Camera stand offset test method and device, electronic equipment and readable medium

Abstract

The embodiment of the invention discloses a camera support offset testing method and device, electronic equipment and a readable medium. A specific implementation mode of the method comprises the following steps: adjusting a distance between a camera bracket in a preset test lamp box and a black rectangular test card with a white background; collecting a test card image sequence of the white-background black rectangular test card in a preset test time period; obtaining camera image resolution information and lens field angle information of the camera; acquiring pixel coordinate information of a preset reference point; performing test reference point extraction processing on the test card image; generating a test reference point pixel coordinate information sequence; based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field angle information and the preset reference point pixel coordinate information, generating an angle offset curve graph corresponding to the camera support; and displaying the generated angle offset curve graph on a preset camera bracket offset test page. According to the embodiment, the accuracy of the offset test of the camera bracket is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a camera bracket offset testing method, device, electronic device, and readable medium. Background Art

[0002] With the continuous development of machine vision and image processing technology, cameras have been widely used in many fields, and camera brackets play an important role in camera installation and fixation. Camera bracket offset test is a technology for performing offset test on camera brackets. At present, when performing offset test on camera brackets, the method usually adopted is: during the test period, by randomly selecting time points, using the camera fixed on the bracket to collect images of the reference object, and comparing these images with the initial images of the same reference object collected at the beginning of the test, in order to determine whether the bracket has been offset.

[0003] However, when the above method is used to perform an offset test on the camera bracket, the following technical problems often occur:

[0004] During the test period, by randomly selecting time points, a camera fixed on the bracket is used to capture images of the reference object, and the captured images are compared with the initial images of the same reference object captured at the beginning of the test to determine whether the bracket has shifted. If the bracket shifts between two image captures and happens to return to the initial position before the random time point capture, the offset between the two image captures cannot be detected, resulting in poor accuracy of the camera bracket offset test.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose a camera bracket offset testing method, device, electronic device and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a camera holder offset test method, the method comprising: adjusting the distance between a camera holder of a fixed camera in a preset test light box and a white background black rectangular test card as a test distance; collecting a test card image sequence of the white background black rectangular test card within a preset test time period by a camera fixed on the above-mentioned camera holder; obtaining the camera image resolution information and lens field of view information of the above-mentioned camera; obtaining preset reference point pixel coordinate information; for each test card image in the above-mentioned test card image sequence, performing test reference point extraction processing on the above-mentioned test card image to obtain the test reference point pixel coordinate information corresponding to the above-mentioned test card image; based on the generated test reference point pixel coordinate information of each test reference point, generating a test reference point pixel coordinate information sequence; based on the test reference point pixel coordinate information sequence, the above-mentioned camera image resolution information, the above-mentioned lens field of view information and the above-mentioned preset reference point pixel coordinate information, generating an angle offset curve graph corresponding to the above-mentioned camera holder; and displaying the generated angle offset curve graph on a preset camera holder offset test page.

