Improving land-cover classification accuracy with a patch-based convolutional neural network: data augmentation and purposive sampling.
Hunsoo SongYongil KimPublished in: JURSE (2019)
Keyphrases
- land cover
- classification accuracy
- network architecture
- remote sensing
- remote sensing images
- multispectral
- change detection
- land cover classification
- satellite images
- geographic information systems
- remote sensing data
- supervised classification
- remotely sensed images
- environmental variables
- neural network
- feature selection
- training data
- remotely sensed data
- databases
- machine learning
- urban growth
- unsupervised learning
- image registration
- high quality
- urban areas