CN113112827B - Intelligent traffic control method and intelligent traffic control system - Google Patents
Intelligent traffic control method and intelligent traffic control system Download PDFInfo
- Publication number
- CN113112827B CN113112827B CN202110398140.9A CN202110398140A CN113112827B CN 113112827 B CN113112827 B CN 113112827B CN 202110398140 A CN202110398140 A CN 202110398140A CN 113112827 B CN113112827 B CN 113112827B
- Authority
- CN
- China
- Prior art keywords
- traffic
- intersection
- lane
- signal lamp
- grade
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/081—Plural intersections under common control
Abstract
The invention relates to the technical field of intelligent traffic, and discloses an intelligent traffic control method and an intelligent traffic control system, wherein the method comprises the following steps: monitoring traffic road conditions, namely acquiring real-time road condition images, monitoring road conditions of each intersection and acquiring vehicle information; analyzing traffic road conditions, namely analyzing the road conditions of lanes in all directions of each intersection according to the vehicle information of each intersection, and calculating the road condition information of the lanes in all directions of each intersection; signal lamp regulation, calculating the traffic grade of each lane at each intersection according to the road condition information of each lane at each intersection; issuing a signal lamp command of a corresponding lane according to the traffic grade of each road junction and each direction lane, thereby regulating and controlling the signal lamp; the traffic signal lamp can be used for pertinently dealing with traffic network traffic road conditions in all periods, the timeliness is high, uninterrupted work can be carried out for 24 hours, intelligent regulation and control of the traffic signal lamp are achieved, and a large amount of labor cost is saved.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to an intelligent traffic control method and an intelligent traffic control system.
Background
With the continuous development of economy, the living standard of people is gradually improved, the possession of private cars is also sharply increased, and further great load is brought to urban traffic.
In the traditional traffic regulation, a fixed time length signal lamp strategy is adopted, and the traffic condition of a traffic network in all time cannot be pertinently dealt with; or a manual signal lamp regulation strategy is adopted, so that the time and the labor are consumed, the labor cost is high, the timeliness is not high, the overall coverage of a traffic network is difficult to achieve, and the influence of different individual judgments is large.
The existing traffic system generally adopts cloud computing to process data, but the traffic scene has higher requirement on timeliness, needs to respond to emergencies in real time, and the cloud computing naturally has time delay, is easily influenced by network fluctuation and has low stability.
Therefore, a technical scheme is desired to be provided for solving the technical problems that the prior art cannot pertinently deal with the traffic network traffic road conditions in all time periods, the timeliness is not high, and intelligent regulation and control of traffic signal lamps cannot be realized.
Disclosure of Invention
In order to solve the above problems, an object of the present invention is to provide an intelligent traffic control method and an intelligent traffic control system, which can specifically respond to traffic conditions of a traffic network in all time periods, have high timeliness, can continuously operate for 24 hours, realize intelligent traffic signal lamp control, and save a large amount of labor cost.
In order to achieve the above object, the technical solution of the present invention is as follows.
An intelligent traffic regulation method comprises the following steps:
monitoring traffic road conditions, namely acquiring real-time road condition images, monitoring road conditions of each intersection and acquiring vehicle information;
analyzing traffic road conditions, namely analyzing the road conditions of lanes in all directions of each intersection according to the vehicle information of each intersection, and calculating the road condition information of the lanes in all directions of each intersection;
signal lamp regulation, calculating the traffic grade of each lane at each intersection according to the road condition information of each lane at each intersection; and issuing a signal lamp command of the corresponding lane according to the traffic grade of the lane at each intersection in each direction, thereby regulating and controlling the signal lamp.
The intelligent traffic control method can pertinently respond to traffic road conditions of a traffic network in all time periods, has high timeliness, can continuously work for 24 hours, issues signal lamp commands of corresponding lanes according to the traffic grades of the lanes in all directions at each intersection, realizes intelligent traffic signal lamp control, and saves a large amount of labor cost.
Further, an object target is obtained through the road condition image, the object target is a motor vehicle, and the vehicle information includes position coordinates, a moving direction and a moving speed of the object target.
