Bayesian Troop-Target Detection, Tracking, and Prediction Using FOPEN-GMTI Radar

Award Information
Agency: Department of Defense
Branch: Defense Advanced Research Projects Agency
Contract: W31P4Q-05-C-R178
Agency Tracking Number: 04SB1-0415
Amount: $5,021,730.00
Phase: Phase II
Program: SBIR
Awards Year: 2005
Solicitation Year: 2004
Solicitation Topic Code: SB041-024
Solicitation Number: 2004.1
Small Business Information
500 West Cummings Park - Ste 3000, Woburn, MA, 01801
DUNS: 859244204
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: Y
Principal Investigator
 Adel El-Fallah
 Associate Group Leader
 (781) 933-5355
Business Contact
 Raman Mehra
Title: President
Phone: (781) 933-5355
Research Institution
The "troop-target" problem of automatic detection, tracking, and prediction of the formations of dismounted ground troops concealed in foliage, using FOPEN-GMTI radars introduces challenges well beyond those encountered in more conventional group-target problems. AD HOC troop formations are considerably more amorphous and unpredictable and they must be deduced from the constituent individuals. Yet these individuals may be small in number, may rapidly change direction and speed, can be widely dispersed, and will usually form no predictable pattern. We address this problem with a theoretically rigorous generalization of the constant-gain Kalman filter to the multitarget domain. The resulting PHD filter propagates a first-order multitarget moment of the multitarget posterior distribution, and first detects and tracks the over-all bulk behavior of a formation. What is being tracked at any time is an estimate of the geographical shape and density of the troop formation. Phase I showed the feasibility assessment for this PHD "bulk" tracking, and demonstrated: (1) successful bulk troop tracking, (2) considerable improvements in CROSS-RANGE accuracy when using two sensors with suitable triangulation geometry, (3) successful inference of troop parameters, and (4) successful formation typing (patrol, skirmish, bivouac, ambush, etc.) inferred from the estimated troop parameters. Phase II emphasis will be on more realistic implementations of the algorithms that include realistic sensor models, higher clutter densities, and hybrid tracking of an individual target and troop-target. The Phase II results will be examined by LM-Orincon with the goal of a Phase III delivery to FORESTER, providing a realistic and concrete Phase III technology transition path into FORESTER and potentially in the Army Future Combat Systems (FCS) program. The project team includes Dr. Ronald Mahler of Lockheed Martin. Lockheed Martin will provide both technical and commercialization support in the application of detection/tracking technologies.

* Information listed above is at the time of submission. *

Agency Micro-sites

SBA logo
Department of Agriculture logo
Department of Commerce logo
Department of Defense logo
Department of Education logo
Department of Energy logo
Department of Health and Human Services logo
Department of Homeland Security logo
Department of Transportation logo
Environmental Protection Agency logo
National Aeronautics and Space Administration logo
National Science Foundation logo
US Flag An Official Website of the United States Government