WO2021051568A1 - Method and apparatus for constructing road network topological structure, and computer device and storage medium - Google Patents

Abstract

Embodiments of the present application relate to the field of artificial intelligence, and relate to a method for constructing a road network topological structure, comprising: obtaining traffic flow data of checkpoints of a road network within a preset time cycle; taking any one of the checkpoints as a reference checkpoint, and comparing the traffic flow data of the reference checkpoint and the traffic flow data of other checkpoints to obtain a candidate upstream checkpoint group and a candidate downstream checkpoint group of each reference checkpoint; determining upstream checkpoints of the reference checkpoint according to the candidate upstream checkpoint group; determining downstream checkpoints of the reference checkpoint according to the candidate downstream checkpoint group; and constructing a road network topological structure according to the reference checkpoints and the upstream checkpoints and downstream checkpoints corresponding to the reference checkpoints, and displaying the road network topological structure at an interactive interface. The present application further provides a device for constructing the road network topological structure, and a computer device and a storage medium. The present application can implement the automated construction of the road network topological structure.

Description

Method, device, computer equipment and storage medium for constructing road network topology structure

This application is based on the Chinese invention patent application filed on September 18, 2019, with the application number 201910883358.6, titled "Methods, devices, computer equipment and storage media for the construction of road network topology", and claims its priority.

Technical field

This application relates to the field of artificial intelligence, and in particular to a method, device, computer equipment, and storage medium for constructing a road network topology.

Background technique

The topological structure of the road network plays an important role in electronic navigation and traffic flow monitoring. In particular, the direction and connectivity of the road network topological structure play a decisive role in the automatic path planning of intelligent transportation systems. However, the inventor realizes that the existing road network topology is mostly obtained through manual collection and drawing, which has the problems of time-consuming and labor-intensive, inaccuracy and incompleteness. Therefore, there is still a lack of an automated road network topology construction method in the prior art.

Summary of the invention

The purpose of the embodiments of the present application is to propose an automated road network topology construction method that does not require manual collection and drawing.

In order to solve the above technical problems, an embodiment of the present application provides a method for constructing a road network topology, including the following steps:

Obtain the traffic flow data of each bayonet of the road network in a preset time period;

Taking any bayonet as the reference bayonet, the vehicle flow data of the reference bayonet is compared with the traffic flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group of each reference bayonet; the candidate The upstream bayonet group includes multiple candidate upstream bayonet ports, and the candidate downstream bayonet group includes multiple candidate downstream bayonet ports;

Divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate upstream bayonet of the group is As the upstream bayonet of the reference bayonet;

Divide the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate downstream bayonet of the group is As the downstream bayonet of the reference bayonet;

Construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology at the interactive interface.

In order to solve the above technical problems, an embodiment of the present application also provides a device for constructing a road network topology, including:

The acquisition module is used to acquire traffic flow data of each bayonet of the road network in a preset time period;

Candidate bayonet determination module, used to use any bayonet as the reference bayonet, compare the traffic data of the reference bayonet with the traffic flow data of other bayonets to obtain the candidate upstream bayonet groups and candidates for each reference bayonet Downstream bayonet group; the candidate upstream bayonet group includes multiple candidate upstream bayonet, and the candidate downstream bayonet group includes multiple candidate downstream bayonet;

The upstream bayonet determination module is used to divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group, when the number is greater than or equal to the determined threshold , The candidate upstream bayonet of the group is used as the upstream bayonet of the reference bayonet;

The downstream bayonet determination module is used to group the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group, when the number is greater than or equal to a certain threshold , The candidate downstream bayonet of the group is regarded as the downstream bayonet of the reference bayonet; and

The construction module is used to construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology structure at the interactive interface.

In order to solve the above technical problem, an embodiment of the present application further provides a computer device, including a memory and a processor, the memory stores computer readable instructions, and the processor implements the above construction method when the computer readable instructions are executed. A step of.

In order to solve the above technical problems, the embodiments of the present application further provide one or more non-volatile readable storage media, the non-volatile readable storage medium stores computer readable instructions, and the computer readable instructions are The processor implements the steps of the above construction method when executed.

The details of one or more embodiments of the present application are set forth in the following drawings and description, and other features and advantages of the present application will become apparent from the description, drawings, and claims.

Description of the drawings

In order to explain the solution in this application more clearly, the following will briefly introduce the drawings used in the description of the embodiments of the application. Obviously, the drawings in the following description are some embodiments of the application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

Fig. 2 is a flowchart of an embodiment of a method for constructing a road network topology according to the present application;

Fig. 3 is an actual schematic diagram of the bayonet in the method for constructing a road network topology of the present application;

FIG. 4 is a flowchart of a specific implementation of step 30 in FIG. 2;

FIG. 5 is a flowchart of a specific implementation of step 301 in FIG. 4;

FIG. 6 is a flowchart of a specific implementation of step 60 in FIG. 2;

Fig. 7 is a flowchart of another embodiment of a method for constructing a road network topology according to the present application;

Fig. 8 is a flowchart of another embodiment of a method for constructing a road network topology according to the present application;

Fig. 9 is a schematic structural diagram of an embodiment of a device for constructing a road network topology according to the present application;

10 is a schematic structural diagram of a specific implementation of the candidate bayonet determination module 402 shown in FIG. 9;

Fig. 11 is a schematic structural diagram of an embodiment of a computer device according to the present application.

detailed description

Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the technical field of the application; the terms used in the specification of the application herein are only for describing specific embodiments. The purpose is not to limit the application; the terms "including" and "having" in the specification and claims of the application and the above-mentioned description of the drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the application or the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence.

In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings.

As shown in FIG. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.

The user can use the terminal devices 101, 102, and 103 to interact with the server 105 through the network 104 to receive or send messages and so on. Various communication client applications, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, and social platform software, may be installed on the terminal devices 101, 102, and 103.

The terminal devices 101, 102, 103 may be various electronic devices with display screens and support for web browsing, including but not limited to smart phones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, moving images) Experts compress standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image experts compress standard audio layer 4) players, laptop portable computers and desktop computers, etc.

The server 105 may be a server that provides various services, for example, a background server that provides support for pages displayed on the terminal devices 101, 102, and 103.

Incidentally, the present application method for constructing the road network topology is generally provided by the embodiment of the server / terminal device performs, correspondingly, means constructed road network topology is generally provided in the server / terminal device.

It should be understood that the numbers of terminal devices, networks, and servers in FIG. 1 are merely illustrative. According to implementation needs, there can be any number of terminal devices, networks, and servers.

Continuing to refer to FIG. 2, there is shown a flowchart of an embodiment of a method for constructing a road network topology according to the present application. The construction method of the road network topology includes the following steps:

Step 20: Obtain traffic flow data of each bayonet of the road network in a preset time period.

In the above step 20, the traffic flow data may be data collected by a monitoring device (for example, a video monitoring device) set at the bayonet, which may include the image when the vehicle passes the bayonet, the time when the vehicle passes the bayonet, and the bayonet The unique identification of the vehicle, the license plate number of the passing vehicle, etc. As shown in Figure 3, the bayonet of the road network refers to the location on the road where monitoring facilities are set up to monitor the road conditions, and the monitoring equipment refers to the electronic equipment used to collect data in the monitoring facilities. The preset time period can be 1 hour, 2 hours, and so on. The preset time period can also be adjusted according to the amount of traffic data actually required. For example, if more traffic data is required, the preset time period can be set during the peak traffic period (for example, from 8 am to 9 am If less traffic data is required, the preset time period can be set in the low traffic period (for example, the time period from 11 pm to 12 pm). In addition, in order to avoid the loss of traffic data at the bayonet due to accidental malfunction of the monitoring equipment, the preset time period can also span multiple days and multiple time periods. For example, the preset time period includes: 9:00 on June 27th Until 10:00 on June 27, 13:00 on June 27 to 14:00 on June 27, 9:00 on June 28 to 10:00 on June 28, June 28 From 13:00 on the day to 14:00 on the 28th of June.

Step 30: Use any bayonet as the reference bayonet, and compare the traffic data of the reference bayonet with the traffic flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group of each reference bayonet; The candidate upstream bayonet group includes multiple candidate upstream bayonet ports, and the candidate downstream bayonet group includes multiple candidate downstream bayonet ports.

Further, as shown in FIG. 4, when the traffic flow data includes the passing image when the vehicle passes through the bayonet and the passing time when the vehicle passes through the bayonet, the above step 30 may include:

Step 301: Extract the image of the license plate area in the pass-through images of the reference bayonet and other bayonet ports, and use the image of the license plate area as a comparison image.

Step 302: Calculate the similarity values between the respective comparison images, and place the traffic data corresponding to the comparison images whose similarity values are greater than the similarity threshold into the same traffic data group.

In the above step 302, the similarity value between the comparison images can be directly calculated through the convolutional neural network. The obtained similarity value can be in the range of 0 to 1. In this case, the similarity threshold can be 0.6, 0.7, 0.8, and so on. The similarity threshold can be selected according to the actual application.

Step 303: In the same traffic data group, take the passing time in the traffic data corresponding to the reference bayonet as the reference time, and place other bayonet corresponding to the traffic data whose passing time is greater than the reference time into the candidate downstream bayonet bayonet of the reference bayonet Group, put the other bayonet corresponding to the traffic flow data whose passing time is less than the reference time into the candidate upstream bayonet group of the reference bayonet.

In the above step 303, for example, the same traffic data group contains the following three traffic data: "Bayonet A, 9:00", "Bayonet B, 9:10", "Bayonet C, 9:00" 20 points". When bayonet A is used as the reference bayonet, bayonet B and bayonet C will be placed in the candidate downstream bayonet group of the reference bayonet. When bayonet B is used as the reference bayonet, bayonet A will be placed in the candidate upstream bayonet group of the reference bayonet, and bayonet C will be placed in the candidate downstream bayonet group of the reference bayonet.

Furthermore, as shown in FIG. 5, the above step 301 may include:

Step 3011: Identify the characters in the passing image, and extract the center pixel coordinate value, the upper left pixel coordinate value, the lower left pixel coordinate value, the upper right pixel coordinate value, and the lower right pixel coordinate value of the character in the passing image.

In the above step 3011, recognizing the characters in the passing image can be realized by recognizing the outline and shape of the characters. After identifying the characters in the image, a rectangular extraction frame can be obtained. The image of the character area is contained in the extraction frame. At this time, the center pixel coordinate value of the character, the upper left pixel coordinate value, the lower left pixel coordinate value, and the upper right pixel The coordinate value and the pixel coordinate value of the lower right corner are respectively the coordinate value of the midpoint pixel of the extraction frame of the character, the coordinate value of the upper left pixel, the coordinate value of the lower left pixel, the coordinate value of the upper right pixel, and the coordinate of the lower right pixel. value. For example, the center pixel coordinate value, the upper left pixel coordinate value, the lower left pixel coordinate value, the upper right pixel coordinate value and the lower right pixel coordinate value of the character "Yue" extracted are (100,100), (80,140), (80, 60), (120,140) and (120,60)...... the center pixel coordinate value of the character "5", the upper left corner pixel coordinate value, the lower left corner pixel coordinate value, the upper right corner pixel coordinate value and the lower right corner pixel coordinate value The values are (300,110), (280,150), (280,70), (320,150), (280,70).

Step 3012: Calculate the average value of the center pixel coordinate values of all characters, and use it as the average center pixel coordinate value.

Step 3013: Calculate the difference between the center pixel coordinate value of each character and the average center pixel coordinate value. When the difference is less than the similar threshold, the upper left corner pixel coordinate value, the lower left corner pixel coordinate value, and the upper right corner pixel coordinate value of the corresponding character are calculated. And the pixel coordinate values of the lower right corner are respectively placed into the upper left corner pixel coordinate value group of the license plate, the lower left corner pixel coordinate value group of the license plate, the upper right corner pixel coordinate value group and the lower right corner pixel coordinate value group of the license plate.

In the above step 3013, the difference between the center pixel coordinate value of the character and the average center pixel coordinate value may be the Euclidean distance value. For example, the center pixel coordinate value is (100,100), and the average center pixel coordinate value is (130,140), that is, the Euclidean distance value

The similar threshold can be set to different values according to the actual test. Since the resolution of the pass image generally remains unchanged, the pixels of the license plate area image in the pass image generally have little change, so by setting the similar threshold to an appropriate value, it is judged whether the difference is less than the similar threshold. It can be judged whether the character is a character in the license plate area. When the difference is greater than the similar threshold, it means that the character is far away from the image of the license plate area in the passing image. It is very likely that it is not the character of the license plate, but other interfering characters. Therefore, the pixel coordinate value of the character is not Place the coordinate value group. In this way, the influence of disturbing characters on the image extraction result can be reduced.

Step 3014: Among all the pixel coordinates in the pixel coordinate value group of the upper left corner of the license plate, take the smallest abscissa as the abscissa of the pixel coordinate value of the upper left corner of the license plate, and take the largest ordinate as the ordinate of the pixel coordinate value of the upper left corner of the license plate. Compose the target pixel coordinate value in the upper left corner.

In the above step 3014, all the pixel coordinates of the pixel coordinate value group of the upper left corner of the license plate are (100, 100), (80, 99), (60, 110) as an example, at this time, the target pixel coordinate value of the upper left corner is (60, 110).

Step 3015: Among all the pixel coordinates in the pixel coordinate value group of the lower left corner of the license plate, take the smallest abscissa as the abscissa of the pixel coordinate value of the lower left corner of the license plate, and take the smallest ordinate as the ordinate of the pixel coordinate value of the lower left corner of the license plate. Compose the target pixel coordinate value in the lower left corner.

In the above step 3015, taking all the pixel coordinates of the pixel coordinate value group of the lower left corner of the license plate as (100,50), (80,48), (60,59) as an example, at this time, the target pixel coordinate value of the lower left corner is ( 60,48).