Further, the road condition information comprises traffic flow, occupancy and retention time of lanes in all directions at each intersection, each intersection is provided with a flow bayonet line, and the traffic flow is the number of motor vehicle objects passing through the flow bayonet line in a preset time period; the occupancy rate is the rate of the motor vehicle running on the single direction lane occupying the length of the lane; the residence time is the average residence time of all the motor vehicles in the lane in a single direction; and calculating the moving track of the target in the preset time period according to the position coordinate, the moving direction and the moving speed of the target in the preset time period, so that the traffic flow, the occupancy and the residence time of each direction lane of each intersection can be obtained according to the moving track of the target.
Further, signal lamp regulation includes:
the traffic grade sorting comprises the steps of calculating the traffic grade of each lane at each intersection in each direction according to the traffic flow, the occupancy and the retention time of each lane at each intersection in each direction, and sorting the traffic grade of each lane at each intersection in each direction;
and issuing a signal lamp command, after the traffic grades are sorted in size, issuing the signal lamp command to control the signal lamp of the lane with the maximum traffic grade to be switched to a traffic state after preset time, and then continuing to perform the traffic grade sorting step.
Further, in the step of issuing a signal lamp command, the signal lamp of the lane with the largest traffic grade is controlled to be switched to a traffic state after 4-6 seconds, and then the traffic grade sorting step is carried out every 10-20 seconds. In the present invention, it is preferable that the traffic lights controlling the lane with the largest traffic level are switched to the traffic state after 5 seconds, and then the traffic level ranking step is performed every 15 seconds.
Furthermore, in traffic road condition analysis, after calculating the traffic flow, the occupancy and the residence time of each direction lane at each intersection, setting a simulated urban road network, wherein the simulated urban road network is a three-dimensional matrix, and taking the intersection as a unit, the traffic flow, the occupancy and the residence time data of each direction lane at each intersection are grouped by taking the single direction lane at the single intersection, and the traffic flow, the occupancy and the residence time data of each group form a three-dimensional vector;
filling the three-dimensional vector representing the single-direction lane of the intersection into a corresponding matrix position according to the actual geographic coordinates of the intersection, wherein the data of the points which do not represent the intersection in the matrix is (0, 0, 0);
inputting the matrix as input data to a feature extractor, and performing feature extraction convolution operation to obtain a feature mapping chart of traffic network data of a simulated urban road network;
obtaining the traffic grade of each lane in each direction at each intersection by using the full-connection layers, and outputting a vector with the size of N R through calculation of the two full-connection layers, wherein N is the number of intersections, and R is the number of the intersections with the most directions in the traffic network of the limited area; and calculating the obtained vector data to obtain the traffic grade of each direction lane of each intersection in the traffic network of the limited area.
And sorting the traffic grades of the lanes in all directions at all the road junctions according to the obtained traffic grades. And the lane with the largest traffic grade switches the signal lamp to the traffic state after 5 seconds. The traffic class calculation is then performed every 15 seconds and the signal light status is changed accordingly.
The invention also provides an intelligent traffic control system, comprising:
the traffic road condition monitoring device is used for acquiring real-time road condition images so as to monitor the road condition of each intersection;
the edge computing terminal can analyze the road condition according to the real-time road condition image and calculate the road condition information of each lane of each intersection in each direction, so that the traffic grade of each lane of each intersection in each direction is calculated according to the road condition information of each lane of each intersection in each direction;
the cloud server is used for receiving road condition information obtained by calculation of the extreme edge terminal and traffic grade data of lanes in each direction at each intersection, and issuing signal lamp commands of corresponding lanes according to the traffic grade of the lanes in each direction at each intersection;
the traffic road condition monitoring device is in communication connection with the edge computing terminal, and the traffic road condition monitoring device acquires a real-time road condition image and transmits the real-time road condition image to the edge computing terminal;
the edge computing terminal is in communication connection with the cloud server, the edge computing terminal calculates road condition information and traffic grades of lanes in all directions of each intersection and uploads the road condition information and the traffic grades to the cloud server in real time, the cloud server synthesizes the traffic grades in all directions of each intersection and sends signal lamp commands to the edge computing terminal, and the edge computing terminal sends specific signal lamp commands to traffic lamps through a signal machine, so that the direction with the highest traffic grade in each intersection can pass through, and therefore signal lamp regulation and control are achieved.
The invention has the beneficial effects that: compared with the prior art, the intelligent traffic control method and the intelligent traffic control system can be used for pertinently dealing with traffic network traffic road conditions in all periods, are high in timeliness and can work continuously for 24 hours, signal lamp commands of corresponding lanes are issued according to the traffic grades of the lanes in all directions at each intersection, traffic signal lamps can be intelligently controlled, and a large amount of labor cost is saved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below.
