With millions of miles of pipeline across the country, protecting critical fuel supplies is more difficult than ever.

The U.S. government wanted to develop an algorithmic solution to detect and classify objects within a certain range of energy pipelines—and make monitoring more efficient and secure. Thanks to advances in satellite capabilities and drone technologies, the necessary aerial imagery was abundant. But automatically differentiating between downed tree limbs and enemy vehicles in those images required a new approach to the problem.

With an Analytics Starter Pack from Topcoder, the government client received on-demand access to more than 100 data scientists who worked to develop algorithmic solutions that detect and evaluate potential risks. A crowd-powered delivery team managed all logistics during the three-week project, including testing the 500+ possible solutions submitted.

The winning solutions rapidly process tens of thousands of images and tag objects with an appropriate threat level. Today, the final algorithmic solution delivered by Topcoder is also being used to drive other government research in planetary satellite classification, Mars reconnaissance, federal disaster response and recovery, and beyond.

Data Scientists
139
Submissions
549
Winning Solutions
5
Duration
3 Weeks