This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Real-Time Epipolar Geometry Estimation of Binocular Stereo Heads
March 2002 (vol. 24 no. 3)
pp. 425-432

Stereo is an important cue for visually guided robots. While moving around in the world, such a robot can use dynamic fixation to overcome limitations in image resolution and field of view. In this paper, a binocular stereo system capable of dynamic fixation is presented. The external calibration is performed continuously taking temporal consistency into consideration, greatly simplifying the process. The essential matrix, which is estimated in real-time, is used to describe the epipolar geometry. It will be shown, how outliers can be identified and excluded from the calculations. An iterative approach based on a differential model of the optical flow, commonly used in structure from motion, is also presented and tested towards the essential matrix. The iterative method will be shown to be superior in terms of both computational speed and robustness, when the vergence angles are less than about 15^{\circ}. For larger angles, the differential model is insufficient and the essential matrix is preferably used instead.

[1] D.H. Ballard, “Animate Vision,” Artificial Intelligence, vol. 48, pp. 57-86, 1991.
[2] M. Björkman and J-O. Eklundh, “A Real-Time System for Epipolar Geometry and Ego-Motion Estimation,” Proc. IEEE Computer Vision and Pattern Recognition Conf., pp. 506-513, Jun. 2000.
[3] M.J. Brooks, L. de Agapito, D.Q. Huynh, and L. Baumela, “Direct Methods for Self-Calibration of a Moving Stereo Head,” Proc. Fourth European Conf. Computer Vision, pp. 415-426, 1996.
[4] I. Cox, S. Hingorani, and S. Rao, “A Maximum Likelihood Stereo Algorithm,” Computer Vision and Image Understanding, vol. 63, no. 3, pp. 542–567, 1996.
[5] K. Daniilidis, “Fixation Simplifies 3D Motion Estimation,” Computer Vision and Image Understanding vol. 68, no. 2, pp. 158-169, Nov. 1997.
[6] C. Fermüller and Y. Aloimonos, “The Role of Fixation in Visual Motion Analysis,” Int'l J. Computer Vision, vol. 11, no. 2, pp. 165-186, 1993.
[7] M.A. Fischler and R.C. Bolles, “Random Sampling Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography,” Proc. Defense Advanced Research Projects Agency, (DARPA), Image Understanding Workshop, pp. 71-88, 1980.
[8] C. Harris, M. Stephens, and A Combined, “Corner and Edge Detector,” Proc. Fourth Alvey Conf., pp. 189-192, 1988.
[9] R. Hartley, “Estimation of Relative Camera Positions for Uncalibrated Cameras,” Proc. European Conf. Computer Vision, G. Sandini, ed., vol. 588, pp. 579-587, May 1992.
[10] J. Heel, “Dynamic Motion Vision,” Proc. Defense Advanced Research Projects Agency, (DARPA), Image Understanding Workshop, pp. 702-713, 1989.
[11] K. Konolige, “Small Vision Systems: Hardware and Implementation,” Proc. Eighth Int'l Symp. Robotics Research, 1997.
[12] T. Kanade, M. Okutomi, and N. Nakahara, “A Multiple-Baseline Stereo Method,” Proc. Defense Advanced Research Projects Agency, (DARPA), Image Understanding Workshop, pp. 409-426, 1992.
[13] H.C. Longuet-Higgins and K. Prazdny, “The Interpretation of a Moving Retinal Image,” Proc. Royal Soc. London, vol. B-208, pp. 385-397, 1980.
[14] H. Longuet-Higgins, “A Computer Algorithm for Reconstructing a Scene from Two Projections,” Nature, vol. 293, pp. 133-135, 1981.
[15] Y. Ma, J. Kosecka, and S. Sastry, “Optimization Criteria and Geometric Algorithms for Motion and Structure Estimation,” Memorandom No. UCB/ERL M99/33, Univ. of California, Berkeley, June 1999.
[16] Y. Ohta and T. Kanade, “Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, no. 2, pp. 139-154, 1985.
[17] P. Torr and D. Murray, “The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix,” Int'l J. Computer Vision, vol. 3, no. 24, pp. 271-300, 1997.
[18] V. Tucakov, M. Sahota, D. Murray, A. Mackworth, J. Little, S. Kingdon, C. Jennings, and R. Barman, “Spinoza: A Stereoscopic Visually Guided Mobile Robot,” Proc. 13th Ann. Hawaii Int'l Conf. System Sciences, pp. 188-197, Jan. 1997.
[19] W.Y. Yau and H Wang, “Fast Relative Depth Computation for an Active Stereo Vision System,” Real-Time Imaging, vol. 5, pp. 189-202, 1999.
[20] Z. Zhang, R. Deriche, O. Faugeras, and Q.T. Luong, “A Rubust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry,” Artificial Intelligence J., vol. 78, pp. 87-119, 1995.

Index Terms:
epipolar geometry, active vision, real-time stereo, dynamic vergence
Citation:
M. Björkman, J.O. Eklundh, "Real-Time Epipolar Geometry Estimation of Binocular Stereo Heads," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 425-432, March 2002, doi:10.1109/34.990147
Usage of this product signifies your acceptance of the Terms of Use.