[0009] In a second aspect, some embodiments of the present disclosure provide a camera bracket offset test device, the device comprising: an adjustment unit, configured to adjust the distance between a camera bracket fixing a camera in a preset test light box and a white-background black rectangular test card to a test distance; a collection unit, configured to collect a test card image sequence of the white-background black rectangular test card within a preset test time period through a camera fixed on the camera bracket; a first acquisition unit, configured to acquire camera image resolution information and lens field of view angle information of the camera; a second acquisition unit, configured to acquire pixel coordinate information of a preset reference point; an extraction processing unit, configured to extract the test card image sequence; For each test card image in the test card, test reference point extraction processing is performed on the test card image to obtain test reference point pixel coordinate information corresponding to the test card image; a first generating unit is configured to generate a test reference point pixel coordinate information sequence based on the generated test reference point pixel coordinate information; a second generating unit is configured to generate an angle offset curve graph corresponding to the camera bracket based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view angle information and the preset reference point pixel coordinate information; a display unit is configured to display the generated angle offset curve graph on a preset camera bracket offset test page.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0012] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the camera support offset test method of some embodiments of the present disclosure, the accuracy of the camera support offset test is improved. Specifically, the reason for the poor accuracy of the camera support offset test is that: during the test time period, by randomly selecting a time point, the image of the reference object is collected using a camera fixed on the support, and the collected image is compared with the initial image of the same reference object collected at the beginning of the test to determine whether the support has offset. If the support has offset between two image acquisitions, it will return to the initial position before the random time point acquisition, and the offset between the two image acquisitions will not be detected, resulting in poor accuracy of the camera support offset test. Based on this, the camera support offset test method of some embodiments of the present disclosure, first, adjusts the distance between the camera support of the fixed camera in the preset test light box and the white background black rectangle test card to the test distance. Thus, the distance between the camera support of the fixed camera and the white background black rectangle test card can be adjusted so that the white background black rectangle test card occupies a larger screen in the camera screen. Then, the camera fixed on the above-mentioned camera support collects the test card image sequence of the above-mentioned white background black rectangle test card within the preset test time period. Thus, a test card image sequence that is more sensitive to instantaneous or intermittent offsets and is used to detect the offset of the camera within a preset test time period can be obtained. Afterwards, the camera image resolution information and the lens field of view angle information of the above-mentioned camera are obtained. Thus, the camera image resolution information and the lens field of view angle information used to generate the angle offset curve diagram of the camera bracket can be obtained. Next, the preset reference point pixel coordinate information is obtained. Thus, the coordinate information of the preset reference point used for the test can be obtained. Then, for each test card image in the above-mentioned test card image sequence, the above-mentioned test card image is subjected to a test reference point extraction process to obtain the test reference point pixel coordinate information corresponding to the above-mentioned test card image. Thus, the reference point extraction process can be performed on the test card image to obtain the test reference point pixel coordinate information used to generate the test reference point pixel coordinate information sequence. Then, based on the generated test reference point pixel coordinate information, a test reference point pixel coordinate information sequence is generated. Thus, a test reference point pixel coordinate information sequence that characterizes the state change of the reference point in the camera picture can be obtained. Afterwards, based on the above-mentioned test reference point pixel coordinate information sequence, the above-mentioned camera image resolution information, the above-mentioned lens field of view angle information and the above-mentioned preset reference point pixel coordinate information, an angle offset curve graph corresponding to the above-mentioned camera bracket is generated. Thus, an angle offset curve graph representing whether the camera bracket is offset can be obtained. Finally, the generated angle offset curve graph is displayed on the preset camera bracket offset test page. Also, when the camera bracket is subjected to an offset test, a test card image sequence representing the state change of the camera bracket, which is more sensitive to instantaneous or intermittent offsets within a preset test time period, is collected.Based on the test card image sequence that characterizes the state change of the camera bracket, the camera bracket is tested for offset, and an angle offset curve graph that characterizes whether the camera bracket is offset is generated. The generated angle offset curve graph can capture accidental, instantaneous or periodic bracket offsets, reduce the impact of the camera bracket offset test when the offset is accidental or periodic (for example, the bracket is offset between two image acquisitions and just returns to the initial position before the acquisition at a random time point), and improve the accuracy of the camera bracket offset test. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of the camera bracket offset testing method according to the present disclosure;

[0015] Figure 2 is a schematic structural diagram of some embodiments of a camera bracket offset testing device according to the present disclosure;

[0016] Figure 3 is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure;

[0017] Figure 4 It is a schematic diagram of an internal application test scenario according to some embodiments of the camera bracket offset test method disclosed herein. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] Figure 1 A process 100 of some embodiments of the camera stand offset test method according to the present disclosure is shown. The camera stand offset test method comprises the following steps:

[0025] Step 101, adjusting the distance between a camera support fixing a camera in a preset test light box and a black rectangular test card with a white background to a test distance.

[0026] In some embodiments, the execution subject (e.g., a computing device) of the camera bracket offset test method can adjust the distance between the camera bracket of the fixed camera in the preset test light box and the black rectangular test card with a white background as the test distance by controlling the slide rail or guide rail installed in the preset test light box. It should be noted that the black rectangular test card with a white background can be placed on the slide rail or the guide rail through a bracket. Optionally, the execution subject can display the preset test distance on the preset camera bracket offset test page to notify the tester to adjust the distance between the camera bracket of the fixed camera in the preset test light box and the black rectangular test card with a white background as the test distance. Among them, the black rectangular test card with a white background can be an image with a white background color including a black rectangle. The center point of the black rectangle in the black rectangular test card with a white background can overlap with the center point of the black rectangular test card with a white background. The preset test light box can be a test light box used to test whether the camera bracket is offset within a preset test time.

