Skip to main content
SpringerLink
Log in

Planar object recognition using projective shape representation

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

Abstract

We describe a model based recognition system, called LEWIS, for the identification of planar objects based on a projectively invariant representation of shape. The advantages of this shape description include simple model acquisition (direct from images), no need for camera calibration or object pose computation, and the use of index functions. We describe the feature construction and recognition algorithms in detail and provide an analysis of the combinatorial advantages of using index functions. Index functions are used to select models from a model base and are constructed from projective invariants based on algebraic curves and a canonical projective coordinate frame. Examples are given of object recognition from images of real scenes, with extensive object libraries. Successful recognition is demonstrated despite partial occlusion by unmodelled objects, and realistic lighting conditions.

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

  • Ayache, N. and Faugeras, O.D. 1986. HYPER: a new approach for the recognition and positioning of two-dimensional objects.IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-8(1):44–54.

    Google Scholar 

  • Ayache, N. and Faugeras, O.D. 1987. Building a consistent 3D representation of a mobile robot environment by combining multiple stereo views. InProc. IJCAI, pp. 808–810.

  • Binford, T.O. 1981. Inferring surfaces from images.Artificial Intelligence, 17:205–244.

    Google Scholar 

  • Binford, T.O. and Levitt, T.S. 1993. Quasi-invariants: theory and explanation. InProc. DARPA IUW, pp. 819–829.

  • Bolles, R.C. and Horaud, R. 1987. 3DPO: a three-dimensional part orientation system. InThree Dimensional Vision, T. Kandae (ed.), Kluwer Academic Publishers, pp. 399–450.

  • Bookstein, F. 1979. Fitting conic sections to scattered data.Computer Vision Graphics and Image Processing, CVGIP-9:56–71.

    Google Scholar 

  • Borgefors, G. 1988. Hierarchical chamfer matching: a parametric edge matching algorithm.IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-10(6):849–865.

    Google Scholar 

  • Brooks, R.A. 1983. Model-based three-dimensional interpretations of two-dimensional images.Pattern Analysis and Machine Intelligence, PAMI-5(2).

  • Califano, A. and Mohan, R. 1992. Multidimensional indexing for recognizing visual shapes.Visual Form, pp. 190–118.

  • Canny, J.F. 1986. A computational approach to edge detection.IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-8(6):679–698.

    Google Scholar 

  • Carlsson, S. 1992. Projectively invariant decomposition of planar shapes. InGeometric Invariance in Computer Vision, J. Mundy and A.P. Zisserman (eds.), MIT Press.

  • Cass, T.A. 1992. Polynomial-time object recognition in the presence of clutter, occlusion, and uncertainty. InProc. ECCV, pp. 834–842.

  • Clemens, D.T. and Jacobs, D.W. 1991. Model group indexing for recognition.IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-13(10):1007–1017.

    Google Scholar 

  • Cox, I.J., Rehg, J.M., and Hingorani, S. 1992. A Bayesian multiple hypothesis approach to contour grouping. InProc. ECCV, pp. 72–77.

  • Demey, S., Zisserman, A., and Beardsley, P. 1992. Affine and projective structure from motion. InProc. BMVC, pp. 49–58.

  • Duda, R.O. and Hart P.E. 1973.Pattern Classification and Scene Analysis. Wiley.

  • Ettinger, G.J. 1988. Large hierarchical object recognition using libraries of parameterized model sub-parts. InProc. CVPR, pp. 32–41.

  • Faugeras, O. 1992. What can be seen in three dimensions with an uncalibrated stereo rig? InProc. ECCV, pp. 563–578.

  • Fisher, R.B. 1989.From Surfaces to Objects: Computer Vision and Three Dimensional Scene Analysis. John Wiley and Sons.

  • Forsyth, D.A., Mundy, J.L., Zisserman, A.P., Coelho, C., Heller, A., and Rothwell, C.A. 1991. Invariant descriptors for 3-D object recognition and pose.IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-13(10):971–991.

    Google Scholar 

  • Forsyth, D.A., Mundy, J.L., Zisserman, A.P., and Rothwell, C.A. 1992. Recognising curved surfaces from their outlines. InProc. ECCV, pp. 639–648.

