Advertisement

Seeing behind occlusions

  • Dana H. Ballard
  • Rajesh P. N. Rao
Recognition I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)

Abstract

The location of objects in images is difficult owing to the view variance of geometric features but can be determined by developing viewinsensitive descriptions of the intensities local to image points. Viewinsensitive descriptions are achieved in this work by describing points in terms of the responses of steerable filters at multiple scales. Owing to the use of multiple scales, the vector for each point is, for all practical purposes, unique, and thus can be easily matched to other instances of the point in other images. We show that this method can be extended to handle the case where the area near a point of interest is partially occluded. The method uses a description of the occluder in the form of a template that can be obtained easily via active vision systems using a method such as disparity filtering.

Keywords

Image Point Match Point Filter Response Slide Projector Backprojection Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. [Bal91]
    D.H. Ballard. Animate vision. Artificial Intelligence, 48:57–86, 1991.Google Scholar
  2. [BW93]
    Dana H. Ballard and Lambert E. Wixson. Object recognition using steerable filters at multiple scales. In Proceedings of the IEEE Workshop on Qualitative Vision, 1993.Google Scholar
  3. [CB92]
    D.J. Coombs and C.M. Brown. Real-time smooth pursuit tracking for a moving binocular head. In IEEE Conference on Computer Vision and Pattern Recognition, pages 23–38, June 1992.Google Scholar
  4. [DS90]
    P.E. Danielsson and O. Seger. Rotation invariance in gradient and higher derivative detectors. Computer Vision, Graphics, and Image Processing, 49(2), February 1990.Google Scholar
  5. [FA91]
    William T. Freeman and Edward H. Adelson. The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(9):891–906, September 1991.Google Scholar
  6. [JM92]
    David G. Jones and Jitendra Malik. A computational framework for determining stereo correspondence from a set of linear spatial filters. In Proceedings of the Second European Conference on Computer Vision, 1992.Google Scholar
  7. [MN93]
    H. Murase and S.K. Nayar. Learning and recognition of 3-d objects from brightness images. Working Notes, A A A I Fall Symp. Series (Machine Learning in Computer Vision: What, Why, and How?, pages 25–29, October 1993.Google Scholar
  8. [MP89]
    Jitendra Malik and Pietro Perona. A computational model of texture segmentation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 326–332, June 1989.Google Scholar
  9. [NS90]
    K. Nakayama and S. Shimojo. Towards a neural understanding of visual surface representation. Cold Spring Harbor Symp. on Quantitative Biology, Vol. 55, The Brain, edited by T. Sejnowski, E.R. Kandel, C.F. Stevens, and J.D. Watson, 1990.Google Scholar
  10. [PG90]
    T. Poggio and F. Girosi. Ai memo 1140, AI Lab, MIT, 1989;. Proc. IEEE, 78:1481, 1990.Google Scholar
  11. [SB91]
    Michael J. Swain and Dana H. Ballard. Color indexing. International Journal of Computer Vision, 7:11–32, November 1991.Google Scholar
  12. [Swa90]
    Michael J. Swain. Color indexing. Technical Report 360, University of Rochester Computer Science Dept., 1990.Google Scholar
  13. [WT92]
    David Wilkes and John K. Tsotsos. Active object recognition. In IEEE Conference on Computer Vision and Pattern Recognition, June 1992.Google Scholar
  14. [WvdM92]
    L. Wiskott and C. von der Malsburg. A neural system for the recognition of partially occluded objects in cluttered scenes. Tr, Inst. fur Neuroinformatik, Ruhr-Universitat Bochum, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Dana H. Ballard
    • 1
  • Rajesh P. N. Rao
    • 1
  1. 1.Computer Science DepartmentUniversity of RochesterRochester

Personalised recommendations