Machine Learning Classification and Accuracy Assessment from High-Resolution Images of Coastal Wetlands

High-resolution images obtained by multispectral cameras mounted on Unmanned Aerial Vehicles (UAVs) are helping to capture the heterogeneity of the environment in images that can be discretized in categories during a classification process. Currently, there is an increasing use of supervised machine...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 13; no. 18; p. 3669
Main Authors Martínez Prentice, Ricardo, Villoslada Peciña, Miguel, Ward, Raymond D., Bergamo, Thaisa F., Joyce, Chris B., Sepp, Kalev
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.09.2021
Subjects
Accuracy
Algorithms
Artificial intelligence
Cameras
Classification
Classifiers
comparison
Datasets
Ecology
Grasslands
Heterogeneity
High resolution
Image classification
Image resolution
K-nearest neighbors algorithm
KNN
Learning algorithms
Machine learning
Pixels
Plant communities
Random Forest
Remote sensing
Sea level
UAV
Unmanned aerial vehicles
Vegetation
Wetlands
Estonia
Online AccessGet full text

Cover

More Information
Summary:High-resolution images obtained by multispectral cameras mounted on Unmanned Aerial Vehicles (UAVs) are helping to capture the heterogeneity of the environment in images that can be discretized in categories during a classification process. Currently, there is an increasing use of supervised machine learning (ML) classifiers to retrieve accurate results using scarce datasets with samples with non-linear relationships. We compared the accuracies of two ML classifiers using a pixel and object analysis approach in six coastal wetland sites. The results show that the Random Forest (RF) performs better than K-Nearest Neighbors (KNN) algorithm in the classification of pixels and objects and the classification based on pixel analysis is slightly better than the object-based analysis. The agreement between the classifications of objects and pixels is higher in Random Forest. This is likely due to the heterogeneity of the study areas, where pixel-based classifications are most appropriate. In addition, from an ecological perspective, as these wetlands are heterogeneous, the pixel-based classification reflects a more realistic interpretation of plant community distribution.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs13183669