A labor-free index-guided semantic segmentation approach for urban vegetation mapping from high-resolution true color imagery.
Peng ZhangCong LinShanchuan GuoWei ZhangHong FangPeijun DuPublished in: Int. J. Digit. Earth (2023)
Keyphrases
- high resolution
- semantic segmentation
- remote sensing
- urban areas
- low resolution
- satellite images
- superpixels
- super resolution
- conditional random fields
- label transfer
- color images
- scene classification
- weakly supervised
- object categories
- multispectral
- high quality
- pascal voc
- image processing
- image patches
- object class
- color histogram
- depth map
- color space
- multiscale
- object classes
- image set
- natural images
- object recognition
- test images
- long range
- bag of words
- topic models
- text classification
- face images