Optimizing the ground sample collection with cost-sensitive active learning for tree species classification using hyperspectral images.
Claudio PerselloMichele DalponteTerje GobakkenErik NæssetPublished in: IGARSS (2013)
Keyphrases
- hyperspectral images
- hyperspectral data
- hyperspectral
- remote sensing
- hyperspectral imagery
- multispectral
- machine learning
- image classification
- classification accuracy
- infrared
- pattern recognition
- target detection
- feature vectors
- support vector machine
- feature set
- sample size
- training set
- feature space
- similarity measure
- computer vision
- data sets