A camera extrinsic parameter calibration method, system and non-volatile computer readable storage medium

Abstract

The application relates to the field of unmanned driving and discloses a camera external parameter calibration method, which is characterized by comprising the following steps: determining the center coordinates of a plurality of groups of ground markers and a vehicle in a calibration site; acquiring a camera image of the calibration site; matching a first center coordinate and a second center coordinate of the same ground marker; the first center coordinate is the coordinate of the ground marker in the calibration site; the second center coordinate is the coordinate of the ground marker in the camera image; calculating the position coordinate of a camera used for shooting the camera image in the calibration site through a PNP algorithm; and calculating the center external parameter of the camera to the vehicle. The first center coordinate of the ground marker and the second center coordinate of the camera image are matched to determine the position coordinate of the camera in the calibration site, and the center external parameter of the camera to the vehicle is calculated, so that the calibration precision is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of autonomous driving, and in particular to a method for calibrating camera extrinsic parameters. Background Technology

[0002] In existing technologies, autonomous driving can significantly reduce labor costs, while related positioning technologies rely on various sensors, including cameras. Unlike commonly used vehicles, autonomous vehicles used in dockside scenarios are characterized by their large size and complex electrical environments. For such large vehicles, it is difficult to ascertain the extrinsic parameters from their sensors to the center of the vehicle body, making extrinsic parameter calibration a challenging task.

[0003] Generally, large IGVs, due to their enormous size, have limited or no common field of view among their sensors, making it difficult to determine the extrinsic parameters of the camera's center on the vehicle. In particular, hand-eye calibration is limited by insufficient positioning accuracy, leading to excessively large extrinsic parameter calibration errors. Inaccurate camera extrinsic parameters significantly amplify positioning errors in the positioning of large vehicles.

[0004] This invention determines the camera's position coordinates at the calibration site by matching the first center coordinates of the ground markers with the second center coordinates of the camera image, and calculates the center extrinsic parameters from the camera to the vehicle, thereby improving calibration accuracy. Summary of the Invention

[0005] This invention determines the camera's position coordinates at the calibration site by matching the first center coordinates of the ground markers with the second center coordinates of the camera image, and calculates the center extrinsic parameters from the camera to the vehicle, thereby improving calibration accuracy.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] In a first aspect, embodiments of the present invention provide a camera extrinsic parameter calibration method, applied to autonomous driving, characterized in that it includes:

[0008] Determine the center coordinates of several sets of ground markers and vehicles in the calibration site; acquire camera images of the calibration site; match the first center coordinates and the second center coordinates of the same ground marker; the first center coordinates are the coordinates of the ground marker in the calibration site; the second center coordinates are the coordinates of the ground marker in the camera image; calculate the position coordinates of the camera used to capture the camera image in the calibration site using the PNP algorithm; calculate the center extrinsic parameters from the camera to the vehicle.

[0009] Optionally, there shall be no fewer than three sets of ground markers.

[0010] Optionally, the step of calculating the camera's position coordinates in the calibration site using the PNP algorithm includes: calculating the camera's position coordinates using the ICP algorithm based on the first center coordinates and the second center coordinates.

[0011] Optionally, the vehicle includes a vehicle body and wheels; the method further includes: obtaining the coordinates of the wheels in a calibration site; calculating the vehicle orientation based on the coordinates of the wheels in the calibration site according to a preset formula; and normalizing the coordinates of the wheels in the calibration site to obtain the vehicle front orientation.

[0012] Optionally, the calculation of the camera-to-vehicle center extrinsic parameters includes: obtaining the camera intrinsic parameter matrix, and solving for the camera-to-vehicle center extrinsic parameters based on the position coordinates of the camera in the calibration site and the center coordinates of the vehicle body in the calibration site.

[0013] Secondly, embodiments of the present invention also provide a vehicle position detection method, characterized in that it includes: determining a central extrinsic parameter using the above-described camera extrinsic parameter calibration method; and determining the vehicle position based on the camera intrinsic parameter matrix, the central extrinsic parameter, and the camera image.

