SBIR/STTR Award attributes
The US Army is updating the capabilities of its combat fleet with its Next Generation Combat Vehicle (NGCV). A core component of the NGCV effort is upgrading the sensing and situational awareness capabilities of combat vehicles, aided by higher resolution electro-optical, infrared, and thermal cameras that can be mounted 360 degrees around the vehicle. Existing Aided and Automatic Target Detection and Recognition (ATD/ATR) technology has trouble processing video imagery from on-the-move ground vehicles because these algorithms rely on stationary camera inputs. To mitigate the problems associated with moving cameras and background motion relative to the sensor, we must model both the camera pose and scene structure to enable existing ATD/ATR algorithms to work on moving future combat vehicles. Our Low-SWAP-C Background Estimation Labeling System (LABELS) provides a fast and accurate stabilization method that will enable legacy ATD/ATR algorithms to function using imagery collected by on-the-move vehicles in real-time. Our approach will localize and map images to a 3-D model of the surroundings that take advantage of the vehicle motion and improve the operators or analyst’s situational awareness. By understanding the egomotion of each camera and its orientation at any moment, LABELS will provide existing ATD/ATR algorithms with a stable model that enables them to detect and track targets of interest in real time.
