CN116127165A - Vehicle position updating method and device, storage medium and electronic device - Google Patents

Abstract

An embodiment of the present invention provides a vehicle location update method, device, storage medium, and electronic device, wherein the method includes: determining the predicted location information of the target vehicle at the second moment according to the location information of the target vehicle at the first moment , where the second moment is later than the first moment; obtain the vehicles located within the target range at the second moment, and obtain the first vehicle set, wherein the target range is determined according to the position information of the target vehicle at the first moment; according to the prediction The location information determines the first vehicle that matches the target vehicle in the first vehicle set, and determines the location information of the target vehicle at the second moment as the location information of the first vehicle. Through the embodiments of the present invention, the problem of inaccurate update of the position of the target vehicle existing in the related art is solved.

Description

Vehicle location updating method, device, storage medium and electronic device

Technical Field

The embodiments of the present invention relate to the field of vehicle detection, and in particular, to a method, device, storage medium and electronic device for updating the position of a vehicle.

Background Art

With the continuous optimization and upgrading of deep learning network models, as well as adaptive research on vehicle issues, the vehicle detection and tracking problems based on video images have been greatly solved, and the real-time detection and tracking capabilities of vehicle targets have been greatly improved. However, high-precision target detection and tracking capabilities cannot be achieved in all scenarios. For example, during rush hour, parking queues at red lights, and other situations, the vehicles in the lanes are too dense, and there are often problems such as multiple inspections, missed inspections, and target ID jumps of vehicle targets. Multiple inspections, missed inspections, and target ID jumps of vehicle targets will lead to inaccurate updates of the target vehicle's position, which in turn restricts the accuracy of vehicle counting. Therefore, in the relevant technologies, there is a problem of inaccurate updates of the target vehicle's position.

With regard to the problem of inaccurate position update of the target vehicle existing in the related art, no effective solution has been proposed yet.

Summary of the invention

Embodiments of the present invention provide a vehicle position update method, device, storage medium and electronic device to at least solve the problem of inaccurate position update of a target vehicle existing in the related art.

According to one embodiment of the present invention, a vehicle position update method is provided, comprising: determining predicted position information of the target vehicle at a second moment based on position information of the target vehicle at a first moment, wherein the second moment is later than the first moment; acquiring vehicles within a target range at the second moment to obtain a first vehicle set, wherein the target range is determined based on the position information of the target vehicle at the first moment; determining a first vehicle matching the target vehicle in the first vehicle set based on the predicted position information, and determining the position information of the first vehicle as the position information of the target vehicle at the second moment.

According to another embodiment of the present invention, a vehicle position update device is also provided, including: a first determination module, used to determine the predicted position information of the target vehicle at a second moment based on the position information of the target vehicle at a first moment, wherein the second moment is later than the first moment; an acquisition module, used to acquire vehicles that are located within a target range at the second moment, and obtain a first vehicle set, wherein the target range is determined based on the position information of the target vehicle at the first moment; a second determination module, used to determine a first vehicle matching the target vehicle in the first vehicle set based on the predicted position information, and determine the position information of the first vehicle as the position information of the target vehicle at the second moment.

According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

Through the present invention, by predicting the position information of the target vehicle at the second moment, determining the first vehicle matching the target vehicle in the first vehicle set according to the predicted position information, accurately finding the vehicle matching the target vehicle among the vehicles identified at the second moment, and determining the position information of the target vehicle at the second moment as the position information of the first vehicle, the accurate update of the position of the target vehicle at different moments is achieved. Therefore, the problem of inaccurate position update of the target vehicle existing in the related art is solved, and the effect of improving the accuracy of the position update of the target vehicle is achieved.

BRIEF DESCRIPTION OF THE DRAWINGS

1 is a block diagram of the hardware structure of a mobile terminal of a vehicle location update method according to an embodiment of the present invention;

FIG2 is a flow chart of a method for updating a vehicle's position according to an embodiment of the present invention;

FIG3 is a schematic diagram of a target vehicle detection area according to an embodiment of the present invention;

FIG4 is a schematic diagram of determining a first vehicle set according to an embodiment of the present invention;

5 is a schematic diagram of a process of updating the position of a vehicle according to a specific embodiment of the present invention;

FIG. 6 is a structural block diagram of a device for updating a position of a vehicle according to an embodiment of the present invention.

