Multi-Image Matching using Multi-Scale Oriented Patches

Multi-scale Oriented Patches (MOPS) extracted at 5 pyramid levels

Multi-Scale Oriented Patches (MOPS) are a minimalist design for local invariant features. They consist of a simple bias-gain normalised patch, sampled at a coarse scale relative to the interest point detection. The low frequency sampling helps to give insensitivity to noise in the interest point position.

MOPS features are located at Harris corners in discrete scale-space and oriented using a blurred local gradient. This defines a rotationally invariant frame in which we sample a feature descriptor, which consists of an 8x8 patch of bias/gain normalised intensity values. The density of features in the image is controlled using a novel adaptive non-maximal suppression algorithm, which gives a better spatial distribution of features than previous approaches. Matching is achieved using a fast nearest neighbour algorithm that indexes features based on their low frequency Haar wavelet coefficients. We use a novel outlier rejection procedure that verifies a pairwise feature match based on a background distribution of incorrect feature matches.

Feature matches are refined using RANSAC and used in an automatic 2D panorama stitcher that has been extensively tested on hundreds of sample inputs.