JRM Vol.20 No.1 pp. 159-170
doi: 10.20965/jrm.2008.p0159


Mask Scale Adjustment (MSA) in Stereo Matching

Zheng Xu, Masanori Idesawa, and Qin Wang

Graduate School of Information Systems, The University of Electro-Communications, 1-5-1 Choufugaoka, Choufu-shi, Tokyo 182-8585, Japan

August 27, 2007
December 14, 2007
February 20, 2008
mask scale adjusting, stereo matching, scale difference, binocularly unpaired part, volume perception

We proposed mask scale adjustment method for stereo matching inspired by volume perception in human visual perception. Stereo matching is required to obtain 3-dimensional (3D) information from stereo pair images, and many sophisticated approaches have been developed to precisely obtain correspondence in stereo pairs. We found a forgotten problem not solved by these methods inherent in stereo matching and originating in the scale difference between stereo pair images. We propose mask scale adjustment for improving matching performance, especially in adjacent areas of binocularly unpaired parts, on objects with curved surfaces. Implementing our proposal into conventional stereo matching would yield more precise 3D information on objects and realize of volume perception.

Cite this article as:
Zheng Xu, Masanori Idesawa, and Qin Wang, “Mask Scale Adjustment (MSA) in Stereo Matching,” J. Robot. Mechatron., Vol.20, No.1, pp. 159-170, 2008.
Data files:
  1. [1] D. Marr, “Vision, a computational into the human representation and processing of visual information,” 1982.
  2. [2] H. Ishikawa and D. Geiger, “Occlusions, Discontinuities, and Epipolar Lines in Stereo,” In the Fifth European Conf. on Computer Vision (ECCV ’98), Freiburg, Germany, pp. 232-248, 1998.
  3. [3] T. Kanade and M. Okutomi, “A Stereo Matching Algorithm with Adaptive Window: Theory and Experiment,” Proc. of the 1991 IEEE, Int. Conf. on Robotics and Automation Sacramento, California, pp. 920-932, 1991.
  4. [4] S. Geman and D. Geman, “Stochastic Relaxation, Gibbs Distributions, and Bayesian Restoration of Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.6, No.6, pp. 721-741, 1984.
  5. [5] D. Scharstein and R. Szeliski, “A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,” Computer Vision, Vol.47, No.1, pp. 7-42, 2002.
  6. [6] S. Baker, T. Sim, and T. Kanade, “A Characterization of Inherent Stereo Ambiguities,” ICCV 8th, pp. 428-435, 2001
  7. [7] T. Iwamoto and M. Idesawa, “Volume Perception and a Processing Method of Unpaired Region in Stereo Vision,” Journal of Robotics and Mechatronics, Vol.9, No.2, p. 121, 1997.
  8. [8] T. Iwamoto, M. Idesawa, and Y. Sakaguchi, “Processing Methods of Unpaired Region in Stereo Vision,” Sensing and Perception, pp. 17-20, 1995 (in Japanese).
  9. [9] O. Watanabe and M. Idesawa, “Effect of an Occluding Contour on the Volume Perception in Binocular Stereopsis,” J. Appl. Phys., Vol.40, pp. 958-960, 2001.
  10. [10] Z. Xu and M. Idesawa, “A Study on Stereo Vision System with Volume Perception Considering Binocularly Unpaired Regions,” Sensing and Perception, pp. 27-32, 2003.
  11. [11] Z. Xu and M. Idesawa, “A Processing Method of Binocularly Unpaired Regions in Stereo Images for Realizing Volume Perception on Computer Vision System,” Proc. of the Sixth Int. Conf. on Human and Computer (HC-2003), pp. 246-252, August, 2003.
  12. [12] R. Sara and R. Bajcsy, “On Occluding Contour Artifacts in Stereo Vision,” Int. Conf. on Computer Vision and Pattern Recognition, pp. 852-857, 1997.
  13. [13] C. L. Zitnick and T. Kanade, “A Cooperative Algorithm for Stereo Matching and Occlusion Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.22, No.7, pp. 657-684, 2000.
  14. [14] J. Sun, N. N. Zheng, and H. Y. Shum, “Stereo Matching Using Belief Propagation,” Proc. 7th European Conf. on Computer Vision, Vol.2, pp. 510-524, 2002.
  15. [15] M. Okutomi and T. Kanade, “A Multiple-Baseline Stereo,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.15, No.4, pp. 353-363, 1993.
  16. [16] D. Marr and T. Poggio, “Cooperative Computation of Stereo Disparity,” Science, Vol.194, pp. 209-236, 1976.
  17. [17] D. Marr and T. Poggio, “A Computational Theory of Human Stereo Vision,” Proc. Royal Soc. London B, Vol.204, pp. 301-328, 1979.
  18. [18] G. Egnal and R. Wildes, “Detecting Binocular Half-Occlusions: Emirical Comparisons of Five Approaches,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.24, No.8, pp. 1127-1133, 2002.
  19. [19] W. Hoff and N. Ahuja, “Surfaces from Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.11, No.2, pp. 121-136, 1989.
  20. [20] M. Z. Brown, D. Burschka, and G. D. Hager, “Advances in Computational Stereo,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.25, No.8, pp. 993-1008, 2003.
  21. [21] Z. Xu and M. Idesawa, “Mask scale adjusting stereo matching method for an object with curved surface,” SPIE Int. Symposium on Optomechatronic Technologies (ISOT 2005), Proc. of SPIE, Vol.6051, 605110O-1-12, 2005.
  22. [22] Z. Xu and M. Idesawa, “A New Method of Stereo Matching for Curved Surface,” Proc. of The 11th Int. Display Workshop 2004, pp. 1551-1554, 2004.
  23. [23] Z. Xu and M. Idesawa, “A New Method to Do Stereo matching in Curved Surface,” Proc. of The 14th Int. Display Workshop 2007, pp. 1235-1238, 2007.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Feb. 25, 2021