WO2022062377A1 - Calibration method and calibration apparatus for camera, and electronic device - Google Patents

Abstract

A calibration method and calibration apparatus for a camera, an electronic device and a computer-readable storage medium. The camera is installed in a vehicle, and the calibration method comprises: by means of the camera, acquiring a target image comprising other vehicles and at least two lane lines (101), wherein the other vehicles are vehicles other than the vehicle installed with the camera; fitting the lane lines to obtain an intersection point (102); acquiring the actual vehicle heights of the other vehicles (103); and on the basis of the other vehicles in the target image, the actual vehicle heights, the intersection point, and camera parameters of the camera, calculating pose parameters of the camera (104). The method may automatically calibrate the camera installed on the vehicle, and significantly saves on costs.

Description

A camera calibration method, calibration device and electronic equipment technical field

The present application belongs to the technical field of calibration, and in particular, relates to a calibration method for a camera, a calibration device, an electronic device, and a computer-readable storage medium.

Background technique

With the rapid development of highway traffic, the accident rate of traffic accidents, especially malignant traffic accidents, is increasing. For the consideration of traffic safety, more and more vehicles are currently equipped with driving safety assistance systems to increase the safety of drivers and vehicles. The realization of various functions of the driving safety assistance system is premised on the perception of the surrounding environment. For example, one or more cameras are used to obtain visual signals such as traffic signals, traffic patterns, road signs and obstacles ahead, and then pass through. The visual image analysis is converted into quantitative information such as traffic signal category or obstacle distance, which provides decision-making basis for functions including safe vehicle distance maintenance, collision avoidance, and safe lane changing.

In computer vision processing, before converting the original image obtained by the camera into a dimensional physical quantity that can be used to provide a basis for decision-making, it is necessary to determine the three-dimensional position and orientation of the camera relative to the world coordinate system where the vehicle is located. A process called calibration.

technical problem

The existing more common calibration method is to manually measure the installation height and angle of the camera, which requires the participation of professionally trained personnel, which is time-consuming, labor-intensive and costly.

technical solutions

In view of this, the present application provides a camera calibration method, a calibration device, an electronic device, and a computer-readable storage medium, which can realize automatic calibration of a camera installed on a vehicle, and significantly save costs.

In a first aspect, the present application provides a method for calibrating a camera, the camera is installed on a vehicle, and the method for calibrating includes:

Acquire a target image including other vehicles and at least two lane lines by using the camera, wherein the other vehicles are vehicles other than the vehicle on which the camera is installed;

Fit the above lane lines to get the intersection point;

Get the actual vehicle height of the other vehicles mentioned above;

Based on the other vehicles in the target image, the actual vehicle height, the intersection, and the camera parameters of the camera, the attitude parameters of the camera are calculated.

In a second aspect, the present application provides a camera calibration device, the camera is mounted on a vehicle, and the calibration device includes:

a first acquisition unit, configured to acquire a target image including other vehicles and at least two lane lines through the camera;

The fitting unit is used to fit the above lane lines to obtain the intersection point;

a second obtaining unit, configured to obtain the actual vehicle heights of the above-mentioned other vehicles;

The calculation unit is configured to calculate and obtain the attitude parameter of the camera based on the other vehicle in the target image, the actual vehicle height, the intersection point and the camera parameter of the camera.

In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor executes the computer program to achieve the above The steps of the method of the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the steps of the method in the first aspect.

