Quantitative Evaluation of Matching Methods and Validity Measures for Stereo Vision

Abstract

The authors present a qualitative and quantitative comparison of various similarity measures that form the kernel of common area-based stereo-matching systems. The authors compare classical difference and correlation measures as well as nonparametric measures based on the rank and census transforms for a number of outdoor images. For robotic applications, important considerations include robustness to image defects such as intensity variation and noise, the number of false matches, and computational complexity. In the absence of ground truth data, the authors compare the matching techniques based on the percentage of matches that pass the left-right consistency test. The authors also evaluate the discriminatory power of several match validity measures that are reported in the literature for eliminating false matches and for estimating match confidence. For guidance applications, it is essential to have an estimate of confidence in the three-dimensional points generated by stereo vision. Finally, a new validity measure, the rank constraint, is introduced that is capable of resolving ambiguous matches for rank transform–based matching.

Get full access to this article

View all access options for this article.

References

Aschwanden, P., and Guggenbühl, W. 1993. Experimental results from a comparative study on correlation-type registration algorithms. In Robust Computer Vision, ed. Förstner, W., and Ruwiedel, S., 268–289. Karlsruhe, Germany: Wickmann .

Ayache, N., and Hansen, C. 1988. Rectification of images for binocular and trinocular stereovision . Proceedings of the Ninth International Conference on Pattern Recognition, November, pp. 11–16 .

Banks, J. 1999. Reliability analysis of transform-based stereo matching techniques, and a new matching constraint. Ph.D. thesis, Queensland University of Technology.

Banks, J., Bennamoun, M., Corke, P., and Kubik, K. 1998. Suitability of non-parametric stereo matching techniques for mining automation . Australian Journal of Intelligent Information Processing Systems 5: 111–119 .

Bhat, D., and Nayar, S. 1996. Ordinal measures for visual correspondence . IEEE Proceedings of Computer Vision and Pattern Recognition, San Francisco, CA, pp. 351–357 .

Bhat, D., and Nayar, S. 1998. Ordinal measures for image correspondence . IEEE Transactions on Pattern Analysis and Machine Intelligence 20: 415–423 .

Bolles, R., Baker, H., and Hannah, M. 1993. The JISCT stereo evaluation. DARPA Image Understanding Workshop, pp. 263–274.

Cochran, S., and Medioni, G. 1992. 3-D surface description from binocular stereo . IEEE Transactions on Pattern Analysis and Machine Intelligence 14: 981–994 .

Dhond, U., and Aggarwal, J. 1989. Structure from stereo—A review . IEEE Transactions on Systems, Man, and Cybernetics 19: 1489–1510 .

10.

Dunn, P., and Corke, P. 1997. Real-time stereopsis using FPGAs . Proceedings of FPGA’97, London, September.

11.

Faugeras, O., Hotz, B., Mathieu, H., et al. 1993. Real time correlation-based stereo: Algorithm, implementations and applications. Technical Report No. 2013, Institut National de Recherche en Informatique et en Automatique .

12.

Fua, P. 1993. A parallel stereo algorithm that produces dense depth maps and preserves image features . Machine Vision and Applications 6: 35–49 .

13.

Fusiello, A., Trucco, E., and Verri, A. 1997. Rectification with unconstrained stereo geometry . Proceedings of BMC’97.

14.

Konolige, K. 1998. Small vision systems: Hardware and implementation. In Eighth International Symposium on Robotics Research, ed. Y. Shirai and S. Hirose, 203–212. New York: Springer-Verlag .

15.

Matthies, L., Kelly, A., Litwin, T., and Tharp, G. 1996. Obstacle detection for unmanned ground vehicles: A progress report. In Robotics Research, the 7th International Symposium, ed. Giralt, G., and Hirzinger, G., 475–486. New York: Springer .

16.

McDonnell, M. J. 1981. Box-filtering techniques . Computer Graphics and Image Processing 17: 65–70 .

17.

Shirai, Y. 1987. Three-Dimensional Computer Vision. New York: Springer-Verlag .

18.

Slama, C., ed. 1980. Manual of Photogrammetry. 4th ed. Falls Creek, VA: American Society of Photogrammetry .

19.

Tomasi, C., and Manduchi, R. 1998. Stereo matching as a nearest neighbour problem . IEEE Transactions on Pattern Analysis and Machine Intelligence 20: 333–340 .

20.

Woodfill, J., and Von Herzen, B. 1997. Real-time stereo vision on the PARTS reconfigurable computer . IEEE Workshop on FPGAs for Custom Computing Machines, April, pp. 242–250 .

21.

Zabih, R. 1994. Individuating unknown objects by combining motion and stereo. Ph.D. thesis, Stanford University.

22.

Zabih, R., and Woodfill, J. 1994. Non-parametric local transforms for computing visual correspondence . 3rd European Conference on Computer Vision, Stockholm, Sweden.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB