Parameter accuracy evaluation method and device, electronic equipment, storage medium and product

Abstract

The present disclosure provides a parameter accuracy evaluation method and device, electronic equipment, storage medium and product, relates to a camera parameter calibration technical field, and particularly relates to a parameter verification technical field. The specific implementation scheme is: taking the imaging plane of a shooting device and the target plane in a parallel state as a target, adjusting the shooting device with calibrated intrinsic parameters; based on the adjusted shooting device, shooting the target plane to obtain an image of the target plane, and determining at least two corner points on the image; calculating the distance of the corner points on the target plane to obtain the calculated value of the real distance between the corner points; obtaining the measured value of the real distance between the corner points, and based on the difference between the calculated value and the measured value, evaluating the accuracy of the shooting device calibration intrinsic parameters. Through the present disclosure, the probability of evaluating the accuracy of intrinsic parameter calibration can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of camera parameter calibration technology, and more particularly to the field of parameter verification technology, specifically to a parameter accuracy evaluation method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] The use of camera equipment has spread across various technological fields, especially in intelligent driving perception technology for autonomous driving, to obtain accurate road information for driving decisions.

[0003] The mapping relationship between points on a captured image and their corresponding points in actual three-dimensional space can be determined by the parameters of the capturing device. The parameters of the camera device can be calibrated in advance, and the accuracy of the calibration results can affect the accuracy of the perceived results. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, storage medium, and product for evaluating parameter accuracy.

[0005] According to a first aspect of this disclosure, a method for evaluating parameter accuracy is provided, the method comprising:

[0006] With the goal of ensuring that the imaging plane of the imaging device is parallel to the target plane, the calibrated imaging device is adjusted; based on the adjusted imaging device, the target plane is photographed to obtain an image of the target plane, and at least two corner points are determined on the image; the distance between the corner points on the target plane is calculated to obtain a calculated value of the true distance between the corner points; a measured value of the true distance between the corner points is obtained, and the accuracy of the calibration parameters of the imaging device is evaluated based on the difference between the calculated value and the measured value.

[0007] According to a second aspect of this disclosure, a parameter accuracy evaluation apparatus is provided, the apparatus comprising:

[0008] An adjustment module is used to adjust the calibrated internal parameters of the shooting device with the goal of making the imaging plane of the shooting device parallel to the target plane; an shooting module is used to take a picture of the target plane based on the adjusted shooting device, obtain an image of the target plane, and determine at least two corner points on the image; a calculation module is used to calculate the distance between the corner points on the target plane, and obtain a calculated value of the true distance between the corner points; an evaluation module is used to obtain a measured value of the true distance between the corner points, and evaluate the accuracy of the calibration internal parameters of the shooting device based on the difference between the calculated value and the measured value.

[0009] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0010] 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 to enable the at least one processor to perform the method of the first aspect or the second aspect.

[0011] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to the first or second aspect.

[0012] According to a fifth aspect of this disclosure, a computer product is provided, including a computer program that, when executed by a processor, implements the method according to the first or second aspect.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0014] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0015] Figure 1 A flowchart illustrating a parameter accuracy evaluation method provided in an embodiment of this disclosure is shown.

[0016] Figure 2 A schematic flowchart of a device adjustment method provided in an embodiment of this disclosure is shown;

[0017] Figure 3 A schematic flowchart of a device adjustment method provided in an embodiment of this disclosure is shown;

[0018] Figure 4 and Figure 5 A schematic diagram of a device adjustment method provided in an embodiment of this disclosure is shown;

[0019] Figure 6 A flowchart illustrating a method for determining surface parallelism according to an embodiment of this disclosure is shown;

[0020] Figure 7 This illustration shows a schematic diagram of a structure for determining the parallelism of surfaces according to an embodiment of the present disclosure;

[0021] Figure 8 This diagram illustrates a structure with surface parallelism error according to an embodiment of the present disclosure.