In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by one or more processors, the steps of the method of the first aspect are implemented.

beneficial effect

Compared with the prior art, the present application has the following beneficial effects: first, a target image including other vehicles and at least two lane lines is obtained through a camera installed on the vehicle, and then the above lane lines are fitted to obtain the intersection point, which is the same as the At the same time, the actual vehicle heights of the above-mentioned other vehicles will also be obtained, and finally the above-mentioned cameras are calculated based on the other vehicles in the target image, the actual vehicle heights of the other vehicles, the intersections obtained after lane line fitting, and the camera parameters of the camera. The pose parameters are used to calibrate the camera. The above process does not rely on static measurement data at all, and the camera's attitude parameters are completely calculated by software methods, which saves the human resources required for static measurement, makes the calibration process more concise, and can significantly save calibration costs. It can be understood that, for the beneficial effects of the second aspect to the fifth aspect, reference may be made to the relevant description in the first aspect, which is not repeated here.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only for the present application. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is the realization flow chart of the calibration method of the camera provided by the embodiment of the present application;

2 is a schematic diagram of a lane line after fitting in a target image provided by an embodiment of the present application;

3 is a schematic diagram of other vehicles included in the target image provided by the embodiment of the present application;

4 is a schematic diagram of the height of a camera provided by an embodiment of the present application;

5 is a schematic diagram of a camera provided in an embodiment of the present application in a world coordinate system;

6 is a structural block diagram of a camera calibration device provided by an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Embodiments of the present invention

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to illustrate the technical solutions proposed in the present application, the following specific embodiments are used for description.

Example 1

Please refer to FIG. 1. FIG. 1 shows a camera calibration method provided by an embodiment of the present application, and the details are as follows:

Step 101, obtaining a target image including other vehicles and at least two lane lines through the camera;

In the embodiment of the present application, the camera to be calibrated is a camera mounted on a vehicle, and the camera can take pictures of the front or rear of the vehicle. Exemplarily, the camera may be installed on the top of the front/rear windshield of the vehicle, or may be installed at other positions of the vehicle, and the installation position of the camera is not limited here. After the camera is started, it will start to shoot uninterruptedly, and only images that include at least one other vehicle (that is, a vehicle other than the vehicle on which the camera is installed) and at least two lane lines can be used to execute the implementation of this application. For the calibration method proposed in this example, for the convenience of description, the image is denoted as the target image. The electronic device will perform target detection on each frame of images obtained by the camera during the continuous shooting process, specifically to detect whether there is at least one other vehicle and at least two lane lines in the image; if there is no at least one other vehicle in the image, And/or, if there are no at least two lane lines in the image, the image is discarded; on the contrary, if there are at least one other vehicle and at least two lane lines in the image, start to execute the method described in this embodiment of the present application based on the image. the various steps proposed. The above-mentioned electronic device may be a host installed on the vehicle, and the electronic device is not limited here.

In some embodiments, since at least two lane lines are required in the target image, and the vehicle is often in a driving state, there are lane lines around it; based on this, it may be that the vehicle with the camera waiting for calibration is driving Only when the camera is used for shooting, the target image containing lane lines and other vehicles can be obtained under the premise of saving computing resources.

In some embodiments, if there are more than two other vehicles in the target image, one vehicle may be selected as the target other vehicle among the two or more other vehicles, and subsequent steps are performed based on the target other vehicle. Considering that there is distortion when the camera is shooting; and the object closer to the edge of the image, the more severe the distortion; therefore, other vehicles at the center position closest to the target image can be selected as the target other vehicles; The other vehicle with the shortest distance from the center is selected as the target other vehicle.

Step 102: Fitting the above lane lines to obtain the intersection point;

In the embodiment of the present application, although the lane lines are parallel in the actual scene, due to the distortion of the camera when shooting, the lane lines are usually not parallel in the target image obtained by shooting. Please refer to Figure 2, which shows a schematic diagram of the fitted lane lines in the target image. The coordinates of the intersection points between the fitted lane lines in the image coordinate system can be written as (x ^h , y ^h ). When performing fitting, the key points of the lane lines to be fitted can be extracted first, and then each lane line is fitted according to these key points to obtain a straight line corresponding to each lane line, so as to obtain the intersection point. For example, if there are lane A and lane B in the target image, for lane A, several key points A1, A2 and A3 of lane A can be extracted; for lane B, the lane can be extracted Several key points B1, B2 and B3 of B, etc.; finally, the lane line A is fitted according to A1, A2 and A3, and the corresponding straight line A' is obtained; and the lane line B is fitted according to B1, B2 and B3, The corresponding straight line B' is obtained; the intersection point of the straight line A' and the straight line B' in the target image is the intersection point finally obtained in this step. This intersection can be approximated as a skyline position.

In some embodiments, if the vehicle is driving on a road with multiple lanes, there may be multiple lane lines in the target image captured by the camera. In order to improve computational efficiency, when there are multiple lane lines in the target image, any two lane lines can be selected for fitting instead of fitting all lane lines.

Step 103, obtaining the actual vehicle heights of the above-mentioned other vehicles;

In the embodiment of the present application, it is also necessary to obtain the actual vehicle height of the other vehicle. Exemplarily, a database may be preset in which the actual vehicle heights of all currently listed vehicle models are stored; then step 103 may be specifically: find out the vehicle type of the other vehicle in the database, and record it as the target vehicle type ; Then read the actual vehicle height of the target vehicle from the database.

In some embodiments, the database may also store vehicle characteristics of each vehicle type, such as color, outline, shape of vehicle lights, vehicle logo and/or text on the vehicle, etc.; then the electronic device may first extract the desired identification from the target image. vehicle features of other vehicles, and then compare the vehicle features of the other vehicles with the vehicle features of each model in the database, specifically calculating the similarity between the vehicle features of the other vehicles and the vehicle features of each model in the database. ; Finally, the vehicle type with the highest similarity between the vehicle characteristics and the vehicle characteristics of the other vehicle may be determined as the target vehicle type.

In some embodiments, the above-mentioned similarity may be cosine similarity; that is, the vehicle features of the other vehicles may be converted into vehicle feature vectors; the vehicle features of each vehicle model in the database are also converted into vehicle feature vectors respectively to calculate The cosine similarity between the vehicle feature vector of the other vehicle and the vehicle feature vector of each vehicle model in the above database.

Step 104: Calculate the attitude parameters of the camera based on the other vehicles in the target image, the actual vehicle height, the intersection, and the camera parameters of the camera.

In this embodiment of the present application, according to the other vehicles in the target image obtained in the previous steps 101-103, the actual vehicle heights of the other vehicles, the intersection of any two lane lines after fitting, and the camera parameters of the camera, The attitude parameters of the camera are obtained by calculation, and the attitude parameters include height and angle.

For height, the calculation process is:

A1. In the acquisition of the above target image, the height difference between the bottom end of the above other vehicles and the above intersection point is recorded as the first height difference;

A2. In the acquisition of the target image, the height difference between the bottom end of the other vehicle and the top end of the other vehicle is recorded as the second height difference;

A3. Calculate the height of the camera based on the first height difference, the second height difference, and the actual vehicle height.

Wherein, an image coordinate system can be established based on the target image. As shown in Fig. 3, Fig. 3 gives a schematic representation of other vehicles included in the target image. As shown in FIG. 4 , a schematic diagram of the height of the camera is given in FIG. 4 . In the image coordinate system, the ordinate of the bottom end of the other vehicle can be marked as b, the ordinate of the top end of the other vehicle can be marked as t, and the coordinates of the intersection point are (x ^h , y ^h ), therefore, the first A height difference H ₁ =by ^h ; a second height difference H ₂ =bt; and the actual vehicle height of the other vehicle is recorded as H ₃ . According to the principle of triangular similarity, it can be known that the calculation formula of the height of the camera is:

H ₀ =H ₃ *H ₁ /H ₂ =H ₃ *(by ^h )/(bt).

For the angle, the following camera parameters need to be used: the focal length of the camera in the direction of the longitudinal axis of the image coordinate system, and the coordinates of the focus of the camera in the direction of the longitudinal axis of the image coordinate system; then the calculation process of the angle is:

B1. Calculate the difference between the ordinate of the above-mentioned intersection and the coordinate of the focus of the camera in the direction of the longitudinal axis of the image coordinate system;

B2. Calculate the ratio of the above difference to the above focal length;

B3. Calculate the angle of the camera according to the arc tangent function and the ratio.

Among them, the calculation formula used in B3 can be obtained based on the principle of pinhole imaging, specifically:

其中u为物距，v为像距，f为焦距；根据上述分析和几何原理，可以计算出世界坐标系中(X,Y,Z)点的物距及像距，并带入到高斯成像原理的公式中，得到： In the above formula, θ is the angle of the camera to be calculated; y ^h is the ordinate of the intersection point; y ⁰ is the coordinate of the focal point of the camera in the direction of the longitudinal axis of the image coordinate system; f is the focal length. It should be noted that the above y ⁰ and f are the internal parameters of the camera and can be obtained directly from the camera. The calculation principle of the above formula is as follows: please refer to FIG. 5, which shows that the camera is installed at a height H ₀ from the ground, and the coordinates of the camera in the world coordinate system are [0, H ₀ , 0] ^T ; and The camera has a certain inclination angle θ with respect to the horizontal plane. After the vehicle driving on the road is photographed by the camera, it is mapped from the three-dimensional world coordinate system to the two-dimensional image coordinate system. Assume that the intersection point (x ^h , y ^h ) of the lane line has the coordinates (X, Y, Z) in the world coordinate system; the formula of the known Gaussian imaging principle is:

Among them, u is the object distance, v is the image distance, and f is the focal length; according to the above analysis and geometric principles, the object distance and image distance at the (X, Y, Z) point in the world coordinate system can be calculated, and brought into the Gaussian imaging In the formula of the principle, we get:

According to Figure 3, since the intersection of lane lines (X, Y, Z) is located at the skyline position in the world coordinate system, Z tends to infinity; according to Figure 4, it can be seen that the skyline and the ground in the camera image are parallel, so the above The height of the intersection point (X, Y, Z) in the three-dimensional world coordinate system should be consistent with the height of the camera, so Y is equal to H ₀ . Bring in the formula to get y ^h = y ⁰ +f*tanθ, so that the camera tilt angle can be obtained

It can be seen from the above that, according to the embodiment of the present application, a target image including other vehicles and at least two lane lines is first obtained through a camera installed on the vehicle, and then the above lane lines are fitted to obtain the intersection point, and at the same time, the The actual vehicle heights of the other vehicles will be acquired, and finally the attitude parameters of the cameras will be calculated based on the other vehicles in the target image, the actual vehicle heights, the intersections and the camera internal parameters of the cameras. The above process does not rely on static measurement data at all, and the camera's attitude parameters are completely calculated by software methods, which saves the human resources required for static measurement, makes the calibration process more concise, and can significantly save calibration costs.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Example 2

Corresponding to the camera calibration method proposed above, an embodiment of the present application provides a camera calibration device, and the calibration device is integrated into an electronic device. Referring to FIG. 6 , the camera calibration device 600 in the embodiment of the present application includes:

a first acquiring unit 601, configured to acquire a target image including other vehicles and at least two lane lines through the above-mentioned camera;

a fitting unit 602, configured to fit the above lane lines to obtain intersection points;

The second obtaining unit 603 is configured to obtain the actual vehicle heights of the above other vehicles;

The calculation unit 604 is configured to calculate and obtain the attitude parameter of the camera based on the other vehicle in the target image, the actual vehicle height, the intersection point and the camera parameter of the camera.

Optionally, the above-mentioned attitude parameter includes height; the above-mentioned calculation unit 604 includes:

a first height difference obtaining subunit, configured to obtain the height difference between the bottom end of the other vehicle and the intersection point in the target image, which is recorded as the first height difference;

a second height difference obtaining subunit, configured to obtain the height difference between the bottom end of the other vehicle and the top end of the other vehicle in the target image, which is recorded as the second height difference;

The height calculation subunit is used for calculating the height of the camera based on the first height difference, the second height difference and the actual vehicle height.