DETAILED DESCRIPTION

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with the embodiments.

It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, FIG1 is a block diagram of the hardware structure of a mobile terminal of the vehicle location update method of an embodiment of the present invention. As shown in FIG1 , the mobile terminal may include one or more (only one is shown in FIG1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that the structure shown in FIG1 is only for illustration and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than those shown in FIG1 , or have a configuration different from that shown in FIG1 .

The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the vehicle location update method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

In this embodiment, a method for updating the position of a vehicle is provided. FIG. 2 is a flow chart of the method for updating the position of a vehicle according to an embodiment of the present invention. As shown in FIG. 2 , the process includes the following steps:

Step S202, determining predicted position information of the target vehicle at a second moment according to the position information of the target vehicle at a first moment, wherein the second moment is later than the first moment;

Step S204, acquiring vehicles located within a target range at the second moment to obtain a first vehicle set, wherein the target range is determined according to the position information of the target vehicles at the first moment;

Step S206: determining a first vehicle matching the target vehicle in the first vehicle set according to the predicted position information, and determining the position information of the first vehicle as the position information of the target vehicle at the second moment.

In this embodiment, the target vehicle is a vehicle identified in a first image taken at a first moment. The position of the target vehicle in the first image is mapped to the actual space to obtain the position information of the target vehicle at the first moment. The position information of the target vehicle at the first moment is predicted to obtain the predicted position information of the target vehicle at the second moment.

Multiple vehicles are identified in the second picture taken at the second moment, and the positions of each vehicle in the actual space at the second moment are determined, and target tracking is performed. The first vehicle is found to be the target vehicle among the multiple vehicles identified in the second picture, and the position information of the first vehicle at the second moment is determined as the position information of the target vehicle at the second moment.

By performing matching operations with multiple vehicles identified in the second image respectively, determine which vehicle is the target vehicle. Before starting the matching operation, perform a preliminary screening on the multiple vehicles identified in the second image: if the position of the target vehicle at the first moment is known, then the position of the target vehicle at the second moment will not be too far away from the position of the target vehicle at the first moment. Therefore, a target range is determined by the position of the target vehicle at the first moment, and the vehicles within the target range at the second moment are added to the first vehicle set. The first vehicle matching the target vehicle is searched in the first vehicle according to the predicted position information, the first vehicle is determined as the target vehicle, and the position information of the first vehicle is determined as the position information of the target vehicle at the second moment.

Through the above steps, by predicting the position information of the target vehicle at the second moment, determining the first vehicle that matches the target vehicle in the first vehicle set according to the predicted position information, accurately finding the vehicle that matches the target vehicle among the vehicles identified at the second moment, and determining the position information of the first vehicle as the position information of the target vehicle at the second moment, the accurate update of the position of the target vehicle at different moments is achieved. Therefore, the problem of inaccurate position update of the target vehicle existing in the related art is solved, and the effect of improving the accuracy of the position update of the target vehicle is achieved.

Optionally, a special target vehicle detection area can be set up. Figure 3 is a schematic diagram of a target vehicle detection area according to an embodiment of the present invention. As shown in Figure 3, the target vehicle detection area can be set at a preset distance from the intersection. Adjacent vehicles in this area are clearly spaced apart, vehicle features are more accurate, video vehicle target detection is highly accurate, and the probability of missed or false detection of targets is low, thereby providing accurate vehicle count and location information for the vehicle statistics link.

You can perform vehicle detection in the target detection area, obtain the number and position of vehicles currently in the target detection area, and establish the current target sequence and the corresponding target frame sequence:

V _trg1 , Box _trg1

V _trg2 , Box _trg2

V _trg3 , Box _trg3

Among them, V _trgi represents the vehicle ID, and Box _trgi represents the target box position corresponding to the vehicle.

分别表示左上，右上，左下，右下四个点的像素坐标。in

Represents the pixel coordinates of the upper left, upper right, lower left, and lower right points respectively.

