USA flag logo/image

An Official Website of the United States Government

Efficient Multitarget Particle Filters for Ground Target Tracking and…

Award Information

Agency:
Department of Defense 		Branch:
Air Force 		Award ID:
67732 		Program Year/Program:
2005 / SBIR
Agency Tracking Number:
F041-204-0644 		Solicitation Year:
N/A 		Solicitation Topic Code:
N/A 		Solicitation Number:
N/A
Small Business Information
Numerica Corporation
4850 Hahns Peak Drive Suite 200 Loveland, CO -
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
 
Phase 2
Fiscal Year: 2005
Title: Efficient Multitarget Particle Filters for Ground Target Tracking and Classification
Agency / Branch: DOD / USAF
Contract: FA8650-05-C-1805
Award Amount: $731,560.00
 

Abstract:

Many factors make the ground target tracking problem decidedly nonlinear and non-Gaussian. Some of these factors include the relatively poor angular accuracy of GMTI sensors, the presence of persistent clutter and target obscuration, and the complexity of target maneuvers. Because these difficulties can lead to a multimodal posterior density, a Bayesian filtering solution is more appropriate than a point estimate. Recently, the particle filter has emerged as a Bayesian inference technique that is both powerful and simple to implement. In Phase I, we established both the feasibility and necessity of using multiple-target particle filters when two or more tracks are linked through measurement contention. We also developed an efficient way to implement these filters by adaptively managing the type of particle filters, the number of particles, and the enumeration of hypotheses during data association. In Phase II, we propose to transition our Phase I prototype into a fully functional particle filter-based ground target tracker/classifier with commercial potential. The most challenging aspects of this transition are (i) the inclusion of feature data to perform joint tracking/classification, (ii) the development of a particle filter-based track initiation method, and (iii) the design of an efficient importance sampling scheme.

Principal Investigator:

Shawn M. Herman
Research Scientist II
9704198343
smherman@numerica.us

Business Contact:

Jeff Poore
Vice President / COO
9704198343
jbpoore@numerica.us
Small Business Information at Submission:

NUMERICA CORP.
PO Box 271246 Fort Collins, CO 80527

EIN/Tax ID: 841349484
DUNS: N/A
Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No