This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
The Performance of Camera Translation Direction Estimators From Optical Flow: Analysis, Comparison, and Theoretical Limits
September 1996 (vol. 18 no. 9)
pp. 927-932

Abstract—A noniterative method using optical flow to recover the translation direction of a moving camera has been previously proposed in [4]. We present a detailed explanation of the bias in this algorithm and compare methods for eliminating this bias, as well as presenting a comprehensive error analysis. This analysis includes a necessary modification to the Cramér-Rao lower bound (CRLB). We propose a simple iterative modification to the algorithm which produces unbiased translation direction estimates that approach the CRLB. Numerical results are used to compare the various techniques on synthetic and real image sequences.

[1] J.L. Barron, D.J. Fleet, and S.S. Beauchemin, “Performance of Optical Flow Techniques,” Int'l J. Computer Vision, vol. 12, no. 1, pp. 43–77, 1994.
[2] A.M. Earnshaw and S.D. Blostein, "The Performance of Camera Translation Direction Estimators," Technical Report 95-10, Dept. of Electrical and Computer Eng., Queen's Univ., 1995.
[3] J.D. Gorman and A.O. Hero, "Lower Bounds for Parametric Estimation with Constraints," IEEE Trans. Information Theory, vol. 36, no. 6, pp. 1,285-1,301, 1990.
[4] D.J. Heeger and A.D. Jepson, “Subspace Methods for Recovering Rigid Motion I: Algorithm and Implementation,” Int'l J. Computer Vision, vol. 7, pp. 95–117, 1992.
[5] B.K. Horn and B.G. Schunck, "Determining Optical Flow," Artificial Intelligence, vol. 17, pp. 185-203, 1981.
[6] A. Jepson and D. Heeger,“A fast subspace algorithm for recovering rigid motion,” Proc. IEEE Motion Workshop,Princeton, pp. 124-131, 1991.
[7] A.D. Jepson and D.J. Heeger, “Linear Subspace Methods for Recovering Translational Direction,” Spatial Vision in Humans and Robots, pp. 39–62, Cambridge Univ. Press, 1993.
[8] K. Kanatani, "Renormalization for Unbiased Estimation," Proc. Fourth Int'l Conf. Computer Vision, pp. 599-606, 1993.
[9] K. Kanatani, “Unbiased Estimation and Statistical Analysis of 3D Rigid Motion from Two Views,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 37-50, Jan. 1993.
[10] W.J. MacLean private communication, 1994.
[11] M. Otte and H.-H. Nagel, "Optical Flow Estimation: Advances and Comparisons," Proc. Third European Conf. Computer Vision, Springer-Verlag, New York, 1994, pp. 51-60.
[12] S. Uras, F. Girosi, A. Verri, and V. Torre, "A Computational Approach to Motion Perception," Biological Cybernetics, vol. 60, no. 1, pp. 79-87, 1988.
[13] J. Weng, N. Ahuja, and T. Huang, "Optimal Motion and Structure Estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 864-884, 1993.
[14] J. Weng,T. Huang,, and N. Ahuja,“Motion and structure from two perspective views:Algorithms, error analysis and error estimation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 5, pp. 451-476, May 1989.
[15] J.H. Wilkinson,The Algebraic Eigenvalue Problem, Oxford Univ. Press, Oxford, UK, 1965.

Index Terms:
Translation direction estimation, linear constraints, optical flow, error analysis, performance comparison.
Citation:
A. Mark Earnshaw, Steven D. Blostein, "The Performance of Camera Translation Direction Estimators From Optical Flow: Analysis, Comparison, and Theoretical Limits," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 9, pp. 927-932, Sept. 1996, doi:10.1109/34.537346
Usage of this product signifies your acceptance of the Terms of Use.