Get the center position U _t of the video target frame, and combine it with the camera calibration system to get the actual spatial position information X _t corresponding to the video target, that is:

Among them, f(x) is the camera calibration system.

In an optional embodiment, in determining the position information of the target vehicle at the second moment as the position information of the first vehicle, the method further includes: determining whether the target vehicle has arrived at a preset position based on the position information of the target vehicle at the second moment; when the target vehicle arrives at the preset position, adding the target vehicle to a target vehicle set, and determining the arrival time of the target vehicle as the second moment, wherein the target vehicle set records the vehicles that have arrived at the preset position and the arrival time corresponding to each vehicle; and determining the traffic flow within the preset time period by the number of vehicles in the target vehicle set that arrive at the preset position within the preset time period.

In this embodiment, after the position information of the target vehicle at the second moment is determined, whether the target vehicle has reached the preset position is determined based on the position information of the target vehicle at the second moment. If the target vehicle has reached the preset position, the target vehicle is added to the target vehicle set, and the time when the target vehicle arrives at the preset position is recorded.

Among them, the preset position can be a line set on the road. The number of vehicles crossing this line is counted to count the traffic flow. The traffic flow counted by the number of vehicles in the above target vehicle set will not be counted repeatedly, thereby ensuring the accuracy of the traffic flow statistics.

When counting the traffic volume in a preset time period, the traffic volume in the preset time period is determined by determining the number of vehicles in the target vehicle set that arrive at the preset position within the preset time period.

Optionally, the following formula can be used to determine whether the target vehicle has reached the preset position:

为目标车辆在所述第二时刻的位置信息。

则判定目标车辆达到预设位置。Where c is the position value of the preset position,

is the position information of the target vehicle at the second moment.

It is determined that the target vehicle reaches the preset position.

In an optional embodiment, determining the predicted position information of the target vehicle at a second moment based on the position information of the target vehicle at a first moment includes: obtaining a first target frame for identifying the target vehicle in a first image, wherein the first image is an image captured by a target shooting device at the first moment; determining the position information of the target vehicle at the first moment based on coordinate information of the first target frame; and inputting the position information of the target vehicle at the first moment into a target prediction model to obtain the predicted position information of the target vehicle at the second moment.

In this embodiment, when predicting the position information of the target vehicle at the second moment, the position information of the target vehicle at the first moment is first determined: the target shooting device is fixed at a fixed position, and the image is shot by the fixed position. The target vehicle is identified in the first image shot at the first moment, and the target vehicle is identified by a first target frame in the first image. The position information of the target vehicle at the first moment is determined by the coordinate information of the target frame in the first image, and the position information of the target vehicle at the first moment is input into the target prediction model. The position is predicted by the prediction model to obtain the predicted position information of the target vehicle at the second moment.

It should be noted that after the target shooting device is fixed, calibration is performed through a calibration system in the target shooting device so that the coordinates of the pixel points in the image shot by the target shooting device can be mapped to positions in the actual space.

By inputting the position information x(k-1) of the target vehicle at the first moment, the target prediction model outputs the predicted position information x(k) of the target vehicle at the second moment.

The target prediction model can be a Kalman filter algorithm model. The Kalman filter algorithm tracks the predicted target position information in real time according to the state model and observation model of the system. In this embodiment, a discrete dynamic system should be selected, which is composed of a q-dimensional dynamic system and an r-dimensional observation system. Among them, the state model of the q-dimensional dynamic system is:

x(k)＝Ax(k-1)+w(k-1)

Where w(k) is the state model error.

The covariance matrix of w(k) is:

Q(k)＝E[w(k)w(k) ^T ]

The observation model of the r-dimensional observation system is:

y(k)＝F(k)+v(k)

Where F(k) is the observation system model, v(k) is the observation system model error, and the covariance matrix of v(k) is:

R(k)＝E[v(k)v(k) ^T ]

Kalman filter covariance prediction equation:

P ₁ (k) = AP (k-1) ^AT + Q (k)

Filter gain equation:

K(k)＝P ₁ (k)C ^T [CP ₁ (k)C ^T +R(k)] ^-1

Filter covariance equation:

P(x)＝P ₁ (k)-K(k)CP ₁ (k)

Filter estimation equation:

