CHERRY HILL, N.J., 13 Oct. 2007. The Defense Advanced Research Projects Agency (DARPA) and the National Geospatial-Intelligence Agency awarded Lockheed Martin a $4.9-million, 18-month program to use brain-inspired technologies to develop a system that will speed an image analyst's job by 100 times.
Called Object Recognition via Brain-Inspired Technology (ORBIT), the system will use electro-optical (EO), light detection and ranging (LIDAR), and brain-inspired technologies to automatically recognize objects in urban environments from ground and aerial surveillance.
ORBIT will fuse commercial airborne EO and LIDAR sensor data into a three-dimensional, photorealistic model of the landscape. Its brain-inspired object-recognition technology will automatically generate lists of recognizable imagery, like mailboxes and dumpsters.
Bilazarian said that ORBIT will determine if an area is of interest, propose potential recognitions of the area, and use previous recognitions to improve the accuracy of object recognition. Analysts could then use previously identified objects to track changes in landscape over time or show possible hostile activity: For example: An image associated with trash may contain an improvised explosive device.
ORBIT is part of DARPA's Urban Reasoning and Geospatial Exploitation Technology (URGENT) program.
ATL leads a team of experts in object recognition and extraction, three-dimensional rendering, and spatial analysis. Teammates include Numenta, SPADAC Inc., Signetron Inc., Teknowledge Corp., and the University of Pennsylvania.