The Intelligence Advanced Research Projects Activity has awarded contracts to teams led by Accenture Federal Services, BlackSky Geospatial Solutions, Kitware and Systems & Technology Research to support a research program that aims to automate search and analysis of multisource satellite imagery.
A test and evaluation team for the Space-based Machine Automated Recognition Technique program assessed and selected the awardees through a broad agency announcement, IARPA said Wednesday.
The team includes experts from Mitre, Johns Hopkins University Applied Physics Laboratory, U.S. Geological Survey, Savannah River National Laboratory and NASA’s Goddard Space Flight Center.
The SMART program seeks to detect, characterize and monitor heavy construction, crop growth and other manmade and natural changes by automating space-based imagery analysis using machine learning and global-scale image processing.
“Current manual exploitation methods do not scale well with the data volumes we’re receiving, and there’s the problem of simultaneously analyzing data from past, current and future space-based systems,” said IARPA Program Manager Jack Cooper. "SMART innovations in data fusion and machine learning techniques will enable automated broad area search at unprecedented temporal resolution and area coverage."