The prediction estimation equation is:

The state vector x(k) in the Kalman filter model is:

x(k)＝[x,y,v _x ,v _y ]

Measurement vector y(k):

y(k)＝[x ^′ ,y ^′ ] ^T

The system parameters are A:

In an optional embodiment, the acquiring of vehicles located within the target range at the second moment to obtain the first vehicle set includes: acquiring a second target frame set, wherein the target frames in the second target frame set correspond one-to-one to the vehicles in the second vehicle set, the second target frame set includes a target frame in a second image for identifying each vehicle in the second vehicle set, the second vehicle set includes vehicles identified in the second image, and the second image is an image captured by a target shooting device at the second moment; determining the position information of each vehicle in the second vehicle set at the second moment according to the coordinate information of each target frame in the second target frame set; searching the second vehicle set for vehicles whose position information at the second moment is within the target range, and determining the found vehicles as the first vehicle set.

In this embodiment, all vehicles identified in the second image taken by the target shooting device at the second moment constitute a second vehicle set, and a target box is used to identify each vehicle in the second image. All target boxes in the second image constitute a second target box set, and the position information of each vehicle in the second vehicle set at the second moment is determined by the coordinate information of each target box in the second target box set in the second image. Then, based on the position information of each vehicle in the second vehicle set at the second moment, the vehicles whose position information at the second moment is within the target range are determined in the second vehicle set and determined as the first vehicle set.

Figure 4 is a schematic diagram of determining the first vehicle set according to an embodiment of the present invention. As shown in Figure 4, five vehicles (labeled 1, 2, 3, 4, and 5 respectively) are identified in the second image, and the position information of the five vehicles at the second moment is _x2,1 , _x2,2 , _x2,3 , _x2,4 , and _x2,5 respectively. The target range is shown as the dotted circle in Figure 4, where vehicle 2 and vehicle 3 are within the target range, and the first vehicle set includes vehicle 1 and vehicle 2.

In an optional embodiment, determining the first vehicle that matches the target vehicle in the first vehicle set includes: determining a matching relationship loss value between each vehicle in the first vehicle set and the target vehicle, wherein the matching relationship loss value is used to represent the error between the matching of each vehicle in the first vehicle set and the target vehicle; and determining the vehicle with the smallest matching relationship loss value in the first vehicle set as the first vehicle that matches the target vehicle.

In this embodiment, the target vehicle is matched with each vehicle in the first vehicle set, and a matching relationship loss value is calculated, and the vehicle with the smallest loss value is determined as the vehicle matching the target vehicle.

As shown in Figure 3, the first vehicle set includes vehicle 1 and vehicle 2. The matching relationship loss value between vehicle 1 and the target vehicle is calculated respectively. If it is 0.2, the matching relationship loss value between vehicle 2 and the target vehicle is calculated. If it is 0.1, the matching relationship loss value between vehicle 2 and the target vehicle is smaller, then vehicle 2 is matched with the target vehicle, that is, vehicle 2 is the target vehicle.

In an optional embodiment, determining the matching relationship loss value between each vehicle in the first vehicle set and the target vehicle includes: performing the following operations for each vehicle in the first vehicle set, when performing the following operations, each vehicle in the first vehicle set is the current vehicle: determining a first loss value according to the position information of the current vehicle at the second moment and the predicted position information of the target vehicle at the second moment, wherein the first loss value represents the center of mass loss value between the current vehicle and the target vehicle; determining a second loss value according to a current target frame and a first target frame used to identify the current vehicle in the second image, wherein the first target frame is a target frame used to identify the target vehicle in the first image, the first image is an image captured by the target capturing device at the first moment, and the first loss value represents the overlapping area loss value between the current target frame and the first target frame; determining a third loss value according to the current target frame and the first target frame, wherein the first loss value represents the area similarity loss value between the current vehicle and the target vehicle; determining the matching relationship loss value between the current vehicle and the target vehicle according to the first loss value, the second loss value and the third loss value.

