A Python library for land use classification based in satellite images.

666 commits | Last update: September 26, 2019

Cite this software

Choose a version:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a reference manager file format:
Download file

What Satsense can do for you

  • Provides a framework for performing land use classification on satellite images
  • Comes with easy to use Jupyter notebook examples
  • Provides an implementation of hand-crafted features commonly used for detecting deprived neighbourhoods in satellite images, like HoG, Lacunarity, NDXI, Pantex, Texton, SIFT
  • Will provide various metrics for measuring performance

Satsense is a Python library for land use classification, with a particular focus on deprived neighbourhood detection. However, many of the algorithms made available through Satsense can be applied in other domains. Detection of deprived neighbourhoods is a land use classification problem that is traditionally solved using hand crafted features like HoG, Lacunarity, NDXI, Pantex, Texton, and SIFT with very high resolution satellite images. One of the problems with assessing the performance of these kind of algorithms for this application, is that there is no easy to use open source reference implementation of such features, a problem that Satsense solves. In the future Satsense will also provide metrics to assess the performance. Satsense is built in a modular way which makes it easy to add your own hand-crafted feature or use deep learning instead of hand crafted features.

Read more
  • Image processing
  • Machine learning
Programming Language
  • Python
  • Apache-2.0
Source code

Participating organizations


  • Berend Weel
    Netherlands eScience Center
  • Elena Ranguelova
    Netherlands eScience Center
  • Bouwe Andela
    Netherlands eScience Center
Contact person
Bouwe Andela
Netherlands eScience Center

Information for page maintainers

OAI-PMH metadata:
citation metadata: