Vehicle brand type identification method based on cascading integrated classifier

Abstract

The invention discloses a method for identifying vehicle brand types on the basis of a cascading integrated classifier, and provides a vehicle brand type identification method based on a cascading integrated classifier. A vehicle face image is positioned and segmented; vehicle face image features are extracted respectively by use of a gradient orientated histogram and Contourlet transformation, and a first-stage integrated classifier for vehicle brand type identification is constructed; and a multilayer nerve network is taken as a sub-classifier of a second-stage integrated classifier, and a vehicle brand type which a vehicle belongs to is determined through the first-stage integrated classifier and the second-stage integrated classifier. Through such steps, the precision and the reliability of an identification system are greatly enhanced, and an important parameter basis is provided for effectively solving such traffic problems of vehicle plate duplication, traffic offences and the like.

Description

technical field [0001] The invention patent relates to the field of intelligent transportation research, especially the research on urban vehicle monitoring and management. Background technique [0002] With the development of "safe city", the identification of vehicle brand type has become one of the research hotspots in the field of traffic management. Vehicle brand type recognition is particularly important in access control systems (ACS), such as parking lots, buildings, and restricted areas that restrict the entry of false (set) license plates by identifying vehicle brand types. At present, most of the research on vehicle recognition is limited to using the license plate as the unique identity feature of the vehicle. For the problem that two vehicles of different brands have the same license plate (that is, stolen license plate), the license plate recognition system cannot identify the authenticity. Therefore, the vehicle brand classification system It is widely used i...

AI Technical Summary

Problems solved by technology

At present, Petrivic proposes a method to characterize the vehicle type based on the gradient features of the image, and uses the closest distance classification method to identify the vehicle type. Although the experimental results can automatically identify certain types of vehicles, the overall accuracy needs to be improved.

Images