The National Geospatial-Intelligence Agency (NGA) has announced a $15,000 prize for an algorithm that can colorize panchromatic images in under 10 hours without human intervention.
The Rapid Image Colorization challenge seeks an algorithm that could colorize panchromatic grey scale images. The algorithm would help make a determination of the images and information collected by NGA more accurate, the challenge announcement explains.
The winning algorithm will be able to colorize images of up to 10 gigapixels within the 10-hour time frame.
“This goes well beyond simple colorization of an old black and white image in terms of the size of the image and the speed at which the colorization must be accomplished,” the challenge announcement said.
NGA aids US policymakers, warfighters and intelligence professionals through imagery and geospatial intelligence information.
“NGA is continually looking for innovative solutions to improve the delivery of GEOINT to our customers,” Christy Monaco, director of the office of ventures and innovation at NGA, said in a press release.
The deadline for submissions is Sept. 9. Individuals and private entities are able to enter, the announcement said.
The announcement was made on challenge.gov, a website that aids the federal government with innovation where federal agencies list challenge and prize competitions to solve problems related to agency missions.
The Rapid Image Colorization challenge is one of three challenges NGA has listed on Challenge.gov. In 2016, NGA awarded more than $200,000 for two challenges seeking data analysis technology and software to track story edits.