3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system

Jun Ichi Meguro, Jun Ichi Takiguchi, Yoshiharu Amano, Takumi Hashizume

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper, a unique dense 3D shape reconstruction method featuring GPS/DR coupled omni-direction multi-baseline motion stereo system is presented. The epipolar plane equation between two Omni Directional Vision images is computed from the GPS/DR's position and posture information. Then, the precise epipolar lines can be obtained robustly by projecting the intersection line between the epipolar plane and the ODVs image plane. The robust matching method featuring hybrid use of the future based matching and the area based matching, as well as the bi-directional matching which chose common mutual matching points to improve robustness is also presented. Voting process using multi-baseline is used to reduce distance error of motion stereo. Hundreds of dense range images are unified based on the precise position/posture information to generate the successive dense 3D outdoor model. The range estimation accuracy within 10 [m] area is 140 [mm], which is equal to a laser radar. It can be said that the proposed omni-directional stereo vision has robustness toward environmental complication and accurate distance estimation performance for rich textured object.

    Original languageEnglish
    Title of host publicationProceedings of the IEEE International Conference on Control Applications
    Pages1807-1812
    Number of pages6
    DOIs
    Publication statusPublished - 2007
    EventJoint 2006 IEEE Conference on Control Applications (CCA), Computer-Aided Control Systems Design Symposium (CACSD) and International Symposium on Intelligent Control (ISIC) - Munich
    Duration: 2006 Oct 42006 Oct 6

    Other

    OtherJoint 2006 IEEE Conference on Control Applications (CCA), Computer-Aided Control Systems Design Symposium (CACSD) and International Symposium on Intelligent Control (ISIC)
    CityMunich
    Period06/10/406/10/6

    Fingerprint

    Navigation systems
    Mobile robots
    Global positioning system
    Stereo vision
    Optical radar

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Meguro, J. I., Takiguchi, J. I., Amano, Y., & Hashizume, T. (2007). 3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system. In Proceedings of the IEEE International Conference on Control Applications (pp. 1807-1812). [4067430] https://doi.org/10.1109/CCA.2006.286165

    3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system. / Meguro, Jun Ichi; Takiguchi, Jun Ichi; Amano, Yoshiharu; Hashizume, Takumi.

    Proceedings of the IEEE International Conference on Control Applications. 2007. p. 1807-1812 4067430.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Meguro, JI, Takiguchi, JI, Amano, Y & Hashizume, T 2007, 3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system. in Proceedings of the IEEE International Conference on Control Applications., 4067430, pp. 1807-1812, Joint 2006 IEEE Conference on Control Applications (CCA), Computer-Aided Control Systems Design Symposium (CACSD) and International Symposium on Intelligent Control (ISIC), Munich, 06/10/4. https://doi.org/10.1109/CCA.2006.286165
    Meguro JI, Takiguchi JI, Amano Y, Hashizume T. 3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system. In Proceedings of the IEEE International Conference on Control Applications. 2007. p. 1807-1812. 4067430 https://doi.org/10.1109/CCA.2006.286165
    Meguro, Jun Ichi ; Takiguchi, Jun Ichi ; Amano, Yoshiharu ; Hashizume, Takumi. / 3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system. Proceedings of the IEEE International Conference on Control Applications. 2007. pp. 1807-1812
    @inproceedings{c7f97b397506453a8fe65d51dd9db959,
    title = "3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system",
    abstract = "In this paper, a unique dense 3D shape reconstruction method featuring GPS/DR coupled omni-direction multi-baseline motion stereo system is presented. The epipolar plane equation between two Omni Directional Vision images is computed from the GPS/DR's position and posture information. Then, the precise epipolar lines can be obtained robustly by projecting the intersection line between the epipolar plane and the ODVs image plane. The robust matching method featuring hybrid use of the future based matching and the area based matching, as well as the bi-directional matching which chose common mutual matching points to improve robustness is also presented. Voting process using multi-baseline is used to reduce distance error of motion stereo. Hundreds of dense range images are unified based on the precise position/posture information to generate the successive dense 3D outdoor model. The range estimation accuracy within 10 [m] area is 140 [mm], which is equal to a laser radar. It can be said that the proposed omni-directional stereo vision has robustness toward environmental complication and accurate distance estimation performance for rich textured object.",
    author = "Meguro, {Jun Ichi} and Takiguchi, {Jun Ichi} and Yoshiharu Amano and Takumi Hashizume",
    year = "2007",
    doi = "10.1109/CCA.2006.286165",
    language = "English",
    isbn = "0780397959",
    pages = "1807--1812",
    booktitle = "Proceedings of the IEEE International Conference on Control Applications",

    }

    TY - GEN

    T1 - 3D reconstruction by a mobile robot using multi-baseline omni-directional motion stereo based on GPS/DR compound navigation system

    AU - Meguro, Jun Ichi

    AU - Takiguchi, Jun Ichi

    AU - Amano, Yoshiharu

    AU - Hashizume, Takumi

    PY - 2007

    Y1 - 2007

    N2 - In this paper, a unique dense 3D shape reconstruction method featuring GPS/DR coupled omni-direction multi-baseline motion stereo system is presented. The epipolar plane equation between two Omni Directional Vision images is computed from the GPS/DR's position and posture information. Then, the precise epipolar lines can be obtained robustly by projecting the intersection line between the epipolar plane and the ODVs image plane. The robust matching method featuring hybrid use of the future based matching and the area based matching, as well as the bi-directional matching which chose common mutual matching points to improve robustness is also presented. Voting process using multi-baseline is used to reduce distance error of motion stereo. Hundreds of dense range images are unified based on the precise position/posture information to generate the successive dense 3D outdoor model. The range estimation accuracy within 10 [m] area is 140 [mm], which is equal to a laser radar. It can be said that the proposed omni-directional stereo vision has robustness toward environmental complication and accurate distance estimation performance for rich textured object.

    AB - In this paper, a unique dense 3D shape reconstruction method featuring GPS/DR coupled omni-direction multi-baseline motion stereo system is presented. The epipolar plane equation between two Omni Directional Vision images is computed from the GPS/DR's position and posture information. Then, the precise epipolar lines can be obtained robustly by projecting the intersection line between the epipolar plane and the ODVs image plane. The robust matching method featuring hybrid use of the future based matching and the area based matching, as well as the bi-directional matching which chose common mutual matching points to improve robustness is also presented. Voting process using multi-baseline is used to reduce distance error of motion stereo. Hundreds of dense range images are unified based on the precise position/posture information to generate the successive dense 3D outdoor model. The range estimation accuracy within 10 [m] area is 140 [mm], which is equal to a laser radar. It can be said that the proposed omni-directional stereo vision has robustness toward environmental complication and accurate distance estimation performance for rich textured object.

    UR - http://www.scopus.com/inward/record.url?scp=43049167064&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=43049167064&partnerID=8YFLogxK

    U2 - 10.1109/CCA.2006.286165

    DO - 10.1109/CCA.2006.286165

    M3 - Conference contribution

    SN - 0780397959

    SN - 9780780397958

    SP - 1807

    EP - 1812

    BT - Proceedings of the IEEE International Conference on Control Applications

    ER -