Recovering affine features from orientation- and scale-invariant ones
This addresses a computer vision problem for researchers and practitioners needing efficient geometric estimation, though it appears incremental as it builds on existing feature detectors and epipolar geometry.
The paper tackles the problem of recovering affine correspondences from orientation- and scale-invariant features like SIFT, proposing a closed-form solution that runs in under 1 millisecond. The method enables single-correspondence homography estimation with accuracy comparable to state-of-the-art methods but makes robust estimation an order of magnitude faster.
An approach is proposed for recovering affine correspondences (ACs) from orientation- and scale-invariant, e.g. SIFT, features. The method calculates the affine parameters consistent with a pre-estimated epipolar geometry from the point coordinates and the scales and rotations which the feature detector obtains. The closed-form solution is given as the roots of a quadratic polynomial equation, thus having two possible real candidates and fast procedure, i.e. <1 millisecond. It is shown, as a possible application, that using the proposed algorithm allows us to estimate a homography for every single correspondence independently. It is validated both in our synthetic environment and on publicly available real world datasets, that the proposed technique leads to accurate ACs. Also, the estimated homographies have similar accuracy to what the state-of-the-art methods obtain, but due to requiring only a single correspondence, the robust estimation, e.g. by locally optimized RANSAC, is an order of magnitude faster.