Comparison of Automatic Classification Methods for Identification of Ice Surfaces from Unmanned-Aerial-Vehicle-Borne RGB Imagery

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F23%3A39920302" target="_blank" >RIV/00216275:25410/23:39920302 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.mdpi.com/2076-3417/13/20/11400" target="_blank" >https://www.mdpi.com/2076-3417/13/20/11400</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/app132011400" target="_blank" >10.3390/app132011400</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Automatic Classification Methods for Identification of Ice Surfaces from Unmanned-Aerial-Vehicle-Borne RGB Imagery

Popis výsledku v původním jazyce

This article describes a comparison of the pixel-based classification methods used to distinguish ice from other land cover types. The article focuses on processing RGB imagery, as these are very easy to obtained. The imagery was taken using UAVs and has a very high spatial resolution. Classical classification methods (ISODATA and Maximum Likelihood) and more modern approaches (support vector machines, random forests, deep learning) have been compared for image data classifications. Input datasets were created from two distinct areas: The Pond Skříň and the Baroch Nature Reserve. The images were classified into two classes: ice and all other land cover types. The accuracy of each classification was verified using a Cohen’s Kappa coefficient, with reference values obtained via manual surface identification. Deep learning and Maximum Likelihood were the best classifiers, with a classification accuracy of over 92% in the first area of interest. On average, the support vector machine was the best classifier for both areas of interest. A comparison of the selected methods, which were applied to highly detailed RGB images obtained with UAVs, demonstrates the potential of their utilization compared to imagery obtained using satellites or aerial technologies for remote sensing.

Název v anglickém jazyce

Comparison of Automatic Classification Methods for Identification of Ice Surfaces from Unmanned-Aerial-Vehicle-Borne RGB Imagery

Popis výsledku anglicky

This article describes a comparison of the pixel-based classification methods used to distinguish ice from other land cover types. The article focuses on processing RGB imagery, as these are very easy to obtained. The imagery was taken using UAVs and has a very high spatial resolution. Classical classification methods (ISODATA and Maximum Likelihood) and more modern approaches (support vector machines, random forests, deep learning) have been compared for image data classifications. Input datasets were created from two distinct areas: The Pond Skříň and the Baroch Nature Reserve. The images were classified into two classes: ice and all other land cover types. The accuracy of each classification was verified using a Cohen’s Kappa coefficient, with reference values obtained via manual surface identification. Deep learning and Maximum Likelihood were the best classifiers, with a classification accuracy of over 92% in the first area of interest. On average, the support vector machine was the best classifier for both areas of interest. A comparison of the selected methods, which were applied to highly detailed RGB images obtained with UAVs, demonstrates the potential of their utilization compared to imagery obtained using satellites or aerial technologies for remote sensing.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

Applied Science - Basel

ISSN

2076-3417

e-ISSN

2076-3417

Svazek periodika

13

Číslo periodika v rámci svazku

20

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

14

Strana od-do

11400

Kód UT WoS článku

001095934000001

EID výsledku v databázi Scopus

—