Vehicle type recognition method based on vehicle face features

Abstract

The invention discloses a vehicle type recognition method based on vehicle face features. The method comprises the following steps of: (1) collecting vehicle images through a monitoring camera, preprocessing the images and detecting and segmenting vehicle face images capable of characterizing vehicle types, wherein the step (1) comprises the following specific procedures of: (1-1) collecting the vehicle images of various types of vehicles by using the monitoring camera, (1-2) preprocessing the images and enhancing the quality of the images through homomorphic filtering, and (1-3) segmenting vehicle face regions capable of characterizing vehicle type features by adopting vehicle face region detection and segmentation based on license plate position information; (2) carrying out Curvelet wavelet transform on the vehicle images so as to extract a vehicle face feature matrix capable of characterizing the vehicle type features; and (3) classifying the Curvelet wavelet feature vectors of the extracted vehicle face images by using a support vector machine classifier so as to recognize the vehicle type. The method provided by the invention can be used for providing more accurate vehicle and vehicle type information for traffic monitoring and is very important for traffic safety and the real-time extraction of traffic information.

Description

technical field [0001] The invention relates to image recognition and traffic safety research technology, in particular to a vehicle type recognition method based on vehicle face features. Background technique [0002] At present, the requirements for the robustness and reliability of the traffic monitoring system in the intelligent transportation system are getting higher and higher. For example, traffic parameters such as traffic volume and vehicle running speed can be calculated according to vehicle detection, tracking and vehicle number statistics. Since vehicle detection methods based on sensors such as ground-sensing coils, ultrasonic waves, and radar cannot identify vehicle types, these methods cannot provide intuitive traffic scene information, however, video sensor-based traffic monitoring systems can effectively provide vehicle number, location, and type Therefore, vehicle detection and type recognition based on video images have become an important research direct...

AI Technical Summary

Problems solved by technology

Since vehicle detection methods based on sensors such as ground induction coils, ultrasonic waves, and radars cannot identify vehicle types, these methods cannot provide intuitive traffic scene information. However, traffic monitoring systems based on video sensors can effectively provide information on the number, location, and type of vehicles. and other traffic parameters, therefore, vehicle detection and type recognition based on video images has become an important research direction in the field of intelligent transportation

At present, the identification of vehicle types based on video sensors is mainly focused on rough classification, that is, the detected vehicles are classified into small cars, medium-sized cars and large cars, etc., but for specific classifications such as Audi, Wulin, Chery, Chevrolet, Cityroen, Ford, Vehicle types like Changan, Hyudai, Mzada, Nissan, Peugot, Buick and Toyota have few methods

Images