I recently stumbled upon a great tool that I wanted to share with you – Terrapattern. It’s a stunning pattern recognition tool that uses deep convolutional neural networks helping people quickly scan extremely large geographical areas for specific visual features. It can for example help finding you: Ships, Buldings, Wave formations, Soccer Stadiums…
Here a short overview on what it is about and how it works:
Terrapattern is an interface for finding “more like this, please” in satellite photos. Simply click an interesting spot on Terrapattern’s map, and it will find other locations that look similar. Terrapattern is particularly useful for locating things that aren’t usually indicated on maps. We think Terrapattern is important because it’s open-source, open-access, and open-ended.
Terrapattern can be briefly described as “a visual search engine for satellite imagery”, “similar-image search for satellite photos”, or “a prototype for visual query-by-example in satellite imagery”. We hope it will help citizen scientists, humanitarians, journalists, and other curious people to discover “patterns of interest”.
Terrapattern is an open-source project created by a collaborative team of artists, creative technologists, and students. Terrapattern is not a company or startup; it is an experimental research prototype, developed in a university setting, whose purpose is to present a new way of exploring, understanding, and organizing the world. Terrapattern went live on May 24th, 2016.
You got curious? Check out these working examples for the follwing cities:
The best thing is, that Terrapattern is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License. Which means that the Terrapattern code and data files are free software and open source and can be downloaded and found on github.