Sensitivity analysis of line correspondence

This correspondence shows that line and point correspondences can obtain orientation with the same accuracy, and that when using line correspondence, using more matching lines does not guarantee that the orientation error can be reduced. Orientation detection using line correspondence is very sensitive to errors in image location. We provide a sensitivity analysis of line correspondence, and conditions which lead to orientation sensitivity due to errors in image location. The orientation error using line correspondence due to offset from the image center is obtained analytically. A method for selecting three matching lines, such that orientation is not sensitive to image location errors and using more matching edges to improve the accuracy of orientation is given. Finally three examples are given to illustrate the concepts and support the theoretical results. The first example shows that an orientation with reasonable accuracy may be obtained by using three matching lines. The second example demonstrates that both point and line correspondences can obtain orientation with the same accuracy. The last example supports experimentally the result regarding the orientation error using line correspondence due to offset of the image center and lens distortion. >

[1]  Thomas S. Huang,et al.  Estimation of rigid body motion using straight line correspondences , 1986, Comput. Vis. Graph. Image Process..

[2]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..

[4]  David W. Jacobs.  Optimal matching of planar models in 3D scenes , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  David A. Forsyth,et al.  Invariant Descriptors for 3D Object Recognition and Pose , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Michel Dhome,et al.  Determination of the Attitude of 3D Objects from a Single Perspective View , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Thomas S. Huang,et al.  A linear algorithm for motion estimation using straight line correspondences , 1988, Comput. Vis. Graph. Image Process..

[8]  David J. Kriegman,et al.  On Recognizing and Positioning Curved 3-D Objects from Image Contours , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Jim Z. C. Lai.  Sensitivity of camera calibration , 1993, Other Conferences.

[10]  Lai Jim Zc.  On the sensitivity of camera calibration , 1993 .

[11]  Masayoshi Kakikura,et al.  A 3-D Sensor System for Teaching Robot Paths and Environments , 1987 .

[12]  Homer H. Chen.  Pose Determination from Line-to-Plane Correspondences: Existence Condition and Closed-Form Solutions , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Yehezkel Lamdan,et al.  Affine invariant model-based object recognition , 1990, IEEE Trans. Robotics Autom..

[14]  Granino A. Korn,et al.  Mathematical handbook for scientists and engineers. Definitions, theorems, and formulas for reference and review , 1968 .

[15]  Jim Z. C. Lai.  Recognition for 3‐D objects based on the determination of the position and the orientation from a noisy single perspective view , 1993 .

[16]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Jim Z. C. Lai,et al.  The effects of a camera's intrinsic parameters on the determination of a coordinate frame , 1993 .

[18]  W. Eric L. Grimson,et al.  The Combinatorics Of Object Recognition In Cluttered Environments Using Constrained Search , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[19]  Daniel P. Huttenlocher,et al.  Fast affine point matching: an output-sensitive method , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.