Multi-Image Matching Using Multi-Scale Oriented Patches
- 1 June 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10636919) , 510-517
- https://doi.org/10.1109/cvpr.2005.235
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
This publication has 10 references indexed in Scilit:
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Robust wide-baseline stereo from maximally stable extremal regionsImage and Vision Computing, 2004
- Multi-scale phase-based local featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A performance evaluation of local descriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recognising panoramasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Reliable feature matching across widely separated viewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Invariant Features from Interest Point GroupsPublished by British Machine Vision Association and Society for Pattern Recognition ,2002
- Evaluation of Interest Point DetectorsInternational Journal of Computer Vision, 2000
- Wide Baseline Stereo Matching based on Local, Affinely Invariant RegionsPublished by British Machine Vision Association and Society for Pattern Recognition ,2000
- Local grayvalue invariants for image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997