Finding Point Correspondences in Motion Sequences Preserving Affine Structure

In this paper the problem of computing the point correspondences in a sequence of time-varying images of a 3D object undergoing nonrigid (affine) motion is addressed. It is assumed that the images are obtained through affine projections. The correspondences are established only from the analysis of the unknown 3D affine structure of the object, without making use of any attributes of the feature points. It is shown that it is possible to establish the point correspondences uniquely (up to symmetry) in the sense that they yield a unique affine structure of the object and that the computation is possible in polynomial time. Two different algorithms for computing the point correspondences are presented. Results on various real image sequences, including a sequence containing independently moving objects, demonstrate the applicability of the structure based approach to motion correspondence.

[1]  J J Koenderink,et al.  Affine structure from motion. , 1991, Journal of the Optical Society of America. A, Optics and image science.

[2]  Maria Francesca Costabile,et al.  A method for detecting correspondences in a sequence of modifying shapes , 1985, Pattern Recognit. Lett..

[3]  Yehezkel Lamdan,et al.  On recognition of 3-D objects from 2-D images , 2011, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[4]  Thomas S. Huang,et al.  Motion and Structure from Orthographic Projections , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Mandayam A. L. Thathachar,et al.  Relaxation Labeling with Learning Automata , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  M. Brady,et al.  Rejecting outliers and estimating errors in an orthogonal-regression framework , 1995, Philosophical Transactions of the Royal Society of London. Series A: Physical and Engineering Sciences.

[7]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[8]  Thomas S. Huang,et al.  Finding point correspondences and determining motion of a rigid object from two weak perspective views , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Azriel Rosenfeld,et al.  Some experiments in relaxation image matching using corner features , 1983, Pattern Recognit..

[10]  W. Eric L. Grimson,et al.  Computational Experiments with a Feature Based Stereo Algorithm , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[12]  William B. Thompson,et al.  Disparity Analysis of Images , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  P. Beardsley,et al.  Affine and Projective Structure from Motion , 1992 .

[14]  A. Shashua.  Correspondence and Affine Shape from Two Orthographic Views: Motion and Recognition , 1991 .

[15]  Robin N. Strickland,et al.  Computing correspondences in a sequence of non-rigid shapes , 1992, Pattern Recognit..

[16]  Xinhua Zhuang,et al.  A simple procedure to solve motion and structure from three orthographic views , 1988, IEEE J. Robotics Autom..

[17]  Hsi-Jian Lee,et al.  Three-frame corner matching and moving object extraction in a sequence of images , 1990, Comput. Vis. Graph. Image Process..

[18]  Narendra Ahuja,et al.  Motion estimation under orthographic projection , 1991, IEEE Trans. Robotics Autom..

[19]  Ian D. Reid,et al.  Tracking foveated corner clusters using affine structure , 1993, 1993 (4th) International Conference on Computer Vision.

[20]  Mandayam A. L. Thathachar,et al.  Analysis of Stochastic Automata Algorithm for Relaxation Labeling , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[22]  Subhashis Banerjee,et al.  Finding Point Correspondences in Motion Sequences Preserving Affine Structure , 1993, BMVC.

[23]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Olivier D. Faugeras,et al.  Motion from point matches: multiplicity of solutions , 1988, Geometry and Robotics.