| 摘要 |
A method of classifying an object such as a vehicle, involves evaluating the degree of correlation between an acquired object image dataset and each of a plurality of reference image data sets. The method comprises the steps of establishing (302) the object's aspect and selecting (304) the plurality of object reference image data sets from a larger group of such data sets on the basis of an assessment of the object's aspect. Where the object is a vehicle, the aspect assessment may be carried out by using automatic number plate recognition techniques. By restricting the correlation evaluation to using reference image data sets only appropriate for the object's identified aspect, less computation is required and faster classification is possible for a given level of processing resources. Alternatively, for a given processing or classification rate, the level of processing resources may be reduced compared to the prior art. Also described is a method of classifying an object wherein the reference image data sets are selected on the basis of the position of a fiducial marker. |
