Seeing Beyond the Patch: Scale-Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery based on Reinforcement Learning.
Yinhe LiuSunan ShiJunjue WangYanfei ZhongPublished in: CoRR (2023)
Keyphrases
- remote sensing imagery
- remote sensing
- semantic segmentation
- high resolution
- reinforcement learning
- change detection
- low resolution
- superpixels
- satellite images
- remote sensing images
- multispectral
- image patches
- super resolution
- remote sensing data
- weakly supervised
- hyperspectral
- image processing
- conditional random fields
- wavelet transformation
- state space
- image analysis
- scene classification
- high frequency
- object categories
- data sets
- maximum likelihood
- learning algorithm
- machine learning
- spatial information
- scale space
- higher order
- high quality