Dense shape and motion from region correspondences by factorization

In this paper, we propose an algorithm for estimating dense shape and motion of dynamic piecewise planar scenes from region correspondences using factorization. Region correspondences are used since they are easier to establish and more reliable than either line or point correspondences. The image measurements required are the centroid and area for each region. Singular value decomposition is employed to find the basis of range space of the motion, shape, and surface normal matrices. By imposing model constraints, motion, shape, and surface normal can be recovered only from region correspondences.

[1]  Mark D. Tabb,et al.  Multiscale structure detection and its application to image segmentation and motion analysis , 1996 .

[2]  Long Quan.  A ne Structure from Line Correspondences with Uncalibrated A ne Cameras , 1999 .

[3]  David B. Cooper,et al.  Structure from motion: a region based approach using affine transformations and moment invariants , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[4]  Yiannis Aloimonos,et al.  Perspective approximations , 1990, Image Vis. Comput..

[5]  Narendra Ahuja,et al.  A direct data approximation based motion estimation algorithm , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[6]  Takeo Kanade,et al.  A sequential factorization method for recovering shape and motion from image streams , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  N. Ahuja,et al.  Segmentation, matching and estimation of structure and motion of textured piecewise planar surfaces , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[8]  S. Negahdaripour,et al.  Motion recovery from image sequences using First-order optical flow information , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[9]  Narendra Ahuja,et al.  Segmentation and Factorization-Based Motion and Structure Estimation for Long Image Sequences , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Takeo Kanade,et al.  Affine structure from line correspondences with uncalibrated affine cameras , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Haim Schweitzer,et al.  Structure from multiple 2D affine correspondences without camera calibration , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Narendra Ahuja,et al.  Multiscale image segmentation by integrated edge and region detection , 1997, IEEE Trans. Image Process..

[13]  Takeo Kanade,et al.  A Paraperspective Factorization Method for Shape and Motion Recovery , 1994, ECCV.