LEDCNet: A Lightweight and Efficient Semantic Segmentation Algorithm Using Dual Context Module for Extracting Ground Objects from UAV Aerial Remote Sensing Images.
Xiaoxiang HanYiman LiuGang LiuQiaohong LiuPublished in: CoRR (2022)
Keyphrases
- lightweight
- segmentation algorithm
- remote sensing images
- object segmentation
- automatic segmentation
- remote sensing
- change detection
- multispectral
- satellite images
- input image
- marked point processes
- image segmentation
- unsupervised segmentation
- graph cuts
- superpixels
- region growing
- shape prior
- segmentation method
- multiple objects
- segmented images
- watershed algorithm
- machine learning
- data sets
- infrared
- natural images
- wireless sensor networks
- active shape model
- man made
- image processing
- initial segmentation
- segmentation procedure