Evaluation of corner extraction schemes using invariance methods

We describe a new method to evaluate corner extraction schemes using invariance methods. Since the locations of centers in an image depend both on the intrinsic parameters of the camera and the relative position and orientation of the object with respect to the camera, the exact positions of corners in an image are generally not known. To circumvent the need for this knowledge, we use sets of points (instead of individual points) extracted from images of polyhedral objects and projective invariants to calculate a manifold of constraints on the coordinates of the corners. We then estimate the variance of the detected corners from the distance of the coordinate vector to this manifold. This is independent of the camera parameters and the relative position and orientation between the camera and the object. Five different kinds of corner extraction schemes are investigated. The purpose of the paper is to show that invariance methods can effectively be used to make this comparison rather than to make a thorough comparison of different corner extraction schemes.

[1]  F. N. David,et al.  LINEAR STATISTICAL INFERENCE AND ITS APPLICATION , 1967 .

[2]  C. R. Rao,et al.  Linear Statistical Inference and its Applications , 1968 .

[3]  Paul Beaudet,et al.  Rotationally invariant image operators , 1978 .

[4]  V. Berzins.  Accuracy of laplacian edge detectors , 1984 .

[5]  H. Crapo,et al.  Spatial Realizations of Linear Scenes , 1986 .

[6]  Karl Rohr.  Über die Modellierung und Identifikation charakteristischer Grauwertverläufe in Realweltbildern , 1990, DAGM-Symposium.

[7]  G. Sparr.  Projective invariants for affine shapes of point configurations , 1991 .

[8]  Rachid Deriche,et al.  On corner and vertex detection , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Gunnar SparrDept.  Projective Invariants for Aane Shapes of Point Conngurations , 1991 .

[10]  Bernd Sturmfels,et al.  Computational Algebraic Geometry of Projective Configurations , 1991, J. Symb. Comput..

[11]  Gunnar Sparr.  Depth Computations from Polyhedral Images , 1992, ECCV.

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

[13]  Aaron Heller,et al.  An experimental evaluation of projective invariants , 1992 .

[14]  Karl Rohr,et al.  Modelling and identification of characteristic intensity variations , 1992, Image Vis. Comput..

[15]  David A. Forsyth,et al.  Extracting projective structure from single perspective views of 3D point sets , 1993, 1993 (4th) International Conference on Computer Vision.

[16]  Karl Rohr,et al.  An efficient approach to the identification of characteristic intensity variations , 1993, Image Vis. Comput..

[17]  Anders Heyden,et al.  Consistency and correction of line-drawings, obtained by projections of piecewise planar objects , 1994, eccv 1994.

[18]  Gunnar Sparr,et al.  A Common Framework for Kinetic Depth, Reconstruction and Motion for Deformable Objects , 1994, ECCV.

[19]  S. P. Mudur,et al.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[20]  A. Heyden,et al.  A canonical framework for sequences of images , 1995, Proceedings IEEE Workshop on Representation of Visual Scenes (In Conjunction with ICCV'95).

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

[22]  Han Wang,et al.  Gray Level Corner Detection , 1998, MVA.