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

Realization of the Micro Population Census by Deep Learning Using Satellite Images in Developing Countries

Research Project

Project/Area Number 20H01483
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 07030:Economic statistics-related
Research InstitutionTokyo City University

Principal Investigator

AKIYAMA Yuki  東京都市大学, 建築都市デザイン学部, 教授 (60600054)

Co-Investigator(Kenkyū-buntansha) 宮崎 浩之  東京大学, 空間情報科学研究センター, 客員研究員 (80764414)
小川 芳樹  東京大学, 空間情報科学研究センター, 講師 (70794296)
宮澤 聡  東京大学, 空間情報科学研究センター, 協力研究員 (70834274)
菅澤 翔之助  慶應義塾大学, 経済学部(三田), 准教授 (50782380)
Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2023: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2022: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2020: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Keywords人口統計 / マイクロジオデータ / 開発途上国 / AI / 深層学習 / 衛星画像 / 建物用途 / 所得水準 / 現地調査
Outline of Research at the Start

本研究は主に複数時点の衛星画像と既存統計を用いて,アジアのメガシティである東京都市圏とバンコク都市圏を対象に,過去から現在に渡って都市とその周辺地域の人口の空間的分布を,その人々の所得水準も含めて時系列的かつ超高精細に(建物単位で)把握する手法を確立する.また深層学習を用いて超高精細な建物と人口の情報を分析することにより,今後都市化が進み人口が増加する可能性が高い地域の推定を可能にする技術も確立する.以上の技術が確立することにより,先進国のみならず開発途上国も含めた世界のあらゆる都市において建物単位という超高精細な人口分布を把握できるマイクロデータを開発するための手法を世界で初めて実現する.

Outline of Final Research Achievements

The objective of this study was to develop a method for understanding the spatial distribution of population, including their income levels, by individual building units in the Asian megacities of Tokyo and Bangkok. This result was achieved through the creation of an AI model capable of automatically extracting individual buildings from satellite images and estimating attributes such as building use, height, and income levels. The model demonstrated the capability to estimate these characteristics with a reasonable degree of accuracy. Furthermore, based on this model, a methodology was established for estimating the population within individual buildings. Prototypes of this data were subsequently developed for both Tokyo and Bangkok. This approach allows for a more detailed understanding of population distribution in urban spaces, facilitating improved urban planning and policy-making in densely populated areas.

Academic Significance and Societal Importance of the Research Achievements

学術的意義:本研究は,開発途上国の都市の人口分布把握に関する既存手法の限界を克服し,データサイエンスと地理学の知見を融合させた新しい人口把握技術を提案した.AIを活用し,高精細な人口統計モデルを構築することで,詳細な人口把握を実現し,国際的な都市研究に対する理解と深化に貢献した.
社会的意義:近年,急拡大する開発途上国の都市では既存の地図や統計の更新が実態に追いつかない問題がある.本研究の成果はインフォーマルセクターも含めた詳細な人口分布の推定を可能にすることで,適切な都市計画とスラム問題の対策に寄与し,持続可能な都市開発を支援する.また,本研究はSDGsの複数のGoalへの貢献も期待される.

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • Research Products

    (41 results)

All 2024 2023 2022 Other

All Int'l Joint Research (6 results) Journal Article (13 results) (of which Peer Reviewed: 12 results,  Open Access: 11 results) Presentation (19 results) (of which Int'l Joint Research: 4 results,  Invited: 6 results) Remarks (2 results) Funded Workshop (1 results)

  • [Int'l Joint Research] Thammasat University/Chulalongkorn University(タイ)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] NYU Shanghai(中国)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] Korea University/Incheon National University(韓国)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] Thammasat University(タイ)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] Thammasat University/Asian Institute of Technology/Chulalongkorn University(タイ)

    • Related Report
      2021 Annual Research Report
  • [Int'l Joint Research] Thammasat University/Asian Institute of Technology/Chulalongkorn University(タイ)

    • Related Report
      2020 Annual Research Report
  • [Journal Article] Locally adaptive spatial quantile smoothing: Application to monitoring crime density in Tokyo2024

    • Author(s)
      Takahiro Onizuka, Shintaro Hashimoto, Shonosuke Sugasawa
    • Journal Title

      Spatial Statistics

      Volume: 59 Pages: 100793-100793

    • DOI

      10.1016/j.spasta.2023.100793

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Geometric-based approach for linking various building measurement data to a 3D city model2024

    • Author(s)
      Ogawa Yoshiki、Sato Go、Sekimoto Yoshihide
    • Journal Title

      PLOS ONE

      Volume: 19 Issue: 1 Pages: 0296445-0296445

    • DOI

      10.1371/journal.pone.0296445

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Examining Model Generality of Instance Segmentation for Building Mapping in Satellite Images - Case Study for Tokyo and Bangkok2023

