Gradient-based local affine invariant feature extraction for mobile robot localization in indoor environments

Jihyo Lee, Hanseok Ko

    Research output: Contribution to journalArticlepeer-review

    17 Citations (Scopus)

    Abstract

    In this paper, we propose a gradient-based local affine invariant feature extraction algorithm (G-LAIFE), using affine moment invariants for robot localization in real indoor environments. The proposed algorithm is an effective feature extraction algorithm that is invariant to image translation and to 3D rotation, and it is within a partial range of the image scale. Representative performance analysis confirms that the proposed G-LAIFE algorithm significantly enhances the recognition rate and is more efficient than the scale invariant feature transform (SIFT), especially in terms of 3D rotation change and computational time.

    Original languageEnglish
    Pages (from-to)1934-1940
    Number of pages7
    JournalPattern Recognition Letters
    Volume29
    Issue number14
    DOIs
    Publication statusPublished - 2008 Oct 15

    Keywords

    • 3D rotation
    • Affine invariant
    • Local feature extraction
    • Translation

    ASJC Scopus subject areas

    • Software
    • Signal Processing
    • Computer Vision and Pattern Recognition
    • Artificial Intelligence

    Fingerprint

    Dive into the research topics of 'Gradient-based local affine invariant feature extraction for mobile robot localization in indoor environments'. Together they form a unique fingerprint.

    Cite this