In this embodiment, the matching relationship loss value is determined by loss values of three different latitudes, including: a first loss value, a second loss value, and a third loss value, wherein the first loss value represents a centroid loss value, the second loss value represents an overlapping area loss value, and the third loss value represents an area similarity loss value;

Normalize the first loss value, the second loss value, and the third loss value:

D(n,m)＝D(n,m)/maxD(n,*)

L(n,m)＝L(n,m)/maxL(n,*)

ΔS(n,m)＝ΔS(n,m)/maxΔS(n,*)

Among them, n represents the target vehicle, m represents a vehicle in the vehicle, * represents all vehicles in the first vehicle set, D(n,m) is the first loss value, L(n,m) is the second loss value, and ΔS(n,m) is the third loss value.

The matching relationship loss value is:

loss(n,m)=αD(n,m)+βL(n,m)+γΔS(n,m)

Among them, α, β, and γ are all preset values.

In an optional embodiment, determining the second loss value based on the current target frame and the first target frame used to identify the current vehicle in the second image includes: determining the overlapping area between the current target frame and the first target frame and the first area of the first target frame; determining the ratio of the overlapping area to the first area; and determining the difference between the ratio and 1 as the second loss value.

In this embodiment, the second loss value is calculated by the current target frame and the first target frame:

为第一目标框的第一面积。Wherein, S is the overlapping area between the current target frame and the first target frame,

is the first area of the first target box.

In an optional embodiment, determining the third loss value based on the current target box and the first target box includes: determining the second area of the current target box and the first area of the first target box; and determining the third loss value based on the difference between the first area and the second area.

In this embodiment, the third loss value is determined by the current target frame and the first target frame:

为当前目标框的第二面积，

为第一目标框的第一面积。in,

is the second area of the current target box,

is the first area of the first target box.

Optionally, the first loss value is determined by using the position information of the current vehicle at the second moment and the predicted position information of the target vehicle at the second moment:

为当前车辆在所述第二时刻的位置信息，

为目标车辆在第二时刻的预测位置信息。in,

is the position information of the current vehicle at the second moment,

is the predicted position information of the target vehicle at the second moment.

Obviously, the above-described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

The present invention will be specifically described below in conjunction with embodiments:

FIG5 is a schematic diagram of a process of updating the position of a vehicle according to a specific embodiment of the present invention, as shown in FIG5 , including:

Step 1: Start. The program starts. Go to step 2.

Step 2: Initialization. Set the preset position, target detection area, etc., and jump to step 3.

Step 3: Camera calibration. This step mainly solves the correspondence between the video pixel value and the actual space distance. The accuracy of video calibration affects the accuracy of subsequent vehicle flow statistics. Jump to step 4.

Step 4: Video target vehicle detection. Use artificial intelligence methods such as deep learning to detect the number and location of target vehicles and assign a unique ID to each target vehicle. Go to step 5.

Step 5: Video target vehicle tracking. The purpose of this step is to have a stable ID for the same target vehicle. Go to step 6.

Step 6: Extract the target frame position point. Based on the target frame position in the video, extract the target frame center point. And map the target frame center point to the actual position in the world coordinate system through the calibration algorithm, and jump to step 7.

Step 7: Obtain the number and status information of target vehicles in the target detection area according to the actual position information of the target. Go to step 8.

Step 8: Update the target vehicle prediction based on the Kalman filter algorithm. Go to step 9.

Step 9: Obtain a first vehicle set based on a preset range. Go to step 10.

Step 10: Calculate the loss value. For each vehicle in the first vehicle set, calculate the loss value with respect to the target vehicle. Jump to step 11.

Step 11: Select the best match. From all loss values, select the vehicle with the smallest loss value as the target vehicle. Go to step 12.

Step 12: Determine whether the vehicle has reached the preset location and perform vehicle flow statistics. If the vehicle has not reached the preset location, jump to step 8 to further predict the target state. If not, jump to step 13.

Step 13: End.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

In this embodiment, a vehicle position updating device is also provided. FIG. 6 is a structural block diagram of a vehicle position updating device according to an embodiment of the present invention. As shown in FIG. 6 , the device includes:

A first determining module 602, configured to determine predicted position information of the target vehicle at a second moment according to the position information of the target vehicle at a first moment, wherein the second moment is later than the first moment;

An acquisition module 604 is used to acquire vehicles located within a target range at the second moment to obtain a first vehicle set, wherein the target range is determined according to the position information of the target vehicles at the first moment;

The second determination module 606 is used to determine a first vehicle matching the target vehicle in the first vehicle set according to the predicted position information, and determine the position information of the first vehicle as the position information of the target vehicle at the second moment.

