| Project/Area Number |
16K16221
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Environmental and ecological symbiosis
|
|---|
| Research Institution | The University of Shiga Prefecture (2018)
Niigata University (2016-2017) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | Unmanned aerial vehicle / 動画像処理 / 画像復元 / 画像処理 / 浅海域 / メディアンフィルタ / ゆらぎ低減 / 深層学習 / 環境推定 / UAV / 画像計測 / 干潟 / 海洋環境推定 / 多クラス対応型領域拡張法 / パノラマ画像 / 画像解析 / 海洋保全 / 情報工学 |
|---|
| Outline of Final Research Achievements |
We have proposed a method to reduce sea level fluctuation that performs smoothing processing with median filter in the time direction in an aerial image including a shallow sea area, and it has become possible to generate ortho images of the sea level and the water surface that were difficult until now .
We also proposed a method of identifying tidal flats using aerial images. In the proposed method, data sets were newly created in the sandbox, water surface, and other three classes, and learning and identification were performed. As a result, 89.6% of the water surface, 91.2% of the sandbox, and 94.0% of others were obtained with sufficient accuracy, indicating the possibility of landform identification.
|
| Academic Significance and Societal Importance of the Research Achievements |
浅海域が含まれる空撮画像において，これまで困難だった海面や水面部のオルソ画像生成が実現したことにより，測量や環境調査など様々な分野でのUAVの活用の範囲が広がることが期待される．
|
