Low-rank SIFT: An Affine Invariant Feature for Place Recognition
This addresses the challenge of robust place recognition in computer vision, particularly for man-made environments, though it appears incremental as an extension of SIFT.
The paper tackles the problem of achieving full affine invariance in visual features for place recognition by introducing Low-rank SIFT, which normalizes local patches to low-rank forms to handle camera orientation changes without simulating affine parameters. The method demonstrates effectiveness in place recognition applications, with efficient computation enabled by convex optimization breakthroughs.
In this paper, we present a novel affine-invariant feature based on SIFT, leveraging the regular appearance of man-made objects. The feature achieves full affine invariance without needing to simulate over affine parameter space. Low-rank SIFT, as we name the feature, is based on our observation that local tilt, which are caused by changes of camera axis orientation, could be normalized by converting local patches to standard low-rank forms. Rotation, translation and scaling invariance could be achieved in ways similar to SIFT. As an extension of SIFT, our method seeks to add prior to solve the ill-posed affine parameter estimation problem and normalizes them directly, and is applicable to objects with regular structures. Furthermore, owing to recent breakthrough in convex optimization, such parameter could be computed efficiently. We will demonstrate its effectiveness in place recognition as our major application. As extra contributions, we also describe our pipeline of constructing geotagged building database from the ground up, as well as an efficient scheme for automatic feature selection.