  • Forsyth, D.A. 1993. Recognizing algebraic surfaces from their outlines. InProc. ICCV, pp. 476–480.

  • Goad, C. 1983. Special purpose automatic programming for 3D model-based vision. InProc. DARPA IUW, pp. 371–381.

  • Grimson, W.E.L. and Lozano-Pérez, T. 1987. Localizing overlapping parts by searching the interpretation tree.IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-9(4):469–482.

    Google Scholar 

  • Grimson, W.E.L. 1990.Object Recognition by Computer, The Role of Geometric Constraints. MIT Press.

  • Gueziec, A. and Ayache, N. 1993. New developments on geometric hashing for curve matching. InProc. CVPR, pp. 703–704.

  • Hartley, R.I., Gupta, R., and Chang, T. 1992. Stereo from uncalibrated cameras. InProc. CVPR, pp. 761–764.

  • Huttenlocher, D.P. and Ullman, S. 1987. Object recognition using alignment. InProc. ICCV, pp. 102–111.

  • Huttenlocher, D.P. 1988. Three-dimensional recognition of solid objects from a two-dimensional image. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, MIT.

  • Huttenlocher, D.P. 1991. Fast affine point matching: an output-sensitive method. InProc. CVPR, pp. 263–268.

  • Jacobs, D.W. 1992. Space efficient 3D model indexing. InProc. CVPR, pp. 439–444.

  • Kalvin, A., Schonberg, E., Schwartz, J.T., and Sharir, M. 1986. Two-dimensional, model-based, boundary matching using footprints.International Journal of Robotics Research, IJRR-5(4):38–55.

    Google Scholar 

  • Koenderink, J.J. and Van Doorn, A.J. 1991. Affine structure from motion.J. Opt. Soc. Am. A., 8(2):377–385.

    Google Scholar 

  • Lamdan, Y., Schwartz, J.T., and Wolfson, H.J. 1988. Object recognition by affine invariant matching. InProc. CVPR, pp. 335–344.

  • Lowe, D.G. 1985.Perceptual Organization and Visual Recognition. Kluwer Academic Publishers.

  • Lowe, D.G. 1987. The viewpoint consistency constraint.International Journal of Computer Vision, IJCV-1(1):57–72.

    Google Scholar 

  • Liu, J., Mundy, J.L., Forsyth, D.A., Zisserman, A., and Rothwell, C.A. 1993. Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders. InProc. CVPR, pp. 123–128.

  • Marr, D. 1982.Vision. Freeman.

  • Maybank, S.J. 1993. Classification Based on the Cross Ratio. InProc. 2nd ARPA/NSF/ESPRIT Workshop on the Applications of Invariance in Computer Vision, Azores, Springer-Verlag Lecture Notes in Computer Science 825, pp. 453–472.

  • Mundy, J.L. and Zisserman, A.P. 1992.Geometric Invariance in Computer Vision. MIT Press.

  • Mundy, J.L., Huang, C., Liu, J., Hoffman, W., Forsyth, D.A., Rothwell, C.A., Zisserman, A., Utcke, S., and Bournez, O. 1994. MORSE: A 3D object recognition system based on geometric invariants. InProc. ARPA Image Understanding Workshop, pp. 1393–1402.

  • Murray, D.W. 1987. Model-based recognition using 3D structure from motion.Image and Vision Computing, IVC-5:85–90.

    Google Scholar 

  • Nayar, S.K. and Bolle, R.M. 1993. Reflectance ratio: a photometric invariant for object recognition. InProc. ICCV, pp. 280–285.

  • Nielsen, L. 1988. Automated guidance of vehicles using vision and projective invariant marking. Automatica, 24:135–148.

    Google Scholar 

  • Pollard, S.B., Pridmore, T.P., Porrill, J., Mayhew, J.E.W., and Frisby, J. P. 1989. Geometrical modeling from multiple stereo views.International Journal of Robotics Research, IJRR-8(4):132–138.

