DeepAqua: Semantic segmentation of wetland water surfaces with SAR imagery using deep neural networks without manually annotated data.
Francisco J. PeñaClara HübingerAmir Hossein PayberahFernando JaramilloPublished in: Int. J. Appl. Earth Obs. Geoinformation (2024)
Keyphrases
- semantic segmentation
- sar imagery
- synthetic aperture radar
- conditional random fields
- superpixels
- target detection
- scene classification
- weakly supervised
- sar images
- object categories
- object classes
- natural images
- pairwise
- three dimensional
- image reconstruction
- object segmentation
- urban areas
- image classification
- computer vision
- segmentation algorithm
- object recognition
- feature selection