[0022] Figure 9A schematic diagram of the structure of a parameter accuracy evaluation device provided in an embodiment of this disclosure is shown;

[0023] Figure 10 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0024] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] The use of camera equipment has spread across various technological fields, especially in intelligent driving perception technology for autonomous driving, to obtain accurate road information for driving decisions.

[0026] The mapping relationship between points on a captured image and their corresponding points in actual three-dimensional space can be determined by the parameters of the capturing device. The parameters of the camera device can be calibrated in advance, and the accuracy of the calibration results can affect the accuracy of the perception results, especially the accuracy of the intrinsic parameter calibration.

[0027] In related technologies, the following two methods are generally used to evaluate the accuracy of the intrinsic parameters of shooting equipment:

[0028] (1) Calculate the coordinates of the corner points on the image in three-dimensional space using the calibration parameters, and then reproject these points in three-dimensional space onto the image. The distance between the reprojected points on the image and the actual corner points on the image is called the reprojection error. The smaller this reprojection error, the more accurate the calibration parameters are generally.

[0029] (2) Calculate the distance between a pair of targets using images. The procedure involves photographing a pair of targets, measuring the distance between the targets and the distance from the targets to the camera, then calculating the distance between the targets in the image using calibration parameters, and comparing it with the measured distance. The smaller the error between the calculated and measured values, the more accurate the calibration parameters are.

[0030] However, when using method (1) to determine the accuracy of the calibration intrinsic parameters, if the corner points of the image taken when using the calibration parameters have been processed, even if the calculated reprojection error is small, problems may still occur in calibrating the extrinsic parameters or in actual use. If the image is retaken, a small number of retaken images will affect the judgment result, while a large number of retaken images will require more time and resources, resulting in low efficiency. Using method (2), generally only one pair of targets is set in the horizontal direction at a time, so the operation needs to be repeated continuously to ensure the test coverage, and the vertical direction is usually rarely fully verified.

[0031] Based on the technical problems involved in the aforementioned technical features, this disclosure proposes a method for evaluating parameter accuracy. Before photographing the target plane, the imaging equipment needs to be adjusted to be parallel to the target plane, thereby acquiring an image of the target plane and calculating the actual distances of the corner points on the image. Furthermore, the accuracy of its intrinsic parameter calibration is evaluated by comparing the difference between the calculated actual distance and the measured actual distance. This disclosure requires only one image of the target plane, saving resources and improving evaluation efficiency. The evaluation results are highly accurate and can fully verify the accuracy of its intrinsic parameter calibration.

[0032] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0033] Figure 1 A flowchart illustrating a parameter accuracy evaluation method provided in an embodiment of this disclosure is shown, as follows: Figure 1 As shown, the method may include:

[0034] In step S110, the imaging device with calibrated internal parameters is adjusted with the goal of making the imaging plane of the imaging device parallel to the target plane.

[0035] In this embodiment of the disclosure, for an imaging device whose internal parameters have been calibrated, the position of the imaging device can be adjusted so that its imaging plane is parallel to the target plane, thereby capturing the target plane in a parallel state.

[0036] The filming equipment can be a video camera, a camera, etc.

[0037] The parameter accuracy assessment provided in this disclosure can be applied to evaluate the accuracy of intrinsic parameter calibration of imaging equipment, especially monocular imaging equipment; for example, to evaluate the accuracy of intrinsic parameters calibrated by monocular cameras, monocular video cameras, and other equipment.

[0038] In step S120, based on the adjusted shooting device, the target plane is captured to obtain an image of the target plane, and at least two corner points are determined on the image.

[0039] In this embodiment of the disclosure, the target plane may be a plane comprising a plurality of square patterns, such as a wall.

[0040] The target plane is photographed using a pre-positioned camera to obtain an image of the target plane. It should be noted that, in this disclosure, only one image of the target plane is required.

[0041] Furthermore, at least two corner points are identified in the image. This disclosure uses the identification of two corner points as an example for illustration, but is not limited to capturing images of two corner points, and the following embodiments are all illustrated using the identification of two corner points as an example.

[0042] In step S130, the distance between the corner points on the target plane is calculated to obtain the calculated value of the actual distance between the corner points.