In an optional embodiment, the above-mentioned device is also used to determine whether the target vehicle has arrived at the preset position based on the position information of the target vehicle at the second moment; when the target vehicle arrives at the preset position, the target vehicle is added to the target vehicle set, and the arrival time of the target vehicle is determined to be the second moment, wherein the target vehicle set records the vehicles that have arrived at the preset position and the corresponding arrival time of each vehicle; the number of vehicles in the target vehicle set that arrive at the preset position within the preset time period is used to determine the traffic flow within the preset time period.

In an optional embodiment, the above-mentioned device is also used to obtain a first target frame for identifying the target vehicle in a first image, wherein the first image is an image captured by a target shooting device at the first moment; determine the position information of the target vehicle at the first moment based on the coordinate information of the first target frame; input the position information of the target vehicle at the first moment into a target prediction model to obtain the predicted position information of the target vehicle at the second moment.

In an optional embodiment, the above-mentioned device is also used to obtain a second target frame set, wherein the target frames in the second target frame set correspond one-to-one to the vehicles in the second vehicle set, the second target frame set includes target frames in the second image for identifying each vehicle in the second vehicle set, the second vehicle set includes vehicles identified in the second image, and the second image is an image captured by a target shooting device at the second moment; determine the position information of each vehicle in the second vehicle set at the second moment according to the coordinate information of each target frame in the second target frame set; search for vehicles in the second vehicle set whose position information at the second moment is within the target range, and determine the found vehicles as the first vehicle set.

In an optional embodiment, the above-mentioned device is also used to determine the matching relationship loss value between each vehicle in the first vehicle set and the target vehicle, wherein the matching relationship loss value is used to represent the matching error between each vehicle in the first vehicle set and the target vehicle; and the vehicle with the smallest matching relationship loss value in the first vehicle set is determined as the first vehicle that matches the target vehicle.

In an optional embodiment, the above-mentioned device is also used to perform the following operations for each vehicle in the first vehicle set, and when performing the following operations, each vehicle in the first vehicle set is the current vehicle: determine a first loss value based on the position information of the current vehicle at the second moment and the predicted position information of the target vehicle at the second moment, wherein the first loss value represents the center of mass loss value between the current vehicle and the target vehicle; determine a second loss value based on the current target frame and the first target frame used to identify the current vehicle in the second image, wherein the first target frame is the target frame used to identify the target vehicle in the first image, and the first image is an image captured by the target shooting device at the first moment, and the first loss value represents the overlapping area loss value between the current target frame and the first target frame; determine a third loss value based on the current target frame and the first target frame, wherein the first loss value represents the area similarity loss value between the current vehicle and the target vehicle; determine the matching relationship loss value between the current vehicle and the target vehicle based on the first loss value, the second loss value and the third loss value.

In an optional embodiment, the above-mentioned device is also used to determine the overlapping area between the current target frame and the first target frame and the first area of the first target frame; determine the ratio of the overlapping area to the first area; and determine the difference between the ratio and 1 as the second loss value.

In an optional embodiment, the above-mentioned device is also used to determine the second area of the current target frame and the first area of the first target frame; and determine the third loss value according to the difference between the first area and the second area.

It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

In an exemplary embodiment, the electronic device may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.

For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims (10)