[0027] In some optional implementations of some embodiments, the execution subject may adjust the distance between the camera support for fixing the camera in the preset test light box and the black rectangular test card with a white background to the test distance by following the steps below:

[0028] The first step is to obtain the horizontal field of view angle of the camera. In practice, the execution subject can obtain the horizontal field of view angle of the camera from a preset product description document. The preset product description document can be a file that records various parameters of the camera. For example, the file can be a PDF file or a JSON file.

[0029] The second step is to obtain the width of the black rectangle test card with a white background as the test card width. In practice, the execution subject can obtain the width of the black rectangle test card with a white background from a preset database.

[0030] The third step is to generate a test distance based on the horizontal field of view angle and the test card width. In practice, the execution subject can input the horizontal field of view angle and the test card width as the first parameter and the second parameter into the preset test distance solution formula to obtain the test distance. The preset test distance solution formula can be The D may be the test distance, the W may be the test card width (second parameter), and the FOV may be the horizontal field of view angle (first parameter). The horizontal field of view angle may represent the horizontal field of view angle of the camera.

[0031] Step 4: Adjust the distance between the camera bracket that fixes the camera in the preset test light box and the black rectangular test card with a white background to the test distance.

[0032] Figure 4 A schematic diagram of an internal application test scenario according to some embodiments of the camera bracket offset test method disclosed herein is shown. Figure 4 4 shows a preset test light box 401, which includes a camera bracket 403, a camera 404 fixed on the camera bracket, and a black rectangular test card 402 with a white background.

[0033] Step 102 : A test card image sequence of a black rectangular test card with a white background is collected by a camera fixed on a camera bracket within a preset test time period.

[0034] In some embodiments, the execution subject may collect a test card image sequence of the black rectangular test card with a white background within a preset test time period through a camera fixed on the camera bracket, wherein each test card image in the test card image sequence has a corresponding collection time.

[0035] In some optional implementations of some embodiments, the execution subject may collect a test card image sequence of the white-background black rectangular test card within a preset test time period through the following steps using a camera fixed on the camera bracket:

[0036] The first step is to determine the starting time point of the preset test time period as the initial time point. As an example, the preset test time period may be "start time: 14:00, October 1, 2023, end time: 16:00, October 1, 2023". The starting time may be 14:00, October 1, 2023.

[0037] In the second step, according to the initial time point, perform the following acquisition steps:

[0038] In a first sub-step, at an initial time point, a camera fixed on the camera bracket captures an image of the black rectangular test card with a white background as a test card image, and the initial time point is determined as the capture time of the test card image.

[0039] The second sub-step is to obtain the system time after a preset time interval after the initial time point. In practice, the execution subject can obtain the system time through a preset function (eg, GetLocalTime function).

[0040] The third sub-step is, in response to determining that the acquired system time is within the above-mentioned preset test time period, determining the acquired system time as the initial time point to update the initial time point.

[0041] The fourth sub-step is to execute the above acquisition step again according to the updated initial time point.

[0042] In the third step, in response to determining that the acquired system time is not within the preset time period, the acquired test card images are arranged from front to back according to the acquisition time corresponding to the test card images to obtain a test card image sequence.

[0043] Step 103, obtaining the camera image resolution information and the lens field of view angle information of the camera.

[0044] In some embodiments, the execution entity may obtain the camera image resolution information and the lens field of view information of the camera. In practice, the execution entity may obtain the camera image resolution information and the lens field of view information of the camera from the preset product description document. The camera image resolution information includes the number of horizontal pixels of the camera and the number of vertical pixels of the camera. The number of horizontal pixels of the camera may be the number of pixels that the camera can capture in the horizontal direction. The number of vertical pixels of the camera may be the number of pixels that the camera can capture in the vertical direction. The lens field of view information includes the horizontal field of view angle and the vertical field of view angle. The horizontal field of view angle may represent the horizontal field of view angle of the camera. The vertical field of view angle represents the vertical field of view angle of the camera.

[0045] Step 104: Obtain pixel coordinate information of a preset reference point.

