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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-image matching using multi-scale oriented patches


    Contributors:
    Brown, M. (author) / Szeliski, R. (author) / Winder, S. (author)


    Publication date :

    2005-01-01


    Size :

    953320 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Binary Histogrammed Intensity Patches for Efficient and Robust Matching

    Taylor, S. / Drummond, T. | British Library Online Contents | 2011


    Image registration using multi-scale texture moments

    Sato, J. / Cipolla, R. | British Library Online Contents | 1995


    Image Matching by Multiscale Oriented Corner Correlation

    Zhao, F. / Huang, Q. / Gao, W. | British Library Conference Proceedings | 2006



    Discriminative training for object recognition using image patches

    Deselaers, T. / Keysers, D. / Ney, H. | IEEE | 2005