Fig. 1 is a schematic structural diagram of an intelligent traffic control system according to embodiment 2;
fig. 2 is a schematic structural diagram of a convolutional neural network of the intelligent traffic control method according to embodiment 1.
Fig. 3 is a schematic diagram of the positions of the a/B/C intersections on the map in the calculation process of the traffic level in embodiment 1.
In the figure, a camera 1; a switch 2; an edge computing terminal 3; a wireless controller 4; a signal machine 5; a traffic light 6; a 4G/5G communication module 7; and a cloud server 8.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Example 1:
referring to fig. 1 to 3, the present embodiment provides an intelligent traffic control method, including:
monitoring traffic road conditions, namely acquiring real-time road condition images, monitoring road conditions of each intersection and acquiring vehicle information;
analyzing traffic road conditions, namely analyzing the road conditions of lanes in all directions of each intersection according to the vehicle information of each intersection, and calculating the road condition information of the lanes in all directions of each intersection;
signal lamp regulation, calculating the traffic grade of each lane at each intersection according to the road condition information of each lane at each intersection; and issuing a signal lamp command of the corresponding lane according to the traffic grade of the lane at each intersection in each direction, thereby regulating and controlling the signal lamp.
The intelligent traffic control method can pertinently respond to traffic road conditions of a traffic network in all time periods, has high timeliness, can continuously work for 24 hours, issues signal lamp commands of corresponding lanes according to the traffic grades of the lanes in all directions at each intersection, realizes intelligent traffic signal lamp control, and saves a large amount of labor cost.
In this embodiment, the target object is obtained through the road condition image, the target object is a motor vehicle, and the vehicle information includes the position coordinate, the moving direction, and the moving speed of the target object.
Specifically, the position coordinates, the moving direction, and the moving speed of the object target are obtained by:
step 1, an object detecting section
Step 1.1 making a data set
And collecting related pictures of the traffic motor vehicles, manually marking the pictures, and making a traffic motor vehicle data set.
Based on the diversification in the natural environment, the pictures in the data set take the following elements into consideration in the collection process: picture in data set includes one or more target objects; secondly, the illumination intensity of the pictures in the data set is diversified; diversification of background environments of pictures in the data set; fourthly, the weather conditions in the data set are diversified; the shooting angle of the data set is diversified.
And manually labeling the pictures in the data set. The content of the labeled object types is as follows: a motor vehicle. The labeled bounding box information further includes the coordinates of the upper left corner and the lower right corner of the bounding box where each object is located, and in this embodiment, the detected object target is a motor vehicle.
Step 1.2 a detectetnet network is trained using the data set to obtain a detectable illicit target object model. Wherein, DetecNet is the existing mature technology, and can be directly used after training, and the process is not repeated herein. Acquiring a picture at the time t from the road end camera 1 as an INPUT image INPUT A, inputting the INPUT image INPUT A into the obtained model, and detecting to obtain an illegal target object O1Coordinate (x) of center point of bounding box1,y1) Width of bounding box W1And the height H of the bounding box1And class C thereof1。
And 2.1, acquiring two pictures at t and t +1 moments from the road end camera 1 as INPUT images INPUT A and INPUT B.
The target tracking SORT algorithm is applied, the SORT algorithm is the existing mature technology, and the process is not described in detail herein. Inputting picture INPUT A, picture INPUT B and object O obtained in step 1.21Coordinate (x) of center point of bounding box1,y1) Width of bounding box W1And the height H of the bounding box1Can obtain O1Bounding box O in Picture INPUT B2Information: center point coordinate (x)2,y2) Width W of2High H2。
The moving direction and the moving speed of the target can be obtained through the data.
For example: vehicle A at t1The coordinate of the time is (x)1,y1). The coordinate at time t2 is (x)2,y2）。
Wherein, in the time period t2-t1Within, the object motion direction is (x)2-x1,y2-y1）；
Speed:
in this embodiment, the traffic information includes traffic flow, occupancy, and retention time of lanes in each direction at each intersection, each intersection is provided with a traffic bayonet line, and the traffic flow is the number of motor vehicle objects passing through the traffic bayonet line in a preset time period; the occupancy rate is the rate of the lane length occupied by the motor vehicle running on the single direction lane; the residence time is the average residence time of all the motor vehicles in the lane in a single direction; and calculating the moving track of the target in the preset time period according to the position coordinate, the moving direction and the moving speed of the target in the preset time period, so that the traffic flow, the occupancy and the residence time of each direction lane of each intersection can be obtained according to the moving track of the target.
