Jet-Based Local Image Descriptors

Anders Boesen Lindbo Larsen, Sune Darkner, Anders Lindbjerg Dahl, Kim Steenstrup Pedersen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    We present a general novel image descriptor based on higherorder differential geometry and investigate the effect of common descriptor choices. Our investigation is twofold in that we develop a jet-based descriptor and perform a comparative evaluation with current state-of-the-art descriptors on the recently released DTU Robot dataset. We demonstrate how the use of higher-order image structures enables us to reduce the descriptor dimensionality while still achieving very good performance. The descriptors are tested in a variety of scenarios including large changes in scale, viewing angle and lighting. We show that the proposed jet-based descriptor is superior to state-of-the-art for DoG interest points and show competitive performance for the other tested interest points.
    Original languageEnglish
    Title of host publicationComputer Vision – ECCV 2012 : Workshops and Demonstrations, Part III
    PublisherSpringer
    Publication date2012
    Pages638-650
    ISBN (Print)978-3-642-33711-6
    ISBN (Electronic)978-3-642-33712-3
    DOIs
    Publication statusPublished - 2012
    Event12th European Conference on Computer Vision (ECCV 2012) - Florence, Italy
    Duration: 7 Oct 201213 Oct 2012
    http://eccv2012.unifi.it/

    Conference

    Conference12th European Conference on Computer Vision (ECCV 2012)
    Country/TerritoryItaly
    CityFlorence
    Period07/10/201213/10/2012
    Internet address
    SeriesLecture Notes in Computer Science
    Volume7584
    ISSN0302-9743

    Fingerprint

    Dive into the research topics of 'Jet-Based Local Image Descriptors'. Together they form a unique fingerprint.

    Cite this