Traffic Flow and Occupancy Information Acquisition Method Based on Road Surface Image Feature Recognition

Abstract

The invention aims to provide a traffic flow and occupation ratio information acquisition method based on road surface image feature identification. According to the method, a low-illumination DSP camera (standard definition or high definition) is used as an acquisition and arithmetic device for acquiring an image frame by frame, wherein the camera is erected above a road surface and acquires road surface feature change information of a monitored area in real time, and the acquired image is processed through a high-speed processor of the camera; according to road surface image features, a BP neural network identification method is designed to conduct real-time identification, and the transportation traffic flow, the average velocity of vehicles, the time occupation ratio of the vehicles and other main parameters are acquired by identifying the conditions of the road surface image features blocked by and covered with the vehicles. The traffic flow and occupation ratio information acquisition method is used for accurately acquiring vehicle travel information on a road in real time, and can reduce overall delay of transportation and improve transportation service when used as input of a traffic signal control and traffic guidance control system,.

Description

Technical field [0001] The invention belongs to the technical field of intelligent transportation systems (ITS), and specifically relates to a method for acquiring information on traffic flow and occupancy. Background technique [0002] With the expansion of the scale of urban construction in my country, the increasing number of vehicles has brought great pressure to road traffic. Traffic jams often occur. If there is real-time and accurate information about traffic conditions, such as traffic volume and occupancy rate, it can be used as traffic signals. Control and the input of the traffic guidance control system play the role of traffic guidance and relieve the current traffic pressure. [0003] Traditional methods for obtaining real-time road vehicle flow and other information, including the use of buried induction coils, microwave radar, and vehicle-specific video recognition technologies, have certain limitations. The detection of magnetic flux changes using ground-sensing coi...

AI Technical Summary

Problems solved by technology

The use of ground sense coils to detect changes in magnetic flux has a high accuracy, but in actual use, engineering construction is difficult, and the road surface needs to be damaged, which is relatively easy to damage and very difficult to maintain; in addition, it is inconvenient to install on roads such as bridges and viaducts.

The traditional video detection and identification of vehicles is mainly based on the identification of the basic characteristics of the vehicle, which is easily affected by weather, illumination, and night lights. Therefore, sometimes the detection accuracy is very low, and the false detection rate is high. It is difficult to use it as a reliable traffic control input parameter.

Microwave radar has low accuracy when detecting low-speed targets, and the equipment price is high

Images