Techies the latest weapon in catching car thieves
- 25 June, 2009 15:16
A computer program using new imaging technology which enables moving police cars to automatically detect stolen cars in traffic, has been developed by researchers at the University of Technology, Sydney (UTS).
The new techniques, based on hexagonal pixels rather than the common square pixels, enables a computer linked to a camera to accurately identify and read number plates in real-time, so the plates can be checked immediately against a database.
According to the National Motor Vehicle Theft Reduction Council, there were a total of 15,025 car thefts in Australia during the first quarter of this year.
Geoff Hughes, director of strategy and programming for the council, who was a consultant on the project, says the technology can not only eliminate the false readings on number plates, but the technology has the potential to be placed in fixed speed cameras.
“One of the failings of existing camera technology is that they often can’t read the state designator on the plate, and because number plate sets are duplicated between jurisdictions, that can confuse the camera,” Hughes said.
By being placed in speed cameras, the technology can potentially be used as an intelligence gathering tool by police to track the way criminal gangs operate and track cars that were identified as being used in a crime.
“Vehicles are often the key to an actual crime being committed because they’re either using it to transport goods or get away from a crime scene.
“As time goes on, the system will be fine-tuned to be able to identify false plates because they are sitting on a Holden when they should be on a Toyota.”
The research, which was carried out over three years with funding of $156,000, resulted in the further development of Spiral Architecture, a data structure in which images are represented as collections of hexagonal pixels.
UTS project leader Professor Xiangjian He, says hexagonal pixels give smoother edges in images than square pixels.
“The beauty of hexagonal pixels is that they can provide equivalent picture quality using 13 percent fewer pixels,” he said.
“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.
“We are now world leaders in hexagonal pixel technology, and the potential is enormous—it could for instance provide improved resolution for still and moving digital cameras and could find many applications improving the object recognition capabilities of robots.”
The team is also exploring the use of this technology for the development of a program to manage parking fine evasions, and the development of a real-time warning system for oversize and overweight trucks.
Alongside its commercialisation partner UniQuest, UTS is exploring a variety of possible industry partners and licensing opportunities for the program.