Maxar Technologies' Radiant Solutions business has received a contract from the National Geospatial-Intelligence Agency to help expedite the development of machine learning algorithms designed to gather data from satellite images.
Radiant Solutions said Tuesday it will provide NGA access to high-resolution satellite images of at least 1 million labeled objects to help the agency launch the 2018 DIUx xView Detection Challenge with Defense Innovation Unit Experimental.
Under the challenge, commercial, academic and research organizations will leverage DigitalGlobe's 30-centimeter satellite images to train algorithms to perform automatic object detection in an effort to address critical global challenges and support humanitarian and national security missions.
“Access to satellite imagery at increasingly high spatial and temporal resolutions, coupled with rapid advances in machine learning algorithms for object detection, has created a disruptive opportunity for NGA and other agency customers to see, understand and anticipate humanitarian and defense activities at a global scale,“ said Tony Frazier, president of Radiant Solutions.
“Our vision is that xView becomes a trusted resource for accelerating open innovation in machine learning,“ added Frazier, a 2018 Wash100 recipient.
NGA has a Creative Commons Non Commercial License to use xView dataset that contains over 1 million labeled objects across 60 various object categories such as construction equipment, damaged buildings and tents.