And 3, specifically calculating the traffic flow, the occupancy and the residence time as follows:
and 3.1, obtaining the motion information and the moving track of the object target in a period of time by using the methods in the object detection part and the object tracking part. If there is an automotive object at t1,t2,t3,t4,...,tnMoving/stopping within a moment, with picture I1,I2,I3,I4,...,InIts position information (center point coordinates, width, height) is obtained by detection and tracking:
and 3.2, the vehicle flow is the number of the motor vehicle objects passing through the flow bayonet line in a time period. Marking bayonet lines in images
Using the data obtained in step 3.1, the value at t can be obtained1-tnWithin a time interval (t)1-tnThe time interval can be any time interval, and the time length of the time interval can be adjusted according to needs, such as within 30s of the time interval of 2 points 30 minutes 10 seconds to 2 points 30 minutes 40 seconds);
the moving track of the object is as follows:
Step 3.3 occupancy is the percentage of the length of the lane that is occupied by vehicles on that lane while driving. Lane assessment areas are marked in the image:
Step 3.4, the residence time information is the average residence time of all the vehicles in the lane on the lane. The retention assessment area is marked in the image:
In this embodiment, the signal lamp regulation includes:
the traffic grade sorting comprises the steps of calculating the traffic grade of each lane at each intersection in each direction according to the traffic flow, the occupancy and the retention time of each lane at each intersection in each direction, and sorting the traffic grade of each lane at each intersection in each direction;
and issuing a signal lamp command, after the traffic grades are sorted in size, issuing the signal lamp command to control the signal lamp of the lane with the maximum traffic grade to be switched to a traffic state after preset time, and then continuing to perform the traffic grade sorting step.
In the embodiment, in the step of issuing the signal lamp command, the signal lamp of the lane with the largest traffic grade is controlled to be switched to the traffic state after 4-6 seconds, and then the traffic grade sorting step is carried out every 10-20 seconds. In the present invention, it is preferable that the traffic lights controlling the lane with the largest traffic level are switched to the traffic state after 5 seconds, and then the traffic level ranking step is performed every 15 seconds.
In the embodiment, in the traffic road condition analysis, after the traffic flow, the occupancy and the residence time of each direction lane at each intersection are calculated, a simulated city road network is set, the simulated city road network is a three-dimensional matrix, the intersection is taken as a unit, the traffic flow, the occupancy and the residence time data of each direction lane at each intersection are grouped by taking the single direction lane at a single intersection, and the traffic flow, the occupancy and the residence time data of each group form a three-dimensional vector;
filling the three-dimensional vector representing the single-direction lane of the intersection into a corresponding matrix position according to the actual geographic coordinates of the intersection, wherein the data of the points which do not represent the intersection in the matrix is (0, 0, 0);
inputting the matrix as input data into a feature extractor, and performing feature extraction convolution operation to obtain a feature mapping chart simulating traffic network data of the urban road network;
obtaining the traffic grade of each lane in each direction at each intersection by using the full-connection layers, and outputting a vector with the size of N R through calculation of the two full-connection layers, wherein N is the number of intersections, and R is the number of the intersections with the most directions in the traffic network of the limited area; and calculating the obtained vector data to obtain the traffic grade of each direction lane of each intersection in the traffic network of the limited area.
Wherein the traffic class is a natural number.
And calculating the N R values-the R direction traffic grade values of the N intersections through the network.
For example, at an intersection with 4 directions, the east-west direction grade L east =1.22, the west-east =2.009, the south-north =1.56, and the north-south =1.97, that is, vehicles in the west-east direction are allowed to pass, and the traffic light state is changed until the network calculates that the traffic grade in other directions is higher; the network calculates the traffic grade of each direction in real time, and the time between each time of phase change of the traffic light is not less than 10 seconds.
Specifically, the calculation process of the traffic class is as follows:
Specifically, it is simply assumed that there are 3 intersections in a city road network, namely, a intersection a-3 directions (left, right, and up), a intersection B-2 directions (up and down), and a intersection C-4 directions (up, down, left, and right).
