One of the big problems with CCTV surveillance – from the point of view of the watchers that is – is that at some point there are holes where they can’t see. Along with that the cameras are only as good as the operators and their profiling skills. However some researchers at Ohio State University have been working on a supposedly smart surveillance system of CCTV camera to deal with these problems.
Their concept involves the stitching of digital images from the viewpoint of a network of camera to create a 360-degree view. then another piece of software will be used to create an overhead map that will be able to fix the ground coordinates of each pixel in the panoramic view. The third piece of the puzzle would then seamlessly track an individual as they move through that space.
As a person walks across a scene, the computer can calculate exactly where the person is on the panorama and aerial map. That information can then be used to instruct a camera to follow him or her automatically using the camera’s pan-and-tilt control. With this system, it will be possible for the computer to ‘hand-off’ the tracking task between cameras as the person moves in and out of view of different cameras.
For the researchers the next step will be to develop an algorithm to spot unusual behaviour. Needless to say the project is being funded by the Air Force Research Lab.
[hat tip to the Danger Room blog]