Vehicle Detection Technology And Application Of Intelligent Transportation System

The number of cars in China’s major cities has increased year by year.While bringing convenience to people’s lives,it has also caused problems such as traffic congestion,environmental pollution,and frequent accidents.The deep-seated reason behind traffic congestion is the instability of traffic flow.This thesis uses intelligent traffic vehicle detection technology as a means to focus on the application of vehicle detection technology to suppress the instability of traffic flow.Through theoretical derivation and simulation experiments,a set of schemes that can effectively alleviate traffic congestion is proposed.The mismatch between public transport infrastructure and urban car ownership has caused traffic congestion,but in addition,drivers’ unreasonable driving is also an important cause of traffic congestion.Most drivers only focus on the movement of the front car.The distance and relative speed from the front car are the main factors for making driving decisions.This is a typical vehicle following model.Because disturbances are transmitted from front to back in one direction,it is easy to cause instability in traffic flow.Therefore,this thesis mentions a bilateral detection and control model that uses both front vehicle information and rear vehicle information to allow two-way transmission of information in the traffic flow,alleviate the one-way transmission and amplification of disturbances,and theoretically proved the feasibility of this model to inhibit traffic flow instability.The measurement error of FMCW radar in the detection system is unavoidable,and from the decision-making to the implementation of system response delay in intelligent transportation,this will affect the performance of the bilateral detection control model.In order to reduce the influence of these factors,this thesis introduces a Kalman filter algorithm to reduce the measurement error of the detection system and predict the vehicle acceleration at the next moment in advance,thereby eliminating the influence of the system delay and improving the performance of the model in suppressing the instability of traffic flow.This thesis experimentally simulates a car following model based on the behavior of most drivers,and finds that it is easy to cause traffic flow instability,and proves that the bilateral detection and control model can effectively suppress traffic flow instability.Two schemes were designed to improve the model.The first solution performs Kalman filtering on the speed and displacement of the vehicle,and predicts the speed and displacement at the next moment in advance,thereby improving the detection accuracy.The second scheme uses the idea of Kalman filtering to extract and predict the core factor acceleration of the driving decision in the bilateral detection and control model.Both schemes effectively alleviate the error of the detection system,eliminate the influence of time delay,make the driving decisions as accurate as possible,effectively restrain the instability of traffic flow,and prove the feasibility of the scheme in this thesis.