[0014] Thirdly, embodiments of the present invention also provide a camera extrinsic parameter calibration device, characterized in that it includes: an image acquisition module for acquiring images of a calibration site; an image calculation module for matching the center coordinates of ground markers in the calibration site with the center coordinates of markers in the camera images; for calculating the position coordinates of the camera in the calibration site; and for calculating the center extrinsic parameters from the camera to the vehicle body.

[0015] Fourthly, embodiments of the present invention also provide an electronic device, characterized in that the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described camera extrinsic calibration method and / or the above-described vehicle position detection method.

[0016] Fifthly, embodiments of the present invention also provide a camera extrinsic parameter calibration system, characterized in that it includes: a surveying tool; the surveying tool is used to survey and determine the center coordinates of several sets of ground markers and vehicles in the calibration site; and the aforementioned electronic equipment.

[0017] Sixthly, embodiments of the present invention also provide a non-volatile computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, which, when executed, can perform the above-described camera extrinsic parameter calibration method and / or the above-described vehicle position detection method.

[0018] The beneficial effects of the embodiments of the present invention are as follows: Unlike the prior art, the present invention relates to the field of autonomous driving and discloses a camera extrinsic parameter calibration method. The present invention determines the position coordinates of the camera in the calibration site by matching the first center coordinates of the ground marker and the second center coordinates of the camera image, and calculates the center extrinsic parameters from the camera to the vehicle, thereby improving the calibration accuracy. Attached Figure Description

[0019] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0020] Figure 1 This is a flowchart of a camera extrinsic parameter calibration method provided in an embodiment of the present invention;

[0021] Figure 2 This is an overhead view of the calibration site provided in an embodiment of the present invention;

[0022] Figure 3 These are camera images of the calibration site provided in the embodiments of the present invention;

[0023] Figure 4 This is a transformation diagram between the image coordinate system and the pixel coordinate system provided in the embodiments of the present invention;

[0024] Figure 5 This is a schematic diagram of the PNP algorithm provided in an embodiment of the present invention;

[0025] Figure 6 This is a flowchart of a vehicle position calibration method provided by an embodiment of the present invention;

[0026] Figure 7 This is provided by the embodiments of the present invention. Figure 6 Flowchart of the method for step S203;

[0027] Figure 8 This is a diagram of a camera extrinsic parameter calibration device provided in an embodiment of the present invention;

[0028] Figure 9 This is a schematic diagram of an electronic device structure provided in an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention. It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed with a different module division or in a different order than that shown in the device schematic diagram or the flowchart.

[0030] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items. Please refer to [link to documentation]. Figure 1 , Figure 1 This is a flowchart of a camera extrinsic parameter calibration method provided by an embodiment of the present invention. The method includes the following steps:

[0031] S101. Determine the center coordinates of several sets of ground markers and vehicles.

[0032] The core of camera extrinsic calibration lies in how to determine the position of the camera in the calibration site and the position coordinates of the vehicle center in the calibration site. In some embodiments, it is first necessary to construct the calibration site and determine the position coordinates of the markers in the calibration site, with no less than three sets of ground markers.

[0033] In some embodiments, such as Figure 2 As shown, Figure 2 This is an overhead view of the calibration site provided in an embodiment of the present invention. Nine markers are placed in the calibration site, which are numbered 1-9 respectively. A coordinate system is constructed and the coordinates of the nine markers are determined by surveying tools. The coordinates of markers 1-9 are (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5), (x6, y6), (x7, y7), (x8, y8), and (x9, y9). The camera coordinates are set to (x0, y0).

[0034] S102. Acquire camera images of the calibration site.

