Skip to main content
SpringerLink
Log in

Improving stereovision matching through supervised learning

  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Most classical local stereovision matching algorithms use features representing objects in both images and compute the minimum difference attribute values. We have verified that the differences in attributes for the true matches cluster in a cloud around a centre. The correspondence is established on the basis of the minimum squared Mahalanobis distance between the difference of the attributes for a current pair of features and the cluster centre (similarity constraint). We introduce a new supervised learning strategy derived from the Learning Vector Quantization (LVQ) approach to get the best cluster centre. Additionally, we obtain the contribution or specific weight of each attribute for matching. We improve the learning law introducing a variable learning rate. The supervised learning and the improved learning law are the most important findings, which are justified by the computed better results compared with classical local stereovision matching methods without learning and with other learning strategies. The method is illustrated with 47 pairs of stereo images.

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

  1. Lee SH, Leou JJ. A dynamic programming approach to line segment matching in stereo vision. Pattern Recognition 1994; 27: 961–986

    Google Scholar 

  2. Marr D, Poggio T. A computational theory of human stereovision. Proc Roy Soc Lond B 1979; 207: 301–328

    Google Scholar 

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

    Google Scholar 

  4. Pollard SB, Mayhew JEW, Frisby JP. PMF: A stereo correspondence algorithm using a disparity gradient limit. Perception 1981; 14: 449–470

    Google Scholar 

  5. Kohonen T. Self-Organization and Associative Memory, Springer-Verlag, New York, 1989

    Google Scholar 

  6. Kohonen T. Self-Organizing Maps, Springer-Verlag, Berlin, 1995

    Google Scholar 

  7. Patterson DW. Artificial Neural Networks Prentice-Hall, Singapore, 1996

    Google Scholar 

  8. Wu JK. Neural Networks and Simulation Methods, Marcel Dekker, New York, 1994

    Google Scholar 

  9. Cruz JM, Pajares G, Aranda J. A neural network approach to the stereovision correspondence problem by unsupervised learning. Neural Networks 1995; 8(5): 805–813

    Google Scholar 

  10. Pajares G. Estrategia de Solucion al Problema de la Correspondencia en Vision Estereoscópica por la Jerarquía Metodológica y la Integración de Criterios. PhD thesis Dpto. Informática y Automática, Facultad Ciencias UNED: Madrid, 1995

    Google Scholar 

  11. Pajares G, Cruz JM, Aranda J. Stereo matching based on the self-organizing feature mapping algorithm. Pattern Recognition Letters 1998 (accepted)

  12. Pajares G, Cruz JM, Aranda J. Relaxation by Hopfield network in stereo image matching. Pattern Recognition 1998; 31(5): 561–574

    Google Scholar 

  13. Dhond AR, Aggarwal JK. Structure from stereo — a review. IEEE Trans Syst Man Cybern 1989; 19: 1489–1510

    Google Scholar 

  14. Ozanian T. Approaches for stereo matching — a review. Modeling Identification Control 1995; 16(2): 65–94

    Google Scholar 

  15. Fua P. A parallel algorithm that produces dense depth maps and preserves image features. Machine Vision and Applic 1993; 6: 35–49

    Google Scholar 

  16. Kim YC, Aggarwal JK. Positioning three-dimensional objects using stereo images. IEEE J Robotics and Automation 1987; 3(4): 361–373

    Google Scholar 

  17. Mousavi MS, Schalkoff RJ. ANN Implementation of stereo vision using a multi-layer feedback architecture. IEEE Trans Sys Man Cybern 1994; 24(8): 1220–1238

    Google Scholar 

  18. Ayache N, Faverjon B. Efficient registration of stereo images by matching graph descriptions of edge segments. Int J Computer Vision 1987; 1: 107–131

    Google Scholar 

  19. Ayache N. Artificial Vision for Mobile Robots: Stereo Vision and Multisensory Perception, MIT Press, Cambridge, MA, 1991

    Google Scholar 

  20. Kim DH, Choi WY, Park RH. Stereo matching technique based on the theory of possibility. Patt Recognition Letters 1994; 13: 735–744

