Extraction of 3-D coordinates from fusion of omnicamera images

Fusion of images obtained from a new type of imaging sensor called an omnicamera is considered. The omnicamera has a hemisphere field of view with a single view point. We propose using multiple omnicameras to increase the capability of a tracking or surveillance system. A method to register the coordinate systems of the two cameras is provided which uses only some landmarks in the input images. The registration also provides 3-D information about objects in the space monitored by the surveillance system. The accuracy of the 3-D information is studied. It is illustrated that there are great advantages to using multiple omnicameras instead of traditional video cameras in a surveillance system.