[0035] S103, Matching the first and second center coordinates of the same ground marker

[0036] The first center coordinates are the coordinates of the ground marker in the calibration site, and the second center coordinates are the coordinates of the ground marker in the camera image, denoted by numbers 1-9 respectively. In some embodiments, such as... Figure 3 As shown, Figure 3 This is a camera image of the calibration site provided in an embodiment of the present invention. In the calibration image, the coordinates of nine placed markers are marked, a coordinate system is constructed, and the coordinates of the nine markers are determined by surveying tools. The coordinates of markers 1-9 are (x'1, y'1), (x'2, y'2), (x'3, y'3), (x'4, y'4), (x'5, y'5), (x'6, y'6), (x'7, y'7), (x'8, y'8), and (x'9, y'9). It should be noted that... Figure 3 and Figure 2 Although the images are of the same landmark, the difference in camera field of view makes them appear different. Figure 2 and Figure 3 There are significant differences. Figure 2 The coordinates of the marker and Figure 3 The coordinates in the camera image are matched one-to-one.

[0037] S104. Calculate the position coordinates of the camera used to capture the camera image at the calibration site using the PNP algorithm.

[0038] The PNP algorithm can be used to determine the camera's position coordinates on the calibration site. In step S102, the first and second center coordinates of the ground markers have been obtained. Now, it is necessary to transform the camera image coordinate system into a pixel coordinate system. For details, please refer to [reference needed]. Figure 4 , Figure 4 This is a transformation diagram between the image coordinate system and the pixel coordinate system provided in an embodiment of the present invention. In some embodiments, the origin of the pixel coordinate system UV image coordinate system is... The x-coordinate U and y-coordinate V represent the row and column of the image, respectively. In the OpenCV visual processing library, u corresponds to x and v corresponds to y. The origin of the XY coordinate system is... Let be the midpoint of the pixel coordinate system. , )represent In the UV coordinate system, dx and dy represent the physical dimensions of each pixel on the horizontal axis (x) and vertical axis (y), respectively. The relationship between the image coordinate system and the pixel coordinate system is as follows:

[0039]

[0040]

[0041] In some embodiments, the unit in the coordinate system is millimeters, so the unit of dx is millimeters per pixel, and the unit of x / dx is pixels, the same as the unit of u. The above formula is often written in matrix form:

[0042]

[0043] Its inverse relation can be expressed as:

[0044]

[0045] By transforming the image coordinate system and the pixel coordinate system, the second center coordinates are transformed into the third center coordinates, where the third center coordinates are the pixel coordinates of the ground markers. At this point, we have completed the input data required by the PNP algorithm.

[0046] Please see Figure 5 , Figure 5 The PNP algorithm principle diagram provided in this embodiment of the invention shows that, taking any point P on triangle ABC, according to the law of cosines, we can obtain:

[0047]

[0048]

[0049]

[0050] make We can obtain:

[0051]

[0052]

[0053]

[0054] make , , We can obtain:

[0055]

[0056]

[0057]

[0058] In some embodiments, the distances AB, BC, and AC can be obtained from the first center coordinate point of the marker. The input second center coordinates can also be used to solve for three cosine values. Specifically, the third center coordinates can be used to obtain the camera's coordinates in the image coordinate system on the normalized image plane based on the camera intrinsic parameter matrix and distortion parameters. At this point, z=1, so the cosine value can be calculated. Since there are only two unknowns, x and y, theoretically, two equations with two unknowns can be solved. (PA, PB, and PC can also be calculated from x and y). Then, the camera's position coordinates can be calculated using the ICP algorithm.

[0059] S105, Calculate the center extrinsic parameters of the camera to the vehicle.

[0060] In some embodiments, camera extrinsic parameters are divided into rotation and translation matrices, which together describe how points are transformed from the world coordinate system to the image coordinate system. The rotation matrix describes the orientation of the world coordinate system axes relative to the image coordinate axes. The translation matrix describes the position of the origin in the camera coordinate system.

[0061] Please refer to Figure 6 , Figure 6 This is a flowchart of a vehicle position calibration method provided by an embodiment of the present invention. The method includes the following steps:

[0062] S201. Obtain the coordinates of the wheels on the calibration site.