The longitude and latitude of the material is A (N)A,EA），（NB,EB），（Nc,Ec）。
Its position on the map is shown in fig. 3.
The longitude and latitude of the 1024 left-most upper corner point are known as (N)o,Eo) Scaling fig. 3 to 1024 × 1024 size, A, B, C also scales to coordinates on 1024 × 1024, where the transformed coordinates in fig. 3 are:
the data of each direction of each intersection is as follows:
a left coordinate
Data is
；
A right coordinate
Data is
；
Coordinate on A
Data is
；
Coordinate on B
Data is
(ii) a Coordinate under B
Data is
；
Coordinate on C
Data is
；
Coordinate under C
Data is
；
C left coordinate
Data is
；
C right coordinate
Data is
；
Wherein the matrix MatinputData of a point not representing an intersection road in (number)car=0，ratioocc=0，timestay=0）。
Mixing the matrix Mat mentioned aboveinputInputting the data into a neural network as input data, and performing feature extraction convolution operation to obtain a feature map of the global traffic network data. In the method proposed by the present invention, the contents are exemplified as shown in fig. 2. As shown in FIG. 2, the input matrix MatinputObtaining the matrix MatinputFeature map of
、
、
、
. The sequence of operation and data processing from front to back is:
predicting the traffic grade of each lane at each intersection in each direction by using the full-connection layer, calculating by using two layers of full-connection layers, and outputting the value of
The vector of (a), where N is the number of intersections, and R is the number of directions of the intersection having the most directions in the traffic network, for example, there are N intersections in a traffic network of a city. Some of these intersections are 4-directional, some 3-directional, 5-directional, and 7-directional. Wherein, the most direction is the intersection with 7 directions, then R = 7; the specific value of the vector is the traffic class scoreactivated。
The obtained vector data is subjected to calculation operations such as activation, inverse normalization and the like to obtain the traffic grade score of each driving lane at each intersection in the global traffic networkactivated。
And sorting the traffic grades of the lanes in all directions at all the road junctions according to the obtained traffic grades. And the lane with the largest traffic grade switches the signal lamp to the traffic state after 5 seconds. The traffic class calculation is then performed every 15 seconds and the signal light status is changed accordingly.
In the present invention, the object detection algorithm is responsible for the detection (coordinates and classes) of the motor vehicle; the object tracking algorithm is responsible for the relation between the object targets among different images in continuous time; the road condition analysis step is responsible for analyzing the real-time traffic condition of the intersection/road end and calculating the appropriate traffic waiting time and signal lamp regulation and control strategy.
Example 2:
referring to fig. 1, the present embodiment provides an intelligent traffic control system, including:
the traffic road condition monitoring device is used for acquiring real-time road condition images so as to monitor the road condition of each intersection;
the edge computing terminal 3 can analyze road conditions according to the real-time road condition images and calculate the road condition information of each lane of each intersection in each direction, so that the traffic grade of each lane of each intersection in each direction is calculated according to the road condition information of each lane of each intersection in each direction;
the cloud server 8 is used for receiving road condition information obtained by calculation of the extreme edge terminal and traffic grade data of lanes in each direction at each intersection, and can issue signal lamp commands of corresponding lanes according to the traffic grade of the lanes in each direction at each intersection;
the traffic road condition monitoring device is in communication connection with the edge computing terminal 3, and the traffic road condition monitoring device acquires a real-time road condition image and transmits the real-time road condition image to the edge computing terminal 3;
the edge computing terminal 3 is in communication connection with the cloud server 8, the edge computing terminal 3 calculates road condition information and traffic grades of lanes in all directions at all road junctions and uploads the road condition information and the traffic grades to the cloud server 8 in real time, the cloud server 8 sends signal lamp commands to the edge computing terminal 3 after synthesizing the traffic grades in all directions at all road junctions, the edge computing terminal 3 sends specific signal lamp commands to the traffic lamps 6 through the annunciator 5, the direction with the highest traffic grade at all road junctions can pass through, and therefore signal lamp regulation and control are achieved.
The edge computing terminal 3 can perform real-time computing and response, the stability is high, the transmission speed is high, a large amount of computing and data are processed at the edge, only the needed structural data are sent to the cloud, and the remote transportation amount is greatly reduced; moreover, the system can work continuously for 24 hours, realizes traffic regulation and control and saves a large amount of labor cost.