    • Author(s)
      Yamanotera Ryota、Akiyama Yuki、Miyazaki Hiroyuki
    • Journal Title

      IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium

      Volume: 2023 Pages: 5724-5727

    • DOI

      10.1109/igarss52108.2023.10282156

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Deep Learning Approach for Classifying the Built Year and Structure of Individual Buildings by Automatically Linking Street View Images and GIS Building Data2023

    • Author(s)
      Ogawa Yoshiki、Zhao Chenbo、Oki Takuya、Chen Shenglong、Sekimoto Yoshihide
    • Journal Title

      IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

      Volume: 16 Pages: 1740-1755

    • DOI

      10.1109/jstars.2023.3237509

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Label Freedom: Stable Diffusion for Remote Sensing Image Semantic Segmentation Data Generation2023

    • Author(s)
      Zhao Chenbo、Ogawa Yoshiki、Chen Shenglong、Yang Zhehui、Sekimoto Yoshihide
    • Journal Title

      IEEE Big Data

      Volume: 2023 Pages: 1022-1033

    • DOI

      10.1109/bigdata59044.2023.10386381

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach2023

    • Author(s)
      Chen, S., Ogawa, Y., Zhao, C., & Sekimoto, Y.
    • Journal Title

      ISPRS Journal of Photogrammetry and Remote Sensing

      Volume: 195 Pages: 129-152

    • DOI

      10.1016/j.isprsjprs.2022.11.006

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] DEVELOPMENT OF DETAILED BUILDING DISTRIBUTION MAP TO SUPPORT SMART CITY PROMOTION -AN APPROACH USING SATELLITE IMAGE AND DEEP LEARNING?2022

    • Author(s)
      Okada K.、Nishiyama N.、Akiyama Y.、Miyazaki H.、Miyazawa S.
    • Journal Title

      ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

      Volume: X-4/W3-2022 Pages: 189-196

    • DOI

      10.5194/isprs-annals-x-4-w3-2022-189-2022

    • Related Report
      2022 Annual Research Report 2021 Annual Research Report 2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] 空間情報を活用した自治体のプランニング~自治体におけるDXによるEBPM実現に向けた取り組み~2022

    • Author(s)
      秋山祐樹
    • Journal Title

      都市計画

      Volume: 71(3) Pages: 84-87

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Accuracy of vacant housing detection models: an empirical evaluation using municipal and national census datasets2022

    • Author(s)
      Sayuda, K., Hong, E., Akiyama, Y., Baba, H., Tokudomi, T., Akatani, T.
    • Journal Title

      Transactions in GIS

      Volume: forthcoming Issue: 7 Pages: 3003-3027

    • DOI

      10.1111/tgis.12992

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Development of Estimation Method for Building Structure Using Open Data and Statistics2022

    • Author(s)
      Takeda, N., Furuya, T. and Akiyama, Y.
    • Journal Title

      IGARSS 2022 Proceedings

      Volume: 2022 Pages: 2438-2441

    • DOI

      10.1109/igarss46834.2022.9883801

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Adaptively robust geographically weighted regression2022

    • Author(s)
      Sugasawa Shonosuke、Murakami Daisuke
    • Journal Title

      Spatial Statistics

      Volume: 48 Pages: 100623-100623

    • DOI

      10.1016/j.spasta.2022.100623

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Development of current estimated household data and agent-based simulation of the future population distribution of households in Japan2022

    • Author(s)
      Kajiwara Kento、Ma Jue、Seto Toshikazu、Sekimoto Yoshihide、Ogawa Yoshiki、Omata Hiroshi
    • Journal Title

      Computers, Environment and Urban Systems

      Volume: 98 Pages: 101873-101873

    • DOI

      10.1016/j.compenvurbsys.2022.101873

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Detection of River Plastic Using UAV Sensor Data and Deep Learning2022

    • Author(s)
      Maharjan Nisha、Miyazaki Hiroyuki、Pati Bipun Man、Dailey Matthew N.、Shrestha Sangam、Nakamura Tai
    • Journal Title

      Remote Sensing

      Volume: 14 Issue: 13 Pages: 3049-3049

    • DOI

      10.3390/rs14133049

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] 空間情報 × AI が拓く新しい空間情報科学分野の研究への挑戦2024

    • Author(s)
      秋山祐樹
    • Organizer
      GISA/GeoAI Seminar 2024’ Spring「GeoAIからみた人流データの表と裏」
    • Related Report
      2023 Annual Research Report
    • Invited
  • [Presentation] Examining Model Generality of Instance Segmentation for Building Mapping in Satellite Images - Case Study for Tokyo and Bangkok2023

