Semi-/Weakly-Supervised Semantic Segmentation Method and Its Application for Coastal Aquaculture Areas Based on Multi-Source Remote Sensing Images - Taking the Fujian Coastal Area (Mainly Sanduo) as an Example.
Chenbin LiangBo ChengBaihua XiaoChenlinqiu HeXunan LiuNing JiaJinfen ChenPublished in: Remote. Sens. (2021)
Keyphrases
- segmentation method
- weakly supervised
- remote sensing images
- superpixels
- multi source
- data integration
- multispectral
- change detection
- remote sensing
- object segmentation
- information fusion
- data fusion
- image segmentation
- active contours
- multiple sources
- segmentation algorithm
- conditional random fields
- energy function
- domain specific
- relation extraction
- data sources
- semi supervised
- semantic similarity
- shape prior
- data sets
- medical images
- higher order
- input image
- multiscale
- database
- semantic information
- natural images
- viewpoint
- watershed segmentation