The Intelligence Advanced Research Projects Activity has launched a prize competition for interested participants to develop machine learning algorithms and automated methods to detect and categorize satellite imagery points of interest.
IARPA’s functional Map of the World challenge seeks to automate identification of land, building and facility use through recognition and categorization of objects from satellite imagery, the Office of the Director of National Intelligence said Tuesday.
“Going into the challenge, these will be the largest functionally annotated databases of satellite imagery made available to the public, and we are excited to see what outcomes will be revealed,” said HakJae Kim, a program manager at IARPA.
IARPA will offer predetermined point-of-interest categories and image sets to fMoW challenge participants from industry and academia, then the agency will ask them to produce an algorithm based on satellite-specific metadata.
Solvers have the chance to win up to $100,000 in cash prizes.
The challenge will run from July through December and winners will be announced in February 2018.