Step 3016: Among all the pixel coordinates in the pixel coordinate value group of the upper right corner of the license plate, take the largest abscissa as the abscissa of the pixel coordinate value of the upper right corner of the license plate, and take the largest ordinate as the ordinate of the pixel coordinate value of the upper right corner of the license plate. Compose the target pixel coordinate value in the upper right corner.

In the above step 3016, taking all the pixel coordinates of the pixel coordinate value group of the upper right corner of the license plate as (400, 100), (380, 99), (360, 110) as an example, at this time, the target pixel coordinate value of the upper right corner is (400, 110).

Step 3017: Among all the pixel coordinates in the pixel coordinate value group of the lower right corner of the license plate, take the largest abscissa as the abscissa of the pixel coordinate value of the lower right corner of the license plate, and take the smallest ordinate as the ordinate of the pixel coordinate value of the lower right corner of the license plate. Compose the target pixel coordinate value in the lower right corner.

In the above step 3017, taking all the pixel coordinates of the pixel coordinate value group of the lower right corner of the license plate as (400, 50), (380, 49), (360, 60) as an example, at this time, the target pixel coordinate value of the lower right corner is ( 400,49).

Step 3018: Extract the image in the area composed of the upper left corner target pixel coordinate value, the lower left corner target pixel coordinate value, the upper right corner target pixel coordinate value and the lower right corner target pixel coordinate value from the passed image, and use it as the license plate area image.

In the above step 3018, based on the examples of the above step 3014, the above step 3015, the above step 3016, and the above step 3017, that is, extract the (60,110), (60,48), (400,110) and (400,49 ) The image in the area composed of coordinate values is used as the image of the license plate area.

In the above step 30, the vehicle flow data of the reference bayonet is compared with the vehicle flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group for each reference bayonet. It can also be implemented in the following two ways :

(1) When the traffic data includes the image when the vehicle passes through the bayonet, the time when the vehicle passes through the bayonet, and the unique identification of the bayonet through which the vehicle passes, the two traffic flows can be determined by comparing the similarity of the entire image Whether the vehicle of the data is the same, if it is the same, continue to compare the time of the two traffic data, and put the unique identifier of the bayonet corresponding to the traffic flow data with the time before it into the candidate upstream of the bayonet corresponding to the traffic data with the time later In the bayonet array, the unique identifier of the bayonet corresponding to the traffic flow data with the later time is placed in the candidate downstream bayonet bayonet array for the bayonet corresponding to the traffic flow data with the previous time.

(2) When the vehicle flow data includes the license plate number of the vehicle passing through the bayonet, the time when the vehicle passes through the bayonet, and the unique identification of the bayonet through which the vehicle passes, the two vehicle flows can also be determined by comparing whether the license plate numbers are the same Whether the vehicle of the data is the same, if it is the same, continue to compare the time of the two traffic data, and put the unique identifier of the bayonet corresponding to the traffic flow data with the time before it into the candidate upstream of the bayonet corresponding to the traffic data with the time later In the bayonet array, the unique identifier of the bayonet corresponding to the traffic flow data with the later time is placed in the candidate downstream bayonet bayonet array for the bayonet corresponding to the traffic flow data with the previous time.

Step 40: Divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group. When the number is greater than or equal to a certain threshold, the upstream candidate of the group is The bayonet is used as the upstream bayonet of the reference bayonet.

In the above step 40, the same candidate upstream bayonet in the candidate upstream bayonet group is divided into one group, and the number of candidate upstream bayonet in each group is counted. The unique identifier of the same bayonet can be calculated in the candidate upstream bayonet. The number of occurrences in the array is implemented. For example, if the unique identifier in the candidate upstream bayonet array includes "0001, 0002, 0001, 0002, 0002", then "0001" appears 2 times in the array, and "0002" appears 3 times in the array, then the bayonet The number of upstream bayonet candidates in group A is two, and the number of upstream bayonet candidates in group B is three. The determination threshold can be adjusted according to actual conditions, and it can be 1, 2, 10, 50, 100, and so on. For example, if the threshold is determined to be 3, the bayonet B is used as the upstream bayonet, and the bayonet A cannot be used as the upstream bayonet.

Step 50: Divide the same candidate downstream bayonet points in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet points in each group. When the number is greater than or equal to a certain threshold, the candidate downstream bayonet of the group is counted. The bayonet is the downstream bayonet of the reference bayonet.

In the above step 50, the same candidate downstream bayonet points in the candidate downstream bayonet group are divided into one group, and the number of candidate downstream bayonet points in each group is counted. It is also possible to calculate the unique identification of the same bayonet at the candidate downstream card points. The number of occurrences in the mouth array is implemented. For example, the unique identifier in the candidate downstream bayonet array includes "0001, 0002, 0001, 0002, 0002", then "0001" appears 2 times in the array, and "0002" appears 3 times in the array, then the bayonet The number of downstream bayonet candidates for group A is 2, and the number of downstream bayonet candidates for bayonet group B is 3. The determination threshold can be adjusted according to actual conditions, and it can be 1, 2, 10, 50, 100, and so on. For example, if the threshold is determined to be 3, the bayonet B is used as the downstream bayonet, and the bayonet A cannot be used as the downstream bayonet.

Step 60: Construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology at the interactive interface.

In the above step 60, when the number of upstream bayonet and downstream bayonet corresponding to each reference bayonet is single, bayonet bays with upstream and downstream relationships can be connected to each other to obtain the road network topology.

Further, as shown in FIG. 6, when the upstream and downstream bayonet ports corresponding to each reference bayonet both include multiple bayonet ports, the above step 60 may include:

Step 601: Use the upstream bayonet of the reference bayonet as the upstream bayonet to be connected, and use any upstream bayonet to be connected as the reference bayonet for connection, if there are no other upstream cards to be connected in the downstream bayonet connected to the reference bayonet Port, connect the reference bayonet as the upstream bayonet.

In the above step 601, for example, the reference bayonet is bayonet A, the upstream bayonet of bayonet A has bayonet B and bayonet C, the downstream bayonet of bayonet B only has A, and the downstream bayonet of bayonet C There are bayonet A and bayonet B. Among them, the downstream bayonet of bayonet C has other upstream bayonet to be connected (ie bayonet B), so bayonet C cannot be used as the upstream bayonet of bayonet A, and bayonet B will be used as the connection of bayonet A Upstream bayonet. That is, in the subsequent steps, bayonet A and bayonet C will not be connected, only bayonet B and bayonet A will be connected. It can be seen that bayonet A, B, C are three bayonet on the same line, and bayonet B is between bayonet A and bayonet C. Through the above step 601, bayonet A, B can be made , C is connected in sequence according to the actual lines, avoiding the error situation of bayonet A connecting bayonet B and bayonet C at the same time.

Step 602: Use the downstream bayonet of the reference bayonet as the downstream bayonet to be connected, and use any downstream bayonet to be connected as the reference bayonet for connection. If there is no other downstream card to be connected in the upstream bayonet connected to the reference bayonet Port, connect the reference bayonet as the downstream bayonet.

