Vehicle model identification method

Abstract

The invention discloses a vehicle type recognition method, and the method comprises the following steps that S01, a vehicle enters into a photographing range of a camera, and the camera captures M frames of vehicle images, and transmits the M frames of vehicle images to a synthesis unit; S02, the synthesis unit splices the shot M frames of vehicle images into a complete vehicle side view, and transmits the vehicle side view to a feature extraction unit; S03, the feature extraction unit outputs vehicle types, axle information and vehicle length information and transmits the vehicle types, the axle information and the vehicle length information to a vehicle type establishing unit; S04, the vehicle model establishing unit outputs vehicle model information according to the vehicle type, the axle information and the vehicle length information. According to the invention, vehicle feature points can be accurately captured, vehicle side images can be rapidly restored, and vehicle model identification can be accurately carried out.

Description

technical field [0001] The invention relates to the field of vehicle management, in particular to a vehicle type identification method. Background technique [0002] With the intelligent development of vehicle management, vehicle type identification becomes more and more important. In the vehicle management system, it is necessary to judge the specific information of the vehicle based on the vehicle model information before proceeding to the next step; for example, the new regulations of the Ministry of Communications stipulate that toll charges for high-speed vehicles need to be determined based on the vehicle model based on the vehicle length, axle and number of passengers . The premise of vehicle type recognition is to obtain the vehicle image, and then carry out vehicle type information identification based on the vehicle image. [0003] For the acquisition of vehicle images in the prior art, the following two methods are usually adopted: (1) a close-up camera is insta...

AI Technical Summary

Problems solved by technology

Since the depth distance of different moving objects is a dynamic variable, the angle error caused by the non-parallel driving of the vehicle along the roadside, and the more or less imaging differences between multiple cameras, this method has the defects of low stitching accuracy and cumbersome deployment and installation.

Images