    Google Scholar 

  • Quan, L., Gros, P., and Mohr, R. 1991. Invariants of a pair of conics revisited. InProc. BMVC, pp. 71–77.

  • Reid, I. 1991. Recognising parameterized models from range data. D. Phil. Thesis, Department of Engineering Science, Oxford University, Oxford.

    Google Scholar 

  • Rigoutsos, I. and Hummel, R. 1991. Implementation of geometric hashing on the connection machine. InProc. IEEE Workshop on Directions in Automated CAD-Based Vision, pp. 76–84.

  • Rothwell, C.A., Forsyth, D.A., Zisserman, A., and Mundy, J.L. 1993a. Extracting projective information from single views of 3D point sets. InProc. ICCV, pp. 573–582.

  • Rothwell, C.A. 1993. Hierarchical object descriptions using invariants. InProc. 2nd ARPA/NSF-ESPRIT Workshop on the Applications of Invariance in Computer Vision, Azores, Springer-Verlag Lecture Notes in Computer Science 825, pp. 397–414.

  • Rothwell, C.A. 1995.Object Recognition through Invariant Indexing. Oxford University Press Science Publications.

  • Schwartz, J.T. and Sharir, M. 1987. Identification of partially obscured objects in two and three dimensions by matching noisy characteristic curves.International Journal of Robotics Research, IJRR-6(2):29–44.

    Google Scholar 

  • Semple, J.G. and Kneebone, G.T. 1952.Algebraic Projective Geometry. OUP.

  • Sha'ashua, A. and Ullman, S. 1988. Structural saliency: the detection of globally salient structures using a locally connected network. InProc. ICCV, pp. 321–327.

  • Sinclair, D.A., Blake, A., Smith, S., and Rothwell, C.A. 1993. Planar region detection and motion recovery.Image and Vision Computing, IVC-11(4):229–234.

    Google Scholar 

  • Slama, C.C. 1980.Manual of Photogrammetry. American Society of Photogrammetry, 4th edition.

  • Stein, F. and Medioni, G. 1992. Structural indexing: efficient 2-D object recognition.Pattern Analysis and Machine Intelligence, PAMI-14:1198–1204.

    Google Scholar 

  • Stockman, G. 1987. Object recognition and localization via pose clustering.Computer Vision Graphics and Image Processing, CVGIP-40:361–387.

    Google Scholar 

  • Taubin, G. and Cooper, D.B. 1991. Object recognition based on moment (or algebraic) invariants.IBM TR-RC17387, IBM T.J. Watson Research Centre P.O. Box 704, Yorktown Heights, NY 10598.

    Google Scholar 

  • Thompson, D.W. and Mundy, J.L. 1987. Three-dimensional model matching from an unconstrained view-point. InProc. ICRA, pp. 208–220.

  • Van Gool, L., Kempenaers, P., and Oosterlinck, A. 1991. Recognition and semi-differential invariants. InProc. CVPR, pp. 454–460.

  • Wayner, P.C. 1991. Efficiently using invariant theory for model-based matching. InProc. CVPR, pp. 473–478.

  • Weiss, I. 1988. Projective invariants of shapes. InProc. DARPA IUW, pp. 1125–1134.

  • Wolfson, H.J. 1992. Object recognition by transformation invariant indexing. InProc. Invariance Workshop, ECCV.

Download references

Author information

Authors and Affiliations

  1. Robotics Research Group, Department of Engineering Science, University of Oxford, Parks Rd., OX1 3PJ, Oxford, UK

    C. A. Rothwell & A. Zisserman

  2. Department of Computer Science, University of Iowa, 52242, Iowa City, IA

    D. A. Forsyth

  3. GE Center for Research and Development, 1 River Rd., 12345, Schenectady, NY

    J. L. Mundy

Authors
  1. C. A. Rothwell
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. Zisserman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. D. A. Forsyth
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. L. Mundy
    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

Rothwell, C.A., Zisserman, A., Forsyth, D.A. et al. Planar object recognition using projective shape representation. Int J Comput Vision 16, 57–99 (1995). https://doi.org/10.1007/BF01428193

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01428193

Keywords

Search

Navigation