Fiscal Year:
2005
Title:
Automatic Generation of Natural and Urban Scenes
Agency / Branch:
DOD / USAF
Contract:
FA8651-05-C-0228
Award Amount:
$99,209.00
Abstract:
The development and evaluation of autonomous precision strike weaponry requires high fidelity image simulation. Data collections involving moving platforms are difficult to schedule and costly to perform. Furthermore, live data collections where the weapon is being guided by an autonomous target acquisition (ATA) system cannot be performed in dense urban environments. The only solution is to develop high fidelity image and navigation simulations of realistic operating environments. Our proposed system is called Automatic Generation of Natural and Urban Scenes (AGNUS). AGNUS takes as input a collection of user specified parameters describing the variability of the desired scene (such as building and population density, street sizes, etc.) and any available mapping information such as Digital Feature Analysis Data and Digital Terrain Elevation Data. AGNUS then generates a metadata representation describing the scene. This meta-information is converted into an attributed geometry model using SAIC's INSSITE tool and output in CHAMP/FLITES data format for image simulation. The seamless combination of these technologies allows IR image generation of complex scenes containing large-scale urban environments. This allows AFRL to evaluate candidate ATA algorithms as two datasets (one for training and one for testing) can be generated that have comparable statistics but are both topologically and geometrically different.
Principal Investigator:
Mark R. Stevens
Principal Scientist
6174913474
mstevens@cra.com
Small Business Information at Submission:
CHARLES RIVER ANALYTICS, INC.
625 Mount Auburn Street Cambridge, MA 02138
EIN/Tax ID:
042803764
DUNS:
N/A
Number of Employees:
Woman-Owned:
No
Minority-Owned:
No
HUBZone-Owned:
No