Calibration of laser scanner and camera fusion system for intelligent vehicles using Nelder-Mead optimization

T.J. Osgood, Yingping Huang

    Research output: Contribution to journalArticle

    6 Citations (Scopus)

    Abstract

    A novel method is presented here for the calibration of a sensor fusion system for intelligent vehicles. In this example, the sensors are a camera and a laser scanner which observe the same scene from different viewpoints. The method employs the Nelder-Mead direct search algorithm to minimize the sum of squared errors between the image coordinates and the re-projected laser data by iteratively adjusting and improving the calibration parameters. The method is applied to a real set of data collected from a test vehicle. Using only 11 well-spaced target points observable by each sensor, 12 intrinsic and extrinsic parameters indicating the position relationship between the sensors can be estimated to give an accurate projection. Experiments show that the method can project the laser points onto the image plane with an average error of 1.01 pixels (1.51 pixels worst case).
    Original languageEnglish
    Article number35101
    JournalMeasurement Science and Technology
    Volume24
    Issue number3
    DOIs
    Publication statusPublished - 2013

    Fingerprint

    Intelligent Vehicle
    Intelligent vehicle highway systems
    Laser Scanner
    scanners
    Fusion
    vehicles
    Calibration
    Fusion reactions
    fusion
    Camera
    Cameras
    cameras
    optimization
    Optimization
    Lasers
    sensors
    Sensors
    pixels
    Sensor
    lasers

    Bibliographical note

    The full text of this item is not available from the repository.

    Keywords

    • calibration
    • Nelder-Mead optimization
    • sensor fusion

    Cite this

    Calibration of laser scanner and camera fusion system for intelligent vehicles using Nelder-Mead optimization. / Osgood, T.J.; Huang, Yingping.

    In: Measurement Science and Technology, Vol. 24, No. 3, 35101, 2013.

    Research output: Contribution to journalArticle

    @article{5be292803098462b95bc1d15795caf53,
    title = "Calibration of laser scanner and camera fusion system for intelligent vehicles using Nelder-Mead optimization",
    abstract = "A novel method is presented here for the calibration of a sensor fusion system for intelligent vehicles. In this example, the sensors are a camera and a laser scanner which observe the same scene from different viewpoints. The method employs the Nelder-Mead direct search algorithm to minimize the sum of squared errors between the image coordinates and the re-projected laser data by iteratively adjusting and improving the calibration parameters. The method is applied to a real set of data collected from a test vehicle. Using only 11 well-spaced target points observable by each sensor, 12 intrinsic and extrinsic parameters indicating the position relationship between the sensors can be estimated to give an accurate projection. Experiments show that the method can project the laser points onto the image plane with an average error of 1.01 pixels (1.51 pixels worst case).",
    keywords = "calibration, Nelder-Mead optimization, sensor fusion",
    author = "T.J. Osgood and Yingping Huang",
    note = "The full text of this item is not available from the repository.",
    year = "2013",
    doi = "10.1088/0957-0233/24/3/035101",
    language = "English",
    volume = "24",
    journal = "Measurement Science and Technology",
    issn = "0957-0233",
    publisher = "IOP Publishing",
    number = "3",

    }

    TY - JOUR

    T1 - Calibration of laser scanner and camera fusion system for intelligent vehicles using Nelder-Mead optimization

    AU - Osgood, T.J.

    AU - Huang, Yingping

    N1 - The full text of this item is not available from the repository.

    PY - 2013

    Y1 - 2013

    N2 - A novel method is presented here for the calibration of a sensor fusion system for intelligent vehicles. In this example, the sensors are a camera and a laser scanner which observe the same scene from different viewpoints. The method employs the Nelder-Mead direct search algorithm to minimize the sum of squared errors between the image coordinates and the re-projected laser data by iteratively adjusting and improving the calibration parameters. The method is applied to a real set of data collected from a test vehicle. Using only 11 well-spaced target points observable by each sensor, 12 intrinsic and extrinsic parameters indicating the position relationship between the sensors can be estimated to give an accurate projection. Experiments show that the method can project the laser points onto the image plane with an average error of 1.01 pixels (1.51 pixels worst case).

    AB - A novel method is presented here for the calibration of a sensor fusion system for intelligent vehicles. In this example, the sensors are a camera and a laser scanner which observe the same scene from different viewpoints. The method employs the Nelder-Mead direct search algorithm to minimize the sum of squared errors between the image coordinates and the re-projected laser data by iteratively adjusting and improving the calibration parameters. The method is applied to a real set of data collected from a test vehicle. Using only 11 well-spaced target points observable by each sensor, 12 intrinsic and extrinsic parameters indicating the position relationship between the sensors can be estimated to give an accurate projection. Experiments show that the method can project the laser points onto the image plane with an average error of 1.01 pixels (1.51 pixels worst case).

    KW - calibration

    KW - Nelder-Mead optimization

    KW - sensor fusion

    U2 - 10.1088/0957-0233/24/3/035101

    DO - 10.1088/0957-0233/24/3/035101

    M3 - Article

    VL - 24

    JO - Measurement Science and Technology

    JF - Measurement Science and Technology

    SN - 0957-0233

    IS - 3

    M1 - 35101

    ER -