvature primal sketch, Tech. Rept. AIM-758, Massachusetts Institute of Technology.

  • Baker, H., 1977. Three dimensional modeling,5th Intern. Joint Conf. Artif. Intell., Cambridge, MA., p. 649–655.

  • Balasubramanyam, P., and Snyder, M., 1991. The P-Field: A computational model for binocular motion processing,Proc. Conf. Comput. Vis. Patt. Recog., Mauii, p. 115–120, June.

  • Baumgart, B.G. 1975. A polyhedral representation for computer vision.Proc. AFIPS Nat. Comput. Conf., 44:589–596.

    Google Scholar 

  • Boissonnat, J.-D., 1985. Surface reconstruction from planar crosssections,Proc. Conf. Comput. Vis. Patt. Recog. IEEE, San Francisco, pp. 393–397, June.

  • Boissonnat, J.-D., Faugeras, O.D., and Bras-Mehlman, E.L., 1988. Representing stereo data with the delaunay triangulation. InProc. 1988 Conf. Robot. Autom. IEEE, Philadelphia, pp. 1798–1803. April.

  • Brady, J.M., Ponce, J., Yuille, A., and Asada, H., 1985. Describing surfaces,Comput. Vis. Graph. Image Process. 32.

  • Brice, C.R., and Fennema, C.L., 1970. Scene analysis using regions,Artificial Intelligence 1(3):205–226.

    Google Scholar 

  • Burns, J.B., 1992. Matching 2D images to multiple 3D objects using view description networks. Ph.D thesis, University of Massachusetts, February 1992. Computer Science Department Tech. Rep. 92-17.

  • Burns, J.B., and Kitchen, L.J., 1988. Rapid object recognition from a large model base using prediction hierarchies,Proc. DARPA Image Understanding Workshop, Washington, D.C., p. 711–719. Morgan-Kaufman, Inc.

  • Canny, J.F., 1984. Finding lines and edges in images, Tech. Rept. TR-720, Massachusetts Institute of Technology.

  • Canny, J.F., 1987. The complexity of robot motion planning, Ph.D. thesis, Massachusetts Institute of Technology.

  • Chien, C.H., and Aggarwal, J.K., 1984. A volume/surface octree representation,Proc. 7th Intern. Conf. Patt. Recog. Montreal, 2:817–820, August.

  • Connolly, C.I., 1984. Cumulative generation of octree models from range data,Proc. 1984 Intern. Conf. Robot. Autom. p. 25, IEEE, March.

  • Connolly, C.I., and Grupen, R., 1992. Applications of harmonic functions to robotics, Tech. Rept. 92-12. COINS Department, University of Massachusetts, February.

  • Connolly, C.I., et al. 1989. GeoMeter: Solid modelling and algebraic manipulation. COINS Department, University of Massachusetts at Amhest, 1989.

  • Dolan, J., and Riseman, E., 1992. Computing curvilinear structure by token-based grouping,Proc. Conf. Comput. Vis. Patt. Recog., June.

  • Faugeras, O.D., 1984. New steps toward a flexible 3-d vision system for robotics,Proc. 7th Intern. Conf. Patt. Recog. Montreal. p. 796, August.

  • Faugeras, O.D., and Hebert, M., 1983. A 3d recognition and positioning algorithm using geometrical matching between primitive surfaces,Proc. 8th Intern. Joint Conf. Artif. Intell. Karlsruhe, p. 996–1002, August.

  • Giblin, P., and Weiss, R., 1987. Reconstruction of surfaces from profiles,Proc. DARPA Image Understanding Workshop, Los Angeles, p. 900–908. Morgan-Kaufman, Inc., February.

  • Grimson, W.E.L., 1981.From Images to Surfaces, The MIT Press Series in Artificial, MIT Press. Cambridge, MA.

    Google Scholar 

  • Grimson, W.E.L., and Lozano-Perez, T., 1985. Search and sensing strategies for recognition and localization of two and three dimensional objects,Proc. 3rd Intern. Symp. Robotics Res., Paris.

  • Grupen, R.A., 1991. Planning grasp strategies for multifingered robot hands,Proc. 1991 Intern. Conf. Robotics Autom., April.

  • Henle, M., 1979,A Combinatorial Introduction to Topology, W.H. Freeman: New York.

    Google Scholar 

  • Herman, M., 1985. Generating detailed scene descriptions from range images,Proc. 1985 Conf. Robotics Autom., IEEE, St. Louis, p. 426, April.

  • Herman, M., and Kanade, T., 1986. Incremental reconstruction of 3D scenes from multiple, complex images,Artificial Intelligence 30(3):289–341.

    Google Scholar 

  • Hoffman, C.M., Hopcroft, J.E., and Karasick, M.S., 1987. Robust set operations on polyhedral solids, Tech. Rept. 87-875, Department of Computer Science, Cornell University, October.

  • Hong, J., Lafferriere, G., Mishra, B., and Tan, X., 1990. Fine manipulation and multifinger hands,Proc. 1990 Intern. Conf. Robotics Autom. IEEE, pp. 1568–1573, May.

