Skip to main content

Advertisement

Springer Nature Link
Log in

Hierarchical stereo and motion correspondence using feature groupings

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

Abstract

Hierarchical feature based stereo matching and motion correspondence algorithms are presented. The hierarchy consists of lines, vertices, edges and surfaces. Matching starts at the highest level of the hierarchy (surfaces) and proceeds to the lowest (lines). Higher level features are easier to match, because they are fewer in number and more distinct in form. These matches then constrain the matches at lower levels. Perceptual and structural relations are used to group matches into islands of certainty. A Truth Maintenance System (TMS) is used to enforce grouping constraints and eliminate inconsistent match groupings. The TMS is also used to carry out belief revisions necessitiated by additions, deletions and confirmations of feature and match hypotheses.

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
$34.99 /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 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

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  • Arnold, R.D. and Binford, T.O. 1980. Geometric constraints in stereo vision. InProceedings, SPIE, Image Processing for Missile Guidance, 238:281–292.

    Google Scholar 

  • Ayache, N. and Faverjon, B. 1987. Efficient registration of stereo images by matching graph descriptions of edge segments.International Journal of Computer Vision, 1:107–131.

    Google Scholar 

  • Ayache, N. and Hansen, C. 1988. Rectification of images for binocular and trinocular stereo vision. InProceedings, International Conference on Pattern Recognition, Rome, Italy.

  • Baker, H.H. and Binford, T.O. 1982. A system for automated stereo mapping. InProceedings, DARPA Image Understanding Workshop, Palo Alto, CA, pp. 215–222.

  • Ballard, D.H. and Brown, C.M. 1982.Computer Vision. Prentice-Hall, Englewood Cliffs, NJ.

    Google Scholar 

  • Beveridge, J.R. and Riseman, E.M. 1992. Hybrid weak-perspective and full-perspective matching. InProceedings, IEEE Computer Vision and Pattern Recognition Conference, Champaign, IL, pp. 432–438.

  • Beveridge, J.R., Weiss, R., and Riseman, E.M. 1990. Combinatorial optimization applied to variable scale 2D model matching. InProceedings, IEEE International Conference on Pattern Recognition, Atlantic City, NJ, pp. 18–23.

  • Bhatnagar, R.K. and Kanal, L.N. 1988. Handling uncertain information: A review of numeric and non-numeric methods. In L.N. Kanal and J.F. Lemmer, editors,Uncertainty in Artificial Intelligence, Elsevier, Amsterdam, The Netherlands, pp. 3–26.

    Google Scholar 

  • Blake, A. and Zisserman, A. 1987.Visual Reconstruction. MIT Press, Cambridge, MA.

    Google Scholar 

  • Bodington, R.M., Sullivan, G.D., and Baker, K.D. 1990. Experiments on the use of the ATMS to label features for object recognition. InProceedings European Conference on Computer Vision, Antibes, France, pp. 542–551.

  • Bolles, R.C. and Cain, R.A. 1982. Recognizing and locating partially visible objects: The local-feature-focus method.International Journal of Robotics Research, 1(3):57–82.

    Google Scholar 

  • Bowen, J.B. and Mayhew, J.E.W. 1988. Consistency maintenance in the revgraph environment.Image and Vision Computing, 6:12–15.

    Google Scholar 

  • Canny, J.F. 1986. A computational approach to edge detection.IEEE Trans, on Patt. Anal. and Mach. Intell., 8:679–698.

    Google Scholar 

  • Chandrasekhar, S. and Chellappa, R. 1991. Passive navigation in a partially known environment. InProceedings, IEEE Workshop on Visual Motion, pp. 2–7.

  • Chung, R.C.K. and Nevatia, R. 1991. Use of monocular groupings and occlusion analysis in a hierarchical stereo system. InProceedings, IEEE Conference on Computer Vision and Pattern Recognition, Maui, HI, pp. 50–55.

  • Crowley, J.L., Stelmaszyk, P., and Discours, C. 1988. Measuring image flow by tracking edge-lines. InProceedings International Conference on Computer Vision, Tampa, FL, pp. 658–664.

  • de Kleer, J. 1986. An assumption-based TMS.Artificial Intelligence, 28:127–162.

    Google Scholar 

  • de Kleer, J. 1986. Problem solving with the ATMS.Artificial Intelligence, 28:197–224.

    Google Scholar 

  • Deriche, R. and Faugeras, O. 1990. Tracking line segments. InProceedings European Conference on Computer Vision, Antibes, France, pp. 259–268.

  • Doyle, J. 1979. A truth maintenance system.Artificial Intelligence, 12:231–272.

    Google Scholar 

  • Faugeras, O.D. and Hebert, M. 1986. The representation, recognition, and locating of 3-D objects.International Journal of Robotics Research, 5(3):27–52, Fall.

    Google Scholar 

  • Faugeras, O.D., Lustman, F., and Toscani, G. 1987. Motion and structure from motion from point and line matches. InProceedings, International Conference on Computer Vision, London, England, pp. 25–34.

  • Grimson, W.E.L. 1981.From Images to Surfaces: A Computational Study of the Human Early Visual System. MIT Press, Cambridge, MA.