[0043] In this embodiment of the disclosure, the focal length of the camera of the shooting device, the distance from the camera to the target plane, and the pixel distance between two corner points can be obtained, thereby calculating the distance between the two corner points when the corner points are on the target plane, and obtaining the calculated value of the actual distance between the two corner points.

[0044] In step S140, the measured value of the distance between corner points is obtained, and the accuracy of the calibrated intrinsic parameters of the shooting device is evaluated based on the difference between the calculated value and the measured value.

[0045] In this embodiment of the disclosure, the measured value of the actual distance between two corner points can be obtained on the target plane, and the difference between the measured value and the calculated value can be compared to determine the accuracy of the calibration parameters of the shooting device.

[0046] If the difference is within the allowable error range, then the calibrated internal parameters are considered relatively accurate.

[0047] This disclosure reduces the error in the distance between corner points by taking parallel images of the target plane. Calculating the true distance between corner points using a single acquired target image eliminates the need for repetitive operations, reduces the number of images taken, improves coverage, and increases the probability of accurate intrinsic parameter calibration.

[0048] In this embodiment of the disclosure, it is necessary to determine whether the imaging plane and the target plane are parallel by using the heading angle and pitch angle between them. The method for determining the heading angle and pitch angle can be found in the following embodiments.

[0049] Figure 2 A schematic flowchart of a device adjustment method provided in an embodiment of this disclosure is shown, such as... Figure 2 As shown, the method may include:

[0050] In step S210, a vertical line perpendicular to the target plane is obtained.

[0051] In step S220, based on the vertical line, the crosshair level is adjusted until the light from the crosshair level coincides with the vertical line, and the center point of the crosshair of the crosshair level on the target plane is determined.

[0052] In step S230, if the area of ​​the target plane in the captured image is greater than a set threshold, the capturing device is adjusted based on the center point.

[0053] In this embodiment of the disclosure, after determining the target plane, a set of vertical lines perpendicular to the target plane can be determined on the vertical plane of the target plane. The larger the number of vertical lines, the better the effect of calculating the distance between corner points.

[0054] Vertical lines can also be determined by an image on another plane, or by using lines themselves.

[0055] Furthermore, a cross-shaped level can be used to pass the reference ray in the vertical direction through a vertical line perpendicular to the target plane, thereby obtaining a reference cross ray on the target plane and determining the center point of the cross ray of the cross-shaped level on the target plane.

[0056] Ensure that the shooting equipment can capture a sufficiently large area of ​​the target plane, and adjust the shooting equipment according to the determined center point.

[0057] In this embodiment of the disclosure, the shooting device can be adjusted by its height, angle, and position. The following embodiments will further illustrate the adjustment of the shooting device.

[0058] Figure 3 A schematic flowchart of a device adjustment method provided in an embodiment of this disclosure is shown, such as... Figure 3 As shown, the method may include:

[0059] In step S310, the center point is marked to determine the marked point.

[0060] In step S320, a light-transmitting pipe is placed vertically between the cross level and the target plane.

[0061] In step S330, the light transmission tube is adjusted so that the cross rays emitted by the cross level are irradiated onto the target plane through the light transmission tube, and the center point of the cross rays is determined to coincide with the marked point.

[0062] In step S340, the height, corner points, and position of the shooting device are adjusted in response to determining that the marker point in the imaging screen of the shooting device is located in the pipe, and the position of the shooting device is determined.

[0063] In this embodiment of the disclosure, a label or a light-emitting diode can be placed at the marked point, especially a high-power light-emitting diode, which can facilitate observation and reduce errors.

[0064] Furthermore, a light-transmitting tube is placed between the cross level and the wall, and the height and angle of the tube are adjusted so that the cross rays pass through the tube and hit the LED (i.e., the marker) on the wall.

[0065] The initial position of the shooting device is placed on a vertical line perpendicular to the target plane. The height, angle, and position of the shooting device are adjusted (fine-tuned) until the marked point in the image image of the shooting device is located in the pipe, thus determining the position of the shooting device. In other words, the shooting device can see the light-emitting diode on the wall through the pipe, and the light-emitting diode is located in the exact center of the pipe and at the principal point position obtained from the camera intrinsic parameter calibration in the image.

