MURAL - Maynooth University Research Archive Library



    FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images


    Konrad, Anna and Eising, Ciarán and Sistu, Ganesh and McDonald, John and Villing, Rudi and Yogamani, Senthil (2022) FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images. In: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SciTePress: Science and Technology Publications, Lda, pp. 340-347. ISBN 9789897585555

    [img]
    Preview
    Download (15MB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Keypoint detection and description is a commonly used building block in computer vision systems particularly for robotics and autonomous driving. However, the majority of techniques to date have focused on standard cameras with little consideration given to fisheye cameras which are commonly used in urban driving and automated parking. In this paper, we propose a novel training and evaluation pipeline for fisheye images. We make use of SuperPoint as our baseline which is a self-supervised keypoint detector and descriptor that has achieved state-of-the-art results on homography estimation. We introduce a fisheye adaptation pipeline to enable training on undistorted fisheye images. We evaluate the performance on the HPatches benchmark, and, by introducing a fisheye based evaluation method for detection repeatability and descriptor matching correctness, on the Oxford RobotCar dataset.

    Item Type: Book Section
    Additional Information: This publication has emanated from research conducted with the financial support of Science Foundation Ireland (SFI) under Grant number 18/CRT/6049 and 16/RI/3399. This is the postprint version of the published paper, which is available at: Konrad, A.; Eising, C.; Sistu, G.; McDonald, J.; Villing, R. and Yogamani, S. (2022). FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-555-5, pages 340-347. DOI: 10.5220/0010795400003124
    Keywords: Keypoints; Interest Points; Feature Detection; Feature Description; Fisheye Images; Deep Learning;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Faculty of Science and Engineering > Electronic Engineering
    Faculty of Science and Engineering > Research Institutes > Hamilton Institute
    Item ID: 15529
    Identification Number: https://doi.org/10.5220/0010795400003124
    Depositing User: Rudi Villing
    Date Deposited: 18 Feb 2022 14:30
    Publisher: SciTePress: Science and Technology Publications, Lda
    Refereed: Yes
    Funders: Science Foundation Ireland (SFI)
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year