[0063] In some embodiments, the center coordinates of the vehicle body on the calibration site are measured using surveying tools, such as a total station. The center coordinates of the four wheels can be measured to calculate the center coordinates. A ground coordinate system is established, and the wheel coordinates are measured as P0(m1, n1), P1(m2, n2), P2(m3, n3), and P3(m4, n4).

[0064] S202. Based on the coordinates of the wheels in the calibrated area, calculate the vehicle orientation according to a preset formula;

[0065] Based on the wheel coordinates obtained in step S201, let the center coordinates of the vehicle body be P(m0, n0), according to the formula... , The coordinates of the vehicle's center can be determined.

[0066] Let Q(JO, K0), according to the formula , This allows us to determine the orientation of the vehicle.

[0067] S203. Normalize the coordinates of the wheels in the calibration site to obtain the vehicle's front orientation.

[0068] Based on Q(JO, K0) obtained from step S203, the orientation of the vehicle can be obtained by normalizing the coordinates of point Q.

[0069] For details, please refer to Figure 7 , Figure 7 This is a flowchart of a method for determining the orientation of a vehicle's front end according to an embodiment of the present invention, including:

[0070] S2031. Establish a vehicle detection model.

[0071] In some embodiments, a pre-trained vehicle detection model is stored in an electronic device, which may be a PC, tablet, mobile phone, or an image acquisition device. First, a vehicle image is acquired and input into the pre-trained vehicle detection model. In some embodiments, the vehicle detection model may be a YOLOv2 neural network model, a convolutional neural network model (CNN), or something similar.

[0072] S2032, Input the target vehicle into the pre-trained vehicle front angle model.

[0073] In some embodiments, the electronic device stores a pre-trained vehicle front angle model. When the electronic device determines the target vehicle, it inputs the target vehicle into the pre-trained vehicle front angle model. Specifically, based on the target vehicle angle model, the normalized angle value of the vehicle is determined; and according to the correspondence between the normalized angle value and the vehicle front orientation angle, the vehicle front orientation angle is determined.

[0074] In some embodiments, the electronic device inputs the vehicle into a pre-trained angle regression model and determines the normalized angle value of the target vehicle based on the vehicle head angle model. Additionally, to determine the vehicle head orientation angle, the electronic device also stores a correspondence between the normalized angle value and the vehicle head orientation angle. After determining the normalized angle value of the target vehicle, the vehicle head orientation angle can be determined based on the normalized angle value and the correspondence.

[0075] In this embodiment of the invention, the target vehicle can be determined based on the pre-trained vehicle detection model, the normalized angle value of the target vehicle can be determined based on the pre-trained vehicle angle model, and the vehicle's front-facing angle can be determined according to the correspondence between the normalized angle value and the vehicle's front-facing angle.

[0076] In some embodiments, calculating the center extrinsic parameters from the camera to the vehicle body includes: obtaining the camera intrinsic parameter matrix, and solving for the center extrinsic parameters from the camera to the vehicle body based on the position coordinates of the camera in the calibration site and the center coordinates of the vehicle body in the calibration site.

[0077] This invention also provides a vehicle position detection method, comprising: determining the central extrinsic parameter using the above-described camera extrinsic parameter calibration method; and determining the vehicle position based on the camera intrinsic parameter matrix, the central extrinsic parameter, and the camera image.

[0078] Accordingly, embodiments of the present invention also provide a camera extrinsic parameter calibration device, such as... Figure 8 As shown, in some embodiments, a camera extrinsic parameter calibration device 80 includes:

[0079] Image acquisition module 801 is used to acquire images of the calibration site;

[0080] The image calculation module 802 is used to match the center coordinates of the ground markers in the calibration site with the center coordinates of the markers in the camera image; to calculate the position coordinates of the camera in the calibration site; and to calculate the center extrinsic parameters from the camera to the vehicle body.