[0046] In some embodiments, the above-mentioned execution entity can obtain the preset reference point pixel coordinate information. Wherein, the above-mentioned preset reference point pixel coordinate information includes a horizontal coordinate value and a vertical coordinate value. Wherein, the above-mentioned preset reference point pixel coordinate information includes a horizontal coordinate value and a vertical coordinate value. The above-mentioned preset reference point pixel coordinate information can represent the position of the reference point in the initial image of the white background black rectangle test card taken before the test. The above-mentioned reference point can be an image point where a vertex of the black rectangle in the initial image is located (for example, the point where the upper right corner vertex of the black rectangle in the white background black rectangle test card is located). The above-mentioned initial image can be an image of the white background black rectangle test card captured by the above-mentioned camera fixed on the above-mentioned camera bracket when the distance between the above-mentioned camera bracket and the white background black rectangle test card is the test distance.

[0047] Step 105: for each test card image in the test card image sequence, perform test reference point extraction processing on the test card image to obtain the test reference point pixel coordinate information corresponding to the test card image.

[0048] In some embodiments, the execution entity may perform test reference point extraction processing on each test card image in the test card image sequence to obtain pixel coordinate information of the test reference point corresponding to the test card image.

[0049] In the process of adopting technical solutions to solve the problems mentioned in the background technology, the following problems are often accompanied:

[0050] During the offset test of the camera bracket, it is necessary to extract the test reference points from the test card image within the preset test time period to obtain the pixel coordinate information of the test reference points. In the face of the above technical problems, the conventional solution is generally to find the reference points in the test card image based on the feature point matching method, and determine the position information of the reference points in the test card image as the pixel coordinate information of the test reference points. However, the above conventional solution still has the following problems:

[0051] The feature point matching method usually relies more on significant and stable reference points in the image. When the camera bracket is offset, resulting in a change in the shooting angle, the shape or size of the reference point in the image may change, thus affecting the accuracy of the match. At the same time, the feature point matching method is more dependent on the image quality to find the reference point in the test card image. If the image quality is poor (such as blur, noise, etc.), it may lead to low feature point (reference point) extraction accuracy or a high number of reference point extraction failures. When the test reference point extraction fails, it needs to be re-extracted, wasting the computer's computing resources.

[0052] The inventors considered the shortcomings of finding reference points in the test card image based on feature point matching and decided to adopt the following solution:

[0053] In some optional implementations of some embodiments, the execution subject may perform test reference point extraction processing on the test card image to obtain the test reference point pixel coordinate information corresponding to the test card image through the following steps:

[0054] The first step is to filter and smooth the test card image to obtain a smoothed test card image. In practice, the execution subject may filter and smooth the test card image using a Gaussian filter to obtain a smoothed test card image.

[0055] The second step is to grayscale the smooth test card image to obtain a grayscale test card image. In practice, the execution subject can grayscale the smooth test card image by using an image grayscale processing technology to obtain a grayscale test card image.

[0056] The third step is to detect the gradient information of each grayscale test card image pixel in the grayscale test card image for each grayscale test card image pixel. Among them, each grayscale test card image pixel in the grayscale test card image corresponds to each gradient information in the gradient information. Each gradient information in the gradient information includes a gradient intensity value and a gradient direction information. In practice, the execution subject can detect the gradient information of each grayscale test card image pixel in the grayscale test card image through a convolution operation (such as a convolution operation of a Sobel operator). The gradient direction information can represent the gradient direction of the pixel in the grayscale test card image. For example, the gradient information can be "gradient intensity value: 145.34, gradient direction information: 63.43 degrees".

[0057] In the fourth step, for each grayscale test card image pixel in the grayscale test card image, perform the following non-maximum suppression processing:

[0058] In a first sub-step, the gradient information of the pixel points of the grayscale test card image in the grayscale test card image is determined as the target gradient information.

[0059] The second sub-step is to determine the gradient direction information included in the target gradient information as the reference gradient direction information.

[0060] The third sub-step is to determine the gradient intensity value included in the target gradient information as a reference gradient intensity value.

