A method for classifying of a known object in a field of view of a camera

摘要

A method for classifying of a known object in a field of view of a digital camera, that a plurality of classifier feature vectors to be developed, wherein each classifier feature vector to any one of a plurality of facets point of view angle of the known object. The digital camera to detect an image in a field of view, which comprises the known object and, on the basis of the captured image, an image feature vector is generated. The image feature vector is with each of the plurality of classifier feature vectors, and one of the plurality of classifier feature vectors, of the image feature vector at the most accurate, is selected. A position of the known object relative to the digital camera, on the basis of the selected classifier feature vector is determined.