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

2020 Fiscal Year Research-status Report

Generative Adversarial Networks Based Multi-Sensor Remote Sensing Image Translation for Disaster Damage Mapping

Research Project

Project/Area Number 19K20308
Research InstitutionInstitute of Physical and Chemical Research

Principal Investigator

He Wei  国立研究開発法人理化学研究所, 革新知能統合研究センター, 研究員 (10819387)

Project Period (FY) 2019-04-01 – 2022-03-31
Keywordsinpainting / flood area detection
Outline of Annual Research Achievements

Summary of Research achievement. The method to simulate optical images from SAR has been developped; deep learning methods to detect flood area and debris flow area have been develpped. The related publications include 1 paper accepted by , 1 paper accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence, 1 paper accpepted by IEEE transactions on image processing, 1 papers accepted by IEEE transactions on geoscience and remote sensing, and 1 paper accepted by IEEE Geoscience and Remote Sensing Maganize.

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

For this project, I have finished the related deep learning/machine learning methods for flood area and debris flow area detection. The next step is to develop the efficient system for the application. On the basis of this project, the publications include 1 paper accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence, 1 paper accpepted by IEEE transactions on image processing, 1 papers accepted by IEEE transactions on geoscience and remote sensing, and 1 paper accepted by IEEE Geoscience and Remote Sensing Maganize.

Strategy for Future Research Activity

1. Develop efficient system for the disaster response application.
2. Promote more general image translation methods, by considering neural architecture search for the optimization of the light model.
3. Target at more challenging journals/conferences such IEEE Transactions on Pattern Analysis and Machine Intelligence and CVPR.

Causes of Carryover

Due to the COVID-2019, the conference traveling has been canceled, and delayed to the next year.

  • Research Products

    (4 results)

All 2021 2020

All Journal Article (4 results)

  • [Journal Article] Interpretable Hyperspectral Artificial Intelligence: When nonconvex modeling meets hyperspectral remote sensing2021

    • Author(s)
      Hong Danfeng、He Wei、Yokoya Naoto、Yao Jing、Gao Lianru、Zhang Liangpei、Chanussot Jocelyn、Zhu Xiaoxiang
    • Journal Title

      IEEE Geoscience and Remote Sensing Magazine

      Volume: 1 Pages: 2~37

    • DOI

      10.1109/MGRS.2021.3064051

  • [Journal Article] Non-local Meets Global: An Integrated Paradigm for Hyperspectral Image Restoration2020

    • Author(s)
      He Wei、Yao Quanming、Li Chao、Yokoya Naoto、Zhao Qibin、Zhang Hongyan、Zhang Liangpei
    • Journal Title

      IEEE Transactions on Pattern Analysis and Machine Intelligence

      Volume: 1 Pages: 1~1

    • DOI

      10.1109/TPAMI.2020.3027563

  • [Journal Article] Breaking Limits of Remote Sensing by Deep Learning From Simulated Data for Flood and Debris-Flow Mapping2020

    • Author(s)
      Yokoya Naoto、Yamanoi Kazuki、He Wei、Baier Gerald、Adriano Bruno、Miura Hiroyuki、Oishi Satoru
    • Journal Title

      IEEE Transactions on Geoscience and Remote Sensing

      Volume: 1 Pages: 1~15

    • DOI

      10.1109/TGRS.2020.3035469

  • [Journal Article] Hyperspectral Image Compressive Sensing Reconstruction Using Subspace-Based Nonlocal Tensor Ring Decomposition2020

    • Author(s)
      Chen Yong、Huang Ting-Zhu、He Wei、Yokoya Naoto、Zhao Xi-Le
    • Journal Title

      IEEE Transactions on Image Processing

      Volume: 29 Pages: 6813~6828

    • DOI

      10.1109/TIP.2020.2994411

URL: 

Published: 2021-12-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi