CN114120642B - Method for three-dimensional reconstruction of road traffic flow, computer equipment and storage medium - Google Patents

Abstract

The invention belongs to the technical field of intelligent transportation, and in particular relates to a three-dimensional reconstruction method of road traffic flow, computer equipment and a storage medium. The method includes: the server obtains the data of the millimeter-wave radar and the camera; the neural network is used to estimate the actual position and vehicle model information of the vehicle on the road; the server encodes the actual position and vehicle model information of all vehicles on the road into a JSON string format push the encoded data to multiple clients; the client establishes a vehicle model database, and the client matches the corresponding 3D model of the vehicle according to the decoded data; the client reconstructs the 3D scene of the traffic flow on the road and displays it . The invention reduces the amount of data transmission between the server and the client, enables the client to reconstruct the three-dimensional model of the traffic flow of the road according to the received text data, and the traffic flow information can be shared with multiple clients, which is beneficial to the development of intelligent transportation develop.

Description

Method for three-dimensional reconstruction of road traffic flow, computer equipment and storage medium

technical field

The invention belongs to the technical field of intelligent transportation, and in particular relates to a three-dimensional reconstruction method of road traffic flow, computer equipment and a storage medium.

Background technique

With the advancement of urbanization, the problem of traffic congestion has become increasingly prominent. Traffic information is an intuitive reflection of road conditions. Timely grasp of traffic information is of great significance for rationally allocating traffic resources and alleviating congestion, and it also provides data support for the development of intelligent transportation. In the current traffic monitoring scene, it is mainly to use the camera to detect the vehicles driving on the road in real time, obtain the vehicle license plate number and judge whether the vehicle violates the regulations, and use the radar to measure the speed of the vehicle.

Since the current monitoring system can only display the detected license plate number, vehicle speed, and vehicle model in text, it cannot model the actual traffic flow on the road, and the monitoring station shares road images with other terminals in the form of video streams. Huge communication bandwidth causes unnecessary transmission overhead. The reason is that:

1. The actual position information of the vehicle on the road is not utilized.

Most of the current monitoring stations only use the model, license plate and speed information of the vehicle, and lack the use of the actual location information of the vehicle. This application uses the neural network to estimate the actual location information and vehicle model of the vehicle on the road, and combines the actual location information and Vehicle models are used for 3D reconstruction of road scenes.

2. Lack of 3D reconstruction system.

Due to the lack of a system that can reconstruct road traffic conditions, currently road monitoring stations are mainly shared with other user terminals in the form of video streams, and the transmission of video streams will bring huge communication overhead. This application encodes the monitored vehicle information into a text format at the server end, shares it with other terminals while using relatively small communication resources, and then establishes a three-dimensional reconstruction system at the terminal. The terminal decodes the data sent by the server and uses the 3D reconstruction system to restore the actual condition of the road traffic flow.

Contents of the invention

In order to solve the problem of huge communication overhead caused by sharing road traffic flow images in the way of video streams in current traffic detection systems, the present invention provides a method for transmission and three-dimensional reconstruction of road traffic flow information, computer equipment and storage media.

The present invention adopts following technical scheme to realize:

A method for three-dimensional reconstruction of road traffic flow, comprising the following steps:

The server obtains the data of millimeter wave radar and camera;

Estimate the actual position of the vehicle on the road and the vehicle model information by using the neural network;

The server encodes the actual position and vehicle model information of all vehicles on the road into data in JSON string format, and pushes the encoded data to multiple clients through the network transmission protocol;

The client establishes a vehicle 3D model database, and is responsible for decoding the received data packets in JSON format, obtaining vehicle model and actual location information, and establishing a virtual road model;

According to the vehicle model obtained by output decoding, the client matches the corresponding 3D model of the vehicle in the vehicle 3D model database, maps the vehicle 3D model to the virtual road model according to the actual position information of the vehicle, and re-establishes the actual traffic flow on the road. situation and display it comprehensively.

As a further solution of the present invention, the method for obtaining the data of the millimeter-wave radar and the camera is to install the millimeter-wave radar and the camera sensor on the speed measuring gantry of the road monitoring station, and obtain the millimeter-wave radar through the measurement of the camera sensor and the millimeter-wave radar respectively. data and camera image data.

