Sometimes two dimensions just aren’t enough. The Intelligence Advanced Research Projects Activity is challenging coders to develop a way to accurately produce 3-D maps from satellite photos.
Beginning July 11, the Multi-View Stereo 3-D Mapping Challenge will have contestants from both industry and academia attempt to find an algorithm that can change satellite images to usable 3-D coordinate points.
With the information, IARPA hopes to develop a more accurate way to automatically find measurements.
“Numerous commercial satellites, including newly emerging CubeSats, cover large areas with higher revisit rates and deliver high-quality imagery in near real-time to customers,” IARPA Program Manager Hakjae Kim said in a statement. “Although the entire Earth has been, and continues to be, imaged multiple times, fully automated data exploitation remains limited.”
The challenge will offer a $100,000 prize pool, spread out between its two phases. The first part — the Explorer Contest — will begin next week and offer $14,000 worth of prizes. The more difficult Master Contest will begin in September, with winners announced in October.
IARPA has hosted two challenges before, including a contest to build a speech recognition system in a noisy environment.
Contact the reporter on this story via email: Jeremy.Snow@FedScoop.com. Follow him on Twitter @JeremyM_Snow. Sign up for the Daily Scoop — all the federal IT news you need in your inbox every morning — here: fdscp.com/sign-me-on.