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

Spatiotemporal modeling for group behavior analysis

Research Project

Project/Area Number 16K00231
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Perceptual information processing
Research InstitutionChiba University

Principal Investigator

Kawamoto Kazuhiko  千葉大学, 大学院工学研究院, 教授 (30345376)

Co-Investigator(Kenkyū-buntansha) 岡本 一志  電気通信大学, 大学院情報理工学研究科, 助教 (10615032)
Project Period (FY) 2016-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords集団行動解析 / 時空間統計モデル / 人物移動予測 / 行動認識 / 深層学習 / データ拡張 / 移動予測 / 人物行動解析 / 行動解析 / クリギング / 時空間統計
Outline of Final Research Achievements

In this study, we develop a spatio-temporal statistical method for group behavior analysis using videos. The proposed method estimates proximity relationships between people or between people and their environment using not only location information but also attribute information. We show that the effectiveness of the proposed method by applying our method to two applications: people movement prediction using surveillance camera images and first-person activity recognition from wearable camera images.

Academic Significance and Societal Importance of the Research Achievements

時空間統計学は,地下資源の埋蔵量推定や土地価格の予測・内挿推定等を目的に,地球統計学や空間計量経済学の分野で独自に発展しており,従来の統計学に対して「位置情報」を明示的に扱うという点で特色がある.本研究は,このような理論研究とコンピュータビジョン分野で発展しているビデオ解析・認識技術を組み合わせるための方法を研究し,複数人物の移動予測に適用した.このような研究は,カメラを用いた安全・安心のための基礎技術として応用することが期待できる.

Report

(5 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (29 results)

All 2019 2018 2017 2016

All Journal Article (8 results) (of which Peer Reviewed: 8 results,  Open Access: 4 results,  Acknowledgement Compliant: 1 results) Presentation (21 results) (of which Int'l Joint Research: 4 results,  Invited: 1 results)

  • [Journal Article] Deep Multi-Task Learning Architecture for First-Person Activity Recognition2019

    • Author(s)
      中村 伊吹、川本 一彦、岡本 一志
    • Journal Title

      電子情報通信学会論文誌D 情報・システム

      Volume: J102-D Issue: 8 Pages: 506-513

    • DOI

      10.14923/transinfj.2018IUP0003

    • ISSN
      1880-4535, 1881-0225
    • Year and Date
      2019-08-01
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Conditional GAN-Based Image Interpolation between Classes and Its Application to Data Augumentation2019

    • Author(s)
      河野 曜平、川本 一彦
    • Journal Title

      電子情報通信学会論文誌D 情報・システム

      Volume: J102-D Issue: 7 Pages: 491-493

    • DOI

      10.14923/transinfj.2019JDL8001

    • ISSN
      1880-4535, 1881-0225
    • Year and Date
      2019-07-01
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] DCVGAN: Depth Conditional Video Generation2019

    • Author(s)
      Nakahira Yuki、Kawamoto Kazuhiko
    • Journal Title

      IEEE International Conference on Image Processing

      Volume: - Pages: 749-753

    • DOI

      10.1109/icip.2019.8803764

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] First-person reading activity recognition by deep learning with synthetically generated images2018

    • Author(s)
      Segawa Yuta, Kawamoto Kazuhiko, Okamoto Kazushi
    • Journal Title

      EURASIP Journal on Image and Video Processing

      Volume: 2018 Issue: 1 Pages: 1-13

    • DOI

      10.1186/s13640-018-0272-z

    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Generative adversarial networks for generating RGB-D videos2018

    • Author(s)
      Yuki Nakahira, Kazuhiko Kawamoto
    • Journal Title

      Proc. of Asia-Pacific Signal and Information Processing, Association Annual Summit and Conference

      Volume: - Pages: 1276-1281

    • DOI

      10.23919/apsipa.2018.8659648

    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] First-Person Activity Recognition by Deep Multi-task Network with Hand Segmentation2018

    • Author(s)
      Shunpei Kobayashi, Kazuhiko Kawamoto
    • Journal Title

      Proc. of ISCIIA&ITCA

      Volume: - Pages: 1-5

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] Kriging-based prediction and interpolation for modeling pedestrian dynamics2017

    • Author(s)
      Kazuhiko Kawamoto, Yoshiyuki Tomura, Kazushi Okamoto
    • Journal Title

      Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems

      Volume: - Pages: 1-4

    • DOI

      10.1109/ifsa-scis.2017.8023264

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] First-Person Vision Based Prediction of Information Seeking and Use Behavior in Library2017

    • Author(s)
      Kazushi Okamoto and Kazuhiko Kawamoto
    • Journal Title

      Journal of Japan Society for Fuzzy Theory and Intelligent Informatics

      Volume: 29 Issue: 2 Pages: 574-578

    • DOI

      10.3156/jsoft.29.2_574

    • NAID

      130006893415

    • ISSN
      1347-7986, 1881-7203
    • Related Report
      2016 Research-status Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Presentation] Shared 2D-convolutions netを用いた深層マルチタスク学習による一人称行動認識2019

    • Author(s)
      小林 春平, 川本 一彦
    • Organizer
      第22回画像の認識・理解シンポジウム
    • Related Report
      2019 Annual Research Report
  • [Presentation] マルチ教師モデルを用いた半教師あり学習による深層物体検出2019

    • Author(s)
      齋藤 恭兵, 川本 一彦
    • Organizer
      第22回画像の認識・理解シンポジウム
    • Related Report
      2019 Annual Research Report
  • [Presentation] デプスからカラーへのドメイン変換を用いたGANによる動画生成2018