Further, the method of using the neural network to estimate the actual position of the vehicle on the road and the vehicle model information is:

Use the target detection neural network to generate the three-dimensional bounding box of the vehicle in the image data and estimate the model of the vehicle;

Project the 3D bounding box of the vehicle onto the 2D image plane to form the 2D bounding box of the target;

Use the formed two-dimensional bounding box to filter the millimeter-wave radar point cloud image of each vehicle, and input the three-dimensional bounding box information containing the vehicle attitude information and the filtered millimeter-wave radar point cloud information to the second convolution A neural network that estimates the actual location of the vehicle in the real world.

Further, the camera image data uses the first convolutional neural network to estimate the three-dimensional bounding box information and vehicle model information of the vehicle.

Further, the method for estimating the actual position of the vehicle on the road and the vehicle model information also includes: connecting the camera sensor, the millimeter-wave radar and the data processing server, deploying a neural network-based vehicle information detector on the server, and detecting the actual position of the vehicle. Location and vehicle model information.

As a further solution of the present invention, the output of the detector is encoded into a string in JSON format, and the data is sent to the client through the network transmission protocol WebSocket.

As a further solution of the present invention, the server encodes the detected vehicle location information and vehicle model information into the form of a JSON character string, and uses the WebSocket transmission protocol to transmit data to the client. The vehicle location information and vehicle model information Shared to multiple clients, so that the three-dimensional display images of road vehicles can be displayed on the terminals of multiple clients.

As a further solution of the present invention, the road traffic flow three-dimensional reconstruction method of the present invention also includes that the client calculates and displays the quantity of trucks, trucks and cars according to the decoded data; the client uses WebGL to reconstruct the three-dimensional scene of the traffic flow on the road and Display, the display content includes the model of the vehicle, the location information of the vehicle and the model of the vehicle.

As a further solution of the present invention, the client is also used to integrate the functions of displaying three-dimensional images, displaying the number of vehicles and displaying the connection status between the client and the server to form a real-time display terminal for traffic flow.

As a further solution of the present invention, the method for the three-dimensional reconstruction and display of the vehicle includes:

The server encodes the location information and model information of the vehicle as strings;

The server uses the network transmission protocol to send the encoded vehicle location information and model information to the user terminal;

The user terminal receives and decodes the information to obtain the actual location and model information of the vehicle;

The user terminal establishes a vehicle 3D model database and matches it with the vehicle model;

The user terminal builds a road model, maps the three-dimensional vehicle model to the road model according to the actual location information of the vehicle, counts and displays the number of various vehicles.

The present invention also includes a computer device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the The instructions are executed by the at least one processor, so that the at least one processor executes the method for three-dimensional reconstruction of road traffic flow.

The present invention also includes a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the method for three-dimensional reconstruction of road traffic flow.

The technical scheme provided by the invention has the following beneficial effects:

1. The present invention can reduce the communication overhead occupied by road traffic monitoring video transmission.

The invention encodes the vehicle flow information on the road into a character string, and sends it to the user terminal by using the network transmission protocol, thereby reducing the communication resources occupied by sharing the road traffic image with the video stream.

2. The present invention can restore the state of traffic flow on the road at the user terminal, remodel the traffic flow on the road, and can intuitively display the state of traffic flow on the road, which is beneficial to the development of intelligent transportation technology.

3. The present invention can share road traffic flow conditions with multiple user terminals, including smart vehicles, road monitoring stations, and law enforcement department user terminals, so as to realize the sharing of road traffic flow information.

The present invention utilizes the first point to greatly reduce the bandwidth occupied by the previous video stream sharing method, and can use the vehicle three-dimensional model library to remodel the traffic flow at the user terminal according to the vehicle model and the actual position information of the vehicle, and the information of the vehicle can be provided for multiple terminal use.

These or other aspects of the present invention will be more clearly understood in the description of the following embodiments. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following will briefly introduce the accompanying drawings that need to be used in the description of exemplary embodiments or related technologies. The accompanying drawings are used to provide a further description of the present invention It should be understood that it constitutes a part of the description, and is used to explain the present invention together with the embodiments of the present invention, and does not constitute a limitation to the present invention. In the attached picture:

FIG. 1 is a flow chart of a method for three-dimensional reconstruction of road traffic flow according to the present invention.

