Applying a deep learning pipeline to classify land cover from low-quality historical RGB imagery.
Harold N. EysterBrian BeckagePublished in: PeerJ Comput. Sci. (2024)
Keyphrases
- low quality
- deep learning
- land cover
- satellite imagery
- remote sensing data
- remote sensing
- high quality
- multispectral
- change detection
- unsupervised learning
- satellite images
- remote sensing images
- supervised classification
- image data
- machine learning
- geographic information systems
- high resolution
- mental models
- computer vision
- image analysis
- spatial data
- color space
- weakly supervised
- data mining
- input image
- ground truth
- urban areas
- data model
- digital elevation models