eduzhai > Applied Sciences > Engineering >

Automatic Dataset Builder for Machine Learning Applications to Satellite Imagery

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Nowadays the use of Machine Learning (ML) algorithms is spreading in thefield of Remote Sensing, with applications ranging from detection andclassification of land use and monitoring to the prediction of many natural oranthropic phenomena of interest. One main limit of their employment is relatedto the need for a huge amount of data for training the neural network, chosenfor the specific application, and the resulting computational weight and timerequired to collect the necessary data. In this letter the architecture of aninnovative tool, enabling researchers to create in an automatic way suitabledatasets for AI (Artificial Intelligence) applications in the EO (EarthObservation) context, is presented. Two versions of the architecture have beenimplemented and made available on Git-Hub, with a specific Graphical UserInterface (GUI) for non-expert users.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×