[0081] As another aspect of the embodiments of the present invention, the present invention provides an electronic device, such as... Figure 9 The diagram shown is a hardware structure schematic of the electronic device 90. Please refer to [link / reference]. Figure 9 The electronic device includes: one or more processors 901 and memory 902. Figure 9 Take the 901 processor as an example.

[0082] The processor 901 and memory 902 can be connected via a bus or other means. Figure 9 Taking the example of a connection between China and Israel via a bus.

[0083] Memory 902, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to a camera extrinsic parameter calibration device in the embodiments of this application (e.g., attached...). Figure 8The image acquisition module 801 and image calculation module 802 are shown. The processor 901 executes various functional applications and data processing of the electronic device by running non-volatile software programs, instructions, and modules stored in the memory 902, i.e., implementing the camera extrinsic parameter calibration method and / or vehicle position detection method of the above method embodiments. The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created according to the use of the controller, etc. Furthermore, the memory 902 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 802 may optionally include memory remotely located relative to the processor 901, and these remote memories can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] The one or more modules are stored in the memory 902, and when executed by the one or more processors 901, they execute the camera extrinsic calibration method and / or vehicle position detection method in any of the above method embodiments.

[0085] The above-described product can perform the methods provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects for performing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in the embodiments of this application.

[0086] This invention also provides a camera extrinsic parameter calibration system, comprising: a surveying tool; the surveying tool being used to survey and determine the center coordinates of several sets of ground markers and vehicles in the calibration site; and electronic equipment as described above.

[0087] This invention also provides a non-volatile computer-readable storage medium storing computer-executable instructions, which are executed by an electronic device using the camera extrinsic parameter calibration method and / or vehicle position detection method in any of the above method embodiments.

[0088] This invention also provides a computer program product, including a computing program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the camera extrinsic parameter calibration method and / or vehicle position detection method in any of the above method embodiments.

[0089] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for at least one computer (which may be a personal computer, server, or network, etc.) to execute the methods described in various embodiments or some parts of the embodiments.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above. For the sake of brevity, they are not provided in the details; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calibrating camera extrinsic parameters, characterized in that, The method comprises: determining the center coordinates of a plurality of sets of ground markers and a vehicle in a calibration site; obtaining a camera image of the calibration site; matching a first center coordinate and a second center coordinate of the same ground marker; the first center coordinate is the coordinate of the ground marker in the calibration site; and the second center coordinate is the coordinate of the ground marker in the camera image; calculating the position coordinate of a camera for shooting the camera image in the calibration site by a PNP algorithm, comprising: converting the second center coordinate into a third center coordinate according to a preset formula; and the third center coordinate is the pixel coordinate of the ground marker; based on the first center coordinate and the third center coordinate, calculating the position coordinate of the camera by an ICP algorithm; obtaining a camera intrinsic matrix, and based on the position coordinate of the camera in the calibration site and the center coordinate of the vehicle body in the calibration site, solving the center extrinsic parameter of the camera to the vehicle body.

2. The camera extrinsic parameter calibration method according to claim 1, characterized in that: the ground markers are not less than three sets.

3. The camera extrinsic parameter calibration method of claim 1, wherein, the vehicle comprises a vehicle body and a wheel; the method further comprises: obtaining the coordinate of the wheel in the calibration site; based on the coordinate of the wheel in the calibration site, calculating the orientation of the vehicle body according to a preset formula; normalizing the coordinate of the wheel in the calibration site to obtain the orientation of the vehicle head.

4. A vehicle position detection method characterized by The method comprises: determining the center extrinsic parameter by the camera extrinsic parameter calibration method according to any one of claims 1-3; based on the camera intrinsic matrix, the center extrinsic parameter and the camera image, determining the position of the vehicle.