    • Author(s)
      中平有樹, 川本一彦
    • Organizer
      情報処理学会CVIM研究会
    • Related Report
      2018 Research-status Report
  • [Presentation] 条件付きGANによるクラス間補間画像を用いたデータ拡張2018

    • Author(s)
      河野曜平, 川本一彦
    • Organizer
      第21回画像の認識・理解シンポジウム
    • Related Report
      2018 Research-status Report
  • [Presentation] 一人称行動認識のための深層マルチタスクモデルアーキテクチャ2018

    • Author(s)
      中村伊吹, 川本一彦
    • Organizer
      第21回画像の認識・理解シンポジウム
    • Related Report
      2018 Research-status Report
  • [Presentation] RGB-D動画生成のためのGAN2018

    • Author(s)
      中平有樹, 川本一彦
    • Organizer
      情報処理学会CVIM研究会
    • Related Report
      2018 Research-status Report
  • [Presentation] マルチドメイン学習による複数物体追跡2018

    • Author(s)
      斉藤恭兵, 川本一彦
    • Organizer
      情報処理学会CVIM研究会
    • Related Report
      2018 Research-status Report
  • [Presentation] Data Assimilation for Pedestrian Tracking Using Deep Convolutional Neural Network2017

    • Author(s)
      Ryosuke NAKAISHI, Kazuhiko KAWAMOTO
    • Organizer
      5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Vision with Deep Learning for Data Assimilation,2017

    • Author(s)
      Kazuhiko Kawamoto
    • Organizer
      the 5th international workshop on frontier of science and technology and the 5th international workshop on advanced computational intelligence and intelligent informatics
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] モーションキャプチャデータとcGANを用いた人物動作ビデオの生成2017

    • Author(s)
      川上倫人,川本一彦
    • Organizer
      第32回信号処理シンポジウム
    • Related Report
      2017 Research-status Report
  • [Presentation] DCNNを用いた人物追跡のためのデータ同化2017

    • Author(s)
      中石涼介, 川本一彦
    • Organizer
      第20回画像の認識・理解シンポジウム
    • Related Report
      2017 Research-status Report
  • [Presentation] GANを用いたデータ拡張2017

    • Author(s)
      河野曜平, 川本一彦
    • Organizer
      情報処理学会研究報告 Vol. 2017-CVIM-207, No.14
    • Related Report
      2017 Research-status Report
  • [Presentation] 一人称視点行動認識のためのニューラルネットワークの小型化2017

    • Author(s)
      中村伊吹, 川本一彦, 岡本一志
    • Organizer
      情報処理学会研究報告, Vol. 2017-CVIM-207, No.9
    • Related Report
      2017 Research-status Report
  • [Presentation] First-Person Activity Recognition by Image Classification2016

    • Author(s)
      Yuta Segawa, Kazuhiko Kawamoto, and Kazushi Okamoto
    • Organizer
      Int. Symposium Computational Intelligence and Industrial Applications
    • Place of Presentation
      北京理工大学,中国
    • Year and Date
      2016-11-03
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] クリギングに基づく人物移動予測2016

    • Author(s)
      戸村恵之, 川本一彦, 岡本一志
    • Organizer
      第26回イ ンテリジェント・システム・シンポジウム
    • Place of Presentation
      大阪大学吹田キャンパス
    • Year and Date
      2016-10-27
    • Related Report
      2016 Research-status Report
  • [Presentation] 画像分類を用いた一人称行動認識2016

    • Author(s)
      瀬川雄太, 川本一彦, 岡本 一志
    • Organizer
      情報処理学会CVIM研究会
    • Place of Presentation
      富山大学五福キャンパス
    • Year and Date
      2016-09-05
    • Related Report
      2016 Research-status Report
  • [Presentation] Plan-Action モデルに基づく人物追跡2016

    • Author(s)
      中石涼介, 川本一彦
    • Organizer
      第32回ファジィシステムシンポジウム
    • Place of Presentation
      佐賀大学本庄キャンパス
    • Year and Date
      2016-08-31
    • Related Report
      2016 Research-status Report
  • [Presentation] 画像分類を用いた一人称行動認識2016

    • Author(s)
      瀬川雄太, 川本一彦, 岡本 一志
    • Organizer
      第19回画像の認識・理解シンポジウム
    • Place of Presentation
      アクトシティ浜松
    • Year and Date
      2016-08-01
    • Related Report
      2016 Research-status Report
  • [Presentation] 時空間クリギングを用いた人物移動予測2016

    • Author(s)
      戸村恵之, 川本一彦, 岡本 一志
    • Organizer
      第19回画像の認識・理解シンポジウム
    • Place of Presentation
      アクトシティ浜松
    • Year and Date
      2016-08-01
    • Related Report
      2016 Research-status Report
  • [Presentation] 歩行者追跡のためのサブゴール推定2016

    • Author(s)
      林悠司, 川本一彦
    • Organizer
      第19回画像の認識・理解シンポジウム
    • Place of Presentation
      アクトシティ浜松
    • Year and Date
      2016-08-01
    • Related Report
      2016 Research-status Report
  • [Presentation] Learning pedestrian dynamics with kriging2016

    • Author(s)
      Kazuhiko Kawamoto, Yoshiyuki Tomura, Kazushi Okamoto
    • Organizer
      15th IEEE/ACIS International Conference on Computer and Information Science
    • Place of Presentation
      岡山コンベンションセンター
    • Year and Date
      2016-06-26
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2016-04-21   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi