Monocular computer vision

The human visual system is usually able to recognize objects as well as their spatial relations without the support of depth information like stereo vision. For this reason one can easily understand cartoons, photographs and movies. It is the aim of the authors´ current research to exploit this aspect of human perception in the context of computer vision. From a monocular TV image one obtains information about the type of an object observed in the scene and its position relative to the camera (viewpoint). This paper deals with the theory of human image understanding as far as used in this system and describes the realization of a vision system based on these principles