Multi-Image Matching Using Multi-Scale Oriented Patches

Matthew Brown, R Szeliski, S Winder

Research output: Contribution to conferencePaperpeer-review

289 Citations (SciVal)

Abstract

This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our 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 8 × 8 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 also introduce 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.
Original languageEnglish
Pages510-517
Number of pages8
DOIs
Publication statusPublished - Jun 2005
EventCVPR 2005: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005 - San Diego
Duration: 20 Jun 200525 Jun 2005

Conference

ConferenceCVPR 2005: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005
CitySan Diego
Period20/06/0525/06/05

Fingerprint

Dive into the research topics of 'Multi-Image Matching Using Multi-Scale Oriented Patches'. Together they form a unique fingerprint.

Cite this