In this embodiment, the traffic road condition monitoring device includes a plurality of cameras 1 respectively disposed at each intersection, and after acquiring a real-time image through the camera 1 at each intersection, the real-time image is transmitted to the edge computing terminal 3 through the switch 2, the edge computing terminal 3 realizes real-time monitoring of the real-time road condition at the intersection through an edge computing method, and the edge computing terminal 3 can be in communication connection with the cloud server 8 through the 4G/5G communication module 7; the traffic data of each single intersection can be uploaded to the cloud server 8 through the 4G/5G communication module 7 in real time, the cloud server 8 integrates traffic data of all intersections and all road sections of the traffic network, a signal lamp strategy is issued to the global edge computing terminal 3, each edge computing terminal 3 sends a specific signal lamp command to the signal machine 5 through the wireless controller 4, and then the signal machine 5 controls the transformation of the traffic lamp 6, so that the traffic control of the global coverage of the traffic network is realized, and the traffic road conditions of the traffic network in all the road sections can be pertinently responded.
The 4G/5G communication module 7, i.e., an IC chip, supports expansion to have a 4G \5G communication function, and in a traffic road segment without an existing network line or a wiring condition, the 4G/5G remote communication function can support normal work of a cloud function in the intelligent traffic control system, such as system cloud update, real-time uploading of road condition data, real-time response of a system cloud command, and the like.
The edge computing terminal 3 obtains the vehicle information of each intersection according to the real-time image, and therefore road condition analysis of lanes in each direction of each intersection is carried out according to the vehicle information; the vehicle information includes the position coordinates, the moving direction, and the moving speed of the object target, the object target is a motor vehicle, and the calculation of the position coordinates, the moving direction, and the moving speed of the object target is described in the calculation process of step 1-2 in embodiment 1.
The road condition information comprises traffic flow, occupancy and retention time of lanes in all directions at each intersection, each intersection is provided with a flow bayonet line, and the traffic flow is the number of motor vehicle objects passing through the flow bayonet line in a preset time period; the occupancy rate is the rate of the lane length occupied by the motor vehicle running on the single direction lane; the residence time is the average residence time of all the motor vehicles in the lane in a single direction; and calculating the moving track of the target in the preset time period according to the position coordinate, the moving direction and the moving speed of the target in the preset time period, so that the traffic flow, the occupancy and the residence time of each direction lane of each intersection can be obtained according to the moving track of the target. The calculation of the traffic flow, occupancy and residence time is described in the calculation procedure of step 3 in example 1; for calculation of the traffic class, see the calculation procedure of step 4 in example 1.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. An intelligent traffic control method is characterized by comprising the following steps:
monitoring traffic road conditions, namely acquiring real-time road condition images, monitoring road conditions of each intersection and acquiring vehicle information, wherein an object target is acquired through the road condition images, the object target is a motor vehicle, and the vehicle information comprises position coordinates, moving direction and moving speed of the object target;
analyzing traffic road conditions, analyzing the road conditions of lanes in all directions of each intersection through vehicle information of each intersection, and calculating the road condition information of the lanes in all directions of each intersection, wherein the road condition information comprises the traffic flow, the occupancy and the residence time of the lanes in all directions of each intersection, each intersection is provided with a flow bayonet line, the traffic flow is the number of motor vehicle objects passing through the flow bayonet line in a preset time period, the occupancy is the ratio of motor vehicles running on a single direction lane to the length of the lane, the residence time is the average residence time of all the motor vehicles on the lane in the single direction lane, and in the preset time period, the moving track of an object target in the preset time period is calculated through the position coordinates, the moving direction and the moving speed of the object target, so that the traffic flow, the traffic flow and the residence time of the lanes in all directions of each intersection are obtained through the moving track of the object target, Occupancy and residence time;
signal lamp regulation, calculating the traffic grade of each lane at each intersection according to the road condition information of each lane at each intersection, and issuing a signal lamp command of a corresponding lane according to the traffic grade of each lane at each intersection, thereby regulating and controlling the signal lamp;
the signal lamp regulation and control comprises: the traffic grade sorting comprises the steps of calculating the traffic grade of each lane at each intersection in each direction according to the traffic flow, the occupancy and the retention time of each lane at each intersection in each direction, and sorting the traffic grade of each lane at each intersection in each direction; issuing a signal lamp command, after sorting the traffic grades, issuing the signal lamp command to control the signal lamp of the lane with the maximum traffic grade to be switched to a traffic state after preset time, and then continuing to perform the traffic grade sorting step;
in the traffic road condition analysis, after calculating the traffic flow, the occupancy and the residence time of each direction lane of each intersection, setting a simulated urban road network, wherein the simulated urban road network is a three-dimensional matrix, taking the intersection as a unit, the traffic flow, the occupancy and the residence time data of each direction lane of each intersection are grouped by taking the single direction lane of a single intersection, and the traffic flow, the occupancy and the residence time data of each group form a three-dimensional vector; filling the three-dimensional vector representing the single-direction lane of the intersection into a corresponding matrix position according to the actual geographic coordinates of the intersection; inputting the matrix as input data to a feature extractor, and performing feature extraction convolution operation to obtain a feature mapping chart of traffic network data of a simulated urban road network; and obtaining the traffic grade of each direction lane of each intersection by using the full-connection layer, outputting vector data by calculating the two full-connection layers, and obtaining the traffic grade of each direction lane of each intersection in the traffic network of the limited area by calculating the obtained vector data.
