Fast Distance Computation with a Stereo Head-Eye System
In this paper, a fast method is presented for computing the 3D Euclidean distance with a stereo head-eye system using a disparity map, a vergence angle, and a relative disparity. Our approach is to use the dense disparity for an initial vergence angle and a fixation point for its distance from a center point of two cameras. Neither camera calibration nor prior knowledge is required. The principle of the human visual system is applied to a stereo head-eye system with reasonable assumptions. Experimental results show that the 3D Euclidean distance can be easily estimated from the relative disparity and the vergence angle. The comparison of the estimated distance of objects with their real distance is given to evaluate the performance of the proposed method.
KeywordsCamera Calibration Stereo Vision Object Point Stereo Match Real Distance
Unable to display preview. Download preview PDF.
- 3.E. Trucco, A. Verri.: Introductory Techniques for 3D Computer Vision. Prentice Hall. Upper Saddle River. NJ (1998)Google Scholar
- 5.G. S. M. Hansen.: Real-time Vergence Control using Local Phase Differences. Machine Graphics and Vision. 5 (1996)Google Scholar
- 6.G.-Q. Wei, W. Brauer, G. Hirzinger.: Intensity-and Gradient-based Stereo Matching using Hierarchical Gaussian Basis Functions. IEEE Trans. on Pattern Analysis and Machine Intelligence. 11 (1999) 1143–1160Google Scholar
- 7.O. Faugeras.: Three-Dimensional Computer Vision-A Geometric Viewpoint. MIT Press. Cambridge. MA. (1993)Google Scholar
- 8.A. Crouzil, L. Massip-Pailhes, S. Castan.: A New Correlation Criterion Based on Gradient Fields Similarity. Proc. Int. Conf. on Pattern Recognition. Vienna, Austria. (1996) 632–636Google Scholar