Homography Based Egomotion Estimation with a Common Direction

O. Saurer, P. Vasseur, R. Boutteau, C. Demonceaux, M. Pollefeys, Friedrich Fraundorfer

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gröbner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.
Originalspracheenglisch
Seiten (von - bis)327-341
Seitenumfang15
FachzeitschriftIEEE Transactions on Pattern Analysis and Machine Intelligence
Jahrgang39
Ausgabenummer2
DOIs
PublikationsstatusVeröffentlicht - 1 Feb 2016

Schlagwörter

    Dies zitieren

    Homography Based Egomotion Estimation with a Common Direction. / Saurer, O.; Vasseur, P.; Boutteau, R.; Demonceaux, C.; Pollefeys, M.; Fraundorfer, Friedrich.

    in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Jahrgang 39, Nr. 2, 01.02.2016, S. 327-341.

    Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

    Saurer, O. ; Vasseur, P. ; Boutteau, R. ; Demonceaux, C. ; Pollefeys, M. ; Fraundorfer, Friedrich. / Homography Based Egomotion Estimation with a Common Direction. in: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016 ; Jahrgang 39, Nr. 2. S. 327-341.
    @article{c4d50c8df67c4a8da5764f9c21418d18,
    title = "Homography Based Egomotion Estimation with a Common Direction",
    abstract = "In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gr{\"o}bner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.",
    keywords = "Cameras, Closed-form solutions, Estimation, Gravity, Robustness, Three-dimensional displays, Transmission line matrix methods, Computer vision, egomotion estimation, homography estimation, structure-from-motion",
    author = "O. Saurer and P. Vasseur and R. Boutteau and C. Demonceaux and M. Pollefeys and Friedrich Fraundorfer",
    year = "2016",
    month = "2",
    day = "1",
    doi = "10.1109/TPAMI.2016.2545663",
    language = "English",
    volume = "39",
    pages = "327--341",
    journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
    issn = "0162-8828",
    publisher = "IEEE Computer Society",
    number = "2",

    }

    TY - JOUR

    T1 - Homography Based Egomotion Estimation with a Common Direction

    AU - Saurer, O.

    AU - Vasseur, P.

    AU - Boutteau, R.

    AU - Demonceaux, C.

    AU - Pollefeys, M.

    AU - Fraundorfer, Friedrich

    PY - 2016/2/1

    Y1 - 2016/2/1

    N2 - In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gröbner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.

    AB - In this paper, we explore the different minimal solutions for egomotion estimation of a camera based on homography knowing the gravity vector between calibrated images. These solutions depend on the prior knowledge about the reference plane used by the homography. We then demonstrate that the number of matched points can vary from two to three and that a direct closed-form solution or a Gröbner basis based solution can be derived according to this plane. Many experimental results on synthetic and real sequences in indoor and outdoor environments show the efficiency and the robustness of our approach compared to standard methods.

    KW - Cameras

    KW - Closed-form solutions

    KW - Estimation

    KW - Gravity

    KW - Robustness

    KW - Three-dimensional displays

    KW - Transmission line matrix methods

    KW - Computer vision

    KW - egomotion estimation

    KW - homography estimation

    KW - structure-from-motion

    U2 - 10.1109/TPAMI.2016.2545663

    DO - 10.1109/TPAMI.2016.2545663

    M3 - Article

    VL - 39

    SP - 327

    EP - 341

    JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

    JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

    SN - 0162-8828

    IS - 2

    ER -