Optionally, the posture parameter includes an angle; the camera parameter includes the focal length of the camera in the direction of the vertical axis of the image coordinate system and the coordinates of the focus of the camera in the direction of the vertical axis of the image coordinate system; the calculation unit 604, include:

a difference calculation subunit, configured to calculate the difference between the ordinate of the intersection point and the coordinate of the focus of the camera in the direction of the longitudinal axis of the image coordinate system;

a ratio calculation subunit, used for calculating the ratio of the above-mentioned difference to the above-mentioned focal length;

The angle calculation subunit is used for calculating the angle of the camera according to the arc tangent function and the ratio.

Optionally, the above fitting unit 602 includes:

The key point extraction subunit is used to extract the key points of the above two lane lines for any two lane lines in the above target image;

The lane line fitting subunit is used to respectively fit the above two lane lines according to the above key points to obtain two straight lines;

The intersection obtaining subunit is used to obtain the intersection of the above two straight lines.

Optionally, the above-mentioned second obtaining unit 603 includes:

The target vehicle type search sub-unit is used to search the above-mentioned other vehicle types in the preset database, which is recorded as the target vehicle type;

The actual vehicle height reading subunit is used to read the actual vehicle height of the above-mentioned target vehicle model.

Optionally, the above-mentioned target vehicle type search subunit includes:

a vehicle feature extraction sub-unit, used for extracting the vehicle features of the above-mentioned other vehicles, where the above-mentioned vehicle features include: color, outline, shape of vehicle lights, vehicle logo and/or text;

a similarity calculation subunit, which is used to calculate the similarity between the vehicle features of the other vehicles and the vehicle features of each vehicle model in the database;

The target vehicle type determination subunit is used for determining the vehicle type with the highest similarity between the vehicle characteristics and the vehicle characteristics of the other vehicles as the target vehicle type.

Optionally, the first acquiring unit 601 is specifically configured to acquire a target image including other vehicles and at least two lane lines through the camera when the vehicle is driving.

It can be seen from the above that, according to the embodiment of the present application, a target image including other vehicles and at least two lane lines is first obtained through a camera installed on the vehicle, and then the above lane lines are fitted to obtain the intersection point, and at the same time, the The actual vehicle heights of the other vehicles will be obtained, and finally the pose parameters of the cameras will be calculated based on the other vehicles, the actual vehicle heights, the intersections and the camera parameters of the cameras in the target image. The above process does not rely on static measurement data at all, and the camera's attitude parameters are completely calculated by software methods, which saves the human resources required for static measurement, makes the calibration process more concise, and can significantly save calibration costs.

Example 3

An embodiment of the present application further provides an electronic device, please refer to FIG. 7 , the electronic device 7 in the embodiment of the present application includes: a memory 701, one or more processors 702 (only one is shown in FIG. A computer program on memory 701 and executable on a processor. The memory 701 is used to store software programs and units, and the processor 702 executes various functional applications and data processing by running the software programs and units stored in the memory 701 to obtain resources corresponding to the above preset events. Specifically, the processor 702 implements the following steps by running the above-mentioned computer program stored in the memory 701:

Obtaining a target image including other vehicles and at least two lane lines through the above-mentioned camera, wherein the above-mentioned other vehicles are vehicles other than the vehicle installed with the above-mentioned camera;

Fit the above lane lines to get the intersection point;

Get the actual vehicle height of the other vehicles mentioned above;

Based on the other vehicles in the target image, the actual vehicle height, the intersection, and the camera parameters of the camera, the attitude parameters of the camera are calculated.