In the above step 602, for example, the reference bayonet is bayonet A, the downstream bayonet of bayonet A has bayonet B and bayonet C, the upstream bayonet of bayonet B only has A, and the upstream bayonet of bayonet C There are bayonet A and bayonet B. Among them, the upstream bayonet of bayonet C has other upstream bayonet to be connected (ie bayonet B), so bayonet C cannot be used as the downstream bayonet of bayonet A, and bayonet B will be used as the connection of bayonet A Downstream bayonet. That is, in the subsequent steps, bayonet A and bayonet C will not be connected, only bayonet B and bayonet A will be connected. It can be seen that the bayonet A, B, C are three bayonet on the same line, and the bayonet B is between the bayonet A and the bayonet C. Through the above step 602, the bayonet A, B can be made , C is connected in sequence according to the actual lines, avoiding the error situation of bayonet A connecting bayonet B and bayonet C at the same time.

Step 603: Connect the reference bayonet to the upstream bayonet at the interactive interface, and connect the reference bayonet to the downstream bayonet.

In the above step 20, step 30, step 40, step 50 and step 60, the vehicle flow data of the reference bayonet is compared with the traffic flow data of other bayonet to obtain the candidate upstream bayonet group and the group of each reference bayonet. Candidate downstream bayonet group, then count the candidate upstream bayonet in the candidate upstream bayonet group to obtain the upstream bayonet of the reference bayonet, and count the candidate downstream bayonet in the candidate downstream bayonet group to obtain the downstream bayonet of the reference bayonet Finally, the road network topology is constructed according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, so as to realize the automatic construction of road network topology and solve the lack of automation in the existing technology. The problem of the construction method of the road network topology.

As shown in FIG. 7, in some optional implementation manners of this embodiment, after step 30 and before step 60, the above-mentioned electronic device may also perform the following steps:

Step 31: Determine whether the difference between the transit time in the traffic flow data of each bayonet and the transit time in the traffic flow data of other bayonet ports is less than the time threshold. If so, the candidate upstream bayonet group and candidate for each bayonet Remove other bayonet points from the downstream bayonet group. If not, keep other bayonet points in the candidate upstream bayonet group and candidate downstream bayonet group of each bayonet.

In the above step 31, the time threshold can be adjusted according to the actual situation, for example, the value can be 1 minute, 2 minutes, 10 minutes, etc. For example, if the passing time in the traffic data of bayonet A is 11:00, the passing time in the traffic data of bayonet B is 11:01, and the time threshold is 2 minutes, the difference in the passing time is 1. If the minute is less than the time threshold, the bayonet B is removed from the candidate upstream bayonet group and the downstream bayonet group of bayonet A.

In actual applications, some bayonet bays are set on the U-turn lanes, and the relationship between these bayonet bays is not the real upstream and downstream relationship. Through the above step 31, it can be detected whether the bayonet is a U-turn relationship, rather than the real upstream and downstream relationship. , And remove the bayonet that is actually a U-turn relationship from the candidate upstream bayonet group and the candidate downstream bayonet group, so that the constructed road network topology is more accurate.

As shown in FIG. 8, in some optional implementation manners of this embodiment, after step 50 and before step 60, the above-mentioned electronic device may also perform the following steps:

Step 51: Use the upstream bayonet of the reference bayonet as the upstream calibration bayonet to obtain the downstream bayonet of the upstream calibration bayonet.

Step 52: Compare the downstream bayonet with the reference bayonet. If they are the same, keep the upstream check bayonet in the upstream bayonet of the reference bayonet; if they are not the same, remove the upstream bayonet from the upstream bayonet of the reference bayonet Check the bayonet.

Step 53: Use the downstream bayonet of the reference bayonet as the downstream calibration bayonet to obtain the upstream bayonet of the downstream calibration bayonet.

Step 54: Compare the upstream bayonet with the reference bayonet. If they are the same, keep the downstream calibration bayonet in the downstream bayonet of the reference bayonet; if they are not the same, remove the downstream bayonet from the downstream bayonet of the reference bayonet Check the bayonet.

In the above step 51, step 52, step 53, and step 54, for example, after step 50, the upstream bayonet of the bayonet B is obtained as A, and the downstream bayonet is C. The upstream bayonet of bayonet A is D, and the downstream bayonet is C. The upstream bayonet of bayonet C is A, and the downstream bayonet is E. Then the upstream bayonet of bayonet B conflicts with the downstream bayonet C of bayonet A, the downstream bayonet of bayonet B conflicts with the upstream bayonet of bayonet C, and the bayonet A and bayonet C conflict. It is a real upstream and downstream relationship, so the bayonet A is removed from the upstream bayonet of the bayonet B, and the bayonet C is removed from the downstream bayonet of the bayonet B.

In practical applications, accidental malfunction of the monitoring equipment can easily lead to missing data for a certain bayonet. Once the missing data occurs, it may also lead to wrong setting of the upstream and downstream relationship between bayonet bays. In addition, the driving situation of the vehicle is more complicated and changeable, and there is no guarantee that the vehicle will walk in the direction of the road. For example, there may be rural trails between bayonet A and bayonet C. Rural trails should not be built in the road network. These rural trails direct traffic to bayonet B, which easily leads to the upstream bayonet and bayonet of bayonet B. The downstream bayonet is wrongly set to bayonet A and bayonet C, but in fact bayonet A and bayonet C are actually the upstream and downstream relationship of each other. Through the above steps 51, 52, 53 and 54, the upstream and downstream relationship of the bayonet can be verified, and the wrong upstream and downstream relationship caused by accident can be eliminated, so that the constructed road network topology can be more accurate.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by instructing relevant hardware through computer-readable instructions, which can be stored in a non-volatile readable storage medium. Here, when the readable instruction is executed, it may include the procedures of the above-mentioned method embodiments. Among them, the aforementioned storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

It should be understood that although the various steps in the flowchart of the drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless explicitly stated in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the order of execution is also It is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

With further reference to FIG. 9, as an implementation of the method shown in FIG. 2, this application provides an embodiment of an apparatus for constructing a road network topology structure. The apparatus embodiment corresponds to the method embodiment shown in FIG. 2. The device can be applied to various electronic devices.

As shown in FIG. 9, the apparatus 400 for constructing a road network topology structure of this embodiment includes: an acquisition module 401, a candidate bayonet determination module 402, an upstream bayonet determination module 403, a downstream bayonet determination module 404, and a construction module 405. among them:

The obtaining module 401 is configured to obtain traffic flow data of each bayonet of the road network in a preset time period.

The candidate bayonet determination module 402 is used to use any bayonet as a reference bayonet, and compare the traffic flow data of the reference bayonet with the traffic flow data of other bayonet bays to obtain the candidate upstream bayonet group and group of each reference bayonet. Candidate downstream bayonet group; Candidate upstream bayonet group contains multiple candidate upstream bayonet, candidate downstream bayonet group contains multiple candidate downstream bayonet.