2. The intelligent traffic control method according to claim 1, wherein in the step of issuing the command of the signal lamps, the signal lamps of the lane with the highest traffic level are controlled to be switched to a traffic state after 4-6 seconds, and then the step of sequencing the traffic levels is performed every 10-20 seconds.
3. The intelligent traffic control method according to claim 1, wherein the simulated urban road network is a 1024 x 3 matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110398140.9A CN113112827B (en) | 2021-04-14 | 2021-04-14 | Intelligent traffic control method and intelligent traffic control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110398140.9A CN113112827B (en) | 2021-04-14 | 2021-04-14 | Intelligent traffic control method and intelligent traffic control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113112827A CN113112827A (en) | 2021-07-13 |
| CN113112827B true CN113112827B (en) | 2022-03-25 |
Family
ID=76716533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110398140.9A Active CN113112827B (en) | 2021-04-14 | 2021-04-14 | Intelligent traffic control method and intelligent traffic control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113112827B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114049760B (en) * | 2021-10-22 | 2022-11-11 | 北京经纬恒润科技股份有限公司 | Traffic control method, device and system based on intersection |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106205156A (en) * | 2016-08-12 | 2016-12-07 | 南京航空航天大学 | A kind of crossing self-healing control method for the sudden change of part lane flow |
| CN108922174A (en) * | 2018-06-20 | 2018-11-30 | 同济大学 | A kind of path dynamic classification method in intersection group around through street Entrance ramp |
| CN109410601A (en) * | 2018-12-04 | 2019-03-01 | 北京英泰智科技股份有限公司 | Method for controlling traffic signal lights, device, electronic equipment and storage medium |
| CN109923608A (en) * | 2016-11-17 | 2019-06-21 | 罗伯特·博世有限公司 | The system and method graded using neural network to mixing voice recognition result |
| CN111275960A (en) * | 2018-12-05 | 2020-06-12 | 杭州海康威视系统技术有限公司 | Traffic road condition analysis method, system and camera |
| CN111583675A (en) * | 2020-05-14 | 2020-08-25 | 吴钢 | Regional road network traffic signal lamp coordination control system and method |
| CN111798665A (en) * | 2020-09-10 | 2020-10-20 | 深圳市城市交通规划设计研究中心股份有限公司 | Road system |
| CN112085954A (en) * | 2019-06-12 | 2020-12-15 | 张雷 | Cascade dynamic interaction control method |
| CN112150832A (en) * | 2020-10-23 | 2020-12-29 | 连云港杰瑞电子有限公司 | Distributed traffic signal control system based on 5G |
| CN112435487A (en) * | 2020-11-11 | 2021-03-02 | 浪潮商用机器有限公司 | Signal lamp control method, device and equipment based on edge calculation and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2187369A3 (en) * | 2008-06-04 | 2012-03-28 | Roads and Traffic Authority of New South Wales | Traffic signals control system |
| CN202394387U (en) * | 2011-12-23 | 2012-08-22 | 北京易华录信息技术股份有限公司 | Traffic condition prediction system fused with plurality of types of traffic data |
| CN109754597B (en) * | 2018-08-02 | 2021-10-08 | 银江股份有限公司 | Urban road regional congestion regulation and control strategy recommendation system and method |
| CN109584558A (en) * | 2018-12-17 | 2019-04-05 | 长安大学 | A kind of traffic flow statistics method towards Optimization Control for Urban Traffic Signals |
| US11375352B2 (en) * | 2020-03-25 | 2022-06-28 | Intel Corporation | Devices and methods for updating maps in autonomous driving systems in bandwidth constrained networks |
-
2021
- 2021-04-14 CN CN202110398140.9A patent/CN113112827B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106205156A (en) * | 2016-08-12 | 2016-12-07 | 南京航空航天大学 | A kind of crossing self-healing control method for the sudden change of part lane flow |
