
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
Kalle Åström, Fredrik Kahl, "Motion Estimation in Image Sequences Using the Deformation of Apparent Contours," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 2, pp. 114127, February, 1999.  
BibTex  x  
@article{ 10.1109/34.748821, author = {Kalle Åström and Fredrik Kahl}, title = {Motion Estimation in Image Sequences Using the Deformation of Apparent Contours}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {21}, number = {2}, issn = {01628828}, year = {1999}, pages = {114127}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.748821}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Pattern Analysis and Machine Intelligence TI  Motion Estimation in Image Sequences Using the Deformation of Apparent Contours IS  2 SN  01628828 SP114 EP127 EPD  114127 A1  Kalle Åström, A1  Fredrik Kahl, PY  1999 KW  Motion KW  surface geometry KW  silhouette KW  epipolar constraint. VL  21 JA  IEEE Transactions on Pattern Analysis and Machine Intelligence ER   
Abstract—The problem of determining the camera motion from apparent contours or silhouettes of a priori unknown curved threedimensional surfaces is considered. In a sequence of images, it is shown how to use the generalized epipolar constraint on apparent contours. One such constraint is obtained for each epipolar tangency point in each image pair. An accurate algorithm for computing the motion is presented based on a maximum likelihood estimate. It is shown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown that in theory the motion can be calculated from the deformation of a single contour. The algorithm has been tested on several real image sequences, for both Euclidean and projective reconstruction. The resulting motion estimate is compared to motion estimates calculated independently using standard featurebased methods. The motion estimate is also used to classify the silhouettes as curves or apparent contours. This is a strong indication that the motion estimate is of good quality. The statistical evaluation shows that the technique gives accurate and stable results.
[1] K. Åström, R. Cipolla, and P.J. Giblin, “Generalised Epipolar Constraints,” Proc. Fouth European Conf. Computer Vision, B.F. Buxton and R. Cipolla, eds., vol. II, pp. 97108, Apr. 1996.
[2] A. Heyden and K. Åström, “Euclidean Reconstruction from Constant Intrinsic Parameters,” Proc. Int'l Conf. Pattern Recognition, vol. 1, pp. 339343, Aug. 1996.
[3] K. Åström and A. Heyden, "Stochastic Analysis of Image Acquisition and ScaleSpace Smoothing," J. Sporring, M. Nielsen, L. Florack, and P. Johansen, eds., Gaussian ScaleSpace Theory. Kluwer Academic Publishers, 1997.
[4] K.B. Atkinson, Close Range Photogrammetry and Machine Vision. Whittles Publishing, 1996.
[5] R. Berthilsson and K. Åström, "Reconstruction of 3DCurves From 2DImages Using Affine Shape Methods for Curves," Proc. Conf. Computer Vision and Pattern Recognition, 1997.
[6] R. Berthilsson, K. Åström, and A. Heyden, "Projective Reconstruction of 3DCurves From Its 2DImages Using Error Models and Bundle Adjustments," Proc. 10th Scandinavian Conf. Image Analysis, pp. 581588,Lappeenranta, Finland, 1997.
[7] A. Blake and A.L. Yuille, eds., Active Vision.Cambridge, Mass.: MIT Press, 1992.
[8] E. Boyer and M.O. Berger, “3D Surface Reconstruction Using Occluding Contours,” Int'l J. Computer Vision, vol. 22, no. 3, pp. 219233, Mar./Apr. 1997.
[9] S. Carlsson, "Sufficient Image Structure for 3D Motion and Shape Estimation," J.O. Eklundh, ed., Proc. Third European Conf. Computer Vision, vol. 1, pp. 8391,Stockholm, 1994.
[10] R. Cipolla, Active Visual Inference of Surface Shape, PhD thesis, Univ. of Oxford, 1991. Also published by SpringerVerlag as LNCS 1016 (1995).
[11] R. Cipolla, K. Åström, and P.J. Giblin, “Motion from the Frontier of Curved Surfaces,” Proc. Fifth Int'l Conf. Computer Vision, pp. 269275, June 1995.
