Natural and artificial low-level seeing systems - Visual interpretation of known objects in constrained scenes

Recent work on the visual interpretation of traffic scenes is described which relies heavily on a priori knowledge of the scene and position of the cam era, and expectations about the shapes of vehicles and their likely movements in the scene. Knowledge is represented in the computer as explicit three-dimensional geometrical models, dynamic filters, and descriptions of behaviour. Model-based vision, based on reasoning with analogue models, avoids many of the classical problems in visual perception: recognition is robust against changes in the image of shape, size, colour and illumination. The three-dimensional understanding of the scene which results also deals naturally with occlusion, and allows the behaviour of vehicles to be interpreted. The experiments with machine vision raise questions about the part played by perceptual context for object recognition in natural vision, and the neural mechanisms which might serve such a role.