qューマノイドを対象にした視聴覚統合による実時間人物追跡 : アクティブオーディションと顔認識の統合  [in Japanese] Real-Time Human Tracking by Audio-Visual Integration for Humanoids : Integration of Active Audition and Face Recognition  [in Japanese]

Access this Article

Search this Article

Author(s)

    • 中臺 一博 NAKADAI Kazuhiro
    • 科学技術振興事業団ERATO北野共生システムプロジェクト Kitano Symbiotic Systems Project,ERATO,Japan Science and Technology Corp.
    • 日台 健一 HIDAI Ken-ichi
    • 科学技術振興事業団ERATO北野共生システムプロジェクト Kitano Symbiotic Systems Project,ERATO,Japan Science and Technology Corp.
    • 奥乃 博 OKUNO Hiroshi
    • 科学技術振興事業団ERATO北野共生システムプロジェクト Kitano Symbiotic Systems Project,ERATO,Japan Science and Technology Corp.
    • 北野 宏明 KITANO Hiroaki
    • 科学技術振興事業団ERATO北野共生システムプロジェクト Kitano Symbiotic Systems Project,ERATO,Japan Science and Technology Corp.

Abstract

This paper describes a real-time human tracking system by audio-visual integrtation for the humanoid <I>SIG</I>. An essential idea for real-time and robust tracking is hierarchical integration of multi-modal information. The system creates three kinds of streams - auditory, visual and associated streams. An auditory stream with sound source direction is formed as temporal series of events from audition module which localizes multiple sound sources and cancels motor noise from a pair of microphones. A visual stream with a face ID and its 3D-position is formed as temporal series of events from vision module by combining face detection, face identification and face localization by stereo vision. Auditory and visual streams are associated into an associated stream, a higher level representation according to their proximity. Because the associated stream disambiguates parcially missing information in auditory or visual streams, “focus-of-attention” control of <I>SIG</I> works well enough to robust human tracking. These processes are executed in real-time with the delay of 200 msec using off-the-shelf PCs distributed via TCP/IP. As a result, robust human tracking is attained even when the person is visually occluded and simultaneous speeches occur.

Journal

  • Journal of the Robotics Society of Japan

    Journal of the Robotics Society of Japan 21(5), 517-525, 2003-07-15

    The Robotics Society of Japan

References:  11

Cited by:  6

Codes

  • NII Article ID (NAID)
    10011243291
  • NII NACSIS-CAT ID (NCID)
    AN00141189
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    02891824
  • NDL Article ID
    6646149
  • NDL Source Classification
    ZN11(科学技術--機械工学・工業)
  • NDL Call No.
    Z16-1325
  • Data Source
    CJP  CJPref  NDL  J-STAGE 
Page Top