Remote Sensing Feature Selection by Kernel Dependence Measures.
Gustavo Camps-VallsJoris M. MooijBernhard SchölkopfPublished in: IEEE Geosci. Remote. Sens. Lett. (2010)
Keyphrases
- remote sensing
- feature selection
- hilbert schmidt independence criterion
- change detection
- multispectral
- feature space
- support vector
- remote sensing imagery
- remote sensing images
- image analysis
- image processing
- satellite images
- hyperspectral
- remote sensing data
- high resolution
- automatic image registration
- satellite imagery
- image fusion
- high spatial resolution
- remotely sensed imagery
- remotely sensed
- multi spectral images
- machine learning
- kernel function
- mutual information
- feature extraction
- land cover
- satellite data
- remote sensing image processing
- environmental sciences
- dimensionality reduction
- remotely sensed images
- hyperspectral imagery
- digital image analysis
- feature set
- hyperspectral remote sensing
- remote sensed images
- geographical information systems
- land cover classification
- support vector machine
- hyperspectral imaging
- remotely sensed data
- high quality