[0066] For example, Figure 4 and Figure 5 A schematic diagram of a device adjustment method provided in an embodiment of this disclosure is shown, such as... Figure 4 As shown, the target plane can be a plane composed of multiple QR codes arranged in a matrix. A vertical line perpendicular to the target plane can be determined by a plane composed of other QR code images. The camera and the level are on the same vertical line perpendicular to the target plane. Figure 4 The light-transmitting duct can be replaced with a perforated planar support. It should be noted that using a light-transmitting duct provides better accuracy. Its side view can be found in the reference diagram. Figure 5 .like Figure 5 As shown, the camera can see labels or LEDs on the wall through the pipe.

[0067] In this embodiment of the disclosure, the inner diameter of the light-transmitting pipe can be selected such that when the camera is placed, it is exactly twice the size of the marker point on the target plane. For example, if a light-emitting diode is placed at the marker point, the inner diameter of the light-transmitting pipe can be preferably no more than twice the size of the light-emitting diode.

[0068] In this embodiment of the disclosure, after the image of the target plane is acquired by the shooting device after the position is adjusted, it can be verified whether the image is parallel to the target plane. The verification method is as follows.

[0069] Figure 6 A flowchart illustrating a method for determining surface parallelism according to an embodiment of this disclosure is shown, as follows: Figure 6 As shown, the method may include:

[0070] In step S610, image processing is performed on the image, and a first horizontal edge line and a first vertical edge line are obtained from the image.

[0071] In this embodiment of the disclosure, the first horizontal edge line is the horizontal edge line of any row of square patterns, and the first vertical edge line is the vertical edge line of any column of square patterns.

[0072] In step S620, the second horizontal edge line and the second vertical edge line are obtained.

[0073] In this disclosure, the second horizontal edge line is the horizontal edge line of the square pattern in other rows, and the second vertical edge line is the vertical edge line of the square pattern in other columns.

[0074] In step S630, a first degree of overlap between the first horizontal edge line and the second horizontal edge line is determined, and a second degree of overlap between the first vertical edge line and the second vertical edge line is determined.

[0075] In step S640, in response to determining that both the first degree of overlap and the second degree of overlap are completely overlapped, it is determined that the imaging plane and the target plane are in a parallel state.

[0076] In this embodiment, the target plane includes multiple square patterns, and the multiple square patterns are arranged in a matrix. The following explanation uses a square image in the target image as an example of a QR code graphic.

[0077] Figure 7 A schematic diagram of a structure for determining the parallelism of surfaces provided in an embodiment of this disclosure is shown, such as... Figure 7 As shown, Figure 7 The horizontal edge line at position 1 is the first horizontal edge line, and the horizontal edge lines at positions 2 and 3 represent the positions where the first horizontal edge line has been moved. The horizontal edge lines at positions 2 and 3 are compared with the edges of the QR code in the image to determine if there is an angle, thus determining whether they overlap and obtaining the degree of overlap. Points A and B in the image are arbitrarily determined corner points.

[0078] Furthermore, the first vertical edge line is moved to determine whether there is an angle between the vertical direction and the edge of the QR code, thereby obtaining the second degree of overlap.

[0079] The first degree of overlap can be the pitch angle, and the second degree of overlap can be the heading angle.

[0080] If both the first and second degrees of overlap are determined to be completely overlapping, then the imaging plane and the target plane are determined to be parallel.

[0081] In this disclosure, Figure 8 This illustration shows a structural diagram of an embodiment of the present disclosure that exhibits surface parallelism error, as shown below. Figure 8 As shown, there is a clear angle between the first horizontal edge line and the lower edge of the QR code, and there is also an angle between the first vertical edge line and the vertical edge of the QR code.