    Google Scholar 

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

    Google Scholar 

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

    Google Scholar 

  • Hoff, W. and Ahuja, N. 1989. Surfaces from stereo: Integrating feature matching, disparity estimation, and contour detection.IEEE Trans. on Patt. Anal. and Mach. Intell., PAMI-11:121–136.

    Google Scholar 

  • Horaud, R. and Skordas, T. 1989. Stereo correspondence through feature grouping and maximal cliques.IEEE Trans. on Patt. Anal. and Mach. Intell., PAMI-11:1168–1180.

    Google Scholar 

  • Horn, B.K.P. 1990. Relative orientation.International Journal of Computer Vision, 4:59–78.

    Google Scholar 

  • Hwang, V.S-S., Davis, L.S., and Matsuyama, T. 1986. Hypothesis integration in image understanding systems.Computer Vision, Graphics and Image Processing, 36:321–371.

    Google Scholar 

  • 1987. Inference Corporation, Los Ageles.ART reference manual.

  • Laskey, K.B. and Lehner, P.E. 1989–90. Assumptions, beliefs and probabilities.Artificial Intelligence, 41:65–77.

    Google Scholar 

  • Lim, H.S. and Binford, T.O. 1988. Curved surface reconstruction using stereo correspondence. InProceedings DARPA Image Understanding Workshop, Cambridge, MA, pp. 809–819.

  • Lim, H.S. and Binford, TO. 1988. Structural correspondence in stereo vision. InProceedings DARPA Image Understanding Workshop, Cambridge, MA, pp. 794–808.

  • Lowe, D.G. 1987. Three-dimensional object recognition from single two-dimensional images.Artificial Intelligence, 31:355–395.

    Google Scholar 

  • Mackworth, A.K. 1977. Consistency in networks of relations.Artificial Intelligence, 8:99–118.

    Google Scholar 

  • Mayhew, J.E.W. and Frisby, J.P. 1981. Psychophysical and computational studies towards a theory of human stereopsis.Artificial Intelligence, 17:349–385.

    Google Scholar 

  • Medioni, G. and Nevatia, R. 1985. Segment-based stereo matching.Computer Vision, Graphics and Image Processing, 31:2–18.

    Google Scholar 

  • Mohan, R. and Nevatia, R. 1989. Using perceptual organization to extract 3-D structures.IEEE Trans. on Patt. Anal. and Mach. Intell., PAMI-11:1121–1139.

    Google Scholar 

  • Ohta, Y. and Kanade, T. 1985. Stereo by intra- and inter-scanline search using dynamic programming.IEEE Trans. on Patt. Anal. and Mach. Intell., PAMI-7:139–154.

    Google Scholar 

  • Price, K.E. 1985. Relaxation matching techniques—A comparison.IEEE Trans. on Patt. Anal. and Mach. Intell., PAMI-7:617–623.

    Google Scholar 

  • Provan, G.M. 1987. Complexity analysis of multiple context TMSs in scene representation. InProceedings AAAI, pp. 1732 -177.

  • Provan, G.M. 1988. Model based object recognition—A truth maintenance approach. InProceedings Fourth IEEE Conference on Artificial Intelligence Applications, San Diego, CA, pp. 230–235.

  • Sawhney, H.S. and Hanson, A.R. 1991. Identification and 3D description of shallow environmental structure in a sequence of images. InProceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 179–185.

  • Sawhney, H.S. and Hanson, A.R. 1992. Affine trackability aids obstacle detection. InProceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 418–424.

  • Stallman, R.M. and Sussman, G.J. 1977. Forward reasoning and dependency-directed back-tracking in a system for computer-aided circuit analysis.Artificial Intelligence, 9:135–196.

    Google Scholar 

  • Venkateswar, V. and Chellappa, R. 1991. A hierarchical approach to detection of buildings in aerial images. Technical Report CAR-TR-567, Center for Automation Research, University of Maryland.

  • Venkateswar, V. and Chellappa, R. 1992. Extraction of straight lines in aerial images.IEEE Trans. on Patt. Anal. and Mach. Intell., 14:1111–1114.

    Google Scholar 

  • Waltz, D. 1975. Understanding line drawings of scenes with shadows. In P.H. Winston, editor,The Psychology of Computer Vision, McGraw-Hill, New York, pp. 19–91.

    Google Scholar 

  • Williams, L.R. and Hanson, A.R. 1988. Translating optical flow into token matches and depth from looming. InProceedings International Conference on Computer Vision, pp. 441–448.

Download references

Author information

Authors and Affiliations

  1. Texas Instruments, PO Box 655474, MS 429, 75265, Dallas, TX

    V. Venkateswar

  2. Dept. of Electrical Engineering, Center for Automation Research, and Institute for Advanced Computer Studies, University of Maryland, 20742, College Park, MD

    R. Chellappa

Authors
  1. V. Venkateswar
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. R. Chellappa
    View author publications

    You can also search for this author inPubMed Google Scholar

Additional information

The support of Defense Advanced Research Projects Agency (ARPA Order No. 8979) and the U.S. Army Engineer Topographic Laboratories under contract DACA 76-92-C-0024 is gratefully acknowledged.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Venkateswar, V., Chellappa, R. Hierarchical stereo and motion correspondence using feature groupings. Int J Comput Vision 15, 245–269 (1995). https://doi.org/10.1007/BF01451743

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01451743

Keywords