CSDL Home C CVPR 2000 Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000
Hilton Head Island, SC, USA
June 15, 2000 to June 15, 2000
Adam Baumberg , Canon Research Centre Europe Ltd
In this paper, 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 characterized using affine texture invariants. The problem of window effects is explicitly addressed by our method - our feature characterization is invariant to linear transformations of the image data including rotation, stretch and skew. The feature matching process is optimized for a structure-from-motion application where we wish to ignore unreliable matches at the expense of reducing the number of feature matches.
Adam Baumberg, "Reliable Feature Matching across Widely Separated Views", CVPR, 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 2000, pp. 1774, doi:10.1109/CVPR.2000.855899