  • Jane, F.T. 1986.Jane's All the World's Aircraft 1986–87. MacDonald and Jane's: London.

    Google Scholar 

  • Jones, J.L., and Lozano-Perez, T., 1990. Planning two-fingered grasps for pick-and-place operations on polyhedra,Proc. 1990 Intern. Conf. Robotics Autom., IEEE, May, pp. 683–688.

  • Khatib, O., 1985. Real-time obstacle avoidance for manipulators and mobile robots,Proc. 1985 Intern. Conf. Robotics Autom. IEEE, pp. 500–505, March.

  • Lim, H.S., and Binford, T.O., 1988, Curved surface reconstruction using stereo correspondence,Proc. DARPA Image Understanding Workshop, Morgan-Kaufman, pp. 809–819.

  • Longuet-Higgins, H.C., 1981. A computer algorithm for reconstructing a scene from two projections,Nature 293 (5828):133–135, September.

    Google Scholar 

  • Lowe, D.M., 1985.Perceptual Organization and Visual Recognition. Kluwer Academic: Norwell, MA.

    Google Scholar 

  • Lozano-Perez, T., 1981. Automatic planning of manipulator transfer movements,IEEE Trans. Syst. Man, Cyber. SMC 11 (10):681–698. October.

    Google Scholar 

  • Lyons, D., 1985. A simple set of grasps for a dextrous hand,Proc. 1985 Intern. Conf. Robotics Autom., IEEE, March, pp. 588–593.

  • Markowsky, G., and Wesley, M.A., 1980. Fleshing out wire frames.IBM J. Res. Develop. 24:582–597, September.

    Google Scholar 

  • Marr, D., 1982.Vision. W.H. Freeman: New York.

    Google Scholar 

  • Meagher, D.J., 1982. Geometric modeling using octree encoding,Comput. Graph. Image Process. 19.

  • Milenkovic, V.J., 1989. Verifiable implementations of geometric algorithms using finite precision, Kapur, D., and Mundy, J.L., eds.,Geometric Reasoning, MIT Press: Cambridge, MA., pp. 377–401.

    Google Scholar 

  • Noyes, T., 1986. Topological processing of edges, Master's thesis, Rensselaer Polytechnic Institute, Dept. Electrical, Computer and Systems Engineering.

  • Oliensis, J., 1991. Shape from shading as a partially well-constrained problem,Proc. Conf. Comput. Vis. Patt. Recog., IEEE, Mauii, pp. 559–564, June.

  • Popplestone, R.J., Brown, C.M., Ambler, A.P., and Crawford, G.F., 1975. Forming models of plane-and-cylinder faceted bodies from light stripes,Proc. 4th Intern. Joint Conf. Artif. Intell., pp. 664–668, September.

  • Potmesil, M., 1983. Generating models of solid objects by matching 3d surface segments,Proc. 8th Intern. Joint Conf. Artif. Intell., Karlsruhe, p. 1089–1093.

  • Shirai, Y., and Suwa, M., 1971. Recognition of polyhedrons with a range finder,Proc. 2nd Intern. Joint Conf. Artif. Intell. pp. 80–87.

  • Shneier, M.O., 1979. A compact relational structure representation,Proc. 6th Intern. Joint Conf. Artif. Intell., Tokyo, pp. 818–826, August.

  • Stenstrom, J.R., 1985. Finding points of high curvature and critical curves from a volume model,Proc. 1985 Conf. Robotics Autom., IEEE, St. Louis, p. 436., April.

  • Stenstrom, J.R., 1988. The application of attributed grammars and related formal models to pattern recognition, Tech. Rept., Ph.D. Thesis, Computer Science Department, Rensselaer Polytechnic Institute, April.

  • Stenstrom, J.R., and Connolly, C.I., 1986. Building wire frames from multiple views,Proc. 1986 Conf. Robotics Autom., IEEE, San Francisco, April.

  • Terzopoulos, D., 1983. The role of constraints and discontinuities in visible-surface reconstruction,Proc. 8th Intern. Joint Conf. Artif. Intell., p. 1073–1077.

  • Thompson, D.W., and Mundy, J.L., 1987. Three dimensional model matching from an unconstrained viewpoint,Proc. 1987 Conf. Robotics Autom. IEEE, Raliegh, NC, pp. 208–220, April.

  • Wesley, M.A., and Markowsky, G., 1981. Fleshing out projections.IBM J. Res. Develop. 25:934–954, November.

    Google Scholar 

  • Whitney, H., 1955. On singularities of mappings of Euclidean spaces: I. Mappings of the plane into the plane,Annals of Mathematics 62(3):374–410.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. the Computer Science Department, University of Massachusetts, 01003, Amherst, MA

    C. Ian Connolly

Authors
  1. J. Ross Stenstrom
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C. Ian Connolly
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

General Electric Corporate Research and Development Center

The first author passed away during the preparation of this manuscript.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Stenstrom, J.R., Connolly, C.I. Constructing object models from multiple images. Int J Comput Vision 9, 185–212 (1992). https://doi.org/10.1007/BF00133701

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00133701

Keywords

Search

Navigation