• Earth Lens running on an iPad showcasing the ability to edit highlighted objects.
  • Earth Lens running on an iPad showcasing the ability to count the number of objects idtentified in an arial image and filter them by object type.
  • Selecting multiple arial images from a gallery to upload for scanning by Earth Lens.
  • Bar graph showing count of various objects identified by object type.

Description

Earth Lens, a Microsoft Garage project, is an open source project for iPad that identifies, tracks, and analyzes objects in aerial imagery to assist in disaster relief and environmental conservation.

The app offers a host of features that humanitarians and environmental researchers can leverage to accelerate their analyses in agricultural, environmental, or disaster relief scenarios:

  • Automatically identify, classify, and label objects in satellite images, encircling like objects in color-coded bounding boxes
  • Count and aggregate objects identified by the machine learning model
  • Toggle classes on/off to focus in on specific objects
  • View images over time alongside a data visualization chart to identify trends and patterns in a Time Series mode
  • Use the app remotely, without an internet connection

Interested in trying Earth Lens? Check out the source code on GitHub, where you can also find instructions on how to build the iPad application and leverage the machine learning model that powers the project. You can learn more or provide feedback via GitHub.

READ THE BLOG POST

Meet the team

Garage Internship

Alex Jordache, Elsie Ju, Kelin Kaardal, Michelle Chen, Nelani Skantharajah, Seara Chen, and Yuchong Pan

 

Coaches: Andrii Kalinichenko, Hailey Musselman, Siddhant Mehta, and Tejbir Sodhana

Garage Internship

Vancouver, BC