Extending deep learning approaches for forest disturbance segmentation on very high-resolution satellite images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985939%3A_____%2F21%3A00547965" target="_blank" >RIV/67985939:_____/21:00547965 - isvavai.cz</a>

Výsledek na webu

<a href="http://hdl.handle.net/11104/0324138" target="_blank" >http://hdl.handle.net/11104/0324138</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1002/rse2.194" target="_blank" >10.1002/rse2.194</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Extending deep learning approaches for forest disturbance segmentation on very high-resolution satellite images

Popis výsledku v původním jazyce

We used satellite imagery of very high resolution in visual spectra represented as pansharpened images (RGB channels). When predicting forest damage, we obtained accuracies higher than 90% on test data for recognition of both windthrow areas and damaged trees impacted by bark beetles. A comparative analysis indicated that the DCNN-based approach outperforms traditional pixel-based classification methods (AdaBoost, random forest, support vector machine, quadratic discrimination) by at least several percentage points. DCNNs can learn a specific pattern of the area of interest and thus yield fewer false positive decisions than pixel-based algorithms. The ability of DCNNs to generalize makes them a good tool for delineating smooth and ill-defined boundaries of damaged forest areas, such as windthrow patches.

Název v anglickém jazyce

Extending deep learning approaches for forest disturbance segmentation on very high-resolution satellite images

Popis výsledku anglicky

We used satellite imagery of very high resolution in visual spectra represented as pansharpened images (RGB channels). When predicting forest damage, we obtained accuracies higher than 90% on test data for recognition of both windthrow areas and damaged trees impacted by bark beetles. A comparative analysis indicated that the DCNN-based approach outperforms traditional pixel-based classification methods (AdaBoost, random forest, support vector machine, quadratic discrimination) by at least several percentage points. DCNNs can learn a specific pattern of the area of interest and thus yield fewer false positive decisions than pixel-based algorithms. The ability of DCNNs to generalize makes them a good tool for delineating smooth and ill-defined boundaries of damaged forest areas, such as windthrow patches.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10618 - Ecology

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Remote Sensing in Ecology and Conservation

ISSN

2056-3485

e-ISSN

2056-3485

Svazek periodika

7

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

14

Strana od-do

355-368

Kód UT WoS článku

000611728600001

EID výsledku v databázi Scopus

2-s2.0-85099971758