• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Recovery of body postures from a monocular image wequence based on probabilistic model learning

Research Project

Project/Area Number 14580427
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionHiroshima City University

Principal Investigator

HAYASHI Akira  Hiroshima City University, Faculty of Information Sciences, Professor, 情報科学部, 教授 (60240909)

Co-Investigator(Kenkyū-buntansha) OKADA Masami  Tokyo Metropolitan University, Faculty of Science, Professor, 理学研究科, 教授 (00152314)
KANBARA Toshihiko  Hiroshima City University, Faculty of Information Sciences, Research Associate, 助手 (60285426)
SUEMATSU Nobuo  Hiroshima City University, Faculty of Information Sciences, Research Associate, 助教授 (70264942)
Project Period (FY) 2002 – 2003
Project Status Completed (Fiscal Year 2003)
Budget Amount *help
¥2,800,000 (Direct Cost: ¥2,800,000)
Fiscal Year 2003: ¥600,000 (Direct Cost: ¥600,000)
Fiscal Year 2002: ¥2,200,000 (Direct Cost: ¥2,200,000)
Keywordspose estimation / monocular image / state space model / sequential Mote Carlo / 逐次モンテカルロ法 / モーションキャプチャ / 人間の動き / コンピュータ・ビジョン / 多様体学習 / モーション・キャプチャー / コンピューター・ビジョン
Research Abstract

In the fields of visual surveillance, welfare robotics, and human interface, it is important that a computer can recognize the posture/motion of people. In this research, we try to estimate human postures from monocular image sequences.
We propose the cyclic motion model which is a state space model to represent motions. In the model, the state of a system is represented by the phase of a motion, assuming that the motion is cyclic. The state (i.e. the phase) is estimated from a monocular image sequence using the sequential Monte Carlo method. Then, the posture is computed from the state. The cyclic motion model is learned from motion capture data. In addition, we extend the cyclic motion model to allow for camera viewpoint changes.
Experiments show the validity of the proposed technique.

Report

(3 results)
  • 2003 Annual Research Report   Final Research Report Summary
  • 2002 Annual Research Report
  • Research Products

    (13 results)

All Other

All Publications (13 results)

  • [Publications] 江本光晴, 林朗, 末松伸朗, 神原利彦: "周期的動作モデルを用いた単眼画像列からの姿勢推定"画像と認識・理解シンポジウム(MIRU2004)、2004. (採択決定). (2004)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] 江本光晴, 林朗, 末松伸朗, 神原利彦: "逐次モンテカルロ法を用いた単眼画像列からの姿勢推定"情報処理学会第66回全国大会論文集. 2:451-2:452 (2004)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] 岩村篤樹, 林朗, 神原利彦, 末松伸朗: "学習による単眼画像からの人間の姿勢の復元"電子・情報関連学会中国支部第53回連合大会講演論文集. 590 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] Mitsuharu Emoto, Akira Hayashi, Nobuo Suematsu, Toshihiko Kanbara: "Pose estimation from monocular image sequences using sequential Monte Carlo (in Japanese)"Proc.Meeting on Image Recognition and Understanding (MIRU 2004), Hakodate, July 23-25. (Accepted). (2004)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] Mitsuharu Emoto: "Pose estimation from monocular image sequences using sequential Monte Carlo"Graduation Thesis, Department of Information Machines and Interfaces, Faculty of Information Sciences, Hiroshima City university. March. (2004)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] Mitsuharu Emoto, Akira Hayashi, Nobuo Suematsu, Toshihiko Kanbara: "Pose estimation form monocular image sequences using the cyclic motion model (in Japanese)"Proc.the 66-th national Convention of IPSJ. Fujisawa, March9-11. 2:451-2:452 (2004)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] Shigeki Iwamura: "Pose estimation from monocular image sequences, a machine learning approach (in Japanese)"Master's thesis, Graduate School, Faculty of Information Sciences, Hiroshima City University. March. (2003)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] Sigeki Iwamura, Akira Hayashi, Toshihiko Kanbara, Nobuo Suematsu: "Human posture recovery from monocular image sequences, a machine learning approach (in Japanese)"Proc.56-th Regional Joint conference of electronics and Information Related Academic Associations (Rentai 2002 in shimane). Matsue, Oct.19-20. 590 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2003 Final Research Report Summary
  • [Publications] 江本光晴, 林朗, 末松伸朗, 神原利彦: "逐次モンテカルロ法を用いた単眼画像列からの姿勢推定"情報処理学会第66回全国大会論文集. 2-451-2-452 (2004)

    • Related Report
      2003 Annual Research Report
  • [Publications] 江本光晴, 林朗, 末松伸朗, 神原利彦: "周期的動作モデルを用いた単眼画像列からの姿勢推定"画像と認識・理解シンポジウム(MIRU2004). (2004)

    • Related Report
      2003 Annual Research Report
  • [Publications] 岩村篤樹: "学習を用いた単眼画像列からの姿勢の推定"広島市立大学大学院情報科学研究科修士論文. (2003)

    • Related Report
      2003 Annual Research Report
  • [Publications] 岩村篤樹, 林朗, 神原利彦, 末松伸朗: "学習による単眼画像からの人間の姿勢の復元"電子・情報関連学会中国支部第53回連合大会講演論文集. 590 (2002)

    • Related Report
      2003 Annual Research Report
  • [Publications] 岩村篤樹, 林朗, 神原利彦, 末松伸朗: "学習による単眼画像列からの人間の姿勢の復元"電気・情報関連学会中国支部第53回連合大会 講演論文集. 590 (2002)

    • Related Report
      2002 Annual Research Report

URL: 

Published: 2002-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi