A novel approach for surveillance using visual and thermal images

New technology has been developed to create uncooled thermal cameras with comparable thermal and spatial resolutions at a fraction of the cost of cryogenically cooled cameras. Still cheaper are infrared arrays which have similar thermal resolution, with a much lower spatial resolution. Work has been carried out to fuse the data from a thermal array with that of a CCTV camera. The pyroelectric array has a low spatial resolution and will only detect objects that are in a state of flux and are hotter than the background. This attribute has the potential for removing most causes of false alarms at little extra cost. A calibration algorithm has been developed which maps correspondence between the two cameras. By concentrating the area of search on that indicated by the thermal camera, the analysis in both images can then be made more elaborate without undue computational effort. An extended Markov model has been developed to fuse and segment the area in the visual and thermal images within an optimal Bayesian framework.