The upstream bayonet determination module 403 is used to divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group and count the number of candidate upstream bayonet in each group. When the number is greater than or equal to the determined threshold, The candidate upstream bayonet of this group is regarded as the upstream bayonet of the reference bayonet.

The downstream bayonet determination module 404 is used to divide the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group, when the number is greater than or equal to the determined threshold, The candidate downstream bayonet of this group is regarded as the downstream bayonet of the reference bayonet.

The construction module 405 is configured to construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology at the interactive interface.

In this embodiment, the vehicle flow data of the reference bayonet is compared with the vehicle flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group for each reference bayonet, and then the candidate upstream bayonet bays are counted. Candidate upstream bayonet in the group to obtain the upstream bayonet of the reference bayonet, count the candidate downstream bayonet in the candidate downstream bayonet group to obtain the downstream bayonet of the reference bayonet, and finally according to each reference bayonet and each reference bayonet The corresponding upstream bayonet and downstream bayonet construct a road network topology structure, so as to realize the automatic construction of the road network topology structure, and solve the problem of the lack of an automated road network topology construction method in the prior art.

10, which is a schematic structural diagram of a specific implementation of the candidate bayonet determination module 402. The candidate bayonet determination module 402 includes an extraction unit 4021, a classification unit 4022, and a determination unit 4023. among them:

The extraction unit 4021 is configured to extract images of the license plate area in the pass images of the reference bayonet and other bayonet ports, and use the image of the license plate area as a comparison image;

The classification unit 4022 is used to calculate the similarity value between the comparison images, and place the traffic flow data corresponding to the comparison images whose similarity value is greater than the similarity threshold into the same traffic flow data group;

The determining unit 4023 is configured to use the passing time in the traffic flow data corresponding to the reference bayonet as the reference time within the same traffic flow data group, and place the other bayonet corresponding to the traffic flow data whose passing time is greater than the reference time into the reference bayonet candidates In the downstream bayonet group, other bayonets corresponding to the traffic flow data whose passing time is less than the reference time are placed into the candidate upstream bayonet group of the reference bayonet.

The specific limitation on the construction device of the road network topology is consistent with the construction method of the above road network topology, and in order to avoid repetition, it will not be repeated one by one.

In order to solve the above technical problems, the embodiments of the present application also provide computer equipment. Please refer to FIG. 11 for details. FIG. 11 is a block diagram of the basic structure of the computer device in this embodiment.

The computer device 11 includes a memory 111, a processor 112, and a network interface 113 that are connected to each other in communication through a system bus. It should be pointed out that the figure only shows the computer device 11 with components 111-113, but it should be understood that it is not required to implement all of the illustrated components, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes, but is not limited to, a microprocessor, a dedicated Integrated Circuit (Application Specific Integrated Circuit, ASIC), Programmable Gate Array (Field-Programmable Gate Array, FPGA), Digital Processor (Digital Signal Processor, DSP), embedded equipment, etc.

The computer device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device.

The memory 111 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static memory Random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disks, optical disks, etc. In some embodiments, the memory 111 may be an internal storage unit of the computer device 11, such as a hard disk or a memory of the computer device 11. In other embodiments, the memory 111 may also be an external storage device of the computer device 11, for example, a plug-in hard disk equipped on the computer device 11, a smart media card (SMC), and a secure digital (Secure Digital, SD) card, flash card (Flash Card), etc. Of course, the memory 111 may also include both an internal storage unit of the computer device 11 and an external storage device thereof. In this embodiment, the memory 111 is generally used to store an operating system and various application software installed in the computer device 11, such as readable instruction codes of a method for constructing a road network topology. In addition, the memory 111 can also be used to temporarily store various types of data that have been output or will be output.

The processor 112 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 112 is generally used to control the overall operation of the computer device 11. In this embodiment, the processor 112 is configured to run the readable instruction code or process data stored in the memory 111, for example, run the readable instruction code of the method for constructing the road network topology.

The network interface 113 may include a wireless network interface or a wired network interface, and the network interface 113 is generally used to establish a communication connection between the computer device 11 and other electronic devices.

This application also provides another implementation manner, that is, to provide one or more non-volatile readable storage media, where the non-volatile readable storage medium stores readable instructions for constructing a road network topology, The readable instructions for constructing the road network topology can be executed by at least one processor, so that the at least one processor executes the steps of the method for constructing a road network topology as described above.

Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to enable a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the method described in each embodiment of the present application.

Claims (20)

1. A method for constructing a road network topology, which is characterized in that it comprises the following steps:

   Obtain the traffic flow data of each bayonet of the road network in a preset time period;

   Taking any bayonet as the reference bayonet, the vehicle flow data of the reference bayonet is compared with the traffic flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group of each reference bayonet; the candidate The upstream bayonet group includes multiple candidate upstream bayonet ports, and the candidate downstream bayonet group includes multiple candidate downstream bayonet ports;

   Divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate upstream bayonet of the group is As the upstream bayonet of the reference bayonet;

   Divide the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate downstream bayonet of the group is As the downstream bayonet of the reference bayonet;

   Construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology at the interactive interface.
2. The construction method according to claim 1, wherein the traffic flow data includes the passing image when the vehicle passes through the bayonet and the passing time when the vehicle passes through the bayonet, and the vehicle flow data of the reference bayonet is combined with other cards. The traffic flow data of the ports are compared to obtain the candidate upstream bayonet group and the candidate downstream bayonet group for each reference bayonet, including:

   Extracting the image of the license plate area in the pass images of the reference bayonet and the other bayonet, and using the image of the license plate area as a comparison image;

   Calculate the similarity value between each comparison image, and place the traffic flow data corresponding to the comparison image whose similarity value is greater than the similarity threshold into the same traffic flow data group;

   In the same traffic data group, take the passing time in the traffic data corresponding to the reference bayonet as the reference time, and place other bayonet corresponding to the traffic flow data whose passing time is greater than the reference time as candidates for the reference bayonet In the downstream bayonet group, another bayonet corresponding to the traffic flow data whose passing time is less than the reference time is placed into the candidate upstream bayonet group of the reference bayonet.
3. The construction method according to claim 2, wherein the extracting the image of the license plate area in the passing image of the reference bayonet and the other bayonet comprises:

   Identify the character in the passing image, and extract the center pixel coordinate value, the upper left pixel coordinate value, the lower left pixel coordinate value, the upper right pixel coordinate value, and the lower right pixel coordinate value of the character in the passing image;

   Calculate the average value of the center pixel coordinate values of all characters, and use it as the average center pixel coordinate value;

   Calculate the difference between the center pixel coordinate value of each character and the average center pixel coordinate value. When the difference value is less than a similar threshold, the upper left pixel coordinate value, the lower left pixel coordinate value, and the upper right pixel coordinate value of the corresponding character are calculated. The value and the pixel coordinate value of the lower right corner are respectively placed in the pixel coordinate value group of the upper left corner of the license plate, the pixel coordinate value group of the lower left corner of the license plate, the pixel coordinate value group of the upper right corner of the license plate and the pixel coordinate value group of the lower right corner of the license plate;

