2021 Fiscal Year Final Research Report
Crown extraction and tree species classification of broadleaf forests using UAV aerial photography derived on leaf-on and -off seasons
Project/Area Number |
19K06143
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 40010:Forest science-related
|
Research Institution | Niigata University |
Principal Investigator |
|
Project Period (FY) |
2019-04-01 – 2022-03-31
|
Keywords | リモートセンシング / UAV / SfM / 落葉広葉樹林 / 樹種分類 / 樹冠 / 樹幹 / 落葉期 |
Outline of Final Research Achievements |
Several studies were performed on individual scale tree species classification, tree crown extraction, and tree stem extraction in broadleaf forests using UAV aerial imagery. In the tree species classification, object-based image classification was performed for natural forests consisting mainly of beech forests, and classification was successfully performed with a Kappa coefficient of 0.726. For individual scale crown extraction, we tried two methods: the valley following method and the lidR package. The accuracy of tree crown extraction was verified for each. For tree stem extraction, UAV aerial photography was conducted in a beech stand during the leaf-off season, and the reconstruction of tree stems was evaluated for several parameters. The direction of the camera (camera angle) was also considered in the tree stem extraction, and the reconstruction rate of tree trunks was higher when the oblique view was employed in addition to the nadir view.
|
Free Research Field |
森林リモートセンシング
|
Academic Significance and Societal Importance of the Research Achievements |
この研究ではUAVの利点がおおいに関係している。それは空間分解能の高さと柔軟な飛行時期の設定である。まず前者について,広葉樹を対象とするということは天然林を対象とすることになるが,それは単木スケールでのアプローチが必須であることを意味する。UAV空撮によってもたらされる高精細な画像データは単木スケールでの樹種分類や樹冠抽出におおいに貢献した。落葉期の画像取得は,雲の下を飛行することのできるUAV の利点であり,人工衛星,航空機では決して撮影することのできない画像が取得できた。樹幹抽出が可能になることにより,落葉期データ取得の意義を提示することができた。
|