[12] R. Cipolla and A. Blake, “Surface Shape from the Deformation of Apparent Contours,” Int'l J. Computer Vision, vol. 9, no. 2, pp. 83112, Nov. 1992.
[13] H. Cramér, Mathematical Methods of Statistics.Princeton, N.J.: Princeton Univ. Press, 1946.
[14] R. Curwen and A. Blake, "Dynamic Contours: RealTime Active Splines," A. Blake and A. Yuille, eds., Active Vision.Cambridge, Mass.: MIT Press, 1992, pp. 3958.
[15] O. Faugeras, "What can be seen in three dimensions with an uncalibrated stereo rig?" Second European Conf. Computer Vision, pp. 563578, 1992.
[16] O. Faugeras, T. Luong, and S. Maybank, “Camera SelfCalibration: Theory and Experiments,” Proc Second European Conf. Computer Vision, pp. 321334, May 1992.
[17] J.D. Foley,A. van Dam,S.K. Feiner,, and J.F. Hughes,Computer Graphics: Principles and Practice,Menlo Park, Calif.: AddisonWesley, 1990.
[18] P.J. Giblin, F.E. Pollick, and J.E. Rycroft, "Recovery of an Unknown Axis or Rotation From the Profiles of a Rotating Surface," J. Optical Soc. Amer., vol. 11A, pp. 1,9761,984, 1994.
[19] P.J. Giblin and R. Weiss, "Reconstruction of Surfaces From Profiles," Proc. First Int'l Conf. Computer Vision, pp. 136144,London, 1987.
[20] T. Joshi, N. Ahuja, J. Ponce, "Structure and Motion Estimation From Dynamic Silhouettes Under Perspective Projection," Int'l Conf. Computer Vision, pp. 290295,Boston, June 1995.
[21] F. Kahl and K. Åström, "Motion Estimation in Image Sequences Using the Deformation of Apparent Contours," Proc. Sixth Int'l Conf. Computer Vision, pp. 934944,Mumbai, India, 1998.
[22] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active Contour Models," Int'l J. Computer Vision, vol. 1, no. 4, pp. 321331, 1987.
[23] J. Porrill and S.B. Pollard, “Curve Matching and Stereo Calibration,” Image and Vision Computing, vol. 9, no. 1, pp. 4550, Feb. 1991.
[24] J.H. Rieger, "Three Dimensional Motion From Fixed Points of a Deforming Profile Curve," Optics Letters, vol. 11,k pp. 123125, 1986.
[25] J.G. Semple and G.T. Kneebone, Algebraic Projective Geometry.Oxford, England: Clarendon Press, 1952.
[26] G. Sparr, "An AlgebraicAnalytic Method for Affine Shapes of Point Configurations," Proc. Seventh Scandinavian Conf. Image Analysis, pp. 274281, 1991.
[27] G. Sparr, “Simultaneous Reconstruction of Scene Structure and Camera Locations from Uncalibrated Image Sequences,” Proc. Int'l Conf. Pattern Recognition '96, pp. 328333, 1996.
[28] R. Szeliski and R. Weiss, "Robust Shape Recovery From Occluding Contours Using a Linear Smoother," T. Terzopoulis and C.M. Brown, eds., RealTime Vision.Cambridge, England: Cambridge Univ. Press, 1994.
[29] F. Ulupinar and R. Nevatia, "Perception of 3D surfaces From 2D Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 318, Jan. 1993.
[30] R. Vaillant and O.D. Faugeras, "Using Extremal Boundaries for 3D Object Modelling," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 157173, Feb. 1992.
[31] B. Vijayakumar, D. Kriegman, and J. Ponce, "InvariantBased Recognition of Complex 3D Curved Objects From Image Contours," Proc. Fifth Int'l Conf. Computer Vision, pp. 508514,Boston, 1995.
[32] B. Vijayakumar, D. Kriegman, and J. Ponce, "Structure and Motion of Curved 3D Objects From Monocular Silhouettes," Proc. Conf. Computer Vision and Pattern Recognition, pp. 327334, 1996.
[33] Z. Zhang, “Determining the Epipolar Geometry and Its Uncertainty—A Review,” Int'l J. Computer Vision, vol. 27, no. 2, pp. 161195, 1998.