| Project/Area Number |
17K08034
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Agricultural environmental engineering/Agricultural information engineering
|
|---|
| Research Institution | Kindai University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
|
|---|
| Keywords | 深度画像 / ドローン / オプティカルフロー / 画像認識 / 騒音 / 害獣 / 画像 / 動物 / 情報システム / 人工知能 |
|---|
| Outline of Final Research Achievements |
We have been researching and developing an efficient autonomic capturing system for harmful animals using some kind of the imaging sensors such as a Kinect. This system can capture the harmful animals with high accuracy according to their spices and number using image which is captured with imaging sensors. In this research, we capture the image of the harmful animals form the upper air using the drone. In this case, extraction from wide range and noise of flying drone are some problems. So we make some experiments about both experimental factors such as the image from upper air and sound noise. We discuss possibility and effectiveness of the captured image from the upper air using drone. In addition, we have measured sound noise by the flying drone. From these experiments under the limited conditions such as gymnastic and so on, extraction of the harmful animals on each one meter is successful by the image captured from the upper air.
|
| Academic Significance and Societal Importance of the Research Achievements |
近年ドローンは個人の利用のみならず多くのビジネスにも利用されつつあり、検査及び監視にもその用途を広めつつある。本研究ではこのような背景から、害獣の撮像手法の新たなアプローチとして広視野角センサカメラとドローンを用いて対象物の背景からの抽出可能性を仮想環境での実験により検討した。この空撮画像の種々の検討により、実環境での空撮による害獣捕獲システムの開発のさらなる展開の一助とでき、一次産業のイノベーション化を加速する社会的意義は大きいと思われる。特にその成果としてドローンの飛行制御に関して特許１件（登録）、研究発表５件（１件は2020.5）となっている。
|