    • Author(s)
      Yamanotera, R., Akiyama, Y. and Miyazaki, H.
    • Organizer
      IGARSS 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 衛星画像と所得に関する統計情報を用いた建物単位の所得水準の推定2023

    • Author(s)
      山野寺瞭太, 秋山祐樹, 宮崎浩之, 宮澤聡
    • Organizer
      CSIS DAYS 2023
    • Related Report
      2023 Annual Research Report
  • [Presentation] 航空写真を活用した開発適地の自動抽出技術の開発2023

    • Author(s)
      堀内仁, 山野寺瞭太, 秋山祐樹
    • Organizer
      第68回土木計画学研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Exploring Building Height Estimation Methods and Their Applications in Micro-Scale Population Data Analysis2023

    • Author(s)
      Maneepong, K. and Akiyama. Y.
    • Organizer
      ACRS 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Estimation of Income Levels per Building Unit Using Satellite Image and Income Statistics2023

    • Author(s)
      Yamanotera, R., Akiyama. Y., Miyazaki, H. and Miyazawa, S.
    • Organizer
      ACRS 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 衛星画像と所得に関する統計情報を用いた建物単位の所得水準の推定2023

    • Author(s)
      山野寺瞭太, 秋山祐樹, 宮﨑浩之
    • Organizer
      第32回地理情報システム学会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 深層学習を用いた衛星画像からの建物抽出モデルの外挿による開発途上国の建物データ整備2023

    • Author(s)
      山野寺瞭太, 秋山祐樹, 宮﨑浩之
    • Organizer
      土木学会第78回年次学術講演会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 建物単位の推計人口を用いた大規模災害時における経済的被害評価手法の開発2023

    • Author(s)
      武田直弥, 秋山祐樹, 古谷貴史
    • Organizer
      CSIS DAYS 2023
    • Related Report
      2023 Annual Research Report
  • [Presentation] 水害危険地域における住宅への被害評価と防災移転の最適化手法の開発2023

    • Author(s)
      齋藤開, 武田直弥, 秋山祐樹
    • Organizer
      第68回土木計画学研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 世帯推計データを用いた大規模災害時における経済的被害評価手法の開発2023

    • Author(s)
      武田直弥, 秋山祐樹, 古谷貴史
    • Organizer
      第32回地理情報システム学会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Research for DXing Municipal Decision Making Using Urban Spatial Information and AI to Realize a Better Life2023

    • Author(s)
      Akiyama, Y.
    • Organizer
      ICGIS 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] 空間情報×AIが拓く新しい都市工学分野の研究への挑戦2023

    • Author(s)
      秋山祐樹
    • Organizer
      オオバ技術発表会2023
    • Related Report
      2023 Annual Research Report
    • Invited
  • [Presentation] 住宅地図と衛星画像を活用した建物高密度地域における建物データの開発2022

    • Author(s)
      山野寺瞭太, 岡田佳佑, 秋山祐樹, 宮崎浩之, 宮澤聡, 菅澤翔之助, 小川芳樹
    • Organizer
      CSIS DAYS 2022
    • Related Report
      2022 Annual Research Report
  • [Presentation] 豪雨災害における住宅への経済的被害評価2022

    • Author(s)
      吉成翔, 武田直弥, 秋山祐樹, 古谷貴史
    • Organizer
      CSIS DAYS 2022
    • Related Report
      2022 Annual Research Report
  • [Presentation] マイクロジオデータ × AI が拓く地理学の社会実装2022

    • Author(s)
      秋山祐樹
    • Organizer
      G空間EXPO2022 日本地理学会主催シンポジウム「地理学の社会実装」
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] 官民の空間情報を結集した自治体DXへの取組とその課題2022

    • Author(s)
      秋山祐樹
    • Organizer
      日本写真測量学会関西支部 第112回空間情報話題交換会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] 都市・産業研究における空間情報の可能性2022

    • Author(s)
      秋山祐樹
    • Organizer
      日本建築学会 都市と産業WG 公開研究会#1
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] 住宅地図と衛星画像を活用した建物高密度地域における建物データの開発2022

    • Author(s)
      山野寺瞭太・岡田佳佑・秋山祐樹・宮崎浩之・宮澤聡・菅澤翔之助・小川芳樹
    • Organizer
      CSIS DAYS 2022
    • Related Report
      2021 Annual Research Report 2020 Annual Research Report
  • [Remarks] 秋山祐樹ウェブサイト

    • URL

      https://akiyama-lab.jp/yuki/

    • Related Report
      2023 Annual Research Report 2022 Annual Research Report
  • [Remarks] 東京都市大学秋山研究室ウェブサイト

    • URL

      https://usis.jp/

    • Related Report
      2023 Annual Research Report
  • [Funded Workshop] Joint seminar between Akiyama lab at TCU and Guan lab at SNU2023

    • Related Report
      2023 Annual Research Report

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi