Motion Field of Curves: Applications

This paper discusses the well known problem of structure from motion for the special case of rigid curves. It is already known that it is theoretically possible to recover the motion and thus the structure of a moving 3D rigid curve observed through one camera given some set of derivatives that are defined on the so-called spatio-temporal surface under the most general camera model of perspective projection. We give here a new simplification of the previous results. In order to show that implementing this theory is indeed feasible, we proceeded towards two main directions. First, we have implemented the special case of planar rigid curves. Second, we show that the derivatives defined on the spatiotemporal surface which are needed in the general case can indeed be computed from the images.

[1]  Ellen C. Hildreth,et al.  Measurement of Visual Motion , 1984 .

[2]  Patrick Bouthemy,et al.  A Maximum Likelihood Framework for Determining Moving Edges , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Rajiv Gupta,et al.  Stereo from uncalibrated cameras , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  O. D. Faugeras,et al.  Camera Self-Calibration: Theory and Experiments , 1992, ECCV.

[5]  Thomas S. Huang,et al.  Estimating three-dimensional motion parameters of a rigid planar patch, II: Singular value decomposition , 1982 .

[6]  Thomas S. Huang,et al.  Theory of Reconstruction from Image Motion , 1992 .

[7]  H C Longuet-Higgins,et al.  The visual ambiguity of a moving plane , 1984, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[8]  Olivier D. Faugeras,et al.  Curve-based stereo: figural continuity and curvature , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Akira Ishii,et al.  Three-View Stereo Analysis , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Olivier Faugeras,et al.  Disambiguating stereo matches with spatio-temporal surfaces , 1992 .

[11]  Olivier Faugeras,et al.  From optical flow of lines to 3D motion and structure , 1989, Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications.

[12]  Shaogang Gong,et al.  Curve motion constraint equation and its applications , 1989, [1989] Proceedings. Workshop on Visual Motion.

[13]  Y. Tsai Roger An Efficient and Accurate Camera Calibration Technique For 3D Machine Vision , 1986, CVPR 1986.

[14]  Johan D'Haeyer Determining motion of image curves from local pattern changes , 1986, Comput. Vis. Graph. Image Process..

[15]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[16]  Hans-Hellmut Nagel,et al.  Displacement vectors derived from second-order intensity variations in image sequences , 1983, Comput. Vis. Graph. Image Process..

[17]  H. C. Longuet-Higgins,et al.  The interpretation of a moving retinal image , 1980, Proceedings of the Royal Society of London. Series B. Biological Sciences.