Sgformer: A Local and Global Features Coupling Network for Semantic Segmentation of Land Cover.
Liguo WengKai PangMin XiaHaifeng LinMing QianChangjie ZhuPublished in: IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2023)
Keyphrases
- semantic segmentation
- land cover
- global features
- remote sensing
- satellite images
- multispectral
- conditional random fields
- weakly supervised
- change detection
- image features
- superpixels
- remote sensing images
- supervised classification
- keypoints
- visual features
- geographic information systems
- scene classification
- feature vectors
- multiscale
- data sets
- classification method
- information extraction
- support vector machine
- high quality
- information retrieval