Assuming that the above is the first possible implementation manner, in the second possible implementation manner provided on the basis of the first possible implementation manner, the above-mentioned attitude parameters include height, the above-mentioned other vehicles based on the above-mentioned other vehicles in the above-mentioned target image , the above-mentioned actual vehicle height, the above-mentioned intersection point and the camera parameters of the above-mentioned camera, and the attitude parameters of the above-mentioned camera are calculated, including:

In acquiring the target image, the height difference between the bottom end of the other vehicle and the intersection point is recorded as the first height difference;

In acquiring the target image, the height difference between the bottom end of the other vehicle and the top end of the other vehicle is recorded as the second height difference;

Based on the first height difference, the second height difference, and the actual vehicle height, the height of the camera is calculated.

In a third possible implementation manner provided on the basis of the above-mentioned first possible implementation manner, the above-mentioned attitude parameter includes an angle, and the above-mentioned camera parameter includes the focal length of the above-mentioned camera in the direction of the longitudinal axis of the image coordinate system and the above-mentioned camera The coordinates of the focus in the direction of the vertical axis of the image coordinate system; the above-mentioned attitude parameters of the above-mentioned camera are calculated based on the above-mentioned other vehicles in the above-mentioned target image, the above-mentioned actual vehicle height, the above-mentioned intersection point and the above-mentioned camera parameters, including:

Calculate the difference between the vertical coordinate of the intersection point and the coordinate of the focus of the camera in the vertical axis direction of the image coordinate system;

Calculate the ratio of the above difference to the above focal length;

The angle of the camera is calculated according to the arc tangent function and the above ratio.

In the fourth possible implementation manner provided on the basis of the above-mentioned first possible implementation manner, the above-mentioned lane lines in the above-mentioned target image are fitted to obtain intersection points, including:

For any two lane lines in the above target image, extract the key points of the above two lane lines;

According to the above key points, the above two lane lines are respectively fitted to obtain two straight lines;

Get the intersection of the above two lines.

In the fifth possible implementation manner provided on the basis of the above-mentioned first possible implementation manner, the above-mentioned acquisition of the actual vehicle heights of the above-mentioned other vehicles includes:

Find the models of the other vehicles mentioned above in the preset database, and record them as the target model;

Read the actual vehicle height of the above target vehicle model.

In the sixth possible embodiment provided on the basis of the fifth possible embodiment above, the above-mentioned vehicle models of the other vehicles are searched in the preset database, and recorded as the target model, including:

Extracting vehicle features of the above-mentioned other vehicles, the above-mentioned vehicle features include: color, outline, shape of headlight, car logo and/or text;

Calculate the similarity between the vehicle features of the above-mentioned other vehicles and the vehicle characteristics of each model in the above-mentioned database;

The vehicle model with the highest degree of similarity between the vehicle characteristics and the vehicle characteristics of the other vehicles described above is determined as the target vehicle type.

In the seventh possible implementation manner provided on the basis of the above-mentioned first possible implementation manner, the above-mentioned acquisition of the target image including other vehicles and at least two lane lines by the above-mentioned camera includes:

When the vehicle is running, a target image including other vehicles and at least two lane lines is acquired by the camera.

It should be understood that, in this embodiment of the present application, the processor 702 may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP) , Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Memory 701 may include read only memory and random access memory, and provides instructions and data to processor 702 . A portion or all of memory 701 may also include non-volatile random access memory. For example, the memory 701 may also store information of device categories.

It can be seen from the above that, according to the embodiment of the present application, a target image including other vehicles and at least two lane lines is first obtained through a camera installed on the vehicle, and then the above lane lines are fitted to obtain the intersection point, and at the same time, the The actual vehicle heights of the other vehicles will be obtained, and finally the pose parameters of the cameras will be calculated based on the other vehicles, the actual vehicle heights, the intersections and the camera parameters of the cameras in the target image. The above process does not rely on static measurement data at all, and the camera's attitude parameters are completely calculated by software methods, which saves the human resources required for static measurement, makes the calibration process more concise, and can significantly save calibration costs.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the above device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of external device software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the system embodiments described above are only illustrative. For example, the division of the above-mentioned modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined. Either it can be integrated into another system, or some features can be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described above as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

If the above-mentioned integrated units are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the associated hardware through a computer program, and the above computer program can be stored in a computer-readable storage medium, the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code may be in the form of source code, object code form, executable file or some intermediate form. The above-mentioned computer-readable storage medium may include: any entity or device capable of carrying the above-mentioned computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer-readable memory, a read-only memory (ROM, Read-Only Memory) ), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the above-mentioned computer-readable storage media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer-readable storage Excluded from the medium are electrical carrier signals and telecommunication signals.