[0082] Once it's confirmed that the captured image is parallel to the target plane, further image distortion correction can be performed, i.e., straightening the lines in the image. After image processing, the pixel distances of the corner points on the image can be measured. The camera focal length, calibrated using the intrinsic parameters of the capturing device, and the vertical distance from the camera to the target plane are obtained. Based on the pixel distances, camera focal length, and vertical distance, the distances of the corner points on the target plane are calculated.

[0083] In this embodiment of the disclosure, the distance of the corner point on the target plane can be calculated using the following formula:

[0084]

[0085] Where h is the pixel distance between two corner points in the distorted image, in pixels. For example, Figure 7 The distance between points A and B on the image. f is the calibrated focal length in pixels; D is the actual measured vertical distance from the front of the camera lens to the wall, plus the starting point of the lens's field of view, in mm; H is the calculated distance between the two corner points in real space (i.e., the calculated value, in mm).

[0086] In this embodiment of the disclosure, by using a QR code array as an image on the target plane, multiple horizontal and vertical lines can be determined. Thus, only one image of the target plane is needed to evaluate the accuracy of the intrinsic parameter calibration of the shooting device, which is simple and convenient.

[0087] In this embodiment of the disclosure, on the target plane, if the difference between the calculated distance between the two corner points and the measured distance between the two corner points is within 0.15% when the two corner points are located at the center of the image, then the calibrated intrinsic parameters of the imaging device are accurate and have high reliability. Similarly, if the difference between the calculated distance between the two corner points and the measured distance between the two corner points is within 0.3% when the two corner points are located at the edge of the image, then the calibrated intrinsic parameters of the imaging device are accurate and have high reliability.

[0088] The target plane disclosed herein can reuse the extrinsic calibration environment, reducing additional space requirements. Furthermore, the target plane provides significantly more space in the vertical direction, allowing for simultaneous verification of both horizontal and vertical directions, as well as central and edge positions, with a single photograph, eliminating the need for repeated operations to ensure test coverage.

[0089] This disclosure allows for more precise adjustment of the camera's main optical axis by adjusting the light-transmitting pipe and the size of the light-emitting diode (LED). Theoretically, an accuracy of ±0.02° can be achieved by adjusting the size of the light-transmitting pipe and the LED, and by centering the LED within the light-transmitting pipe.

[0090] Based on and Figure 1 The method shown follows the same principle. Figure 9 A schematic diagram of a parameter accuracy evaluation device provided in an embodiment of this disclosure is shown, as follows: Figure 9 As shown, the parameter accuracy evaluation device 900 may include:

[0091] The adjustment module 901 is used to adjust the calibrated internal parameters of the shooting device with the goal of making the imaging plane of the shooting device parallel to the target plane; the shooting module 902 is used to take a picture of the target plane based on the adjusted shooting device, obtain an image of the target plane, and determine at least two corner points on the image; the calculation module 903 is used to calculate the distance between the corner points on the target plane, and obtain a calculated value of the true distance between the corner points; the evaluation module 904 is used to obtain a measured value of the true distance between the corner points, and evaluate the accuracy of the calibration internal parameters of the shooting device based on the difference between the calculated value and the measured value.

[0092] In this embodiment of the disclosure, the adjustment module 901 is used to obtain a vertical line perpendicular to the target plane; based on the vertical line, adjust the cross level until the light rays of the cross level coincide with the vertical line, and determine the center point of the cross rays of the cross level on the target plane; if the area of ​​the target plane in the captured image is greater than a set threshold, adjust the shooting device based on the center point.

[0093] In this embodiment of the disclosure, the adjustment module 901 is used to mark the center point and determine the mark point; to place a light-transmitting pipe vertically between the cross level and the target plane; to adjust the light-transmitting pipe so that the cross rays emitted by the cross level illuminate the target plane through the light-transmitting pipe, and to determine that the center point of the cross rays coincides with the mark point; to adjust the height, corner point and position of the shooting device, and to determine the position of the shooting device in response to determining that the mark point in the imaging screen of the shooting device is located in the light-transmitting pipe.

[0094] In this embodiment of the disclosure, the target plane includes a plurality of square patterns, and the plurality of square patterns are arranged in a matrix.

