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

Precise 3-D remote sensing using multi-spectral image estimation and accurate 3-D reconstruction

Research Project

Project/Area Number 20K06319
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 41040:Agricultural environmental engineering and agricultural information engineering-related
Research InstitutionToyohashi University of Technology

Principal Investigator

Kanazawa Yasushi  豊橋技術科学大学, 工学(系)研究科(研究院), 准教授 (50214432)

Co-Investigator(Kenkyū-buntansha) 小林 健一  一関工業高等専門学校, その他部局等, 講師 (80707513)
佐藤 建  一関工業高等専門学校, その他部局等, 特命助教 (70647643)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords高精細3-Dリモートセンシング / マルチスペクトル画像推定 / 圃場3-D計測 / 糖度推定 / 高精細3Dリモートセンシング / ドローン映像処理 / IT農業 / 3D形状対応付け / 3次元復元
Outline of Research at the Start

本研究では,高精細3-Dリモートセンシングと題し,安価なカメラ付きドローンで撮影した圃場の映像のみを用い,通常の可視カメラ画像から可視以外のスペクトルの画像の高精度な推定を行うと共に,その情報を用いた個々の作物の細かな情報の認識および計測し,高精度かつリアルタイムな3次元計測技術を用いて,推定した個々の作物の詳細な情報を計測した 3 次元形状に重畳することで立体的な解析を可能とする技術を開発する.また本技術の他の分野への応用,例えば,ドローンによる河川の河岸や湖沼における高精細な各種調査への応用などを図る.

Outline of Final Research Achievements

We aimed to develop a high-precision 3-D remote sensing technology, which can assist small- and medium-scale farmers to operate their sustainable agriculture. There are three cores for doing this: (1) estimation of other single-band image from visible image, (2) easy computation or estimation of plant condition such as sugar content and vegetation index, (3) 3-D information estimation of farm field. For estimation of NIR and Red-channel image from visible image, we adopt GAN-based method; for easy estimation of sugar content, we use only visible image taken by a drone; for 3-D information of the farm, we proposed the new method that can find the difference between difference scales and ranges and we also proposed accurate depth estimation method from single image. From experiments, we find the effectiveness of our methods. In future work, we aim to establish a high-precision 3-D remote sensing using these methods.

Academic Significance and Societal Importance of the Research Achievements

日本に多い中小規模の農家は,働き手の高齢化だけでなく,慢性的な人手不足の問題があり,本研究で提案している高精細3-Dリモートセンシング技術に対する成果は,このような中小規模の農家に対する持続可能の農業を行える手助けと成り得ると考える.これは,比較的高価な機械の多い農家に対して,安価なドローンを導入するだけで,リモート糖度推定や圃場の状態の把握などを簡単に行えるようになるためである.

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (8 results)

All 2023 2022 2021 2020

All Journal Article (3 results) (of which Peer Reviewed: 3 results,  Open Access: 2 results) Presentation (5 results) (of which Int'l Joint Research: 2 results,  Invited: 1 results)

  • [Journal Article] TP-GAN: Simple Adversarial Network With Additional Player for Dense Depth Image Estimation2023

    • Author(s)
      Andi Hendra, Yasushi Kanazawa
    • Journal Title

      IEEE Access

      Volume: 11 Pages: 44176-44191

    • DOI

      10.1109/access.2023.3272292

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Underground object recognition using interpolated GPR images2022

    • Author(s)
      徳重 海都,金澤 靖,園田 潤,木本 智幸
    • Journal Title

      Proceedings of the Annual Conference of JSAI

      Volume: JSAI2022 Issue: 0 Pages: 2P5GS1003-2P5GS1003

    • DOI

      10.11517/pjsai.JSAI2022.0_2P5GS1003

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Smaller Residual Network for Single Image Depth Estimation2021

    • Author(s)
      HENDRA Andi、KANAZAWA Yasushi
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E104.D Issue: 11 Pages: 1992-2001

    • DOI

      10.1587/transinf.2021EDP7076

    • NAID

      130008110015

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2021-11-01
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Presentation] 支配的平面を用いたスケールの異なる点群での位置合わせ2023

    • Author(s)
      永田 青鳥,金澤 靖
    • Organizer
      動的画像処理実利用化ワークショップ (DIA2023)
    • Related Report
      2022 Annual Research Report
  • [Presentation] 果実の近赤外波長域における反射光の特性を用いたウェアラブルな糖度系開発2023

    • Author(s)
      小出 佑,芦田 和毅,金澤 靖
    • Organizer
      情報処理学会第85回全国大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Accuracy Improvement of Depth Estimation from Single Image by Using 3rd Player in GAN2021

    • Author(s)
      Andi Hendra, Yasushi Kanazawa
    • Organizer
      The 7th IIEEJ International Conference on Image Electronics and Visual Computing (IEVC2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] UAV搭載マルチスペクトルカメラによる柿圃場における相対糖度のリモート推定2021

    • Author(s)
      大関 克弥,金澤 靖
    • Organizer
      電子情報通信学会パターン認識とメディア理解研究会
    • Related Report
      2020 Research-status Report
  • [Presentation] 3D reconstruction and pattern recognition methods for the search activity of missing persons and lost items by tsunami2020

    • Author(s)
      Yasushi Kanazawa
    • Organizer
      ICSItech 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research / Invited

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi