This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Camera Geometries for Image Matching in 3-D Machine Vision
September 1989 (vol. 11 no. 9)
pp. 897-915

The location of a scene element can be determined from the disparity of two of its depicted entities (each in a different image). Prior to establishing disparity, however, the correspondence problem must be solved. It is shown that for the axial-motion stereo camera model the probability of determining unambiguous correspondence assignments is significantly greater than that for other stereo camera models. However, the mere geometry of the stereo camera system does not provide sufficient information for uniquely identifying correct correspondences. Therefore, additional constraints derived from justifiable assumptions about the scene domain and from the scene radiance model are utilized to reduce the number of potential matches. The measure for establishing the correct correspondence is shown to be a function of the geometrical constraints, scene constraints, and scene radiance model.

[1] N. Alvertos, D. Brzakovic, and R. C. Gonzalez, "Correspondence in pairs of images acquired by camera displacement in depth," inSPIE Vol. 726, Intelligent Robots and Computer Vision: Fifth in a Series, Oct. 1986, pp. 131-136.
[2] D. H. Ballard and C. M. Brown,Computer Vision. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[3] S. T. Barnard and M. A. Fischler, "Computational stereo,"Comput. Surveys, vol. 14, no. 4, pp. 553-572, 1982.
[4] D. J. Burr, "A fast filtering operator for robot stereo vision," inIEEE Proc. 7th Int. Conf. Pattern Recognition, vol. 2, Montreal, P.Q., Canada, 1984, pp. 669-672.
[5] K.S. Fu, R.C. Gonzalez, and C.S.G. Lee,Introduction to Robotics: Control, Sensing, Vision, and Intelligence, McGraw-Hill, New York, 1987.
[6] R.C. Gonzalez and P. Wintz,Digital Image Processing, Addison-Wesley, Reading, Mass., 1987.
[7] W. E. L. Grimson, "Aspects of a computational theory of human stereo vision," inProc. Image Understanding Workshop, College Park, MD, Apr. 1980, pp. 128-149.
[8] W. E. L. Grimson,From Images to Surfaces. Cambridge, MA: MIT Press, 1981.
[9] E. R. Haddow, J. F. Boyce, and S. A. Lloyd, "A new binocular stereo algorithm," inImage Analysis, Proc. 4th Scandinavian Conf., Trondheim, Norway, June 1985, pp. 175-182.
[10] B. K. P. Horn,Robot Vision. New York: McGraw-Hill, 1986.
[11] J. J. Hwang, "Computer stereo vision for three-dimensional object location," Dep. Elec. Eng., Univ. Tennessee, Tech. Rep., Aug. 1980.
[12] K. Ikeuchi, "Reconstructing a depth map from intensity maps," inIEEE Proc. 7th Int. Conf. Pattern Recognition, vol. 2, Montreal, P.Q., Canada, 1984, pp. 736-738.
[13] H. Itoh, A. Miyauchi, and S. Ozawa, "Distance measuring method using only simple vision constructed for moving robots," inIEEE Proc. 7th Int. Conf. Pattern Recognition, vol. 1, Montreal, P.Q., Canada, 1984, pp. 192-195.
[14] R. Jain, S. L. Bartlett, and N. O'Brien, "Motion stereo using ego-motion complex logarithmic mapping,"IEEE Trans. Pattern Anal. Machine Intell., vol. 9, no. 3, pp. 356-369, May 1987.
[15] Y. Jing-yu and L. Ke, "An effective algorithm for matching stereo image pairs," inImage Analysis, Proc. 4th Scandinavian Conf., Trondheim, Norway, June 1985, pp. 183-189.
[16] M. Kass, "Computing visual correspondence," inFrom Pixels to Predicates, A. P. Pentland, Ed. Norwood, NJ: Ablex, 1986, pp. 78-92.
[17] D. Marr and T. Poggio, "A theory of human stereo vision," Tech. Rep. AI Memo 451, Artificial Intell. Lab., Mass. Inst. Technol., Cambridge, Nov. 1977.
[18] D. Marr and T. Poggio, "A computational theory of human vision,"Proc. Roy. Soc. London, vol. B204, pp. 301-328, 1979.
[19] N. O'Brien and R. Jain, "Axial motion stereo," inProc. IEEE Workshop Computer Vision, Apr. 1984, pp. 88-92.
[20] V. Torre, A. Verri, and A. Fiumicelli, "Stereo accuracy for robotics," inRobotics Research, vol. 3, O. D. Faugeras and Giralt, Eds., 1986, pp. 5-9.
[21] R. Y. Tsai, "Multiframe image point matching and 3-D surface reconstruction,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, no. 2, pp. 159-173, Mar. 1983.
[22] T. D. Williams, "Depth from camera motion in a real world scene,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, no. 6, pp. 511-516, Nov. 1980.
[23] R. J. Woodham, "A computational vision approach to remote sensing," inIEEE Proc. Computer Vision and Pattern Recognition, pp. 2-12, San Francisco, CA, June 19-23, 1985, pp. 2-12.
[24] Y. Yakimovsky and R. Cunningham, "A system for extracting 3-D measurements from a stereo pair of TV cameras,"Comput. Graphics Image Processing, vol. 7, pp. 195-209, 1978.

Index Terms:
3D machine vision; camera geometry; computer vision; pattern recognition; image matching; axial-motion stereo camera model; scene domain; scene radiance model; geometrical constraints; scene constraints; computer vision; computerised pattern recognition
Citation:
N. Alvertos, D. Brzakovic, R.C. Gonzalez, "Camera Geometries for Image Matching in 3-D Machine Vision," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 9, pp. 897-915, Sept. 1989, doi:10.1109/34.35494
Usage of this product signifies your acceptance of the Terms of Use.