[0095] The adjustment module 901 is further configured to perform image processing on the image, and in the image, acquire a first horizontal edge line and a first vertical edge line, wherein the first horizontal edge line is the horizontal edge line of any row of square patterns, and the first vertical edge line is the vertical edge line of any column of square patterns; acquire a second horizontal edge line and a second vertical edge line, wherein the second horizontal edge line is the horizontal edge line of other rows of square patterns, and the second vertical edge line is the vertical edge line of other columns of square patterns; determine a first degree of overlap between the first horizontal edge line and the second horizontal edge line, and determine a second degree of overlap between the first vertical edge line and the second vertical edge line; in response to determining that both the first degree of overlap and the second degree of overlap are completely overlapped, determine that the imaging plane and the target plane are in a parallel state.

[0096] In this embodiment of the disclosure, the calculation module 903 is used to measure the pixel distance of the corner point on the image; obtain the camera focal length of the shooting device intrinsic parameter calibration, and obtain the vertical distance from the camera of the shooting device to the target plane; and calculate the distance of the corner point on the target plane based on the pixel distance, the camera focal length, and the vertical distance.

[0097] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0098] In an exemplary embodiment, an 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 method described in the above embodiments. The electronic device may be the computer or server described above.

[0099] In an exemplary embodiment, the readable storage medium may be a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the above embodiments.

[0100] In an exemplary embodiment, the computer program product includes a computer program that, when executed by a processor, implements the method described in the above embodiments.

[0101] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0102] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0103] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0104] like Figure 10 As shown, device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1002 or a computer program loaded from storage unit 1008 into random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0105] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of monitors, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0106] The computing unit 1001 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as parameter accuracy evaluation methods. For example, in some embodiments, the parameter accuracy evaluation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the parameter accuracy evaluation method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform a parameter accuracy evaluation method by any other suitable means (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0109] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0111] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0112] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0113] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0114] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for evaluating parameter accuracy, the method comprising: With the goal of making the imaging plane of the imaging device parallel to the target plane, the position of the imaging device with calibrated internal parameters is adjusted; Based on the adjusted shooting equipment, the target plane is photographed to obtain an image of the target plane, and two corner points are determined on the image; Calculate the distance between the corner points on the target plane to obtain the calculated value of the actual distance between the corner points; Obtain the measured value of the actual distance between the corner points, and evaluate the accuracy of the calibration parameters of the shooting device based on the difference between the calculated value and the measured value; The calculation of the distance of the corner point on the target plane includes: Measure the pixel distance of the corner point on the image; Obtain the camera focal length calibrated by the intrinsic parameters of the shooting device, and obtain the vertical distance from the camera of the shooting device to the target plane; Based on the pixel distance, the camera focal length, and the vertical distance, calculate the distance of the corner point on the target plane; The distance between the corner point and the target plane is calculated according to the following formula: Where h is the pixel distance between two corner points in the image after distortion correction, f is the calibrated camera focal length; D is the actual measured vertical distance from the front edge of the camera lens to the target plane, plus the starting point of the lens's field of view; H is the calculated distance between the two corner points in real space.

2. The method according to claim 1, wherein, The step of adjusting the imaging device to achieve a parallel relationship between the imaging plane of the imaging device and the target plane includes: Obtain a perpendicular line to the target plane; Based on the vertical line, adjust the cross level until the light from the cross level coincides with the vertical line, and determine the center point of the cross light from the cross level on the target plane. If the area of ​​the target plane in the captured image is greater than a set threshold, the capturing device is adjusted based on the center point.

3. The method according to claim 2, wherein, Adjusting the shooting device based on the center point includes: Mark the center point to determine the marking point; A light-transmitting pipe is placed vertically between the cross level and the target plane; Adjust the light transmission channel so that the cross rays emitted by the cross level are illuminating the target plane through the light transmission channel, and determine that the center point of the cross rays coincides with the mark point; Adjusting the height, angle, and position of the shooting device, in response to determining that the marker point in the imaging screen of the shooting device is located in the light-transmitting pipe, determines the position of the shooting device.