[0061] The fourth sub-step is to determine the target gradient direction based on the reference gradient direction information. In practice, the execution subject may compare the reference gradient direction information with each preset angle, and in response to determining that the angle corresponding to the gradient direction corresponding to the reference gradient direction information is one of the preset angles, determine the gradient direction information as the target gradient direction. As an example, the preset angles may be "0 degrees, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees, 315 degrees, 360 degrees". Then, in response to determining that the angle corresponding to the gradient direction corresponding to the reference gradient direction information is not one of the preset angles, the execution subject may compare the angle corresponding to the gradient direction corresponding to the reference gradient direction information with the corresponding range of each preset angle range information to determine the preset angle range in which the angle of the reference gradient direction information is located. Among them, each preset angle range information has a corresponding preset angle. Afterwards, the execution subject may determine the preset angle range information of the preset angle range in which the angle of the reference gradient direction information is located as the target preset angle range information. Afterwards, the execution subject may determine the preset angle corresponding to the target preset angle range information as the target gradient direction. As an example, the above-mentioned preset angle range information can be {"greater than 0 degrees and less than or equal to 22.5 degrees", "greater than 22.5 degrees and less than 45 degrees", "greater than 45 degrees and less than or equal to 67.5 degrees", "greater than 67.5 degrees and less than 90 degrees", "greater than 90 degrees and less than or equal to 112.5 degrees", "greater than 112.5 degrees and less than 135 degrees", "greater than 135 degrees and less than or equal to 157.5 degrees", "greater than 157.5 degrees and less than 180 degrees", "greater than 180 degrees and less than or equal to 202.5 degrees", "greater than 202.5 degrees and less than 225 degrees", "greater than 225 degrees and less than or equal to 247.5 degrees", "greater than 247.5 degrees and less than 270 degrees", "greater than 270 degrees and less than or equal to 292.5 degrees", "greater than 292.5 degrees and less than 315 degrees", "greater than 315 degrees and less than or equal to 337.5 degrees", "greater than 337.5 degrees and less than 360 degrees". Among them, the above-mentioned "greater than 0 degrees and less than or equal to 22.5" is a preset angle range information, corresponding to 0 degrees. "greater than 22.5 degrees and less than 45 degrees" corresponds to 45 degrees, "greater than 45 degrees and less than or equal to 67.5 degrees" corresponds to 45 degrees, "greater than 67.5 degrees and less than 90 degrees" corresponds to 90 degrees, and "greater than 90 degrees and less than or equal to 112.5 degrees" corresponds to 90 degrees. "greater than 112.5 degrees and less than 135 degrees" corresponds to 135 degrees. "greater than 135 degrees and less than or equal to 157.5 degrees" corresponds to 135 degrees. "greater than 157.5 degrees and less than 180 degrees" corresponds to 180 degrees. "greater than 180 degrees and less than or equal to 202.5 degrees" corresponds to 180 degrees. "greater than 202.5 degrees and less than 225 degrees" corresponds to 225 degrees."Greater than 225 degrees and less than or equal to 247.5 degrees" corresponds to 225 degrees. "Greater than 247.5 degrees and less than 270 degrees" corresponds to 270 degrees. "Greater than 270 degrees and less than or equal to 292.5 degrees" corresponds to 270 degrees. "Greater than 292.5 degrees and less than 315 degrees" corresponds to 315 degrees. "Greater than 315 degrees and less than or equal to 337.5 degrees" corresponds to 315 degrees. "Greater than 337.5 degrees and less than 360 degrees" corresponds to 0 degrees. As an example, the above-mentioned reference gradient direction information may be "63.43 degrees", and the preset angle range information of the preset angle range where "63.43 degrees" is located may be "greater than 45 degrees and less than or equal to 67.5 degrees", then the above-mentioned target gradient direction may be 45 degrees.

[0062] In a fifth sub-step, the grayscale test card image pixel point having the smallest distance from the grayscale test card image pixel point in the positive direction of the target gradient direction in the grayscale test card image is determined as the first adjacent pixel point, and the gradient intensity value corresponding to the first adjacent pixel point is determined as the first gradient intensity value. The distance may be a Euclidean distance.

[0063] The sixth sub-step is to determine the grayscale test card image pixel point that is the shortest distance from the grayscale test card image pixel point in the negative direction of the target gradient direction in the grayscale test card image as the second adjacent pixel point, and to determine the gradient intensity value corresponding to the second adjacent pixel point as the second gradient intensity value.

[0064] The seventh sub-step is, in response to determining that the reference gradient intensity value is less than or equal to the first gradient intensity value or the second gradient intensity value, updating the gradient intensity value included in the gradient information corresponding to the pixel point of the grayscale test card image to a preset value, so as to update the gradient information corresponding to the pixel point of the grayscale test card image. The preset value may be 0.

[0065] The fifth step is to determine the gradient information of each grayscale test card image pixel point after the above-mentioned non-maximum suppression processing as a gradient information set to be screened, wherein each gradient information to be screened in the above-mentioned gradient information set to be screened corresponds one-to-one to each grayscale test card image pixel point in the above-mentioned grayscale test card image.

