Non-cooperative Target Tracking and Identification on UAV Platform

Award Information
Agency: Department of Defense
Branch: Army
Contract: W15P7T-11-C-A805
Agency Tracking Number: A111-034-0778
Amount: $100,000.00
Phase: Phase I
Program: SBIR
Awards Year: 2011
Solicitation Year: 2011
Solicitation Topic Code: A11-034
Solicitation Number: 2011.1
Small Business Information
Intelligent Automation, Inc.
15400 Calhoun Drive, Suite 400, Rockville, MD, -
DUNS: 161911532
HUBZone Owned: N
Woman Owned: Y
Socially and Economically Disadvantaged: N
Principal Investigator
 Roger Xu
 Research and Development/Senior Dir
 (301) 294-5242
 hgxu@i-a-i.com
Business Contact
 Mark James
Title: Director, Contracts&Proposals
Phone: (301) 294-5221
Email: mjames@i-a-i.com
Research Institution
 Stub
Abstract
To achieve the goal of biometric tagging, tracking and localization (TTL) of non-cooperative high value targets based on existing UAV payloads, IAI proposes to develop an integrated real-time tracking and identification system that can automatically track and recognize non-cooperative targets (people of interest) in urban or rural environments. The proposed system is built on top of fast UAV trajectory control, innovative multiple-target tracking, and 3D imaging technologies-enhanced facial recognition approach. There are several key features in the proposed system. First, Innovative target tracking framework based on off-the-shelf target tracking module and a two-level inference engine can handle various non-cooperative target moving patterns under complex cluster environments. Second, by actively integration of target tracking and UAV control algorithms in a closed-loop, the tasks of keeping targets on track and within the sensor's FOV becomes possible. Fast sub-optimal trajectory generation and swift camera pointing control on the fly enable UAV re-acquiring track of lost targets in no time. Third, upon detection of potential targets, camera is automatically adjusted for higher resolution face image capturing, and then 3D imaging technologies enhanced facial recognition algorithm is applied to highly increase the facial recognition rate.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government