1. A method for updating the position of a vehicle, comprising: Determining predicted position information of the target vehicle at a second moment according to the position information of the target vehicle at a first moment, wherein the second moment is later than the first moment; Acquire vehicles located within a target range at the second moment to obtain a first vehicle set, wherein the target range is determined according to position information of the target vehicles at the first moment; A first vehicle matching the target vehicle is determined in the first vehicle set according to the predicted position information, and the position information of the first vehicle is determined as the position information of the target vehicle at the second moment. 2. The method according to claim 1, characterized in that, after determining the position information of the target vehicle at the second moment as the position information of the first vehicle, the method further comprises: Determining whether the target vehicle has reached a preset position according to the position information of the target vehicle at the second moment; When the target vehicle arrives at the preset position, the target vehicle is added to a target vehicle set, and the arrival time of the target vehicle is determined to be the second moment, wherein the target vehicle set records the vehicles that have arrived at the preset position and the arrival time corresponding to each vehicle; The vehicle flow rate within the preset time period is determined by the number of vehicles in the target vehicle set that arrive at the preset position within the preset time period. 3. The method according to claim 1, characterized in that the step of determining the predicted position information of the target vehicle at the second moment based on the position information of the target vehicle at the first moment comprises: Acquire a first target frame for identifying the target vehicle in a first image, wherein the first image is an image captured by a target capturing device at the first moment; Determining the position information of the target vehicle at the first moment according to the coordinate information of the first target frame; The position information of the target vehicle at the first moment is input into a target prediction model to obtain the predicted position information of the target vehicle at the second moment. 4. The method according to claim 1, characterized in that the acquiring of the vehicles located within the target range at the second moment to obtain the first vehicle set comprises: Acquire a second target frame set, wherein the target frames in the second target frame set correspond one-to-one to the vehicles in the second vehicle set, the second target frame set includes target frames in the second image for identifying each vehicle in the second vehicle set, the second vehicle set includes vehicles identified in the second image, and the second image is an image captured by the target capturing device at the second moment; Determining the position information of each vehicle in the second vehicle set at the second moment according to the coordinate information of each target frame in the second target frame set; The second vehicle set is searched for vehicles whose position information at the second moment is within the target range, and the searched vehicles are determined as the first vehicle set. 5. The method according to claim 4, characterized in that the determining the first vehicle matching the target vehicle in the first vehicle set comprises: Determine a matching relationship loss value between each vehicle in the first vehicle set and the target vehicle, wherein the matching relationship loss value is used to represent an error in matching each vehicle in the first vehicle set with the target vehicle; The vehicle with the smallest matching relationship loss value in the first vehicle set is determined as the first vehicle matching the target vehicle. 6. The method according to claim 5, characterized in that the determining of the matching relationship loss value between each vehicle in the first vehicle set and the target vehicle comprises: Perform the following operations for each vehicle in the first vehicle set, where each vehicle in the first vehicle set is a current vehicle: Determine a first loss value according to the position information of the current vehicle at the second moment and the predicted position information of the target vehicle at the second moment, wherein the first loss value represents a center of mass loss value between the current vehicle and the target vehicle; Determine a second loss value according to a current target frame and a first target frame in the second image for identifying the current vehicle, wherein the first target frame is a target frame in the first image for identifying the target vehicle, the first image is an image captured by the target capturing device at the first moment, and the first loss value represents an overlapping area loss value between the current target frame and the first target frame; Determine a third loss value according to the current target frame and the first target frame, wherein the first loss value represents an area similarity loss value between the current vehicle and the target vehicle; A matching relationship loss value between the current vehicle and the target vehicle is determined according to the first loss value, the second loss value and the third loss value. 7. The method according to claim 6, characterized in that Determining the second loss value according to the current target frame and the first target frame used to identify the current vehicle in the second image includes: determining an overlapping area between the current target frame and the first target frame and a first area of the first target frame; determining a ratio of the overlapping area to the first area; and determining a difference between the ratio and 1 as the second loss value; Determining the third loss value based on the current target frame and the first target frame includes: determining the second area of the current target frame and the first area of the first target frame; and determining the third loss value based on the difference between the first area and the second area. 8. A vehicle position updating device, comprising: A first determining module, configured to determine predicted position information of the target vehicle at a second moment according to position information of the target vehicle at a first moment, wherein the second moment is later than the first moment; An acquisition module, used for acquiring vehicles located within a target range at the second moment to obtain a first vehicle set, wherein the target range is determined according to position information of the target vehicles at the first moment; A second determination module is used to determine a first vehicle matching the target vehicle in the first vehicle set according to the predicted position information, and determine the position information of the first vehicle as the position information of the target vehicle at the second moment. 9. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented. 10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of claims 1 to 7 when executing the computer program.

Images