CCTV cameras 'taught to listen'


Scientists are working on adapting the software to react to crowd noise


CCTV cameras which use artificial intelligence software are being developed to "hear" sounds like windows smashing, researchers have revealed.
University of Portsmouth scientists are working on adapting the software so it can also react to crowd noise.
Crimes would be captured on camera faster and response times improved.
The news comes after the BBC learned councils in southern England routinely used powers brought in to fight terrorism and crime to spy on people.
Figures obtained by BBC South showed the Regulation of Investigatory Powers Act (Ripa) was used more than 750 times by the councils in 2007/08.
If in a car park someone smashes a window, the camera would turn to look at them and the camera operator would be alerted


Dr David Brown


The new three-year surveillance study is being funded by the Engineering and Physical Sciences Research Council (EPSRC).
The existing software is sophisticated enough to identify minor visual cues such as whether a car aerial is up or more complex activity such as violent behaviour, researchers said.
Dr David Brown, from the University of Portsmouth, said: "The visual-recognition software will be able to identify visual patterns but for the next stage we want to get the camera to pivot if it hears a certain type of sound.
"So, if in a car park someone smashes a window, the camera would turn to look at them and the camera operator would be alerted.
'Read' profiles
"The longer artificial intelligence is in the software the more it learns."
He added: "Later versions will get cleverer as time goes on, perhaps eventually being able to identify specific words being said or violent sounds.
"In identifying sound we are looking for the shapes of sound.
"In the same way, if you close your eyes, you can trace the shape of a physical object and 'read' its profile with your hand, we are developing shapes of sound so the software recognises them." By the end of the study, the researchers hope to have generated algorithms - a mathematical formula for solving problems - that can be used inside existing CCTV software. Then each successive generation of algorithms would become more sophisticated as they "learn" what they are looking and listening out for.