FIG. 2 is a schematic flow chart of vehicle acquisition data processing in an example of a method for three-dimensional reconstruction of road traffic flow in an embodiment of the present invention.

Fig. 3 is a flow chart of estimating actual location information and vehicle model of a vehicle on a road in a method for 3D reconstruction of road traffic flow in an embodiment of the present invention.

Fig. 4 is a schematic diagram of the architecture of the first convolutional neural network in the method for 3D reconstruction of road traffic flow in an embodiment of the present invention.

FIG. 5 is a schematic diagram of the composition of each module of the first convolutional neural network architecture in the method for 3D reconstruction of road traffic flow in an embodiment of the present invention in FIG. 4 .

Fig. 6 is a schematic diagram of the structure of the second convolutional neural network in the method for 3D reconstruction of road traffic flow in an embodiment of the present invention.

FIG. 7 is a schematic diagram of data processing and data communication between the server and the client in an embodiment of the present invention.

Fig. 8 is a schematic diagram of the three-dimensional reconstruction of road traffic flow performed by the client according to the information of the server in an embodiment of the present invention.

FIG. 9 is a schematic diagram of a real-time display terminal of traffic flow realized by a client using the three-dimensional road traffic flow reconstruction method of the present invention in an embodiment of the present invention.

FIG. 10 is a schematic diagram of another perspective of the real-time display terminal of traffic flow in one embodiment of the present invention shown in FIG. 9 .

FIG. 11 is a schematic diagram of another perspective of the real-time display terminal of traffic flow in one embodiment of the present invention shown in FIG. 9 .

detailed description

In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

The technical solutions in the exemplary embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the exemplary embodiments of the present invention. Obviously, the described exemplary embodiments are only part of the embodiments of the present invention, rather than Full examples. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

A method for three-dimensional reconstruction of road traffic flow provided by the present invention uses the neural network to estimate the actual position and vehicle model information of the vehicle from the data of the camera and the millimeter-wave radar at the server end, encodes the information into a character string, and transmits it using the network transmission protocol For multiple clients, the client establishes a vehicle 3D model library, decodes the data sent by the server to obtain the actual location and model information of the vehicle, matches the vehicle model in the vehicle model library, and establishes a road model, and maps the vehicle model to the road model to display. Solve the current problem of huge communication overhead caused by sharing road traffic video images between multiple clients. Moreover, the present invention enables the client to reconstruct a three-dimensional model of the traffic flow on the road using the received information, which is beneficial to the development of intelligent transportation technology and solves the problem that the detection information display of the current road detection system is not intuitive enough.

The technical scheme of the present invention will be further described below in conjunction with specific embodiments:

Referring to FIG. 1 , FIG. 1 is a flow chart of a method for three-dimensional reconstruction of road traffic flow provided by the present invention.

An embodiment of the present invention provides a method for three-dimensional reconstruction of road traffic flow. In order to solve the problem of huge communication overhead caused by multi-client sharing of video streams in the current traffic detection system, the method includes the following steps:

S1. Install the millimeter-wave radar and camera sensor on the road speed measuring gantry, and respectively connect the camera sensor and the millimeter-wave radar to the data processing server, and deploy a neural network-based vehicle information detector on the server to detect the actual position and location of the vehicle. Vehicle model information.

In this embodiment, the server acquires the data of the millimeter wave radar and the camera. Among them, the equipment used for data collection is the millimeter-wave radar and camera installed on the road gantry. When the vehicle passes through the road section where the equipment is installed, the radar point cloud data of the vehicle is collected by the millimeter-wave radar, and the camera image data of the vehicle is collected by the camera. The server deploys a neural network detector to estimate the actual location information and vehicle model of the vehicle in the real world from millimeter-wave radar and camera data.

Install millimeter-wave radar and camera sensors on the speed-measuring gantry of the road monitoring station, and obtain millimeter-wave radar data and camera image data through camera sensor and millimeter-wave radar measurements respectively.

Among them, the collected millimeter-wave radar data is transmitted through the Gigabit Ethernet interface, and the collected camera image data is transmitted through the Universal Serial Bus (Universal Serial Bus).

