Auto-calibration of depth camera networks for people tracking

Otto Korkalo (Corresponding Author), Tommi Tikkanen, Paul Kemppi, Petri Honkamaa

    Research output: Contribution to journalArticleScientificpeer-review

    2 Citations (Scopus)

    Abstract

    We address the problem of calibrating an embedded depth camera network designed for people tracking purposes. In our system, the nodes of the network are responsible for detecting the people moving in their view, and sending the observations to a centralized server for data fusion and tracking. We employ a plan-view approach where the depth camera views are transformed to top-view height maps where people are observed. As the server transforms the observations to a global plan-view coordinate system, accurate geometric calibration of the sensors has to be performed. Our main contribution is an auto-calibration method for such depth camera networks. In our approach, the sensor network topology and the initial 2D rigid transformations that map the observations to the global frame are determined using observations only. To distribute the errors in the initial calibration, the transformation parameters and the estimated positions of people are refined using a global optimization routine. To overcome inaccurate depth camera parameters, we re-calibrate the sensors using more flexible transformations, and experiment with similarity, affine, homography and thin-plate spline mappings. We evaluate the robustness, accuracy and precision of the approach using several real-life data sets, and compare the results to a checkerboard-based calibration method as well as to the ground truth trajectories collected with a mobile robot.

    Original languageEnglish
    Number of pages18
    JournalMachine Vision and Applications
    DOIs
    Publication statusAccepted/In press - 28 Mar 2019
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Cameras
    Calibration
    Servers
    Sensors
    Data fusion
    Global optimization
    Splines
    Mobile robots
    Sensor networks
    Trajectories
    Topology
    Experiments

    Keywords

    • Auto-calibration
    • Depth camera network
    • Depth distortion
    • People tracking
    • Thin-plate spline

    Cite this

    @article{ab4a5f84a2034b929cfc2d1ec52b479b,
    title = "Auto-calibration of depth camera networks for people tracking",
    abstract = "We address the problem of calibrating an embedded depth camera network designed for people tracking purposes. In our system, the nodes of the network are responsible for detecting the people moving in their view, and sending the observations to a centralized server for data fusion and tracking. We employ a plan-view approach where the depth camera views are transformed to top-view height maps where people are observed. As the server transforms the observations to a global plan-view coordinate system, accurate geometric calibration of the sensors has to be performed. Our main contribution is an auto-calibration method for such depth camera networks. In our approach, the sensor network topology and the initial 2D rigid transformations that map the observations to the global frame are determined using observations only. To distribute the errors in the initial calibration, the transformation parameters and the estimated positions of people are refined using a global optimization routine. To overcome inaccurate depth camera parameters, we re-calibrate the sensors using more flexible transformations, and experiment with similarity, affine, homography and thin-plate spline mappings. We evaluate the robustness, accuracy and precision of the approach using several real-life data sets, and compare the results to a checkerboard-based calibration method as well as to the ground truth trajectories collected with a mobile robot.",
    keywords = "Auto-calibration, Depth camera network, Depth distortion, People tracking, Thin-plate spline",
    author = "Otto Korkalo and Tommi Tikkanen and Paul Kemppi and Petri Honkamaa",
    year = "2019",
    month = "3",
    day = "28",
    doi = "10.1007/s00138-019-01021-z",
    language = "English",
    journal = "Machine Vision and Applications",
    issn = "0932-8092",
    publisher = "Springer",

    }

    Auto-calibration of depth camera networks for people tracking. / Korkalo, Otto (Corresponding Author); Tikkanen, Tommi; Kemppi, Paul; Honkamaa, Petri.

    In: Machine Vision and Applications, 28.03.2019.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Auto-calibration of depth camera networks for people tracking

    AU - Korkalo, Otto

    AU - Tikkanen, Tommi

    AU - Kemppi, Paul

    AU - Honkamaa, Petri

    PY - 2019/3/28

    Y1 - 2019/3/28

    N2 - We address the problem of calibrating an embedded depth camera network designed for people tracking purposes. In our system, the nodes of the network are responsible for detecting the people moving in their view, and sending the observations to a centralized server for data fusion and tracking. We employ a plan-view approach where the depth camera views are transformed to top-view height maps where people are observed. As the server transforms the observations to a global plan-view coordinate system, accurate geometric calibration of the sensors has to be performed. Our main contribution is an auto-calibration method for such depth camera networks. In our approach, the sensor network topology and the initial 2D rigid transformations that map the observations to the global frame are determined using observations only. To distribute the errors in the initial calibration, the transformation parameters and the estimated positions of people are refined using a global optimization routine. To overcome inaccurate depth camera parameters, we re-calibrate the sensors using more flexible transformations, and experiment with similarity, affine, homography and thin-plate spline mappings. We evaluate the robustness, accuracy and precision of the approach using several real-life data sets, and compare the results to a checkerboard-based calibration method as well as to the ground truth trajectories collected with a mobile robot.

    AB - We address the problem of calibrating an embedded depth camera network designed for people tracking purposes. In our system, the nodes of the network are responsible for detecting the people moving in their view, and sending the observations to a centralized server for data fusion and tracking. We employ a plan-view approach where the depth camera views are transformed to top-view height maps where people are observed. As the server transforms the observations to a global plan-view coordinate system, accurate geometric calibration of the sensors has to be performed. Our main contribution is an auto-calibration method for such depth camera networks. In our approach, the sensor network topology and the initial 2D rigid transformations that map the observations to the global frame are determined using observations only. To distribute the errors in the initial calibration, the transformation parameters and the estimated positions of people are refined using a global optimization routine. To overcome inaccurate depth camera parameters, we re-calibrate the sensors using more flexible transformations, and experiment with similarity, affine, homography and thin-plate spline mappings. We evaluate the robustness, accuracy and precision of the approach using several real-life data sets, and compare the results to a checkerboard-based calibration method as well as to the ground truth trajectories collected with a mobile robot.

    KW - Auto-calibration

    KW - Depth camera network

    KW - Depth distortion

    KW - People tracking

    KW - Thin-plate spline

    UR - http://www.scopus.com/inward/record.url?scp=85064218936&partnerID=8YFLogxK

    U2 - 10.1007/s00138-019-01021-z

    DO - 10.1007/s00138-019-01021-z

    M3 - Article

    AN - SCOPUS:85064218936

    JO - Machine Vision and Applications

    JF - Machine Vision and Applications

    SN - 0932-8092

    ER -