| CN109923608A (en) * | 2016-11-17 | 2019-06-21 | 罗伯特·博世有限公司 | The system and method graded using neural network to mixing voice recognition result |
| CN108922174A (en) * | 2018-06-20 | 2018-11-30 | 同济大学 | A kind of path dynamic classification method in intersection group around through street Entrance ramp |
| CN109410601A (en) * | 2018-12-04 | 2019-03-01 | 北京英泰智科技股份有限公司 | Method for controlling traffic signal lights, device, electronic equipment and storage medium |
| CN111275960A (en) * | 2018-12-05 | 2020-06-12 | 杭州海康威视系统技术有限公司 | Traffic road condition analysis method, system and camera |
| CN112085954A (en) * | 2019-06-12 | 2020-12-15 | 张雷 | Cascade dynamic interaction control method |
| CN111583675A (en) * | 2020-05-14 | 2020-08-25 | 吴钢 | Regional road network traffic signal lamp coordination control system and method |
| CN111798665A (en) * | 2020-09-10 | 2020-10-20 | 深圳市城市交通规划设计研究中心股份有限公司 | Road system |
| CN112150832A (en) * | 2020-10-23 | 2020-12-29 | 连云港杰瑞电子有限公司 | Distributed traffic signal control system based on 5G |
| CN112435487A (en) * | 2020-11-11 | 2021-03-02 | 浪潮商用机器有限公司 | Signal lamp control method, device and equipment based on edge calculation and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113112827A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111473980B (en) | Intelligent automobile automatic driving capability test system | |
| CN109073404A (en) | For the system and method based on terrestrial reference and real time image generation navigation direction | |
| CN108389403A (en) | The traffic lights and speed(-)limit sign intelligent adjusting method captured based on vehicle flowrate | |
| CN111862632A (en) | Method and device for preventing congestion of intelligent traffic signal lamp | |
| CN102519475A (en) | Intelligent navigation method and equipment based on augmented reality technology | |
| CN106023622B (en) | A kind of method and apparatus of determining traffic lights identifying system recognition performance | |
| CN113112827B (en) | Intelligent traffic control method and intelligent traffic control system | |
| CN112329553B (en) | Lane line marking method and device | |
| CN113313943B (en) | Road side perception-based intersection traffic real-time scheduling method and system | |
| CN112288906A (en) | Method and device for acquiring simulation data set, storage medium and electronic equipment | |
| CN207676489U (en) | A kind of municipal intelligent traffic control system | |
| CN111275787A (en) | Method and system for drawing map by using automobile data recorder | |
| CN111554153B (en) | Integrated comprehensive experiment platform for intelligent traffic teaching, scientific research and display | |
| CN115762192A (en) | Smart city construction system based on big data | |
| CN113112866B (en) | Intelligent traffic early warning method and intelligent traffic early warning system | |
| CN210515649U (en) | Intelligent traffic signal control system based on raspberry group and internet | |
| CN116504078A (en) | Traffic control method and system for primary school crossing | |
| CN204791557U (en) | Car navigation detects heavy positioning system | |
| Yang et al. | CAVTest: A closed connected and automated vehicles test field of Chang’an university in China | |
| CN114266775B (en) | Street lamp illumination control method and system for moving object detection | |
| US11392134B1 (en) | System for tuning parameters of a thermal sensor based on a region of interest | |
| US11397439B1 (en) | System for tuning parameters of a thermal sensor to improve object detection | |
| CN104751648A (en) | Signal lamp self-adaptive control system and method for large park traffic safety | |
| CN115205311A (en) | Image processing method, image processing apparatus, vehicle, medium, and chip | |
| CN110059724A (en) | A kind of acquisition methods and device of visual sample |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |