You are here

Evaluation of High Performance Computing Enabled Multiple-Target Tracking Based on Massive Parallelism for Urban Surveillance Areas

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8750-15-C-0025
Agency Tracking Number: F13A-T10-0086
Amount: $721,894.00
Phase: Phase II
Program: STTR
Solicitation Topic Code: AF13-AT10
Solicitation Number: 2013.1
Timeline
Solicitation Year: 2013
Award Year: 2015
Award Start Date (Proposal Award Date): 2015-01-27
Award End Date (Contract End Date): 2017-01-26
Small Business Information
20271 Goldenrod Lane Suite 2066
Germantown, MD 20876-4104
United States
DUNS: 967349668
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: Yes
Principal Investigator
 Genshe Chen
 CTO
 (240) 481-5397
 gchen@intfusiontech.com
Business Contact
 Yingli Wu
Phone: (301) 515-7261
Email: yingliwu@intfusiontech.com
Research Institution
 Temple University
 Haibin Ling
 
Dept. of Computer & Informatio 1805 N. Broad St.,
Philadelphia, PA 19122
United States

 (215) 204-6973
 Nonprofit College or University
Abstract

ABSTRACT: Threat detection of people, vehicles, and others as well as person-vehicle interactions (dismounts) of possible malicious intent are difficult problems due to the complexity of the problem space. The wide area motion imagery (WAMI) systems aid analysts to track and identify dismounts, but typically produce an overwhelmingly large amount of information. The large scale data input challenges existing situational awareness algorithms in time complexity and storage requirements. The lack of computationally efficient moving target indicator (MTI) analysis tools has become a bottleneck for utilizing WAMI data in urban surveillance. The Phase I effort has resulted in high-performance computing solutions to handle the large scale data requirements. We obtained promising results to validate our developed approaches. These preliminary yet promising results obtained in the Phase I study clearly demonstrate that IFTs HPC-MTT, which use the graphics processing unit, multi-core processor, and Hadoop technology, provides innovative and effective on-board and off-board solutions,. Based on the Phase I design and evaluation of our HPC-MTT tool, we believe that it is time to revise, extend, and optimize the Phase I research results using a massively parallel framework with Service-Oriented-Architecture.; BENEFIT: The proposed high-performance-computing (HPC) enabled multiple-target-tracking (MTT) architecture has tremendous potential for many military applications. The proposed tool can be used to reduce latency to improve E2AT. In C4ISR, the proposed technology can also improve efficiency in the systems that help warfighters process information, such as in the counter-insurgency and counter-IED areas. In addition, there are some relevant Defense Acquisition Programs within DoD, such as Distributed Common Ground Station-Navy (DCGS-N), DCGS-X (Air Force), DCGS Army (DCGS-A) system, and AFRL E2AT and PCPADX. Other potential commercial applications include disaster response, environmental research, combating drug trafficking, air-traffic control, law-enforcement, search and rescue operations and anti-terrorist activity.

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

US Flag An Official Website of the United States Government