The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The recorded technical solutions are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in the application. within the scope of protection.

Claims (10)

A camera calibration method, characterized in that the camera is mounted on a vehicle, and the calibration method includes: acquiring, by the camera, a target image including other vehicles and at least two lane lines, wherein the other vehicles are vehicles other than the vehicle on which the camera is installed; Fitting the lane line to obtain the intersection point; Obtain the actual vehicle height of the other vehicle; Based on the other vehicles in the target image, the actual vehicle height, the intersection point and the camera parameters of the camera, the attitude parameters of the camera are calculated. The calibration method according to claim 1, wherein the attitude parameter includes a height, and the camera based on the other vehicle in the target image, the actual vehicle height, the intersection and the camera parameters, the attitude parameters of the camera are calculated, including: In acquiring the target image, the height difference between the bottom end of the other vehicle and the intersection point is recorded as the first height difference; In acquiring the target image, the height difference between the bottom end of the other vehicle and the top end of the other vehicle is recorded as the second height difference; Based on the first height difference, the second height difference and the actual vehicle height, the height of the camera is calculated. The calibration method according to claim 1, wherein the attitude parameter includes an angle, and the camera parameter includes the focal length of the camera in the direction of the longitudinal axis of the image coordinate system and the focus of the camera on the image. The coordinates in the direction of the longitudinal axis of the coordinate system; the attitude parameters of the camera are calculated based on the other vehicles in the target image, the actual vehicle height, the intersection point and the camera parameters of the camera, include: calculating the difference between the ordinate of the intersection and the coordinate of the focus of the camera in the direction of the longitudinal axis of the image coordinate system; calculating the ratio of the difference to the focal length; The angle of the camera is calculated according to the arc tangent function and the ratio. The calibration method according to claim 1, wherein the fitting of the lane lines in the target image to obtain the intersection point comprises: For any two lane lines in the target image, extract the key points of the two lane lines; According to the key points, the two lane lines are respectively fitted to obtain two straight lines; Get the intersection of the two lines. The calibration method according to claim 1, wherein the obtaining the actual vehicle heights of the other vehicles comprises: Find the model of the other vehicle in the preset database, and record it as the target model; Read the actual vehicle height of the target vehicle model. The calibration method according to claim 5, wherein the searching for the vehicle type of the other vehicle in a preset database is recorded as the target vehicle type, comprising: extracting vehicle features of the other vehicles, the vehicle features including: color, outline, shape of lights, logo and/or text; respectively calculating the similarity between the vehicle characteristics of the other vehicles and the vehicle characteristics of each vehicle model in the database; The vehicle model with the highest similarity between the vehicle characteristics and the vehicle characteristics of the other vehicles is determined as the target vehicle type. The calibration method according to claim 1, wherein the acquiring a target image including other vehicles and at least two lane lines through the camera comprises: When the vehicle is driving, a target image including other vehicles and at least two lane lines is acquired by the camera. A camera calibration device, characterized in that the camera is mounted on a vehicle, and the calibration device includes: a first acquisition unit, configured to acquire a target image including other vehicles and at least two lane lines through the camera; a fitting unit, used for fitting the lane line to obtain the intersection point; a second acquiring unit, configured to acquire the actual vehicle heights of the other vehicles; A calculation unit, configured to calculate and obtain the attitude parameter of the camera based on the other vehicle in the target image, the actual vehicle height, the intersection point and the camera parameter of the camera. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, when the processor executes the computer program, the computer program according to claim 1 to 7. The method of any one. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images