[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Planning multiple observations for object recognition

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

Abstract

Most computer vision systems perform object recognition on the basis of the features extracted from a single image of the object. The problem with this approach is that it implicitly assumes that the available features are sufficient to determine the identity and pose of the object uniquely. If this assumption is not met, then the feature set is insufficient, and ambiguity results. Consequently, much research in computer vision has gone toward finding sets of features that are sufficient for specific tasks, with the result that each system has its own associated set of features. A single, general feature set would be desirable. However, research in automatic generation of object recognition programs has demonstrated that predetermined, fixed feature sets are often incapable of providing enough information to unambiguously determine either object identity or pose. One approach to overcoming the inadequacy of any feature set is to utilize multiple sensor observations obtained from different viewpoints, and combine them with knowledge of the 3-D structure of the object to perform unambiguous object recognition. This article presents initial results toward performing object recognition by using multiple observations to resolve ambiguities. Starting from the premise that sensor motions should be planned in advance, the difficulties involved in planning with ambiguous information are discussed. A representation for planning that combines geometric information with viewpoint uncertainty is presented. A sensor planner utilizing the representation was implemented, and the results of pose-determination experiments performed with the planner are discussed.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Arman, F., and Aggarwal, J.K. 1991. Automatic generation of recognition strategies using CAD models,Proc. IEEE Workshop on Directions in Automated CAD-Based Vision, pp. 124–133.

  • Balakumar, P., Robert, J.C., Hoffman, R., Ikeuchi, K., and Kanade, T. 1991. Vantage: A frame-based geometric/sensor modeling system—Programmer/User's Manual, vol. 1.0, CMU-RI-TR-91-31, The Robotics Institute, Carnegie Mellon University.

  • Bolles, R.C., and Horaud, P. 1987. 3DPO: A three-dimensional part orientation system. In T. Kanade, ed.,Three-Dimensional Machine Vision, Kluwer: Boston, MA, pp. 399–450.

    Google Scholar 

  • Brost, R.C. 1988. Automatic grasp planning in the presence of uncertainty,Intern. J. Robot. Res. 7(1): 3–17.

    Google Scholar 

  • Camps, O.I., Shapiro, L.G., and Haralick, R.M. 1991. PREMIO: an overview,Proc. IEEE Workshop on Directions in Automated CAD-Based Vision, pp. 11–21.

  • Cowan, C.K., and Kovesi, P.D. 1988. Automatic sensor placement from vision task requirements,IEEE Trans. on Patt. Anal. Mach. Intell. 10(3): 407–416.

    Google Scholar 

  • Flynn, P.J., and Jain, A.K. 1991. BONSAI: 3D object recognition using constrained search.IEEE Trans. Patt. Anal. Mach. Intell. 13 (10): 1066–1075.

    Google Scholar 

  • Fujiwara, Y., Nayar, S., and Ikeuchi, K. 1991. Appearance simulator for computer vision research, CMU-RI-TR-91-16, The Robotics Institute, Carnegie Mellon University.

  • Goad, C. 1983. Special purpose automatic programming for 3D model-based vision,Proc. DARPA Image Understanding Workshop, Arlington, VA, pp. 94–104.

  • Goldberg, K., and Mason, M. 1990. Bayesian grasping.Proc. IEEE Intern. Conf. Robot. Autom., pp. 1264–1269.

  • Gremban, K.D., and Ikeuchi, K. 1993. Appearance-based vision and the automatic generation of object recognition code. In A.K. Jain and P.J. Flynn, eds.,Three-Dimensional Object Recognition Systems, Elsevier Science Publishers: New York, pp. 229–258.

    Google Scholar 

  • Hansen, C., and Henderson, T.C. 1989. CAGD-based computer vision,IEEE Trans. Patt. Anal. Mach. Intell. 11(11): 1181–1193.

    Google Scholar 

  • Hong, K.S., Ikeuchi, K., and Gremban, K.D. 1990. Minimum cost aspect classification: A module of a vision algorithm compiler,Proc. 10th Intern. Conf. Patt. Recog., Atlantic City, pp. 65–69.

  • Hutchinson, S.A., and Kak, A.C. 1989. Planning sensing strategies in robot work cell with multi-sensor capabilities,IEEE Trans. Robot. Autom. 5(6): 765–783.

    Google Scholar 

  • Ikeuchi, K. 1987. Generating an interpretation tree from a CAD model for 3-D object recognition in bin-picking tasks,Intern. J. Comput. Vis. 1 (2): 145–165.

    Google Scholar 

  • Ikeuchi, K., and Hong, K.S. 1991. Determining linear shape change.Comput. Vis., Graphics, Image Process. 53(2): 154–170.

    Google Scholar 

  • Ikeuchi, K., and Kanade, T. 1988. Automatic generation of object recognition programs,Proc. IEEE 76(8): 1016–1035.

    Google Scholar 

  • Koenderink, J.J., and van Doom, A.J. 1979. The internal representation of solid shape with respect to vision,Biological Cybernetics 32: 211–216.

    Google Scholar 

  • Liu, C.H., and Tsai, W.H. 1990. 3D curved object recognition from multiple 2d camera views.Comput. Vis., Graphics, Image Process. 50: 177–187.

    Google Scholar 

  • Maver, J., and Bajcsy, R. 1990. How to decide from the first view where to look next,Proc. DARPA Image Understanding Workshop, Pittsburgh, pp. 482–496.

  • Sato, K., Ikeuchi, K., and Kanade, T. 1992. Model based recognition of specular objects using sensor models.Comput. Vis., Graphics, Image Process. 55(2): 155–169.

    Google Scholar 

  • Safranek, R.J., Gottschlich, S., and Kak, A.C. 1990. Evidence accumulation using binary frames of discernment for verification vision.IEEE Trans. Robot. Autom. 6(4): 407–417.

    Google Scholar 

  • Seibert, M., and Waxman, A.M. 1992. Adaptive 3-D object recognition from multiple views,IEEE Trans. Patt. Anal. Mach. Intell. 14(2): 107–124.

    Google Scholar 

  • Shafer, G. 1976.A Mathematical Theory of Evidence. Princeton Univ. Press: Princeton, NJ.

    Google Scholar 

  • Tan, M. 1990. CSL: A cost-sensitive learning system for sensing and grasping objects,Proc. IEEE Intern. Conf. Robot. Autom., pp. 858–863.

  • Wallack, A.S., and Canny, J.F. Linear time algorithm for object localization using scanning. Unpublished manuscript.

  • Yi, S., Haralick, R.M., and Shapiro, L.G. 1990. Automatic sensor and light source positioning for machine vision,Proc. 10th Intern. Conf. Patt. Recog., Atlantic City, pp. 55–59.

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, Carnegie Mellon University, 5000 Forbes Avenue, 15213, Pittsburgh, PA

    Keith D. Gremban & Katsushi Ikeuchi

Authors
  1. Keith D. Gremban
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Katsushi Ikeuchi
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Gremban, K.D., Ikeuchi, K. Planning multiple observations for object recognition. Int J Comput Vision 12, 137–172 (1994). https://doi.org/10.1007/BF01421201

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01421201

Keywords

Search

Navigation