Low-rank SIFT: An Affine Invariant Feature for Place Recognition

08/07/2014
by   Chao Yang, et al.
0

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.

READ FULL TEXT

page 1

page 4

research
12/15/2010

TILT: Transform Invariant Low-rank Textures

In this paper, we show how to efficiently and effectively extract a clas...
research
08/09/2016

A Factorization Approach to Inertial Affine Structure from Motion

We consider the problem of reconstructing a 3-D scene from a moving came...
research
10/16/2017

Nonsmooth Frank-Wolfe using Uniform Affine Approximations

Frank-Wolfe methods (FW) have gained significant interest in the machine...
research
03/05/2018

Affine Differential Invariants for Invariant Feature Point Detection

Image feature points are detected as pixels which locally maximize a det...
research
08/01/2013

Domain-invariant Face Recognition using Learned Low-rank Transformation

We present a low-rank transformation approach to compensate for face var...
research
06/22/2023

Generalized Low-Rank Update: Model Parameter Bounds for Low-Rank Training Data Modifications

In this study, we have developed an incremental machine learning (ML) me...
research
04/08/2011

Gaussian Affine Feature Detector

A new method is proposed to get image features' geometric information. U...

Please sign up or login with your details

Forgot password? Click here to reset