   Among all the pixel coordinates in the pixel coordinate value group of the upper left corner of the license plate, the smallest abscissa is taken as the abscissa of the pixel coordinate value of the upper left corner of the license plate, and the largest ordinate is taken as the ordinate of the pixel coordinate value of the upper left corner of the license plate to form The coordinate value of the target pixel in the upper left corner;

   Among all the pixel coordinates in the pixel coordinate value group of the lower left corner of the license plate, the smallest abscissa is taken as the abscissa of the pixel coordinate value of the lower left corner of the license plate, and the smallest ordinate is taken as the ordinate of the pixel coordinate value of the lower left corner of the license plate to form The coordinate value of the target pixel in the lower left corner;

   Among all the pixel coordinates in the pixel coordinate value group of the upper right corner of the license plate, the largest abscissa is taken as the abscissa of the pixel coordinate value of the upper right corner of the license plate, and the largest ordinate is taken as the ordinate of the pixel coordinate value of the upper right corner of the license plate to form The coordinate value of the target pixel in the upper right corner;

   Among all the pixel coordinates in the pixel coordinate value group of the lower right corner of the license plate, the largest abscissa is taken as the abscissa of the pixel coordinate value of the lower right corner of the license plate, and the smallest ordinate is taken as the ordinate of the pixel coordinate value of the lower right corner of the license plate to form The coordinate value of the target pixel in the lower right corner;

   Extracting from the passing image an image in a region composed of the upper left corner target pixel coordinate value, the lower left corner target pixel coordinate value, the upper right corner target pixel coordinate value, and the lower right corner target pixel coordinate value, Use it as the image of the license plate area.
4. The construction method according to claim 1, wherein the traffic flow data includes the passing time of the vehicle passing through the bayonet, and the traffic flow data of each bayonet is compared with the traffic flow data of other bayonet to obtain After the steps of candidate upstream bayonet group and candidate downstream bayonet group for each bayonet, it also includes:

   Determine whether the difference between the transit time in the traffic flow data of each bayonet and the transit time in the traffic flow data of the other bayonet is less than the time threshold, and if so, in the candidate upstream bayonet of each bayonet The other bayonet is removed from the group and the candidate downstream bayonet group, if not, the other bayonet is retained in the candidate upstream bayonet group and the candidate downstream bayonet group for each bayonet.
5. The construction method according to claim 1, characterized in that in said grouping the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and counting the number of candidate downstream bayonet in each group, When the number is greater than or equal to the determined threshold, after the step of using the candidate downstream bayonet of the group as the downstream bayonet of the reference bayonet, the method further includes:

   Taking the upstream bayonet of the reference bayonet as the upstream verification bayonet to obtain the downstream bayonet of the upstream verification bayonet;

   Compare the downstream bayonet with the reference bayonet. If they are the same, keep the upstream check bayonet in the upstream bayonet of the reference bayonet; if they are not the same, use the reference bayonet Remove the upstream check bayonet from the upstream bayonet;

   Taking the downstream bayonet of the reference bayonet as the downstream verification bayonet to obtain the upstream bayonet of the downstream verification bayonet;

   Compare the upstream bayonet with the reference bayonet, if they are the same, keep the downstream check bayonet in the downstream bayonet of the reference bayonet, if they are not the same, then use the reference bayonet The downstream check bayonet is removed from the downstream bayonet.
6. The construction method according to claim 1, wherein the upstream bayonet and the downstream bayonet corresponding to each reference bayonet each include multiple bayonet bays, wherein the reference bayonet and each reference bayonet The upstream bayonet and downstream bayonet corresponding to the port construct a road network topology, and displaying the road network topology at the interactive interface includes:

   Take the upstream bayonet of the reference bayonet as the upstream bayonet to be connected, and use any upstream bayonet to be connected as the reference bayonet for connection, if there is no other upstream bayonet to be connected in the downstream bayonet of the connection reference bayonet , Then use the connection reference bayonet as the upstream bayonet;

   Take the downstream bayonet of the reference bayonet as the downstream bayonet to be connected, and use any downstream bayonet to be connected as the reference bayonet for connection, if there is no other downstream bayonet to be connected in the upstream bayonet of the reference bayonet. , Use the connection reference bayonet as the downstream bayonet;

   At the interactive interface, connect the reference bayonet to the upstream bayonet, and connect the reference bayonet to the downstream bayonet.
7. A device for constructing a road network topology structure, which is characterized in that it comprises:

   The acquisition module is used to acquire traffic flow data of each bayonet of the road network in a preset time period;

   Candidate bayonet determination module, used to use any bayonet as the reference bayonet, compare the traffic data of the reference bayonet with the traffic flow data of other bayonets to obtain the candidate upstream bayonet groups and candidates for each reference bayonet Downstream bayonet group; the candidate upstream bayonet group includes multiple candidate upstream bayonet, and the candidate downstream bayonet group includes multiple candidate downstream bayonet;

   The upstream bayonet determination module is used to divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group, when the number is greater than or equal to the determined threshold , The candidate upstream bayonet of the group is used as the upstream bayonet of the reference bayonet;

   The downstream bayonet determination module is used to group the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group, when the number is greater than or equal to a certain threshold , The candidate downstream bayonet of the group is regarded as the downstream bayonet of the reference bayonet; and

   The construction module is used to construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology structure at the interactive interface.
8. The construction device according to claim 7, wherein the candidate bayonet determination module comprises:

   An extraction unit, configured to extract images of license plate regions in passing images of the reference bayonet and the other bayonet bays, and use the image of the license plate region as a comparison image;

   The classification unit is used to calculate the similarity value between the comparison images, and put the traffic flow data corresponding to the comparison images whose similarity value is greater than the similarity threshold into the same traffic flow data group;

   The determining unit is configured to, within the same traffic data group, use the passing time in the traffic data corresponding to the reference bayonet as the reference time, and place other bayonet points corresponding to the traffic flow data whose passing time is greater than the reference time into the said vehicle flow data group. In the candidate downstream bayonet group of the reference bayonet, other bayonet corresponding to the traffic flow data whose passing time is less than the reference time are placed into the candidate upstream bayonet group of the reference bayonet.
9. A computer device includes a memory and a processor, wherein computer readable instructions are stored in the memory, and the processor implements the following steps when the processor executes the computer readable instructions:

   Obtain the traffic flow data of each bayonet of the road network in a preset time period;

   Taking any bayonet as the reference bayonet, the vehicle flow data of the reference bayonet is compared with the traffic flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group of each reference bayonet; the candidate The upstream bayonet group includes multiple candidate upstream bayonet ports, and the candidate downstream bayonet group includes multiple candidate downstream bayonet ports;

   Divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate upstream bayonet of the group is As the upstream bayonet of the reference bayonet;

   Divide the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate downstream bayonet of the group is As the downstream bayonet of the reference bayonet;

   Construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology at the interactive interface.
10. The computer device according to claim 9, wherein the traffic flow data includes the passing image when the vehicle passes through the bayonet and the passing time when the vehicle passes through the bayonet, and the vehicle flow data of the reference bayonet is combined with other cards. The traffic flow data of the ports are compared to obtain the candidate upstream bayonet group and the candidate downstream bayonet group for each reference bayonet, including:

