You are here

Automated Video Surveillance at Night

Award Information
Agency: Department of Defense
Branch: Defense Advanced Research Projects Agency
Contract: W31P4Q-04-C-R306
Agency Tracking Number: 03ST1-0044
Amount: $0.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: N/A
Solicitation Number: N/A
Solicitation Year: N/A
Award Year: 2004
Award Start Date (Proposal Award Date): N/A
Award End Date (Contract End Date): N/A
Small Business Information
11600 Sunrise Valley Drive
Reston, VA 20191
United States
DUNS: 038732173
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Alan Lipton
 Chief Technology Officer
 (703) 654-9352
Business Contact
 Paul Brewer
Title: VP, New Technology
Phone: (703) 654-9314
Research Institution
 University of Pennsylvania
 J Shi
GRASP Lab, Levine Hall
Philadelphia, PA 19104
United States

 (215) 746-2851
 Nonprofit College or University

ObjectVideo and Prof. Jianbo Shi from the University of Pennsylvania are pleased to submit this Phase II proposal for DARPAs Surveillance at Night Small Business Technology Transfer (STTR) program, involving the creation of techniques and technologies intended to solve problems experienced by real-world intelligent, automated CCTV systems in low- or no-light scenarios. In addition to technology creation, system testing and evaluation is anticipated to be accomplished at the National Guard Bureau / Army National Guard headquarters facility in Arlington, VA in cooperation with the Army National Guard (ANG). The project will make use of the current capabilities of the ObjectVideoT Video Early Warning (VEW) system, and the advanced capabilities emerging in this Phase II STTR research and development effort. The participation of the National Guard Bureau / Army National Guard in this project will provide rigorous testing of these technologies in real world environments, under realistic conditions and against real world problems. There are three key technical challenges. (1) Development of learning algorithms, so that the software can automatically classify unusual nocturnal behavior without user specification. (2) Development of suitable computer vision algorithms so that the system can hand off targets between multiple color, low-light, or thermal cameras at night. (3) Development of suitable computer vision algorithms for robust nighttime object detection, tracking, and classification that greatly exceed the performance of today's systems. ObjectVideo already has significant experience with computer vision-based automated video surveillance technologies and their application to real-world physical security and force protection challenges. Our interactions with customers in dozens of real-world deployments that include coverage of ports of entry on the Northern US Border reinforce the central ideas behind this project: 1) that installed CCTV and lighting infrastructure is often designed for daytime operation and produces video signals that are unusable by either human security professionals or automated systems such as VEW at night, 2) that a broad range of nighttime phenomenology that ranges from sensor effects (AGC, automatic calibration), to static and dynamic lighting effects can cause automated systems to suffer performance degradation that is not acceptable to the customer. Solving these real-world problems will yield commercial systems that are more robust, usable in more environments, and will result in enhanced security for the user.

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

US Flag An Official Website of the United States Government