WRIGHT-PATTERSON AFB, Ohio, 9 March 2012.Photo analysis experts in the U.S. Office of the Director of National Intelligence in Washington are working with the U.S. Air Force Research Laboratory at Wright-Patterson Air Force Base, Ohio, to develop quick ways for intelligence analysts to determine the locations and camera angles of intelligence imagery and video as part of the Finder program of the U.S. Intelligence Advanced Research Projects Agency (IARPA).
Intelligence experts in the Air Force Research Lab awarded four contracts this week collectively worth $54.7 million for the first phase of the IARPA Finder program to develop technology that, with the aid of an intelligence analyst, geolocates an outdoor image or video from anywhere on the land surface of the world, via the use of publicly available information.
The Air Force Research Lab is managing the Finder research program on behalf of the IARPA Office of Incisive Analysis. IARPA is the research arm of the Office of the Director of National Intelligence.
The Air Force Research Lab has awarded Finder phase-one contracts to Applied Research Associates Inc. in Albuquerque, N.M.; the BAE Systems Electronic Systems sector in Burlington, Mass.; Science, Engineering, and Technology (SET) Corp. in Arlington, Va.; and ObjectVideo Inc. in Reston, Va. Applied Research won a $15.3 million contract, BAE Systems won a $13.8 million contract, SET won a $9.9 million contract, and ObjectVideo won a $15.6 million contract. The Finder program should extend through April 2016.
Even consumer-grade cameras today have the ability to tag images and videos with the location of the image on the Earth's surface. This tagging ability is called geolocation.
Some imagery, however, does not have a geolocation tag, which taxes intelligence analysts who typically want to know the location of the camera, image, or objects in the scene. Without geolocation tagging, analysts try to deduce as much as they can using reference data from sources such as overhead and ground-based images, digital elevation data, existing well-understood image collections, surface geology, geography, and cultural information. This approach is laborious, time-consuming, and sometimes unsuccessful.
Researchers have developed automated ways to use techniques such as large-scale ground-level image acquisition, crowd-sourcing, and sophisticated image matching, which tend to work best in well-traveled areas with large populations where the image or video of interest contains notable features such as mountains or buildings.
The Finder Program aims to build on this kind of existing research to augment the analyst's geolocation abilities, such as integrating the analyst's abilities with automated geolocation technologies; fusing open-source data; and expanding automated geolocation technologies to all terrain and large search areas.
The Finder program seeks to maintain the human analyst as an essential part of the process, as well as to understand the extent to which publicly available information can help intelligence analysts gelocate images and video.
For more information contact the Office of the Director of National Intelligence at http://www.dni.gov/, IARPA at www.iarpa.gov, Applied Research Associates at www.ara.com, BAE Systems Electronic Systems at www.baesystems.com, SET Corp. at www.setcorp.com, ObjectVideo at www.objectvideo.com, or the Air Force Research Lab at www.wpafb.af.mil/afrl.
