Scientists at the University of Portsmouth are trying to update artificial intelligence software used by CCTV cameras to provide them with the ability to “hear" sounds like windows smashing. The researchers say that the upgraded software could capture crimes on camera faster, and improve response times.
To make this possible, they add, the Engineering and Physical Sciences Research Council (EPSRC) is funding a three-year surveillance study.
Dr. David Brown, an expert from the university, said that the existing software was sophisticated enough to identify minor visual cues such as whether a car aerial was up or more complex activity such as violent behaviour.
"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," the BBC quoted him as saying.
"The longer artificial intelligence is in the software the more it learns," he added. He even expressed hope that the software would some day become clever enough to identify spoken words. "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," he said.
"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," he added.
Brown and his colleagues hope that by the end of the study, they would have generated algorithms (mathematical formula for solving problems) that can be used inside existing CCTV software.
Each successive generation of algorithms, he said, would become more sophisticated as they "learn" what they were looking and listening out for.