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

Research on automatic generation of drawing songs for easy-to-understand object descriptions

Research Project

Project/Area Number 16K12455
Research Category

Grant-in-Aid for Challenging Exploratory Research

Allocation TypeMulti-year Fund
Research Field Perceptual information processing
Research InstitutionNational Institute of Advanced Industrial Science and Technology

Principal Investigator

Kanezaki Asako  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (00738073)

Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Keywords物体認識 / 画像セグメンテーション / 機械学習 / マルチビュー画像 / 姿勢推定 / 教師なし学習 / 画像認識 / コンピュータビジョン / 自然言語処理 / パターン認識
Outline of Final Research Achievements

With the aim of explaining unknown objects in images with easy-to-understand expressions, we tackled to develop elemental technology for the automatic generation of drawing songs based on general object recognition. In order to describe an unknown object, humans generate a metaphorical expression such as "Like xxx" or "Like placing xxx on yyy", using some common and imaginable objects. In order to develop such a system, we proposed a novel 3D object recognition method using multi-view images. We also proposed an unsupervised image segmentation method that decomposes unknown objects in images into separated regions without using any prior knowledge.

Academic Significance and Societal Importance of the Research Achievements

第一に,様々な角度から物体を撮影し,一般的な名称を推論する三次元物体認識技術を開発した.本研究は深層学習を用いており,物体の姿勢の教師信号を人間が与えることなく,自動的に獲得できる点が新しい.提案手法は三次元物体検索の国際的コンペティションSHREC’17にて,二部門で世界第一位の性能を記録した.第二に,画像内の物体をパーツに分解する教師無し画像セグメンテーション技術を開発した.深層学習を用いた画像セグメンテーションの研究例は多く存在するが,そのほとんどが教師あり学習である.提案手法は畳み込みニューラルネットワークを用いるが,事前学習等の学習を一切必要としない点が新しい.

Report

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

    (10 results)

All 2019 2018 2016 Other

All Presentation (8 results) (of which Int'l Joint Research: 3 results) Book (1 results) Remarks (1 results)

  • [Presentation] Salient object detection on hyperspectral images using features learned from unsupervised segmentation task2019

    • Author(s)
      Nevrez Imamoglu, Guanqun Ding, Yuming Fang, Asako Kanezaki, Toru Kouyama, and Ryosuke Nakamura
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Unsupervised Image Segmentation by Backpropagation2018

    • Author(s)
      Asako Kanezaki
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints2018

    • Author(s)
      Asako Kanezaki, Yasuyuki Matsushita, and Yoshifumi Nishida.
    • Organizer
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] 視点教示なし多視点画像深層学習による物体のカテゴリ・姿勢同時推定2018

    • Author(s)
      金崎 朝子、松下 康之、西田 佳史
    • Organizer
      画像センシングシンポジウム
    • Related Report
      2017 Research-status Report
  • [Presentation] IBC127: Video Dataset for Fine-grained Bird Classification2016

    • Author(s)
      Tomoaki Saito, Asako Kanezaki
    • Organizer
      IEEE International Conference on Multimedia & Expo (ICME)(国際学会)
    • Place of Presentation
      The Westin Seattle(シアトル, WA, アメリカ)
    • Related Report
      2016 Research-status Report
  • [Presentation] Kinect等の色距離センサを用いた点群処理と3D物体認識―ベーシックな手法と最新動向・ソフトウェアの紹介―2016

    • Author(s)
      金崎朝子
    • Organizer
      第22回 画像センシングシンポジウム(SSII2016)(招待講演)
    • Place of Presentation
      パシフィコ横浜(神奈川県横浜市)
    • Related Report
      2016 Research-status Report
  • [Presentation] 色距離センサを用いた点群処理と三次元物体認識に関する研究紹介2016

    • Author(s)
      金崎朝子
    • Organizer
      画像応用技術専門委員会2016年度第3回研究会(招待講演)
    • Place of Presentation
      中央大学後楽園キャンパス(東京都文京区)
    • Related Report
      2016 Research-status Report
  • [Presentation] 画像認識とロボティクスにおける人工知能研究の現状2016

    • Author(s)
      金崎朝子
    • Organizer
      (公財)長野県テクノ財団 アルプスハイランド地域センター「旬」の技術研究会(招待講演)
    • Place of Presentation
      長野県工業技術総合センター(長野県松本市)
    • Related Report
      2016 Research-status Report
  • [Book] Multimodal Scene Understanding2019

    • Author(s)
      Michael Ying Yang, Bodo Rosenhahn, Vittorio Murino
    • Total Pages
      525
    • Publisher
      Elsevier
    • ISBN
      9780128173589
    • Related Report
      2018 Annual Research Report
  • [Remarks] Unsupervised Image Segmentation by Backpropagation

    • URL

      https://kanezaki.github.io/pytorch-unsupervised-segmentation/

    • Related Report
      2017 Research-status Report

URL: 

Published: 2016-04-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi