Self-calibration of radially symmetric distortion by model selection

Jun Fujiki, Hideitsu Hino, Yumi Usami, Shotaro Akaho, Noboru Murata

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

    4 Citations (Scopus)

    Abstract

    For self-calibration of general radially symmetric distortion (RSD) of omnidirectional cameras such as fish-eye lenses, calibration parameters are usually estimated so that curved lines, which are supposed to be straight in the real-world, are mapped to straight lines in the calibrated image, which is assumed to be taken by an ideal pin-hole camera. In this paper, a method of calibrating RSD is introduced base on the notion of principal component analysis (PCA). In the proposed method, the distortion function, which maps a distorted image to an ideal pin-hole camera image, is assumed to be a linear combination of a certain class of basis functions, and an algorithm for solving its coefficients by using line patterns is given. Then a method of selecting good basis functions is proposed, which aims to realize appropriate calibration in practice. Experimental results for synthetic data and real images are presented to demonstrate the performance of our calibration method.

    Original languageEnglish
    Title of host publicationProceedings - International Conference on Pattern Recognition
    Pages1812-1815
    Number of pages4
    DOIs
    Publication statusPublished - 2010
    Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul
    Duration: 2010 Aug 232010 Aug 26

    Other

    Other2010 20th International Conference on Pattern Recognition, ICPR 2010
    CityIstanbul
    Period10/8/2310/8/26

    Fingerprint

    Pinhole cameras
    Calibration
    Principal component analysis
    Lenses
    Cameras

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Fujiki, J., Hino, H., Usami, Y., Akaho, S., & Murata, N. (2010). Self-calibration of radially symmetric distortion by model selection. In Proceedings - International Conference on Pattern Recognition (pp. 1812-1815). [5597210] https://doi.org/10.1109/ICPR.2010.447

    Self-calibration of radially symmetric distortion by model selection. / Fujiki, Jun; Hino, Hideitsu; Usami, Yumi; Akaho, Shotaro; Murata, Noboru.

    Proceedings - International Conference on Pattern Recognition. 2010. p. 1812-1815 5597210.

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

    Fujiki, J, Hino, H, Usami, Y, Akaho, S & Murata, N 2010, Self-calibration of radially symmetric distortion by model selection. in Proceedings - International Conference on Pattern Recognition., 5597210, pp. 1812-1815, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, 10/8/23. https://doi.org/10.1109/ICPR.2010.447
    Fujiki J, Hino H, Usami Y, Akaho S, Murata N. Self-calibration of radially symmetric distortion by model selection. In Proceedings - International Conference on Pattern Recognition. 2010. p. 1812-1815. 5597210 https://doi.org/10.1109/ICPR.2010.447
    Fujiki, Jun ; Hino, Hideitsu ; Usami, Yumi ; Akaho, Shotaro ; Murata, Noboru. / Self-calibration of radially symmetric distortion by model selection. Proceedings - International Conference on Pattern Recognition. 2010. pp. 1812-1815
    @inproceedings{4175bb37d9da484eb6a2a7a66328c094,
    title = "Self-calibration of radially symmetric distortion by model selection",
    abstract = "For self-calibration of general radially symmetric distortion (RSD) of omnidirectional cameras such as fish-eye lenses, calibration parameters are usually estimated so that curved lines, which are supposed to be straight in the real-world, are mapped to straight lines in the calibrated image, which is assumed to be taken by an ideal pin-hole camera. In this paper, a method of calibrating RSD is introduced base on the notion of principal component analysis (PCA). In the proposed method, the distortion function, which maps a distorted image to an ideal pin-hole camera image, is assumed to be a linear combination of a certain class of basis functions, and an algorithm for solving its coefficients by using line patterns is given. Then a method of selecting good basis functions is proposed, which aims to realize appropriate calibration in practice. Experimental results for synthetic data and real images are presented to demonstrate the performance of our calibration method.",
    author = "Jun Fujiki and Hideitsu Hino and Yumi Usami and Shotaro Akaho and Noboru Murata",
    year = "2010",
    doi = "10.1109/ICPR.2010.447",
    language = "English",
    isbn = "9780769541099",
    pages = "1812--1815",
    booktitle = "Proceedings - International Conference on Pattern Recognition",

    }

    TY - GEN

    T1 - Self-calibration of radially symmetric distortion by model selection

    AU - Fujiki, Jun

    AU - Hino, Hideitsu

    AU - Usami, Yumi

    AU - Akaho, Shotaro

    AU - Murata, Noboru

    PY - 2010

    Y1 - 2010

    N2 - For self-calibration of general radially symmetric distortion (RSD) of omnidirectional cameras such as fish-eye lenses, calibration parameters are usually estimated so that curved lines, which are supposed to be straight in the real-world, are mapped to straight lines in the calibrated image, which is assumed to be taken by an ideal pin-hole camera. In this paper, a method of calibrating RSD is introduced base on the notion of principal component analysis (PCA). In the proposed method, the distortion function, which maps a distorted image to an ideal pin-hole camera image, is assumed to be a linear combination of a certain class of basis functions, and an algorithm for solving its coefficients by using line patterns is given. Then a method of selecting good basis functions is proposed, which aims to realize appropriate calibration in practice. Experimental results for synthetic data and real images are presented to demonstrate the performance of our calibration method.

    AB - For self-calibration of general radially symmetric distortion (RSD) of omnidirectional cameras such as fish-eye lenses, calibration parameters are usually estimated so that curved lines, which are supposed to be straight in the real-world, are mapped to straight lines in the calibrated image, which is assumed to be taken by an ideal pin-hole camera. In this paper, a method of calibrating RSD is introduced base on the notion of principal component analysis (PCA). In the proposed method, the distortion function, which maps a distorted image to an ideal pin-hole camera image, is assumed to be a linear combination of a certain class of basis functions, and an algorithm for solving its coefficients by using line patterns is given. Then a method of selecting good basis functions is proposed, which aims to realize appropriate calibration in practice. Experimental results for synthetic data and real images are presented to demonstrate the performance of our calibration method.

    UR - http://www.scopus.com/inward/record.url?scp=78149486213&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=78149486213&partnerID=8YFLogxK

    U2 - 10.1109/ICPR.2010.447

    DO - 10.1109/ICPR.2010.447

    M3 - Conference contribution

    AN - SCOPUS:78149486213

    SN - 9780769541099

    SP - 1812

    EP - 1815

    BT - Proceedings - International Conference on Pattern Recognition

    ER -