| 研究課題/領域番号 |
19K20308
|
|---|
| 研究機関 | 国立研究開発法人理化学研究所 |
|---|
研究代表者 |
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)
|
|---|
| 研究期間 (年度) |
2019-04-01 – 2022-03-31
|
| キーワード | inpainting / flood area detection |
|---|
| 研究実績の概要 |
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.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
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.
|
| 今後の研究の推進方策 |
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.
|
| 次年度使用額が生じた理由 |
Due to the COVID-2019, the conference traveling has been canceled, and delayed to the next year.
|
