| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field
May 1989 (vol. 11 no. 5)
pp. 477-489
One of the major areas in research on dynamic scene analysis is recovering 3-D motion and structure from optical flow information. Two problems which may arise due to the presence of noise in the flow field are examined. First, motion parameters of the sensor or a rigidly moving object may be extremely difficult to estimate because there may exist a large set of significantly incorrect solutions which induce flow fields similar to the correct one. The second problem is in the decomposition of the environment into independently moving objects. Two such objects may induce optical flows which are compatible with the same motion parameters, and hence, there is no way to refute the hypothesis that these flows are generated by one rigid object. These ambiguities are inherent in the sense that they are algorithm-independent. Using a mathematical analysis, situations where these problems are likely to arise are characterized. A few examples demonstrate the conclusions. Constraints and parameters which can be recovered even in ambiguous situations are presented.
[1] 477G. Adiv, "Determining 3-D motion and structure from optical flow generated by several moving objects,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, pp. 384-401, July 1985.[2] G. Adiv, "Interpreting optical flow," Ph.D. dissertation, Dep. Comput. Inform. Sci., Univ. Massachusetts, Amherst, 1985.[3] J.-Q. Fang and T. S. Huang, "Solving three dimensional small-rotation motion equations," inProc. IEEE Conf. Comput. Vision Pattern Recognition, Washington, DC, 1983, pp. 253-258.[4] J.-Q. Fang and T. S. Huang, "Estimating 3-D movement of a rigid object: Experimental results," inProc. Int. Joint Conf. Art. Intell., Karlsruhe, Germany, 1983, pp. 1035-1037.[5] A. Hanson and E. Riseman, Ed.,Computer Vision Systems. New York: Academic, 1978, pp. 303-334.[6] D. T. Lawton, "Processing dynamic image sequences from a moving sensor," Ph.D. dissertation (TR 84-05), Dep. Comput. Inform. Sci., Univ. Massachusetts, Amherst, 1984.[7] H. C. Longuet-Higgins, "A computer algorithm for reconstructing a scene from two projections,"Nature, vol. 293, pp. 133-135, Sept. 1981.[8] K. Prazdny, "Egomotion and relative depth map from optical flow,"Biol. Cybern., vol. 36, pp. 87-102, 1980.[9] A. Ralston,A First Course in Numerical Analysis. New York: McGraw-Hill, 1965.[10] J. H. Rieger and D. T. Lawton, "Determining the instantaneous axis of translation from optical flow generated by arbitrary sensor motion," inProc. ACM Interdisciplinary Workshop Motion(Toronto), 1983, pp. 33-41.[11] J. W. Roach and J. K. Aggarwal, "Determining the movement of objects from a sequence of images, "IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, pp. 554-562, Nov. 1980.[12] R. Y. Tsai and T. S. Huang, "Estimating three dimensional motion parameters of a rigid planar patch, II: Singular value decomposition,"IEEE Trans. Acoust. Speech, Signal Processing, vol. ASSP-30, no. 4, pp. 525-534, Aug. 1982.[13] S. Ullman,The Interpretation of Visual Motion. Cambridge, MA: M.I.T. Press, 1979.[14] S. Ullman, "Analysis of visual motion by biological and computer systems,"Computer, vol. 14, pp. 57-69, Aug. 1981.[15] A. M. Waxman and S. Ullman, "Surface structure and 3-D motion from image flow: A kinematic approach," Cen. Automation Res., Univ. Maryland, College Park, CAR-TR-24, 1983.
Index Terms:
computer vision; 3D motion recovery; structure recovery; dynamic scene analysis; optical flow information; computer vision; parameter estimation
Citation:
G. Adiv, "Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 5, pp. 477-489, May 1989, doi:10.1109/34.24780