[0066] The sixth step is to perform dual threshold detection processing on each grayscale test card image pixel point corresponding to the above-mentioned gradient information set to be screened, and obtain a first edge grayscale test card image pixel point set and a second edge grayscale test card image pixel point set. Among them, the gradient intensity value of each first edge grayscale test card image pixel point (strong edge pixel point) in the above-mentioned first edge grayscale test card image pixel point set is greater than the first preset threshold. The gradient intensity value of each second edge grayscale test card pixel point (weak edge pixel point) in the above-mentioned second edge grayscale test card image pixel point set is less than or equal to the above-mentioned first preset threshold and greater than the second preset threshold.

[0067] In the seventh step, based on the above-mentioned first edge grayscale test card image pixel point set, the above-mentioned second edge grayscale test card image pixel point set is subjected to pseudo-edge pixel point elimination processing to obtain the eliminated second edge grayscale test card image pixel point set. In practice, the above-mentioned execution subject uses the edge connection technology to perform pseudo-edge pixel point elimination processing on the above-mentioned second edge grayscale test card image pixel point set to obtain the eliminated second edge grayscale test card image pixel point set. Specifically, the above-mentioned execution can use the edge connection technology to check whether each second edge grayscale test card pixel point in the second edge grayscale test card image pixel point set is connected to at least one first edge grayscale test card image pixel point. If the second edge grayscale test card pixel point is connected to at least one first edge grayscale test card image pixel point, then the second edge grayscale test card pixel point is retained. If the second edge grayscale test card pixel point is not connected to any first edge grayscale test card image pixel point, then the second edge grayscale test card pixel point is eliminated from the above-mentioned second edge grayscale test card image pixel point set.

[0068] In the eighth step, the edge grayscale test card image pixel points in the first edge grayscale test card image pixel point set and the second edge grayscale test card image pixel point set that are eliminated and that meet the preset screening conditions are determined as test reference point pixel points. The preset screening conditions may be conditions for screening test reference point pixel points. For example, here, the preset screening conditions may be that the horizontal coordinate and the vertical coordinate of the pixel point may be that the pixel point in the first edge grayscale test card image pixel point set and the second edge grayscale test card image pixel point set that are eliminated is one of the four vertices of the quadrilateral (black rectangle) in the edge grayscale test card image, and the horizontal coordinate and the vertical coordinate of the pixel point meet the preset vertex selection conditions. As an example, the preset vertex selection conditions may be "the horizontal coordinate value is greater than the horizontal coordinate values ​​corresponding to at least two of the other three vertices, and the vertical coordinate value is greater than the vertical coordinate values ​​corresponding to at least two of the other three vertices". Optionally, the above-mentioned preset screening condition can be "the similarity between the edge grayscale test card image pixel point and the preset reference point is the largest among the similarities between each edge grayscale test card image pixel point in the first edge grayscale test card image pixel point set and each similarity between the preset reference point in the above-mentioned second edge grayscale test card image pixel point set after excluding the second edge grayscale test card image pixel point set."

[0069] In the ninth step, the position information of the pixel point of the test reference point in the grayscale test card image is determined as the pixel coordinate information of the test reference point, wherein the pixel coordinate information of the test reference point includes a horizontal coordinate value and a vertical coordinate value.

