Scene interpretation by fusing intermediate results of multiple visual sensory information processing

Proposes a scene interpretation system which makes use of intermediate results of multiple visual sensory information processing for efficient object recognition. By using the intermediate results, the scene interpretation can start just after the necessary information is obtained. Therefore, the total computation time can be reduced. Since the range acquisition by multi-stage stereo method needs a longer time than color image segmentation, the intermediate results of the stereo method are sent to a fusion process in order to make the interpretation process efficient. The authors apply the method to scenes including cars, trees, road, and ground regions, and show to what extent the computation time can be reduced by the method