Communications of the ACM
Smart Cctv Learns to Spot Suspicious Types
Credit: iStockPhoto.com
An international team of computer scientists led by Shaogang Gong at Queen Mary, University of London are developing intelligent video-surveillance software designed to spot suspicious individuals for a next-generation closed-circuit television system called Samurai.
The system employs algorithms to profile behavior, and it also can account for changes in lighting conditions so it can track people as they move from one camera's viewing field to another. The system also can learn the probable routes people will take as well as follow targets as they move in a crowd, zeroing in on their distinctive shape, their luggage, and the people they are walking with. The system issues alerts when it spots deviant behavior, and is designed to adjust its reasoning according to feedback from the operator.
"The use of relevant feedback from human operators will be a very important part of these technologies," says Paul Miller of Queen's University's Center for Secure Information Technologies. "The key is developing learning algorithms that work not only in the lab but that are robust in real-world applications."
The Samurai team demonstrated a prototype system in November and said the system successfully recognized potential threats that human operators may have missed, using footage captured at Heathrow airport.
From New Scientist
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA 
No entries found