Dynamic programming and cue-generation for automatic vehicle model identification

The authors describe an application of dynamic programming based matching to vehicle identification. An edge map is first generated and various preprocessing stages are carried out culminating in the use of a two-dimensional Hough transform to generate a cued region containing a putative car. A dynamic programming search (edge list search) is then carried out to identify the type of car, e.g. Citroen, Lada, mini, van etc., within the located area. This model identification method has been applied to a number of different real images and has been found to be successful. Illustrative results are given. Even when the shape is fragmented and embedded in the background, the matching between the reference shape and image will automatically identify the set of observed segments that best match the reference shape