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 /spl times/ 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.

Keywords

RANSACArtificial intelligencePattern recognition (psychology)Invariant (physics)Computer scienceFeature extractionScale spaceMatching (statistics)Feature (linguistics)Computer visionMathematicsHaar waveletOutlierPanoramaFeature vectorWavelet transformWaveletImage (mathematics)Discrete wavelet transformImage processing

Affiliated Institutions

Related Publications

Publication Info

Year
2005
Type
article
Volume
1
Pages
510-517
Citations
399
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

399
OpenAlex

Cite This

Mathew Brown, Richard Szeliski, Simon Winder (2005). Multi-Image Matching Using Multi-Scale Oriented Patches. , 1 , 510-517. https://doi.org/10.1109/cvpr.2005.235

Identifiers

DOI
10.1109/cvpr.2005.235