Created by Golan Levin, David Newbury, and Kyle McDonald, with the assistance of Golan’s students at CMU, Irene Alvarado, Aman Tiwari, and Manzil Zaheer, Terrapattern is a visual search tool for satellite imagery. The project provides journalists, citizen scientists, and other researchers with the ability to quickly scan large geographical regions for specific visual features.
Terrapattern uses a deep convolutional neural network (DCNN), based on the ResNet (“Residual Network”) architecture developed by Kaiming He et al. The team trained a 34-layer DCNN using hundreds of thousands of satellite images labeled in OpenStreetMap, teaching the neural network to predict the category of a place from a satellite photo. In the process, their network learned which high-level visual features (and combinations of those features) are important for the classification of satellite imagery. They used 466 of the Nominatim categories (such as “airport”, “marsh”, “gas station”, “prison”, “monument”, “church”, etc.), with approximately 1000 satellite images per category. Their resulting model, which took 5 days to compute on an nVidia 980 GPU, has a top-5 error rate of 25.4%.
There has been many machine learning projects produced over the last year – especially drawing on computer vision. We see openCV and similar pixel based CV tools being replaced with neural networks. Even though the technology has been around for a few years now, thanks to the quick rise of opensource tools, artists are beginning to utilise techniques that were until now only available to the researchers. It is important to note that Terrapattern is not intended to allow users to locate their long lost teddy or other ‘personal’ searches since Terrapattern relies on map tiles to seek out similar items. This means that objects larger than 20m meters are much easier to find than (say) an iPhone. Nonetheless, it does shed considerable light on where this technology is heading, or even more worrisome what already exists, and just how easy it is with sufficient resources and computing power to locate pretty much anything left out in the open.
Here are some more example searches you can try with Terrapattern: baseball diamonds • semi-trailer trucks on highways • USAF bombers • cracked tarmac • bridges • fracking wells • swimming pools in the woods • Christmas tree farms • tennis courts • wastewater treatment pans • football stadium logos • overpasses • solar panels • scrap yards • transformer stations…