It should be noted that, as shown in Figure 2, this embodiment is used to process millimeter-wave radar point cloud data and camera image data, and use neural network algorithms to estimate the actual position information and vehicle location information of the vehicle on the road from the data. model. A specific processing method is to use the first convolutional neural network and the second convolutional neural network for data processing.

The camera image data uses the first convolutional neural network to estimate the three-dimensional bounding box information and vehicle model information of the vehicle.

The millimeter-wave radar data uses the second convolutional neural network combined with the three-dimensional bounding box information of the vehicle to estimate the specific position information of the three-dimensional center of the vehicle on the road. Referring to Fig. 3, the method for estimating the actual position information of the vehicle on the road includes:

S11. The first convolutional neural network estimates the three-dimensional bounding box information and vehicle model information of the vehicle;

S12, using the position of the three-dimensional bounding box in the image to filter the point cloud image;

S13. Input the filtered millimeter-wave radar point cloud image and the three-dimensional bounding box information of the vehicle into the second convolutional neural network;

S14. The second convolutional neural network estimates the actual position information of the vehicle.

In this embodiment, the method for estimating the actual position information of the vehicle on the road is specifically: generating a point cloud image of the millimeter-wave radar data according to the acquired millimeter-wave radar data; using the first convolutional neural network to generate a three-dimensional surrounding of the vehicle from the image data Frame, project the vehicle's three-dimensional bounding box onto the two-dimensional image plane to form a two-dimensional bounding box, use the vehicle's two-dimensional bounding box to filter the millimeter-wave radar point cloud, and filter out the radar point cloud of the same vehicle; the screened radar point cloud The three-dimensional bounding box information of the cloud and the vehicle is input to the second convolutional neural network to estimate the specific position information of the three-dimensional center of the vehicle on the road. Encode the output of the detector into a string in JSON format, and send the data to the client through the network transmission protocol WebSocket.

In this embodiment, the first convolutional neural network is combined with a deep aggregation feature extraction network architecture, and the overall structure of the first convolutional neural network is shown in FIG. 4 .

The composition of each module in Figure 4 is shown in Figure 5, including known neural network modules:

Conv : convolutional layer;

BN : Batch Normalization/Normalization (Batch Normalization);

Relu: linear rectification function (Rectified Linear Unit);

Concat: tensor splicing;

Pooling: Pooling;

Full connection: full connection layer;

Flatten: fully connected layer;

Sigmoid: Sigmoid activation function for neural networks.

In this embodiment, the structure of the second convolutional neural network is shown in FIG. 6 .

S2. Encode the output of the detector into a string in JSON format, and send the data to the client through the network transmission protocol WebSocket.

In this embodiment, the actual vehicle position and vehicle model information estimated by the server-side neural network are encoded into a string in JSON format, and then the vehicle position information and model information are sent to multiple clients through the WebSocket network protocol, see Figure 7 shown.

In this embodiment, the WebSocket is based on the TCP protocol and can provide a reliable connection between the client and the server.

S3. Multiple clients are established, and the clients receive and decode the data sent by the server to obtain the model and location information of all vehicles.

In this embodiment, based on the WebSocket transmission protocol, the server data can share the detected vehicle data with multiple clients at the same time, and each client can obtain the location and model information of the vehicle. Among them, the server encodes the actual position and vehicle model information of all vehicles on the road into data in JSON string format, and pushes the encoded data to multiple clients through the network transmission protocol.

S4. Establish a 3D model database of the vehicle type on the client terminal, and display the model at a corresponding position according to the obtained vehicle model and position information.

In this embodiment, the client establishes a vehicle three-dimensional model database, as shown in Figure 8, after receiving the JSON string information, the client decodes the data packet to obtain the model and location information of the vehicle, and searches for a suitable model in the three-dimensional model database. Vehicle models, and build road models in the virtual three-dimensional space, map the vehicle models to the road model for display according to the actual position information of the vehicles, re-establish the actual conditions of traffic flow on the road, and display them in an all-round way.