5. A camera extrinsic parameter calibration apparatus, characterized in that, The method comprises: an image acquisition module for obtaining a camera image of a calibration site; an image calculation module for matching a first center coordinate and a second center coordinate of the same ground marker; the first center coordinate is the coordinate of the ground marker in the calibration site; and the second center coordinate is the coordinate of the ground marker in the camera image; calculating the position coordinate of a camera for shooting the camera image in the calibration site by a PNP algorithm, comprising: converting the second center coordinate into a third center coordinate according to a preset formula; and the third center coordinate is the pixel coordinate of the ground marker; based on the first center coordinate and the third center coordinate, calculating the position coordinate of the camera by an ICP algorithm; obtaining a camera intrinsic matrix, and based on the position coordinate of the camera in the calibration site and the center coordinate of the vehicle body in the calibration site, solving the center extrinsic parameter of the camera to the vehicle body.

6. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the camera extrinsic parameter calibration method according to any one of claims 1-3 and / or the vehicle position detection method according to claim 4.

7. A camera extrinsic parameter calibration system, comprising: The method comprises: a surveying tool for surveying and determining the center coordinates of a plurality of sets of ground markers and a vehicle in a calibration site; and the electronic device according to claim 6. The method comprises: determining the center coordinates of a plurality of sets of ground markers and a vehicle in a calibration site; obtaining a camera image of the calibration site; matching a first center coordinate and a second center coordinate of the same ground marker; the first center coordinate is the coordinate of the ground marker in the calibration site; and the second center coordinate is the coordinate of the ground marker in the camera image; calculating the position coordinate of a camera for shooting the camera image in the calibration site by a PNP algorithm, comprising: converting the second center coordinate into a third center coordinate according to a preset formula; and the third center coordinate is the pixel coordinate of the ground marker; based on the first center coordinate and the third center coordinate, calculating the position coordinate of the camera by an ICP algorithm; obtaining a camera intrinsic matrix, and based on the position coordinate of the camera in the calibration site and the center coordinate of the vehicle body in the calibration site, solving the center extrinsic parameter of the camera to the vehicle body.

2. The camera extrinsic parameter calibration method according to claim 1, characterized in that: the ground markers are not less than three sets. the vehicle comprises a vehicle body and a wheel; the method further comprises: obtaining the coordinate of the wheel in the calibration site; based on the coordinate of the wheel in the calibration site, calculating the orientation of the vehicle body according to a preset formula; normalizing the coordinate of the wheel in the calibration site to obtain the orientation of the vehicle head. The method comprises: determining the center extrinsic parameter by the camera extrinsic parameter calibration method according to any one of claims 1-3; based on the camera intrinsic matrix, the center extrinsic parameter and the camera image, determining the position of the vehicle. The method comprises: an image acquisition module for obtaining a camera image of a calibration site; an image calculation module for matching a first center coordinate and a second center coordinate of the same ground marker; the first center coordinate is the coordinate of the ground marker in the calibration site; and the second center coordinate is the coordinate of the ground marker in the camera image; calculating the position coordinate of a camera for shooting the camera image in the calibration site by a PNP algorithm, comprising: converting the second center coordinate into a third center coordinate according to a preset formula; and the third center coordinate is the pixel coordinate of the ground marker; based on the first center coordinate and the third center coordinate, calculating the position coordinate of the camera by an ICP algorithm; obtaining a camera intrinsic matrix, and based on the position coordinate of the camera in the calibration site and the center coordinate of the vehicle body in the calibration site, solving the center extrinsic parameter of the camera to the vehicle body. The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the camera extrinsic parameter calibration method according to any one of claims 1-3 and / or the vehicle position detection method according to claim 4. The method comprises: a surveying tool for surveying and determining the center coordinates of a plurality of sets of ground markers and a vehicle in a calibration site; and the electronic device according to claim 6.

8. A non-transitory computer readable storage medium, comprising: The computer readable storage medium stores computer executable instructions which, when executed, can perform the camera extrinsic parameter calibration method according to any one of claims 1-3 and / or the vehicle position detection method according to claim 4.

Images