How do you think the new GigE standards will influence the machine vision industry?
Respond or ask your question now!
The Eye in the Sky
How FPGA-based imaging systems enhance collision avoidance on unmanned aircraft.
by Len Yencharis
What do you remember about your drive in to work today? If you are like most commuters, you disengage your brain from the task of driving and focus on other thoughts-allowing your subconscious autopilot to get you to your destination. The commute normally continues like this until the occasional inconsiderate driver forces you to react.
Now consider the risk of totally relying on autopilot systems to navigate the crowded skies over large American cities. Security concerns raised after September 11th and recent military events have accelerated the urgency to use unmanned aerial vehicles (UAVs), or drones, to monitor the skies while vigilantly monitoring possible terrorist targets on the ground. These UAVs exist now, but they cannot be deployed over American cities because they do not meet Federal Aviation Administration requirements for flying in the National Airspace. Federal Aviation Administration Regulation 7610.4J states that remotely-operated aircraft (a.k.a. UAVs) must have the ability to "see and avoid" air traffic with the same level of safety as a human pilot in order to operate like manned aircraft in the National Air Space (NAS). The capability must be effective against all air traffic, with or without active, transponder-based collision avoidance systems. Currently, no UAV "see and avoid" capability exists, so UAVs operating in the NAS must obtain Certificates of Authorization, a cumbersome process, and use either chase planes or ground-based observers.
Defense Research Associates, Inc. (DRA), working through a Small Business Innovative Research program with the Air Force Research Laboratories' Sensors Directorate (AFRL/SN), has developed technology called Detect and Avoid (DAA) that addresses the FAA's "see and avoid" requirement. AFRL/SNJT is the Electro-Optical (EO) Threat and Target Detection Technology branch at Wright Patterson AFB. SNJT has been working passive threat detection for over twenty years and has a state-of-the-art laboratory for calibrating and characterizing UV/IR/Visible sensors. SNJT has been developing discrimination algorithms for missile warning that have been leveraged for use in See and Avoid. DRA is a small engineering company that specializes in electronic warfare, real-time simulation, image processing and signal processing. DRA works with the research components of the Department of Defense to meet the technological needs of the systems development and war-fighting components.
AFRL/SN and the Predator/Global Hawk program offices sponsored DRA to adapt missile detection technology to the Detect/See and Avoid application. The DAA system uses low-cost optical sensors, processors and DRA's proprietary software to detect collision course aircraft. DRA used a validated AFRL/SN human vision model called OPEC and custom simulation software to numerically quantify the detection ranges required for "an equivalent level of safety." DRA performed developmental flight demonstrations on a surrogate UAV aircraft. These demonstrations showed DAA technology currently meets Global Hawk and Predator low and medium altitude detection range requirements (where threat of collision is greatest). Based on these successes, AFRL/SN has funded further development of the technology.