FAI: Fast Affine Invariant Features Detection and Descriptor Extraction

Invariant feature detectors and descriptors are a common tool now for many computer vision tasks. Recently, fast and efficient variants such as BRISK were developed to offset the computational burden of traditional invariant descriptors such as SIFT. A common thread in invariant descriptors is affine invariance which improves matching performance in large baseline situations. In this work we describe an extension of BRISK to include affine invariance and propose an efficient method to estimate the rectifying affine transformations from an Intensity Moment matrix. Furthermore, the affine invariant descriptor is sampled directly from the underlying image without costly image warping. The proposed method shows exceptionally good performance compared to SURF and BRISK on image sequences with locally planar features at comparable speeds as BRISK.