You are here

Detection, Tracking and Classification of Multiple Targets using Advanced Beamforming and Classification Methods

Award Information
Agency: Department of Defense
Branch: Army
Contract: DAAE30-02-C-1058
Agency Tracking Number: A012-1116
Amount: $69,947.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: N/A
Solicitation Number: N/A
Timeline
Solicitation Year: N/A
Award Year: 2002
Award Start Date (Proposal Award Date): N/A
Award End Date (Contract End Date): N/A
Small Business Information
5412 Hilldale Court
Fort Collins, CO 80526
United States
DUNS: 035801864
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 M. Azimi-Sadjadi
 CEO
 (970) 226-6706
 infsyst@aol.com
Business Contact
 S. Sheedvash
Title: COO
Phone: (970) 226-6706
Email: infsyst@aol.com
Research Institution
N/A
Abstract

"The problem of detection, classification and tracking of multiple vehicles in battlefield situations is the focus of this Phase I research. Typically, multiple unattended sparse passive acoustic arrays are exploited to monitor, track and identify thepotential targets. Although, the present technology is capable of successfully detecting, tracking and classifying single targets, extension to multiple targets especially when they are closely spaced pose many technical difficulties. As a result, newschemes are needed to provide fast and accurate detection and identification of different types of targets from passive arrays of acoustic sensors.To address this problem, we propose to study and develop dedicated methods for multiple target detection/classification and tracking. One primary criterion is to develop fast algorithms that don't make any a priori assumption about the number oftargets, target's dynamical information and initial conditions, and background interference and clutter. We will develop a subband-based direction of arrival (DOA) estimation method for better differentiation of different tonal features of the signaturesand a sequential Bayes method for target (vehicle) classification. The algorithms will be tested on several multiple target cases that involve various target scenarios, high density of clutter and correlated interference, and collected in differentenvironmental conditions. In battlefield situatio

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

US Flag An Official Website of the United States Government