Vehicle type identification method and system

Abstract

The invention provides a vehicle type identification method. The method comprises steps that on the basis of a vehicle brand and a pattern, headstock image sample sets and tailstock image sample sets are classified to acquire multiple categories of multiple vehicle images; on the basis of the multiple categories of multiple vehicle images, a depth convolution neural network is at least trained; at least characteristic codes of multiple vehicle images of various categories are respectively extracted through utilizing the trained depth convolution neural network, and a characteristic code / type / vehicle image relationship database is constructed; the trained depth convolution neural network is utilized to extract a characteristic code of to-be-identified vehicle images, the type information of a vehicle is determined according to the characteristic code / type / vehicle image relationship database, and the vehicle brand and the pattern of the vehicle are identified. The invention further provides a vehicle type identification system. The method and the system can adapt to various environments, accuracy of identifying the vehicle category information is improved, and the method and the system have wide application prospects.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a vehicle type recognition method and system. Background technique [0002] With the rapid development of my country's national economy, the number of vehicles used by enterprises and purchased by residents is increasing. Effective analysis of vehicle type information has become inevitable. Vehicle type recognition technology can provide powerful data support for urban vehicle management and related policy formulation, and national economic development statistics. The vehicle type recognition technology based on image processing is a very important technology in the intelligent transportation system (Intelligent Transport System, referred to as ITS), and also occupies an important position in the field of computer vision applications. This technology can analyze and identify specific vehicles, so as to be applied to dealing with traffic accidents, vehicle monitoring and management...

AI Technical Summary

Problems solved by technology

The use of these methods has limitations. For example, these methods have a high recognition rate in clear scenes, but in blurred scenes, such as blurred images caused by weather changes and light changes, and night scenes, the recognition rate tends to be higher. Low; In addition, the frontal images (front and rear) of the vehicle are generally selected for brand recognition. Due to the complex appearance of the vehicle, there are strict requirements on the shooting distance and shooting angle between the detected vehicle and the camera.

Images