Semantic Labeling in Remote Sensing Corpora Using Feature Fusion-Based Enhanced Global Convolutional Network with High-Resolution Representations and Depthwise Atrous Convolution.
Teerapong PanboonyuenKulsawasd JitkajornwanichSiam LawawirojwongPanu SrestasathiernPeerapon VateekulPublished in: Remote. Sens. (2020)
Keyphrases
- remote sensing
- feature fusion
- high resolution
- image processing
- convolutional network
- multispectral
- feature extraction
- satellite images
- multiple features
- convolutional neural networks
- image analysis
- high spatial resolution
- image fusion
- super resolution
- high frequency
- semantic information
- image data
- multi sensor
- supervised learning
- unsupervised learning
- training data
- data sets
- low level features
- high quality
- active learning