Researchers at the University of Technology, Sydney, (UTS) Australia, have developed software that uses new imaging technology to enable moving police cars to automatically detect stolen cars in traffic. The new imaging techniques, which are based on hexagonal pixels instead of the traditional square pixels, allow a computer connected to a camera to accurately identify and read license plate numbers in real time.
Geoff Hughes at Australia's National Motor Vehicle Theft Reduction Council says the technology could be placed in fixed speeding cameras, which often cannot differentiate between plates from different states. The technology is based on the development of spiral architecture, a data structure in which images are represented as collections of hexagonal pixels.
UTS professor Xiangjian He says hexagonal pixels create images with smoother edges than square pixels, and can provide pictures of equal quality using 13 percent fewer pixels. "It's not a new idea, but what our team has done is use hexagonal pixels to develop much better methods of curve detection than is possible with square pixels, and this has opened the way for much quicker and more accurate shape identification," He says.
Outside of law enforcement, the technology could improve digital cameras and object recognition capabilities in robots.
From Computerworld Australia
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA
No entries found