In the embodiment of the present invention, a high-precision three-dimensional vehicle model is used to achieve a better visualization effect. Users can customize various types of vehicle model styles, and according to the performance of the client hardware, the user can change the fineness of the model so that the display The frame rate reached the ideal level.

The loading of the vehicle model utilizes WebGL technology, so that the client only needs to visit a specific webpage to watch the scene of the 3D reconstruction of the vehicle.

Among them, the client counts and displays the number of trucks, trucks, and cars based on the decoded data; the client uses WebGL to reconstruct and display the 3D scene of traffic flow on the road. The display content includes vehicle models, vehicle location information and vehicle model.

S5. The client terminal integrates the vehicle quantity statistics function, the server connection status display function and the 3D scene display function to form a complete real-time display terminal of traffic flow, as shown in FIG. 9 .

In this embodiment, the vehicle counting function can display the number of different types of vehicles, and in the embodiment of the present invention, it can display the number of cars, trucks and trucks.

The display of the three-dimensional scene in the embodiment of the present invention is a 360-degree omni-directional display, and the user can switch the viewing angle by dragging the mouse on the client terminal, as shown in Fig. 10 and Fig. 11 .

It should be noted that in the three-dimensional visual display of vehicles, according to the processed output data, the specific location, driving speed, vehicle model, license plate and other information of the vehicle can be displayed. Among them, according to the output vehicle model information in a car The correct model is selected from the 3D model library. In this embodiment, the models can be classified into car models, motorcycle models, truck models, truck models, and bus models. The screened models will be combined with the output position information and used for 3D visualization using WebGL.

In other embodiments of the present invention, WebGL can be replaced by OpenGL when displaying the three-dimensional reconstruction of road traffic flow, but the effect is the same.

The invention provides a method for three-dimensional reconstruction of road traffic flow, which can reduce the huge communication overhead caused by directly sharing video information of road traffic flow between clients. Use the neural network to estimate the actual position and vehicle model of the vehicle from the data of the camera and millimeter-wave radar, store it on the server side in the form of text, and encode it into a string in JSON format, and send it to multiple clients through WebSocket. The terminal decodes the information, matches the vehicle model from the established vehicle three-dimensional model library according to the vehicle model information, and uses the actual position information of the vehicle to map the vehicle model to the virtual road model for display. The invention enables the traffic flow on the road to be three-dimensionally reconstructed by the client without sharing the video stream, reduces the overhead of signal transmission, is beneficial to the sharing and interaction of traffic information, and is beneficial to the development of intelligent traffic technology.

It should be understood that although the above description is in a certain order, these steps are not necessarily executed in sequence in the above order. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, some of the steps in this embodiment may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be executed at different times, and the order of execution of these steps or stages is also different. It must be performed sequentially, but may be performed alternately or alternately with other steps or at least a part of steps or stages in other steps.

In one embodiment of the present invention, a computer device is also provided in the embodiment of the present invention, including at least one processor, and a memory connected to the at least one processor in communication, and the memory stores information that can be The instructions executed by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor executes the method for three-dimensional reconstruction of road traffic flow, and the above method is realized when the processor executes the instructions.

In one embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the method for three-dimensional reconstruction of road traffic flow.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be realized by instructing related hardware through computer programs represented by computer instructions, and the computer programs can be stored in a non-volatile computer. In the readable storage medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile memory and volatile memory.

Nonvolatile memory may include read only memory, magnetic tape, floppy disk, flash memory, or optical memory, among others. Volatile memory can include random access memory or external cache memory. By way of illustration and not limitation, RAM can take various forms, such as static random access memory or dynamic random access memory, among others.

To sum up, the three-dimensional reconstruction method, computer equipment and storage medium of the road traffic flow provided by the present invention can be used in the detection and reconstruction display of the road traffic flow in the currently known application fields, as well as the current intelligent transportation, automatic driving, and road management and control. , Transportation planning field.

