Skip to main content
SpringerLink
Log in

Object recognition by combining paraperspective images

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

Abstract

This paper provides a study on object recognition under paraperspective projection. Discussed is the problem of determining whether or not a given image was obtained from a 3-D object to be recognized. First it is clarified that paraperspective projection is the first-order approximation of perspective projection. Then it is shown that, if we represent an object as a set of its feature points and the object undergoes a rigid transformation or an affine transformation, any paraperspective image can be expressed as a linear combination of several appropriate paraperspective images: we need at least three images for rigid transformations; whereas we need at least two images for affine transformations. Particularly in the case of a rigid transformation, the coefficients of the combination have to satisfy two conditions: orthogonality and norm equality. A simple algorithm to solve the above problem based on these properties is presented: a linear, single-shot algorithm. Some experimental results with synthetic images and real images are also given.

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. 1976. Computer description of curved objects. IEEE Trans. on Computers, 25:439–449.

    Google Scholar 

  • Aloimonos, J. 1989. Shape from texture. Biological Cybernetics, 58(5):345–360.

    Google Scholar 

  • Aloimonos, J. and Basu, A. 1986. Shape and 3-D motion from contour without point to point correspondence: General principles. In Proc. of CVPR, pp. 518–527.

  • Besl, P.J. and Jain, R.C. 1985. Three-dimensional object recognition. ACM Computing Surveys, 1(17):75–145.

    Google Scholar 

  • Binford, T.O. 1971. Visual perception by computer. In Proc. IEEE Conf. on Systems and Control.

  • Burns, J.B., Weiss, R.S., and Riseman, E.M. 1993. View variation of point-set and line-segment features. IEEE Trans. on PAMI, 15(1):51–68.

    Google Scholar 

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

  • Marr, D. and Nishihara, H.K. 1978. Representation and recognition of the spatial organization of three-dimensional shapes. Proc. of R. Soc. Lond. B, 100:269–294.

    Google Scholar 

  • Moses, Y. and Ullman, S. 1992. Limitations of non model-based recognition systems. In Proc. of the 2nd ECCV, pp. 820–828.

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

  • Ohta, Y., Maenobu, K., and Sakai, T. 1981. Obtaining surface orientation from texels under perspective projection. In Proc. of the 7th IJCAI, pp. 746–751.

  • Poelman, C.J. and Kanade, T. 1992. A paraperspective factorization method for shape and motion recovery. Technical Report, CMUCS-92-208, School of Computer Science, Carnegie Mellon Univ. PA.

  • Poelman, C.J. and Kanade, T. 1994. A paraperspective factorization method for shape and motion recovery. In Proc. of the 3rd ECCV. 2: 97–108.

  • Poggio, T. 1990. 3D object recognition: On a result of Basri and Ullman. IRST Technical Report, 9005-03, Trento, Italy.

  • Poggio, T. and Edelman, S. 1990. A network that learns to recognize three-dimensional objects. Nature, 343(6225):263–266.

    Google Scholar 

  • Rothwell, C.A., Forsyth, D.A., Zisserman, A., and Mundy, J.L. 1993. Extracting projective structure from single perspective views of 3D point sets. In Proc. of ICCV4, pp. 573–582.

  • Soroka, B.I. and Bajcsy, R.K. 1976. Generalized cylinders from serial sections. In Proc. of the 3rd Int. J. Conf. on Pattern Recognition, pp. 734–735.

  • Sugimoto, A. 1993. Projective invariant of lines on adjacent planar regions in a single view. ATR Technical Report, TR-H-034, ATR, Kyoto, Japan.

    Google Scholar 

  • Sugimoto, A. 1994. Geometric invariant of noncoplanar lines in a single view. In Proc. of the 12th Int. Conf. on Pattern Recognition, 1: 190–195.

  • Sugimoto, A. 1995. Invariants within the context of vision and their applications (in Japanese). SIG-CV-93, Information Processing Society of Japan, pp. 19–34.

  • Sugimoto, A. and Murota, K. 1993a. 3D object recognition by combination of perspective images. In Proc. of SPIE Conf. 1904: 183–195.

  • Sugimoto, A. and Murota, K. 1993b. Recognition by combination of paraperspective images. In Proc. of The 8th Scandinavian Conf. on Image Analysis, 2:1161–1169.

  • Ullman, S. and Basri, R. 1991. Recognition by linear combinations of models. IEEE Trans. on PAMI, 13(10):992–1006.

    Google Scholar 

  • Weiss, I. 1993. Geometric invariants and object recognition. Int. J. of Computer Vision, 10(3):207–231.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. ATR Human Information Processing Research Laboratories, Soraku-gun, 619-02, Kyoto, Japan

    Akihiro Sugimoto

Authors
  1. Akihiro Sugimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This work was done while the author was with ATR Auditory and Visual Perception Research Laboratories.

Advanced Research Laboratory Hitachi, Ltd.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sugimoto, A. Object recognition by combining paraperspective images. Int J Comput Vision 19, 181–201 (1996). https://doi.org/10.1007/BF00055804

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00055804

Keywords

Search

Navigation