Time-varying shape tensors for scenes with multiply moving points

We derive single view indexing functions for dynamic scenes - where dynamic is defined as a scene consisting of multiply moving points each moving independently with constant velocity. The indexing functions we derive are view independent and form a generalization of the "shape tensors" associated with rigid scenes by introducing a time-varying parameter We derive those indexing functions under full 3D projective, 3D affine, and various reduced configurations. The indexing functions were implemented and tested for matching against objects for which their non-rigid motion is an intrinsic part of their character - human gait recognition and hand gesture identification are the two chosen application examples.

[1]  D D Hoffman,et al.  Structure from two orthographic views of rigid motion. , 1989, Journal of the Optical Society of America. A, Optics and image science.

[2]  David W. Jacobs,et al.  Space and Time Bounds on Indexing 3D Models from 2D Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Long Quan,et al.  Invariants of 6 Points from 3 Uncalibrated Images , 1994, ECCV.

[4]  Michael Werman,et al.  Trilinearity of three perspective views and its associated tensor , 1995, Proceedings of IEEE International Conference on Computer Vision.

[5]  Bill Triggs,et al.  Matching constraints and the joint image , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Anders Heyden,et al.  Reconstruction from image sequences by means of relative depths , 1995, Proceedings of IEEE International Conference on Computer Vision.

[7]  Stefan Carlsson,et al.  Duality of reconstruction and positioning from projective views , 1995, Proceedings IEEE Workshop on Representation of Visual Scenes (In Conjunction with ICCV'95).

[8]  Olivier D. Faugeras,et al.  On the geometry and algebra of the point and line correspondences between N images , 1995, Proceedings of IEEE International Conference on Computer Vision.

[9]  Michael Werman,et al.  Duality of Multi-Point and Multi-Frame Geometry: Fundamental Shape Matrices and Tensors , 1996, ECCV.

[10]  P. Anandan,et al.  Parallax Geometry of Pairs of Points for 3D Scene Analysis , 1996, ECCV.

[11]  James W. Davis,et al.  The representation and recognition of human movement using temporal templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Daphna Weinshall,et al.  From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications , 1998, ECCV.

[13]  Charles R. Dyer,et al.  Interpolating view and scene motion by dynamic view morphing , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[14]  Amnon Shashua,et al.  On the synthesis of dynamic scenes from reference views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[15]  Lior Wolf,et al.  On the Structure and Properties of the Quadrifocal Tensor , 2000, ECCV.

[16]  Amnon Shashua,et al.  Trajectory Triangulation: 3D Reconstruction of Moving Points from a Monocular Image Sequence , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Lior Wolf,et al.  Homography Tensors: On Algebraic Entities that Represent Three Views of Static or Moving Planar Points , 2000, ECCV.

[18]  Mei Han,et al.  Reconstruction of a Scene with Multiple Linearly Moving Objects , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[19]  A. Shashua,et al.  On projection matrices P/sup k//spl rarr/P/sup 2/, k=3,...,6, and their applications in computer vision , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[20]  Stefan Carlsson.  Recognizing Walking People , 2003, Int. J. Robotics Res..