Upper-body contour xtraction and tracking using face and body shape variance information

Kazuki Hoshiai, Shinya Fujie, Tetsunori Kobayashi

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

    Abstract

    We propose a fitting method using a model that integrates face and bod□ shape variance information for upperbod□ contour extraction and tracking. Accurate bod□-contour extraction is necessar□ for various applications, such as pose estimation, gesture recognition, and so on. In this stud□, we regard it as the shape model fitting problem. A model including shape variance information can fit to the contour robustl□ even in the nois□ case. AAMs are one of these models and can fit to a face successfull□ It needs appearance information for effective fitting, but it can not be used in our case because appearance of upper-bod□ easil□ changes b□ clothes. Instead of intensit image, proposed method uses edge image as appearance information. However, discrimination between a true contour edge of upperbod□ and other edges is difficult. To solve this problem, we integrate shape models of upper bod□ and face. It is expected that this integrated model is more robust to edges in clutter background and various locations of the bod□ than a bod□ shape model using onl□ bod□ shape information. We conduct experiments and confirm improvement in accurac □b□ integration of face and bod□ variance information.

    Original languageEnglish
    Title of host publication2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008
    Pages391-398
    Number of pages8
    DOIs
    Publication statusPublished - 2008
    Event2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008 - Daejeon
    Duration: 2008 Dec 12008 Dec 3

    Other

    Other2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008
    CityDaejeon
    Period08/12/108/12/3

    Fingerprint

    Gesture recognition
    Experiments

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Vision and Pattern Recognition
    • Human-Computer Interaction

    Cite this

    Hoshiai, K., Fujie, S., & Kobayashi, T. (2008). Upper-body contour xtraction and tracking using face and body shape variance information. In 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008 (pp. 391-398). [4755983] https://doi.org/10.1109/ICHR.2008.4755983

    Upper-body contour xtraction and tracking using face and body shape variance information. / Hoshiai, Kazuki; Fujie, Shinya; Kobayashi, Tetsunori.

    2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008. 2008. p. 391-398 4755983.

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

    Hoshiai, K, Fujie, S & Kobayashi, T 2008, Upper-body contour xtraction and tracking using face and body shape variance information. in 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008., 4755983, pp. 391-398, 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008, Daejeon, 08/12/1. https://doi.org/10.1109/ICHR.2008.4755983
    Hoshiai K, Fujie S, Kobayashi T. Upper-body contour xtraction and tracking using face and body shape variance information. In 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008. 2008. p. 391-398. 4755983 https://doi.org/10.1109/ICHR.2008.4755983
    Hoshiai, Kazuki ; Fujie, Shinya ; Kobayashi, Tetsunori. / Upper-body contour xtraction and tracking using face and body shape variance information. 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008. 2008. pp. 391-398
    @inproceedings{4f93586288924b1fab750d5b03a0c6c6,
    title = "Upper-body contour xtraction and tracking using face and body shape variance information",
    abstract = "We propose a fitting method using a model that integrates face and bod□ shape variance information for upperbod□ contour extraction and tracking. Accurate bod□-contour extraction is necessar□ for various applications, such as pose estimation, gesture recognition, and so on. In this stud□, we regard it as the shape model fitting problem. A model including shape variance information can fit to the contour robustl□ even in the nois□ case. AAMs are one of these models and can fit to a face successfull□ It needs appearance information for effective fitting, but it can not be used in our case because appearance of upper-bod□ easil□ changes b□ clothes. Instead of intensit image, proposed method uses edge image as appearance information. However, discrimination between a true contour edge of upperbod□ and other edges is difficult. To solve this problem, we integrate shape models of upper bod□ and face. It is expected that this integrated model is more robust to edges in clutter background and various locations of the bod□ than a bod□ shape model using onl□ bod□ shape information. We conduct experiments and confirm improvement in accurac □b□ integration of face and bod□ variance information.",
    author = "Kazuki Hoshiai and Shinya Fujie and Tetsunori Kobayashi",
    year = "2008",
    doi = "10.1109/ICHR.2008.4755983",
    language = "English",
    isbn = "9781424428229",
    pages = "391--398",
    booktitle = "2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008",

    }

    TY - GEN

    T1 - Upper-body contour xtraction and tracking using face and body shape variance information

    AU - Hoshiai, Kazuki

    AU - Fujie, Shinya

    AU - Kobayashi, Tetsunori

    PY - 2008

    Y1 - 2008

    N2 - We propose a fitting method using a model that integrates face and bod□ shape variance information for upperbod□ contour extraction and tracking. Accurate bod□-contour extraction is necessar□ for various applications, such as pose estimation, gesture recognition, and so on. In this stud□, we regard it as the shape model fitting problem. A model including shape variance information can fit to the contour robustl□ even in the nois□ case. AAMs are one of these models and can fit to a face successfull□ It needs appearance information for effective fitting, but it can not be used in our case because appearance of upper-bod□ easil□ changes b□ clothes. Instead of intensit image, proposed method uses edge image as appearance information. However, discrimination between a true contour edge of upperbod□ and other edges is difficult. To solve this problem, we integrate shape models of upper bod□ and face. It is expected that this integrated model is more robust to edges in clutter background and various locations of the bod□ than a bod□ shape model using onl□ bod□ shape information. We conduct experiments and confirm improvement in accurac □b□ integration of face and bod□ variance information.

    AB - We propose a fitting method using a model that integrates face and bod□ shape variance information for upperbod□ contour extraction and tracking. Accurate bod□-contour extraction is necessar□ for various applications, such as pose estimation, gesture recognition, and so on. In this stud□, we regard it as the shape model fitting problem. A model including shape variance information can fit to the contour robustl□ even in the nois□ case. AAMs are one of these models and can fit to a face successfull□ It needs appearance information for effective fitting, but it can not be used in our case because appearance of upper-bod□ easil□ changes b□ clothes. Instead of intensit image, proposed method uses edge image as appearance information. However, discrimination between a true contour edge of upperbod□ and other edges is difficult. To solve this problem, we integrate shape models of upper bod□ and face. It is expected that this integrated model is more robust to edges in clutter background and various locations of the bod□ than a bod□ shape model using onl□ bod□ shape information. We conduct experiments and confirm improvement in accurac □b□ integration of face and bod□ variance information.

    UR - http://www.scopus.com/inward/record.url?scp=63549111521&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=63549111521&partnerID=8YFLogxK

    U2 - 10.1109/ICHR.2008.4755983

    DO - 10.1109/ICHR.2008.4755983

    M3 - Conference contribution

    SN - 9781424428229

    SP - 391

    EP - 398

    BT - 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008

    ER -