Compared with the present technology, the present invention has two advantages. The first point is to reduce the huge communication overhead caused by sharing the video stream of road vehicles between the traffic monitoring station and the user end. At present, the road monitoring data is generally shared between the traffic flow monitoring station and the client by directly sharing the video data stream. The increase in the number of clients will bring huge communication overhead. The present invention uses the neural network to estimate the actual position and model of the vehicle from the data of the camera and millimeter-wave radar, encodes the actual position and model of the vehicle into data in a string format, and uses the network transmission protocol WebSocket to reliably transmit the data to the client , reducing the communication overhead caused by data transmission between the server and the client. The second point is that the traffic flow on the road can be reconstructed and displayed in 3D on the client side, which is conducive to the development of intelligent transportation. The detection information of the current road detection system can only be displayed in two dimensions in the form of text, which is not intuitive enough. The present invention utilizes the position information of the vehicle estimated at the first point, integrates the model of the vehicle, screens the models with the help of the vehicle three-dimensional model library, maps the vehicle model to the road model according to the actual position of the vehicle, and can intuitively display the road vehicle status.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. within range.

Claims (8)

1. A road traffic flow three-dimensional reconstruction method is characterized by comprising the following steps:

the server acquires data of the millimeter wave radar and the camera;

estimating the actual position of the vehicle on the road and the vehicle model information by using a neural network;

the server encodes the actual positions and vehicle model information of all vehicles on the road into data in a JSON character string format, and pushes the encoded data to a plurality of clients through a network transmission protocol;

the client establishes a vehicle three-dimensional model database and is responsible for decoding the received JSON format data packet, acquiring the vehicle model and actual position information and establishing a virtual road model;

the client matches a three-dimensional model corresponding to the vehicle in a vehicle three-dimensional model database according to the vehicle model obtained by the output decoding, maps the vehicle three-dimensional model to a virtual road model according to the actual position information of the vehicle, reestablishes the actual condition of traffic flow on the road, and displays the actual condition in all directions;

the method for estimating the actual position of the vehicle on the road and the vehicle model information by using the neural network comprises the following steps:

generating a three-dimensional bounding box of the vehicle and an estimated model of the vehicle in the image data by using a target detection neural network;

projecting the vehicle three-dimensional surrounding frame to a two-dimensional image plane to form a target two-dimensional surrounding frame;

and screening the millimeter wave radar point cloud picture of each vehicle by using the formed two-dimensional bounding box, and combining the three-dimensional bounding box information containing the vehicle attitude information with the screened millimeter wave radar point cloud information to estimate the actual position of the vehicle in the real world.

2. The method for three-dimensional reconstruction of road traffic flow according to claim 1, wherein the method for obtaining the data of the millimeter wave radar and the camera is to install the millimeter wave radar and the camera sensor on a speed measuring gantry of the road monitoring station, and obtain the millimeter wave radar data and the camera image data through the measurement of the camera sensor and the millimeter wave radar respectively.

3. The method for three-dimensional reconstruction of road traffic stream according to claim 2, wherein the method of estimating the actual position of the vehicle on the road and the vehicle model information further comprises: the camera sensor and the millimeter wave radar are connected with the data processing server, and a vehicle information detector based on a neural network is deployed on the server to detect the actual position and the vehicle model information of the vehicle.

4. The method for three-dimensional reconstruction of road traffic flow according to claim 1, wherein the server encodes the detected vehicle position information and vehicle model information into a JSON character string form, and transmits data to the clients by using a WebSocket transmission protocol, and the vehicle position information and the vehicle model information are shared to the clients so that three-dimensional display images of the road vehicles are displayed at terminals of the clients.

5. The three-dimensional road traffic flow reconstruction method according to claim 1, further comprising the steps of counting and displaying the number of trucks, trucks and cars by the client according to the decoded data; the client side utilizes a 3D drawing protocol WebGL (Web Graphics Library) to reconstruct and display a three-dimensional scene of traffic flow on the road, and display contents comprise models of vehicles, position information of the vehicles and vehicle models.

6. The method for three-dimensional reconstruction of road traffic flow according to claim 5, characterized in that the client is further used for integrating a three-dimensional image display function, a vehicle number display function and a display function of a connection state of the client and the server to form a real-time traffic flow display terminal.

7. A computer device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to cause the at least one processor to perform the method of three-dimensional reconstruction of roadway traffic flows as recited in any one of claims 1-6.

8. A computer-readable storage medium storing computer instructions for causing a computer to execute the method for three-dimensional reconstruction of a road flow according to any one of claims 1 to 6.

Images