Abnormal vehicle distance identification method based on multi-source information

Abstract

The invention discloses an abnormal vehicle distance identification method based on multi-source information, and the method comprises the steps: collecting the road and vehicle information in a monitored road segment through roadside thunder and sight equipment, obtaining the position information of all target vehicles in the monitored road segment, and processing the position information of alltarget vehicles; obtaining a front-back distance Li between all target vehicles on the same lane and establishing a vehicle distance Gaussian normal distribution model of each lane; determining a judgment threshold Lis of the suspected abnormal vehicle distance in the current state based on a lane vehicle distance Gaussian normal distribution model; comparing the distance Li between the front vehicle and the rear vehicle between the target vehicles in the same lane with the judgment distance Lis, and inputting the information of the vehicles of which the distance Li between the front vehicle and the rear vehicle is not greater than the judgment distance Lis into a judgment system for the suspected abnormal vehicle distance in the next step for further abnormal judgment; and based on the safe vehicle-following distance threshold Lmax, carrying out abnormality judgment on the screened target vehicle with the suspected abnormal vehicle distance.

Description

technical field [0001] The invention belongs to the field of intelligent transportation system vehicle-road coordination active safety, in particular to an abnormal vehicle distance identification method based on multi-source information. Background technique [0002] With the rapid development of social economy, people's requirements for quality of life are also constantly improving. As a means of transportation for travel and a means of delivery for goods, the number of cars is also increasing. However, a series of traffic safety issues that followed have also aroused great attention from the government. Studies have shown that if the abnormal following behavior of vehicles on the road can be detected and found in a few seconds before the accident occurs, the abnormal behavior can be eliminated through effective measures, and the relevant information of the abnormal behavior can be notified to nearby vehicles, 90% of accidents can be effectively avoided. of automobile re...

AI Technical Summary

Problems solved by technology

At present, the abnormal vehicle distance detection method based on this type of equipment, no matter compare from distance (application publication number CN105336217A etc.) or compare from time (application publication number CN110969895A etc.), they all just compare single item, false alarm relatively high rate

Images