Skip to content

This repository supports the practical aspect of my computer science research on water bodies detection in satellite imagery

License

Notifications You must be signed in to change notification settings

nzamski/WaterRecognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

81 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WaterRecognition

This repository contains all programs, models and results files needed for my research. Basically, there are 3 types of models built here (from high complexity to low):

  • Deep Learning Neural Networks (including CNNs)
  • Machine Learning Models (Logistic Regression & SGD)
  • Traditional computer vision algorithm (Otsu's Method)

The dataset used for training and testing the models is publicly accesible. This dataset contains pairs of source images (satellite images) and mask images (segmented maps in white and black, categorized by water and non-water, respectively).

About

This repository supports the practical aspect of my computer science research on water bodies detection in satellite imagery

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published