Abstract
This paper describes a real-time stereo vision system that is required to support high-level object based tasks in a tele-operated environment. Stereo vision is computationally expensive, due to having to find corresponding pixels. Correlation is a fast, standard way to solve the correspondence problem. This paper analyses the behaviour of correlation based stereo to find ways to improve its quality while maintaining its real-time suitability. Three methods are suggested. Two of them aim to improve the disparity image especially at depth discontinuities, while one targets the identification of possible errors in general. Results are given on real stereo images with ground truth. A comparison with five standard correlation methods is provided. All proposed algorithms are described in detail and performance issues and optimisation are discussed. Finally, performance results of individual parts of the stereo algorithm are shown, including rectification, filtering andcorrelation using all proposed methods. The implemented system shows that errors of simple stereo correlation, especially in object border regions, can be reduced in real-time using non-specialised computer hardware.
Similar content being viewed by others
References
Boykov, Y., Veksler, O., and Zabih, R. 1998. A variable window approach to early vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20:1283–1294.
Cox, I.J., Hingorani, S.L., Rao, S.B., and Maggs, B.M. 1996. A maximum likelihood stereo algorithm. Computer Vision and Image Understanding, 63:542–567.
Faugeras, O., Hotz, B., Mathieu, H., Viville, T., Zhang, Z., Fua, P., Thron, E., Moll, L., Berry, G., Vuillemin, J., Bertin, P., and Proy, C. 1993. Real time correlation-based stereo: Algorithm, implementations and application. INRIA, Tech. Rep. 2013.
Fua, P. 1993. A parallel stereo algorithm that produces dense depth maps and preserves image features. Machine Vision and Applications, 6:35–49.
Fusiello, A., Roberto, V., and Trucco, E. 1997. Efficient stereo with multiple windowing. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Puerto Rico. IEEE: Piscataway, NJ, pp. 858–863.
Kanade, T. and Okutomi, M. 1994. Astereo matching algorithm with an adaptive window: Theory and experiment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16:920.
Konolige, K. 1997. Small vision systems: Hardware and implementation. In Eighth International Symposium on Robotics Research, Hayama, Japan. Springer: London, pp. 203–212.
Little, J.J. 1992. Accurate early detection of discontinuities. In Proceedings of the Vision Interface Conference VI'92, Vancouver, Canada, pp. 97–102.
Marr, D. and Poggio, T. 1979. A computational theory of human stereo vision. Proceedings of the Royal Society, B-204:301–328.
Matthies, L., Kelly, A., and Litwin, T. 1995. Obstacle detection for unmanned ground vehicles: A progress report. In International Symposium of Robotics Research, Munich, Germany.
Moravec, H. 1997. Toward automatic visual obstacle avoidance. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, Cambridge, MA, pp. 584–590.
Szeliski, R. and Zabih, R. 1999. An experimental comparison of stereo algorithms. In Vision Algorithms: Theory and Practice, Springer-Verlag: Corfu, Greece, pp. 1–19.
Volpe, R., Balaram, J., Ohm, T., and Ivlev, R. 1996. The rocky 7 mars rover prototype. In International Conference on Intelligent Robots and Systems, Osaka, Japan, vol. 3, pp. 1558–1564.
Zabih, R. and Woodfill, J. 1994. Non-parametric local transforms for computing visual correspondance. In Proceedings of the European Conference of Computer Vision 94, pp. 151–158.
Zitnick, C. and Kanade, T. 1999. A cooperative algorithm for stereo matching and occlusion detection. Carnegie Mellon University, Robotics Institute, Pittsburgh, PA, Tech. Rep. CMU-RI-TR-99-35.
Zitnick, C.L. and Kanade, T. 2000. Acooperative algorithm for stereo matching and occlusion detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22:675–684.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Hirschmüller, H., Innocent, P.R. & Garibaldi, J. Real-Time Correlation-Based Stereo Vision with Reduced Border Errors. International Journal of Computer Vision 47, 229–246 (2002). https://doi.org/10.1023/A:1014554110407
Issue Date:
DOI: https://doi.org/10.1023/A:1014554110407