Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification.
Shaohui MeiJingyu JiQianqian BiJunhui HouQian DuWei LiPublished in: IGARSS (2016)
Keyphrases
- hyperspectral
- spatial information
- hyperspectral data
- hyperspectral images
- hyperspectral imagery
- spatial resolution
- pixel classification
- hyperspectral image classification
- band selection
- multispectral
- spatial features
- remote sensing
- infrared
- spectral bands
- convolutional neural networks
- hyperspectral imaging
- hyperspectral remote sensing
- land cover classification
- spectral imagery
- target detection
- image data
- spatial relations
- spectral data
- information content
- spatial relationships
- spectral resolution
- local binary pattern
- pattern recognition
- satellite images
- active learning
- random projections
- multi band
- classification accuracy
- remote sensing images
- image classification
- feature set
- discriminative ability
- image analysis
- spectral signatures
- color histogram
- feature vectors
- image retrieval
- feature space
- machine learning
- high spatial resolution
- co occurrence
- contextual information