4. The method according to claim 1 or 2, wherein, The target plane comprises multiple square patterns, and the multiple square patterns are arranged in a matrix. Determining that the imaging plane and the target plane are parallel includes: The image is processed, and a first horizontal edge line and a first vertical edge line are obtained in the image. The first horizontal edge line is the horizontal edge line of any row of square patterns, and the first vertical edge line is the vertical edge line of any column of square patterns. Obtain the second horizontal edge line and the second vertical edge line, wherein the second horizontal edge line is the horizontal edge line of the square pattern in other rows, and the second vertical edge line is the vertical edge line of the square pattern in other columns; Determine the first degree of overlap between the first horizontal edge line and the second horizontal edge line, and determine the second degree of overlap between the first vertical edge line and the second vertical edge line; In response to determining that both the first degree of overlap and the second degree of overlap are completely overlapping, it is determined that the imaging plane and the target plane are parallel.

5. A parameter accuracy assessment device, the device comprising: An adjustment module is used to adjust the position of the calibrated internal parameters of the shooting device with the goal of making the imaging plane of the shooting device parallel to the target plane. The shooting module is used to capture the target plane based on the adjusted shooting device, obtain an image of the target plane, and determine two corner points on the image; A calculation module is used to calculate the distance of the corner points on the target plane to obtain the calculated value of the true distance between the corner points. Specifically, the calculation module is used to measure the pixel distance of the corner points on the image; obtain the camera focal length of the shooting device's intrinsic parameter calibration, and obtain the vertical distance from the camera of the shooting device to the target plane; based on the pixel distance, the camera focal length, and the vertical distance, calculate the distance of the corner points on the target plane, and the calculated distance of the corner points on the target plane satisfies the following formula: Where h is the pixel distance between two corner points in the image after distortion correction, f is the calibrated camera focal length; D is the actual measured vertical distance from the front edge of the camera lens to the target plane, plus the starting point of the lens's field of view; H is the calculated distance between the two corner points in real space. An evaluation module is used to obtain the measured value of the actual distance between the corner points, and to evaluate the accuracy of the calibration parameters of the shooting device based on the difference between the calculated value and the measured value.

6. The apparatus according to claim 5, wherein, The adjustment module is used for: Obtain a perpendicular line to the target plane; Based on the vertical line, adjust the cross level until the light from the cross level coincides with the vertical line, and determine the center point of the cross light from the cross level on the target plane. If the area of ​​the target plane in the captured image is greater than a set threshold, the capturing device is adjusted based on the center point.

7. The apparatus according to claim 6, wherein, The adjustment module is used for: Mark the center point to determine the marking point; A light-transmitting pipe is placed vertically between the cross level and the target plane; Adjust the light transmission channel so that the cross rays emitted by the cross level are illuminating the target plane through the light transmission channel, and determine that the center point of the cross rays coincides with the mark point; Adjusting the height, corner points, and position of the shooting device, in response to determining that the marker point in the imaging screen of the shooting device is located in the light-transmitting pipe, determines the position of the shooting device.

8. The apparatus according to claim 5 or 6, wherein, The target plane comprises multiple square patterns, and the multiple square patterns are arranged in a matrix. The adjustment module is also used for: The image is processed, and a first horizontal edge line and a first vertical edge line are obtained in the image. The first horizontal edge line is the horizontal edge line of any row of square patterns, and the first vertical edge line is the vertical edge line of any column of square patterns. Obtain the second horizontal edge line and the second vertical edge line, wherein the second horizontal edge line is the horizontal edge line of the square pattern in other rows, and the second vertical edge line is the vertical edge line of the square pattern in other columns; Determine the first degree of overlap between the first horizontal edge line and the second horizontal edge line, and determine the second degree of overlap between the first vertical edge line and the second vertical edge line; In response to determining that both the first degree of overlap and the second degree of overlap are completely overlapping, it is determined that the imaging plane and the target plane are parallel.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-4.

Images