    Extracting the image of the license plate area in the pass images of the reference bayonet and the other bayonet, and using the image of the license plate area as a comparison image;

    Calculate the similarity value between each comparison image, and place the traffic flow data corresponding to the comparison image whose similarity value is greater than the similarity threshold into the same traffic flow data group;

    In the same traffic data group, take the passing time in the traffic data corresponding to the reference bayonet as the reference time, and place other bayonet corresponding to the traffic flow data whose passing time is greater than the reference time as candidates for the reference bayonet In the downstream bayonet group, another bayonet corresponding to the traffic flow data whose passing time is less than the reference time is placed into the candidate upstream bayonet group of the reference bayonet.
11. The computer device according to claim 10, wherein said extracting the image of the license plate area in the passing image of the reference bayonet and the other bayonet comprises:

    Identify the character in the passing image, and extract the center pixel coordinate value, the upper left pixel coordinate value, the lower left pixel coordinate value, the upper right pixel coordinate value, and the lower right pixel coordinate value of the character in the passing image;

    Calculate the average value of the center pixel coordinate values of all characters, and use it as the average center pixel coordinate value;

    Calculate the difference between the center pixel coordinate value of each character and the average center pixel coordinate value. When the difference value is less than a similar threshold, the upper left pixel coordinate value, the lower left pixel coordinate value, and the upper right pixel coordinate value of the corresponding character are calculated. The value and the pixel coordinate value of the lower right corner are respectively placed in the pixel coordinate value group of the upper left corner of the license plate, the pixel coordinate value group of the lower left corner of the license plate, the pixel coordinate value group of the upper right corner of the license plate and the pixel coordinate value group of the lower right corner of the license plate;

    Among all the pixel coordinates in the pixel coordinate value group of the upper left corner of the license plate, the smallest abscissa is taken as the abscissa of the pixel coordinate value of the upper left corner of the license plate, and the largest ordinate is taken as the ordinate of the pixel coordinate value of the upper left corner of the license plate to form The coordinate value of the target pixel in the upper left corner;

    Among all the pixel coordinates in the pixel coordinate value group of the lower left corner of the license plate, the smallest abscissa is taken as the abscissa of the pixel coordinate value of the lower left corner of the license plate, and the smallest ordinate is taken as the ordinate of the pixel coordinate value of the lower left corner of the license plate to form The coordinate value of the target pixel in the lower left corner;

    Among all the pixel coordinates in the pixel coordinate value group of the upper right corner of the license plate, the largest abscissa is taken as the abscissa of the pixel coordinate value of the upper right corner of the license plate, and the largest ordinate is taken as the ordinate of the pixel coordinate value of the upper right corner of the license plate to form The coordinate value of the target pixel in the upper right corner;

    Among all the pixel coordinates in the pixel coordinate value group of the lower right corner of the license plate, the largest abscissa is taken as the abscissa of the pixel coordinate value of the lower right corner of the license plate, and the smallest ordinate is taken as the ordinate of the pixel coordinate value of the lower right corner of the license plate to form The coordinate value of the target pixel in the lower right corner;

    Extracting from the passing image an image in a region composed of the upper left corner target pixel coordinate value, the lower left corner target pixel coordinate value, the upper right corner target pixel coordinate value, and the lower right corner target pixel coordinate value, Use it as the image of the license plate area.
12. The computer device according to claim 9, wherein the traffic flow data includes the passing time of the vehicle passing through the bayonet, and the traffic flow data of each bayonet is compared with the traffic flow data of other bayonet to obtain After the steps of candidate upstream bayonet group and candidate downstream bayonet group for each bayonet, it also includes:

    Determine whether the difference between the transit time in the traffic flow data of each bayonet and the transit time in the traffic flow data of the other bayonet is less than the time threshold, and if so, in the candidate upstream bayonet of each bayonet The other bayonet is removed from the group and the candidate downstream bayonet group, if not, the other bayonet is retained in the candidate upstream bayonet group and the candidate downstream bayonet group for each bayonet.
13. 9. The computer device according to claim 9, wherein in said group of candidate downstream bayonet bayonet candidates, the same candidate downstream bayonet bayonet is divided into one group, and the number of candidate downstream bayonet bayonet candidates in each group is counted, When the number is greater than or equal to the determined threshold, after the step of using the candidate downstream bayonet of the group as the downstream bayonet of the reference bayonet, the method further includes:

    Taking the upstream bayonet of the reference bayonet as the upstream verification bayonet to obtain the downstream bayonet of the upstream verification bayonet;

    Compare the downstream bayonet with the reference bayonet. If they are the same, keep the upstream check bayonet in the upstream bayonet of the reference bayonet; if they are not the same, use the reference bayonet Remove the upstream check bayonet from the upstream bayonet;

    Taking the downstream bayonet of the reference bayonet as the downstream verification bayonet to obtain the upstream bayonet of the downstream verification bayonet;

    Compare the upstream bayonet with the reference bayonet. If they are the same, keep the downstream check bayonet in the downstream bayonet of the reference bayonet; if they are not the same, use the reference bayonet The downstream check bayonet is removed from the downstream bayonet.
14. The computer device according to claim 9, wherein the upstream bayonet and the downstream bayonet corresponding to each reference bayonet each include a plurality of bayonet bays, wherein the reference bayonet and each reference bayonet The upstream bayonet and downstream bayonet corresponding to the port construct a road network topology, and displaying the road network topology at the interactive interface includes:

    Take the upstream bayonet of the reference bayonet as the upstream bayonet to be connected, and use any upstream bayonet to be connected as the reference bayonet for connection, if there is no other upstream bayonet to be connected in the downstream bayonet of the connection reference bayonet , Then use the connection reference bayonet as the upstream bayonet;

    Take the downstream bayonet of the reference bayonet as the downstream bayonet to be connected, and use any downstream bayonet to be connected as the reference bayonet for connection, if there is no other downstream bayonet to be connected in the upstream bayonet of the reference bayonet. , Use the connection reference bayonet as the downstream bayonet;

    At the interactive interface, connect the reference bayonet to the upstream bayonet, and connect the reference bayonet to the downstream bayonet.
15. One or more non-volatile readable storage media, wherein computer readable instructions are stored on the non-volatile readable storage media, and when the computer readable instructions are executed by a processor, the following steps are implemented:

    Obtain the traffic flow data of each bayonet of the road network in a preset time period;

    Taking any bayonet as the reference bayonet, the vehicle flow data of the reference bayonet is compared with the traffic flow data of other bayonet bays to obtain the candidate upstream bayonet group and the candidate downstream bayonet group of each reference bayonet; the candidate The upstream bayonet group includes multiple candidate upstream bayonet ports, and the candidate downstream bayonet group includes multiple candidate downstream bayonet ports;

    Divide the same candidate upstream bayonet in the candidate upstream bayonet group into one group, and count the number of candidate upstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate upstream bayonet of the group is As the upstream bayonet of the reference bayonet;

