Method for recognizing vehicle type based on Doppler traffic radar

Abstract

The invention relates to a method for recognizing a vehicle type based on a Doppler traffic radar, which is used for effectively reflecting a traffic condition of a road in real time. The method comprises the following steps of: acquiring a radar echo power spectrum time sequence which changes over time with a periodogram method by taking a time domain digital echo signal of the forwardly mountedDoppler traffic radar as signal input; modeling a vehicle into a target body comprising a plurality of scattering centers, wherein the scattering centers are related to distance and frequency spectrum energy of the radar, so that the power spectrum sequence of a same target reflects the profile of the target; then combining effective frequency spectrum characteristic with principal component analysis (PCA) and linear discriminant analysis (LDA) for dimension reduction; and typing by using classifiers such as a support vector machine (SVM) and the like. By adopting the method, the vehicle typecan be accurately recognized in real time, the accuracy rate for dividing a large vehicle type, a medium vehicle type and a small vehicle type reaches 90 percent, the requirements of most of users can be met, and the method has board application prospect.

Description

technical field [0001] The invention designs the field of traffic information collection in intelligent traffic, and specifically relates to a method for identifying vehicle types based on Doppler traffic radar. Background technique [0002] The traffic information collection system is an indispensable basic component of the intelligent transportation system. The traffic information collection system relies on traffic information sensors. The ability of sensors to accurately acquire traffic data in real time is crucial to traffic control, public safety and traffic planning. With the development of economy and society, modern cities have become more congested, and traffic problems have attracted widespread attention. The accelerated pace of life makes people expect better traffic conditions. [0003] Many types of traffic information collection equipment have been widely used, such as buried coil detectors, which have been used for more than 50 years and have been used up t...

AI Technical Summary

Problems solved by technology

High-range resolution radar requires high bandwidth, which often limits its use

FSR is forward scatter radar, which can improve the sensitivity of the system, but the distance resolution is poor and the working angle is small, so the target and the radar are required to be very close

Images