This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Optimal Visual Motion Estimation: A Note
September 1992 (vol. 14 no. 9)
pp. 959-964

The problem of estimating 3D motion in an optimal manner using correspondences of features in two views is analyzed. The importance of having an optimal estimator is twofold: first, for the estimation itself and, second, for the bound it offers on how much sensitivity one can expect from a two-frame, point-based motion algorithm. The optimal estimator turns out to be nonlinear, and for that reason, techniques that provide very good initial guesses for the iterative computation of the optimal estimator are developed.

[1] G. Adiv, "Inherent ambiguities in recovering 3-D motion and structure from a noisy flow field," inProc. IEEE CVPR Conf., 1985, pp. 70-77.
[2] J. Aisbett, "An iterated estimation of the motion parameters of a rigid body from noisy displacement vectors,"IEEE Trans. Patt. Anal. Machine Intell., vol. 12, pp. 1092-1098, 1991.
[3] O. Bottema and B. Roth,Theoretical Kinematics. New York: North Holland, 1979.
[4] A. Bruss and B. K. P. Horn, "Passive navigation,"CVGIPvol. 21, pp. 3-20, 1983.
[5] O. D. Faugeras and S. J. Maybank, "Motion from point matches: Multiplicity of solutions," inProc. Workshop Visual Motion, Irvine, CA, 1989, pp. 248-255.
[6] B. K. P. Horn, "Motion fields are hardly ever ambiguous,"Int. J. Comp. Vision, vol. 1, pp. 259-274, 1987.
[7] B. K. P. Horn, "Relative orientation," A.I. Memo 994, AI Lab, Mass. Inst. Technol., Cambridge, Sept. 1987.
[8] B. K. P. Horn and E. Weldon, "Direct motion recovery," inProc. IEEE ICCV, 1987.
[9] C. Jerian and R. Jain, "Polynomial algorithms for structure from motion," inProc. 2nd ICCV(Tarpon Springs, FL), 1988.
[10] H. C. Longuet-Higgins, "A computer algorithm for reconstructing a scene from two projections,"Nature, vol. 293, pp. 133-135, 1981.
[11] H. C. Longuet-Higgins and K. Prazdny, "The interpretation of a moving retinal image," inProc. Royal Soc. London B, vol. 208, pp. 385-397, 1984.
[12] J. Philip, "Estimation of three-dimensional motion of rigid objects from noisy observations,"IEEE Trans. Patt. Anal. Machine Intell., vol. 13, pp. 61-66, 1991.
[13] K. Prazdny, "Determining the instantaneous direction of motion from optical flow generated by a curvilinearly moving observer,"Comput. Vision Graphics Image Processing, vol. 17, pp. 94-97, 1981.
[14] M. E. Spetsakis, "The geometry and statistics of visual motion," Ph.D. thesis, Comput. Vision Lab., Cent. Automat. Res., Univ. Maryland, College Park, 1989.
[15] M. E. Spetsakis and J. Aloimonos, "Optimal computing of structure from motion using point correspondences in two frames," Tech. Rep. CARTR-389, Comput. Vision Lab., Cent. Automat. Res., Univ. Maryland, College Park, 1988.
[16] M. E. Spetsakis and J. Aloimonos, "Optimal computing of structure from motion using point correspondences in two frames," Tech. Rep. CARTR-389, Comput. Vision Lab., Cent. Automat. Res., Univ. Maryland, College Park, 1988.
[17] M. E. Spetsakis and J. Aloimonos, "A multiframe approach to visual motion perception,"Int. J. Comput. Vision, vol. 6, pp. 245-255, 1991.
[18] R. Y. Tsai and T. S. Huang, "Uniqueness and estimation of three dimensional motion parameters of rigid objects with curved surfaces,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, pp. 13-27, 1984.
[19] R. Y. Tsai and T. S. Huang, "Uniqueness and estimation of three dimensional motion parameters of rigid objects," inProc. DARPA Image Understanding Workshop, 1984.
[20] S. Ullman, "The interpretation of visual motion," Ph.D. thesis, Mass. Inst. of Technol., Dept. of Elect. Eng. Comput. Sci., 1979.
[21] A. Waxman and K. Wohn, "Image flow theory," inAdvances in Computer Vision(C. M. Brown, Ed.). New York: Erlbaum, 1987.
[22] J. Weng, T. S. Huang, and N. Ahuja, "A two-step approach to optimal motion and structure estimation," inProc. IEEE Workshop Comput. Vision, 1987, pp. 355-357.

Index Terms:
3D motion estimation; picture processing; two frame point based motion; parameter estimation; optimisation; optimal estimator; iterative methods; optimisation; parameter estimation; picture processing
Citation:
M.E. Spetsakis, Y. Aloimonos, "Optimal Visual Motion Estimation: A Note," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 9, pp. 959-964, Sept. 1992, doi:10.1109/34.161355
Usage of this product signifies your acceptance of the Terms of Use.