IARPA initiative aids satellite imagery automation

The Intelligence Advanced Research Projects Activity (IARPA) has launched a multi-year research effort officials said is designed to automate broad-area search of multi-source satellite imagery.

The Space-based Machine Automated Recognition Technique (SMART) program detects, monitors, and characterizes the progression of dynamic processes that include heavy construction or crop growth.

“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,” IARPA Program Manager Jack Cooper said. “SMART innovations in data fusion and machine learning techniques will enable automated broad area search at unprecedented temporal resolution and area coverage.”

Authorities indicated by augmenting the manual imagery analysis process with global-scale image processing and machine learning, SMART would provide timely discovery and robust monitoring of man-made and natural change.

IARPA has awarded SMART research contracts to teams led by Accenture Federal Services, Kitware, BlackSky Geospatial Solutions, and Systems & Technology Research.

IARPA invests in high-risk, high-payoff research programs to address some of the intelligence community’s most difficult challenges.

The four research thrusts within IARPA are Analysis, which seeks to maximize insight from information collected in a timely fashion; Anticipatory Intelligence – the development of technologies providing decision-makers with timely and accurate forecasts for a range of events relevant to national security; Collection – striving to improve the value of collected data from all sources dramatically; and Computing, which endeavors to counter new capabilities implemented by adversaries that could threaten the ability to operate freely and effectively in a networked world.