This Article 
 Bibliographic References 
 Add to: 
A Multiple-Baseline Stereo
April 1993 (vol. 15 no. 4)
pp. 353-363

A stereo matching method that uses multiple stereo pairs with various baselines generated by a lateral displacement of a camera to obtain precise distance estimates without suffering from ambiguity is presented. Matching is performed simply by computing the sum of squared-difference (SSD) values. The SSD functions for individual stereo pairs are represented with respect to the inverse distance and are then added to produce the sum of SSDs. This resulting function is called the SSSD-in-inverse-distance. It is shown that the SSSD-in-inverse-distance function exhibits a unique and clear minimum at the correct matching position, even when the underlying intensity patterns of the scene include ambiguities or repetitive patterns. The authors first define a stereo algorithm based on the SSSD-in-inverse-distance and present a mathematical analysis to show how the algorithm can remove ambiguity and increase precision. Experimental results with real stereo images are presented to demonstrate the effectiveness of the algorithm.

[1] D. Marr and T. Poggio, "A theory of human stereo vision," inProc. Roy. Soc.(London), 1979, pp. 301-328, vol. B.
[2] W. E. L. Grimson, "Computational experiments with a feature based stereo algorithm,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-7, no. 1, pp. 17-34, Jan. 1985.
[3] S. T. Barnard, "Stochastic stereo matching over scale,"Int. J. Comput. Vision, pp. 17-32, 1989.
[4] M. J. Hannah, "A system for digital stereo image matching,"Photogram. Eng. Remote Sensing, vol. 55, no. 12, pp. 1765-1770, Dec. 1989.
[5] J. -S. Chen and G. Medioni, "Parallel multiscale stereo matching using adaptive smoothing," inECCV90, 1990, pp. 99-103.
[6] R. C. Bolles, H. H. Baker, and D. H. Marimont, "Epipolar-plane image analysis: An approach to determining structure from motion,"Int. J. Comput. Vision, vol. 1, no. 1, 1987.
[7] M. Yamamoto, "The image sequence analysis of three-dimensional dynamic scenes," Tech. Rep. 893, Electrotech. Lab., Agency of Indus. Sci. Technol., Tsukuba, Ibaraki, Japan, May 1988.
[8] L. Matthies, R. Szeliski, and T. Kanade, "Kalman filter-based algorithms for estimating depth from image sequences,"Int. J. Comput. Vision, vol. 3, pp. 209-236, 1989.
[9] J. Heel, "Dynamic motion vision," inProc. DARPA Image Understanding Workshop(Palo Alto, CA), May 23-26, 1989, pp. 702-713.
[10] B. Wilcox, "Telerobotics and Mars rover research at JPL," Lecture at Carnegie Mellon Univ., Oct. 1987.
[11] H. P. Moravec, "Visual mapping by a robot rover," inProc. IJCAI, 1979, pp. 598-600.
[12] L. Matthies and M. Okutomi, "A Bayesian foundation for active stereo vision," inProc. SPIE Sensor Fusion II: Human Machine Strategies, Nov. 1989, pp. 62-74.
[13] M. Yachida, Y. Kitamura, and M. Kimachi, "Trinocular vision: New approach for correspondence problem," inProc. ICPR, 1986, pp. 1041-1044.
[14] V. J. Milenkovic and T. Kanade, "Trinocular vision using photometric and edge orientation constraints," inProc. Image Understanding Workshop(Miami Beach, FL), Dec. 1985, pp. 163-175.
[15] N. Ayache and F. Lustman, "Fast and reliable passive trinocular stereo vision," inProc. ICCV, 1987, pp. 422-426.
[16] R. Y. Tsai, "Multiframe image point matching and 3-d surface reconstraction,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-5, no. 2, Mar. 1983.
[17] T. Kanade and T. Nakahara, "Experimental results of multibaseline stereo," inIEEE Special Workshop Passive Ranging(Princeton, NJ), Oct. 1991.
[18] M. Okutomi and T. Kanade, "A locally adaptive window for signal matching," inProc. Int. Conf. Comput. Vision, Dec. 1990; also inInt. J. Comput. Vision, vol. 7, no. 2, pp. 143-162, 1992.

Index Terms:
computer vision; multiple-baseline stereo; stereo matching method; lateral displacement; precise distance estimates; computer vision; stereo image processing
M. Okutomi, T. Kanade, "A Multiple-Baseline Stereo," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 4, pp. 353-363, April 1993, doi:10.1109/34.206955
Usage of this product signifies your acceptance of the Terms of Use.