    Google Scholar 

  21. Hoff W, Ahuja N. Surface from stereo: integrating feature matching, disparity estimation, and contour detection. IEEE Trans Patt Anal Machine Intell 1989; 11: 121–136

    Google Scholar 

  22. Wuescher DM, Boyer KL. Robust contour decomposition using a constraint curvature criterion. IEEE Trans Patt Anal Machine Intell 1991; 13(1): 41–51

    Google Scholar 

  23. Breuel TM. Finding lines under bounded error. Pattern Recognition 1996; 29 (1): 167–178

    Google Scholar 

  24. Zhou Y, Chellapa R. Artificial Neural Networks for Computer Vision, Springer-Verlag, Berlin, 1992

    Google Scholar 

  25. Yu SS, Tsai WH. Relaxation by the Hopfield neural network. Pattern Recognition 1992; 25(2): 197–209

    Google Scholar 

  26. Ruichek Y, Postaire JG. A neural matching algorithm for 3-D reconstruction from stereo pairs of linear images. Pattern Recognition Letters 1996; 17: 387–398

    Google Scholar 

  27. Lew MS, Huang TS, Wong K. Learning and feature selection in stereo matching. IEEE Trans Patt Anal Machine Intell 1994; 16(9): 869–881

    Google Scholar 

  28. Huertas A, Medioni G. Detection of intensity changes with subpixel accuracy using Laplacian-Gaussian masks. IEEE Trans Patt Anal Machine Intell 1986; 8(5): 651–664

    Google Scholar 

  29. Leu JG, Yau HL. Detecting the dislocations in metal crystals from microscopic images. Pattern Recognition 1991; 24(1): 41–56

    Google Scholar 

  30. Krotkov EP. Active Computer Vision by Cooperative focus and Stereo, Springer-Verlag, Berlin, 1989

    Google Scholar 

  31. Kahn P, Kitchen L, Riseman EM. A fast line finder for vision-guided robot navigation. IEEE Trans Patt Anal Machine Intell 1990; 12(11): 1098–1102

    Google Scholar 

  32. Maravall D. Reconocimiento de Formas y Visión Artificial, RAMA, Madrid, 1993

    Google Scholar 

  33. Tanaka S, Kak AC. A rule-based approach to binocular stereopsis. In: Jain RC, Jain AK (eds) Analysis and Interpretation of Range Images, Springer-Verlag, 1990

  34. Nevatia R, Babu KR. Linear feature extraction and description. Computer Vision, Graphics and Image Process 1980; 13: 257–269

    Google Scholar 

  35. Mardia KV. Statistics of Directional Data, Academic Press, London, 1972

    Google Scholar 

  36. Duda RO, Hart PE. Pattern Classification and Scene Analysis. Wiley, New York, 1973

    Google Scholar 

  37. Kosko B. Neural Networks and Fuzzy Systems, Prentice-Hall, Englewood Cliffs, NJ, 1992

    Google Scholar 

  38. Martin-Smith P, Pelayo FJ, Diaz A, Ortega J, Prieto A. A learning algorithm to obtain self-organizing maps using fixed neighbourhood Kohonen networks. In: Mira J, Cabestany J, Prieto A (eds), New Trends in Neural Computation, Springer-Verlag, 1993, 297–304

  39. Haykin S. Neural Networks: A Comprehensive Foundation, Macmillan. New York, 1994

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dpto. Arquitectura de Computadores y Automatica, Facultad de CC. Físicas, Universidad Complutense, 28040, Madrid, Spain

    G. Pajares, J. M. de la Cruz & J. A. López-Orozco

Authors
  1. G. Pajares
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. M. de la Cruz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. A. López-Orozco
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to G. Pajares.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pajares, G., de la Cruz, J.M. & López-Orozco, J.A. Improving stereovision matching through supervised learning. Pattern Analysis & Applic 1, 105–120 (1998). https://doi.org/10.1007/BF01237939

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01237939

Keywords

Search

Navigation