    Divide the same candidate downstream bayonet in the candidate downstream bayonet group into one group, and count the number of candidate downstream bayonet in each group. When the number is greater than or equal to a certain threshold, the candidate downstream bayonet of the group is As the downstream bayonet of the reference bayonet;

    Construct a road network topology structure according to each reference bayonet and the upstream bayonet and downstream bayonet corresponding to each reference bayonet, and display the road network topology at the interactive interface.
16. The non-volatile readable storage medium according to claim 15, wherein the traffic flow data includes a passing image when the vehicle passes through the bayonet and the passing time when the vehicle passes through the bayonet, and the reference bayonet Compare the traffic flow data of other bayonet with the traffic flow data of other bayonet to obtain the candidate upstream bayonet group and candidate downstream bayonet group of each reference bayonet, including:

    Extracting the image of the license plate area in the pass images of the reference bayonet and the other bayonet, and using the image of the license plate area as a comparison image;

    Calculate the similarity value between each comparison image, and place the traffic flow data corresponding to the comparison image whose similarity value is greater than the similarity threshold into the same traffic flow data group;

    In the same traffic data group, take the passing time in the traffic data corresponding to the reference bayonet as the reference time, and place other bayonet corresponding to the traffic flow data whose passing time is greater than the reference time as candidates for the reference bayonet In the downstream bayonet group, another bayonet corresponding to the traffic flow data whose passing time is less than the reference time is placed into the candidate upstream bayonet group of the reference bayonet.
17. The non-volatile readable storage medium according to claim 16, wherein said extracting the image of the license plate area in the passing image of the reference bayonet and the other bayonet comprises:

    Identify the character in the passing image, and extract the center pixel coordinate value, the upper left pixel coordinate value, the lower left pixel coordinate value, the upper right pixel coordinate value, and the lower right pixel coordinate value of the character in the passing image;

    Calculate the average value of the center pixel coordinate values of all characters, and use it as the average center pixel coordinate value;

    Calculate the difference between the center pixel coordinate value of each character and the average center pixel coordinate value. When the difference value is less than a similar threshold, the upper left pixel coordinate value, the lower left pixel coordinate value, and the upper right pixel coordinate value of the corresponding character are calculated. The value and the pixel coordinate value of the lower right corner are respectively placed in the pixel coordinate value group of the upper left corner of the license plate, the pixel coordinate value group of the lower left corner of the license plate, the pixel coordinate value group of the upper right corner of the license plate and the pixel coordinate value group of the lower right corner of the license plate;

    Among all the pixel coordinates in the pixel coordinate value group of the upper left corner of the license plate, the smallest abscissa is taken as the abscissa of the pixel coordinate value of the upper left corner of the license plate, and the largest ordinate is taken as the ordinate of the pixel coordinate value of the upper left corner of the license plate to form The coordinate value of the target pixel in the upper left corner;

    Among all the pixel coordinates in the pixel coordinate value group of the lower left corner of the license plate, the smallest abscissa is taken as the abscissa of the pixel coordinate value of the lower left corner of the license plate, and the smallest ordinate is taken as the ordinate of the pixel coordinate value of the lower left corner of the license plate to form The coordinate value of the target pixel in the lower left corner;

    Among all the pixel coordinates in the pixel coordinate value group of the upper right corner of the license plate, the largest abscissa is taken as the abscissa of the pixel coordinate value of the upper right corner of the license plate, and the largest ordinate is taken as the ordinate of the pixel coordinate value of the upper right corner of the license plate to form The coordinate value of the target pixel in the upper right corner;

    Among all the pixel coordinates in the pixel coordinate value group of the lower right corner of the license plate, the largest abscissa is taken as the abscissa of the pixel coordinate value of the lower right corner of the license plate, and the smallest ordinate is taken as the ordinate of the pixel coordinate value of the lower right corner of the license plate to form The coordinate value of the target pixel in the lower right corner;

    Extracting from the passing image an image in a region composed of the upper left corner target pixel coordinate value, the lower left corner target pixel coordinate value, the upper right corner target pixel coordinate value, and the lower right corner target pixel coordinate value, Use it as the image of the license plate area.
18. The non-volatile readable storage medium according to claim 15, wherein the traffic flow data includes the transit time of the vehicle passing through the bayonet, and the traffic flow data of each bayonet is combined with the traffic flow of other bayonet. After the data is compared to obtain the candidate upstream bayonet group and candidate downstream bayonet group for each bayonet, it also includes:

    Determine whether the difference between the transit time in the traffic flow data of each bayonet and the transit time in the traffic flow data of the other bayonet is less than the time threshold, and if so, in the candidate upstream bayonet of each bayonet The other bayonet is removed from the group and the candidate downstream bayonet group, if not, the other bayonet is retained in the candidate upstream bayonet group and the candidate downstream bayonet group for each bayonet.
19. The non-volatile readable storage medium according to claim 15, wherein in the group of candidate downstream bayonet ports, the same candidate downstream bayonet ports are grouped into one group, and the candidate downstream bayonet ports in each group are counted. The number of bayonet, when the number is greater than or equal to the determined threshold, after the step of using the candidate downstream bayonet of the group as the downstream bayonet of the reference bayonet, the method further includes:

    Taking the upstream bayonet of the reference bayonet as the upstream verification bayonet to obtain the downstream bayonet of the upstream verification bayonet;

    Compare the downstream bayonet with the reference bayonet. If they are the same, keep the upstream check bayonet in the upstream bayonet of the reference bayonet; if they are not the same, use the reference bayonet Remove the upstream check bayonet from the upstream bayonet;

    Taking the downstream bayonet of the reference bayonet as the downstream verification bayonet to obtain the upstream bayonet of the downstream verification bayonet;

    Compare the upstream bayonet with the reference bayonet. If they are the same, keep the downstream check bayonet in the downstream bayonet of the reference bayonet; if they are not the same, use the reference bayonet The downstream check bayonet is removed from the downstream bayonet.
20. The non-volatile readable storage medium according to claim 15, wherein the upstream bayonet and the downstream bayonet corresponding to each reference bayonet each include multiple bayonet bays, wherein the reference bayonet bayonet The upstream bayonet and the downstream bayonet corresponding to each of the reference bayonet ports construct a road network topology structure, and displaying the road network topology structure at the interactive interface includes:

    Take the upstream bayonet of the reference bayonet as the upstream bayonet to be connected, and use any upstream bayonet to be connected as the reference bayonet for connection, if there is no other upstream bayonet to be connected in the downstream bayonet of the reference bayonet. , Then use the connection reference bayonet as the upstream bayonet;

    Take the downstream bayonet of the reference bayonet as the downstream bayonet to be connected, and use any downstream bayonet to be connected as the reference bayonet for connection, if there is no other downstream bayonet to be connected in the upstream bayonet of the connection reference bayonet , Use the connection reference bayonet as the downstream bayonet;

    At the interactive interface, connect the reference bayonet to the upstream bayonet, and connect the reference bayonet to the downstream bayonet.

Images