An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing.
Emma Izquierdo-VerdiguierRaúl Zurita-MillaPublished in: Int. J. Appl. Earth Obs. Geoinformation (2020)
Keyphrases
- remote sensing
- random forest
- decision trees
- feature set
- multi spectral images
- multispectral
- remote sensing images
- remotely sensed
- change detection
- random forests
- hyperspectral images
- remote sensing imagery
- image analysis
- land cover classification
- high resolution
- support vector
- satellite images
- classification accuracy
- hyperspectral
- hyperspectral data
- satellite data
- remote sensing data
- pattern recognition
- image fusion
- image processing
- land cover
- feature extraction
- automatic image registration
- hyperspectral imagery
- decision tree learning algorithms
- ensemble methods
- remotely sensed data
- hyperspectral remote sensing
- support vector machine
- feature vectors
- feature space
- feature selection
- machine learning algorithms
- support vector machine svm
- image classification
- training set
- machine learning
- data sets
- remote sensed images
- earth observation
- supervised classification
- svm classifier
- benchmark datasets
- naive bayes
- supervised learning
- semi supervised
- neural network