Terrapattern – Neural network visual search tool for satellite imagery

Category Javascript Members Processing People , , Posted on:

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%.

Sorry, this is Members Only content. Please Log-in.

Join us today by becoming a Member.

  • Archive: More than 3,500 project profiles, scores of essays, interviews and reviews.
  • Publish: Post your projects, events, announcements.
  • No Ads: No advertisements, miners, banners.
  • Education: Tutorials (beginners and advanced) with code examples, downloads.
  • Jobs Archive: Find employers who have recruited here in the past (over 800 jobs).
  • Discounts: Special offers and giveaways (events, books and media).

Become a Member

/++

SensorTape – 3D-aware dense sensor network on a roll of tape

Developed by the team at MIT Media Lab’s Responsive Environments group, SensorTape is a sensor network in a form factor of a tape that allows users to create large sensor networks.

Overloaded.supply – Superfluous (object) futures

Created by Ignacio Pérez (ECAL MID), Overloaded.supply is a critical tool that questions our models of manufacturing and consumption, exploiting the control of creation algorithms in order to interrogate current patterns of design, production and legislation.

basil.js – Computational and generative design using Adobe InDesign

Sorry, this is Members Only content. Please Log-in. Join us today by becoming a Member. Archive: More than 3,500 project profiles, scores of essays, interviews and reviews.Publish: Post your projects, events, announcements.No Ads: No advertisements, miners, banners.Education: Tutorials (beginners and advanced) with code examples, downloads.Jobs Archive: Find employers who have recruited here in the past…

IM Blanky – Self-positioning and representing blanket by Studio NMinusOne

Sorry, this is Members Only content. Please Log-in. Join us today by becoming a Member. Archive: More than 3,500 project profiles, scores of essays, interviews and reviews.Publish: Post your projects, events, announcements.No Ads: No advertisements, miners, banners.Education: Tutorials (beginners and advanced) with code examples, downloads.Jobs Archive: Find employers who have recruited here in the past…

/+

/++

Free Universal Construction Kit – a disruption aimed at the society / F.A.T. Lab

Sorry, this is Members Only content. Please Log-in. Join us today by becoming a Member. Archive: More than 3,500 project profiles, scores of essays, interviews and reviews.Publish: Post your projects, events, announcements.No Ads: No advertisements, miners, banners.Education: Tutorials (beginners and advanced) with code examples, downloads.Jobs Archive: Find employers who have recruited here in the past…