An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series.
Charlotte PelletierSilvia ValeroJordi IngladaGérard DedieuNicolas ChampionPublished in: IGARSS (2016)
Keyphrases
- satellite images
- random forest
- land cover
- high resolution
- image features
- remote sensing
- urban areas
- multispectral
- change detection
- remote sensing images
- satellite imagery
- decision trees
- remotely sensed images
- feature set
- landsat tm
- digital elevation models
- ensemble methods
- remotely sensed
- multi label
- spatial resolution
- image classification
- base classifiers
- object recognition
- high quality
- computer vision
- hyperspectral
- image processing
- image analysis
- reinforcement learning
- high spatial resolution
- similarity measure
- feature selection