Reliable feature matching across widely separated views

TLDR

Conventional stereo matching assumes known camera geometry, whereas this work does not rely on prior knowledge of relative camera positions or orientations. The study introduces a robust feature‑matching method that determines relative camera pose by matching features across arbitrary viewpoints. The method detects features in multiple images, characterises them with affine‑invariant texture descriptors robust to rotation, stretch, and skew, and optimises matching for structure‑from‑motion by discarding unreliable correspondences.

Abstract

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.