Skip to content

axin1301/Road_network_extraction_impoverished_counties

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is the code repository for Leveraging Deep Learning-based Road Extraction from Satellite Imagery for Socioeconomic Analysis in Impoverished Counties.

  1. pre-processing: identify the noisy or cloud covered satellite imagery.

  2. CoANet3: generate the road masks based on the CoANet model pretrained on the DeepGlobe dataset. Please refer to the original github repository for detailed description (CoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery).

  3. post-processing: concat the road masks and perform morthological operations.

  4. topology_construction: transform the road skeleton image into the road network shapefile. Please refer to the original github repository for detailed description (Learning to Generate Maps from Trajectories).

  5. process_RN2.py: transform the road network shapefile into graph and calculate the structural features.

  6. sample_roadnetwork: an example of the extracted road network in one impoverished county. The whole dataset is too large to upload here. We are trying to upload them elsewhere.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages