This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Rigid Body Segmentation and Shape Description from Dense Optical Flow Under Weak Perspective
February 1997 (vol. 19 no. 2)
pp. 139-143

Abstract—We present an algorithm for identifying and tracking independently moving rigid objects from optical flow. Some previous attempts at segmentation via optical flow have focused on finding discontinuities in the flow field. While discontinuities do indicate a change in scene depth, they do not in general signal a boundary between two separate objects. The proposed method uses the fact that each independently moving object has a unique epipolar constraint associated with its motion. Thus motion discontinuities based on self-occlusion can be distinguished from those due to separate objects. The use of epipolar geometry allows for the determination of individual motion parameters for each object as well as the recovery of relative depth for each point on the object. The algorithm assumes an affine camera where perspective effects are limited to changes in overall scale. No camera calibration parameters are required. A Kalman filter based approach is used for tracking motion parameters with time.

[1] G. Adiv, "Determining Three-Dimensional Motion and Structure From Optical Flow Generated by Several Moving Objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 7, no. 4, pp. 384-401, 1985.
[2] M. Black and P. Anandan, "Constraints for the Early Detection of Discontinuity From Motion," Proc. Nat'l Conf. AI, pp. 1060-1066,Boston, 1990.
[3] A. Blake and A. Zisserman, Visual Reconstruction.Cambridge, Mass.: MIT Press, 1987.
[4] B. Cernuschi-Frias, D.B. Cooper, Y.P. Hung, and P.N. Belhumeur, "Toward a Model-Based Bayesian Theory for Estimating and Recognizing Parameterized 3D Objects Using Two or More Images Taken From Different Positions," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, pp. 1028-1052, 1989.
[5] O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint.Cambridge, Mass.: MIT Press, 1993.
[6] S. Geman and D. Geman, "Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 6, pp. 721-741, Nov. 1984.
[7] S.L. Horowitz and T. Pavlidis, "Picture Segmentation by a Directed Split-and-Merge Procedure," Proc. Second Int'l Conf. Pattern Recognition, pp. 424-433, 1974.
[8] J.J. Koenderink and A.J. van Doorn, "Affine Structure From Motion," J. Optical Soc. America A, vol. 8, no. 2, pp. 377-385, 1991.
[9] Q.-T. Luong, R. Deriche, O.D. Faugeras, and T. Papadopoulo, "On Determining the Fundamental Matrix: Analysis of Different Methods and Experimental Results," Technical Report RR-1894, INRIA, 1993. A shorter version appeared in the Israeli Conf. Artificial Intelligence and Computer Vision.
[10] Y.G. Leclerc, "Constructing Simple Stable Descriptions for Image Partitioning," Int'l J. Computer Vision, vol. 3, pp. 72-102, 1989.
[11] H.C. Longuet-Higgins, "A Computer Algorithm for Reconstructing a Scene from Two Projections," Nature, vol. 293, pp. 133-135, 1981.
[12] H.-H. Nagel, G. Socher, H. Kollnig, and M. Otte, "Motion Boundary Detection in Image Sequences by Local Stochastic Tests," Proc. Third European Conf. Computer Vision, vol. 2, pp. 305-316,Stockholm, 1994.
[13] S. Soatto, R. Frezza, and P. Perona, "Recursive Motion Estimation on the Essential Manifold," Proc. Third European Conf. Computer Vision, vol. 2, pp. 61-72,Stockholm, 1994.
[14] L.S. Shapiro, A.P. Zisserman, and M. Brady, "Motion From Point Matches Using Affine Epipolar Geometry," Proc. Third European Conf. Computer Vision, vol. 2, pp. 73-84,Stockholm, 1994.
[15] R.Y. Tsai and T.S. Huang, "Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects With Curved Surfaces," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 6, pp. 13-27, 1984.
[16] C. Tomasi and T. Kanade, "Shape and Motion From Image Streams Under Orthography: A Factorization Method," Int'l J. Computer Vision, vol. 9, no. 2, pp. 137-154, 1992.
[17] W. Thompson, K. Mutch, and V. Berzins, "Dynamic Occlusion Analysis in Optical Flow Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 7, no. 4, pp. 374-383, 1985.
[18] 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.
[19] J. Weber, "Scene Partitioning via Statistic-Based Region Growing," IS and T SPIE Symp. Electronic Imaging: Science and Technology,San Jose, Calif., 1995.
[20] J. Weber and J. Malik, "Rigid Body Segmentation and Shape Description From Dense Optical Flow Under Weak Perspective," Proc. Fifth ICCV, pp. 12-20,Boston, 1995.
[21] J. Weber and J. Malik, "Robust Computation of Optical Flow in a Multi-Scale Differential Framework," Int'l J. Computer Vision, vol. 14, no. 1, 1995.

Index Terms:
Optical flow, epipolar constraint, fundamental matrix, shape from motion, motion segmentation, scene partitioning problem.
Citation:
Joseph Weber, Jitendra Malik, "Rigid Body Segmentation and Shape Description from Dense Optical Flow Under Weak Perspective," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 2, pp. 139-143, Feb. 1997, doi:10.1109/34.574794
Usage of this product signifies your acceptance of the Terms of Use.