Reliable feature matching across widely separated views

We present a robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints. Unlike conventional stereo matching approaches we assume no prior knowledge about the relative camera positions and orientations. In fact in our application this is the information we wish to determine from the image feature matches. Features are detected in two or more images and characterised using affine texture invariants. The problem of window effects is explicitly addressed by our method-our feature characterisation is invariant to linear transformations of the image data including rotation, stretch and skew. The feature matching process is optimised for a structure-from-motion application where we wish to ignore unreliable matches at the expense of reducing the number of feature matches.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  A. Gruen.  ADAPTIVE LEAST SQUARES CORRELATION: A POWERFUL IMAGE MATCHING TECHNIQUE , 1985 .

[3]  Yoshiaki Shirai,et al.  Three-Dimensional Computer Vision , 1987, Symbolic Computation.

[4]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[5]  R. J. Schalko.  Digital Image Processing and Computer Vision , 1989 .

[6]  Jan Flusser,et al.  Pattern recognition by affine moment invariants , 1993, Pattern Recognit..

[7]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Roberto Cipolla,et al.  Extracting the Affine Transformation from Texture Moments , 1994, ECCV.

[9]  Rachid Deriche,et al.  Robust Recovery of the Epipolar Geometry for an Uncalibrated Stereo Rig , 1994, ECCV.

[10]  L. Falkenhagen.  Depth Estimation from Stereoscopic Image Pairs Assuming Piecewise Continuos Surfaces , 1995 .

[11]  Alexander Kadyrov.  Triple Features for Linear Distorted Images , 1995, CAIP.

[12]  Paul A. Beardsley,et al.  3D Model Acquisition from Extended Image Sequences , 1996, ECCV.

[13]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[15]  Tony Lindeberg,et al.  Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure , 1997, Image Vis. Comput..

[16]  G. Xu,et al.  A unified approach to image matching and segmentation in stereo, motion and object recognition via recovery of epipolar geometry , 1997 .

[17]  Philippe Montesinos,et al.  A Fast Matching Method for Color Uncalibrated Images using Differential Invariants , 1998, BMVC.

[18]  Andrew Zisserman,et al.  Wide baseline stereo matching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[19]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.