Superpixel Partitioning of Very High Resolution Satellite Images for Large-Scale Classification Perspectives with Deep Convolutional Neural Networks.
Tristan PostadjianArnaud Le BrisClément MalletHichem SahbiPublished in: IGARSS (2018)
Keyphrases
- satellite images
- convolutional neural networks
- multispectral
- landsat tm
- remotely sensed
- remote sensing
- classification accuracy
- classification algorithm
- satellite imagery
- high resolution satellite images
- support vector
- change detection
- feature selection
- support vector machine
- multi spectral images
- data sets
- feature extraction
- pattern recognition
- image classification
- training set
- supervised classification
- urban areas
- feature vectors
- remote sensing images
- land cover
- hyperspectral
- support vector machine svm
- google earth
- neural network