[0070] The above technical solution and its related contents, as an inventive point of an embodiment of the present disclosure, solve the technical problem of "the number of reference point extraction failures is large, and re-extraction wastes computer computing resources". The factors that lead to the large number of reference point extraction failures and the waste of computer computing resources are often as follows: the feature point matching method usually relies more on significant and stable reference points in the image. When the camera bracket is offset, resulting in a change in the shooting angle, the shape or size of the reference point in the image may change, thereby affecting the accuracy of the matching. At the same time, the method based on feature point matching to find the reference point in the test card image is highly dependent on the image quality. If the image quality is poor (such as blur, noise, etc.), it may lead to a low feature point (reference point) extraction accuracy or a large number of reference point extraction failures. When the test reference point extraction fails, it is necessary to re-extract, wasting computer computing resources. If the above factors are solved, the effect of reducing the number of reference point extraction failures and reducing the waste of computer resources can be achieved. In order to achieve this effect, in the first step, the test card image is filtered and smoothed to obtain a smoothed test card image. In this way, the noise in the test card image can be reduced and the accuracy of the test reference point extraction can be improved. The second step is to perform grayscale processing on the smoothed test card image to obtain a grayscale test card image. The third step is to detect the gradient information of each grayscale test card image pixel in the grayscale test card image, wherein each grayscale test card image pixel in the grayscale test card image corresponds to each gradient information in the gradient information, and each gradient information in the gradient information includes a gradient intensity value and a gradient direction information. Thus, the gradient information of each grayscale test card image pixel in the grayscale test card image can be obtained. The gradient information reflecting the change of the grayscale value in the image can be obtained. The fourth step is to perform the following non-maximum suppression processing for each grayscale test card image pixel in the grayscale test card image: the first sub-step is to determine the gradient information of the grayscale test card image pixel in the grayscale test card image as the target gradient information. The second sub-step is to determine the gradient direction information included in the target gradient information as the reference gradient direction information. The third sub-step is to determine the gradient intensity value included in the target gradient information as the reference gradient intensity value. The fourth sub-step is to determine the target gradient direction based on the reference gradient direction information. The fifth sub-step is to determine the grayscale test card image pixel point that is the smallest distance from the grayscale test card image pixel point in the positive direction of the target gradient direction in the grayscale test card image as the first adjacent pixel point, and to determine the gradient intensity value corresponding to the first adjacent pixel point as the first gradient intensity value. Thus, the first gradient intensity value for updating the gradient information corresponding to the grayscale test card image pixel point can be obtained.The sixth sub-step is to determine the grayscale test card image pixel point that is the smallest distance from the grayscale test card image pixel point in the negative direction of the target gradient direction in the grayscale test card image as the second adjacent pixel point, and to determine the gradient intensity value corresponding to the second adjacent pixel point as the second gradient intensity value. Thus, a second gradient intensity value for updating the gradient information corresponding to the grayscale test card image pixel point can be obtained. The seventh sub-step is to update the gradient intensity value included in the gradient information corresponding to the grayscale test card image pixel point to a preset value in response to determining that the reference gradient intensity value is less than or equal to the first gradient intensity value or less than or equal to the second gradient intensity value, so as to update the gradient information corresponding to the grayscale test card image pixel point. Thus, the gradient information corresponding to the grayscale test card image pixel point can be updated to suppress the interference of the gradient information of the grayscale test card image pixel point with a smaller gradient intensity value on the extraction. In the fifth step, each gradient information of each grayscale test card image pixel point after the non-maximum suppression process is determined as a gradient information set to be screened, wherein each gradient information to be screened in the gradient information set to be screened corresponds to each grayscale test card image pixel point in the grayscale test card image. In the sixth step, based on the gradient information set to be screened, each grayscale test card image pixel point corresponding to the gradient information set to be screened is subjected to dual threshold detection processing to obtain a first edge grayscale test card image pixel point set and a second edge grayscale test card image pixel point set. Thus, the first edge grayscale test card image pixel point set representing strong edge pixels and the second edge grayscale test card image pixel point set representing weak edge pixels can be detected by dual threshold detection processing. The first edge grayscale test card image pixel point set and the second edge grayscale test card image pixel point set can be sets where test reference points are located. In the seventh step, based on the first edge grayscale test card image pixel point set, the second edge grayscale test card image pixel point set is subjected to pseudo edge pixel point elimination processing to obtain a second edge grayscale test card image pixel point set eliminated. Thus, the second edge grayscale test card image pixel point set representing weak edge pixels can be processed by pseudo-edge pixel elimination to improve the accuracy of edge pixels. In the eighth step, the edge grayscale test card image pixel points that meet the preset screening conditions in the first edge grayscale test card image pixel point set and the second edge grayscale test card image pixel point set that are eliminated are determined as test reference point pixels. Thus, the test reference point pixels can be screened out in the first edge grayscale test card image pixel point set that represents the edge information of a relatively stable rectangle and the second edge grayscale test card image pixel point set that are eliminated. In the ninth step, the position information of the above-mentioned test reference point pixels in the above-mentioned grayscale test card image is determined as the test reference point pixel coordinate information, wherein the above-mentioned test reference point pixel coordinate information includes a horizontal coordinate value and a vertical coordinate value.Also, because the gradient information of each grayscale test card image pixel point in the grayscale test card image is detected, each gradient information reflects the change of the grayscale value in the image, and the edge information of the image can be captured. When the camera bracket is offset, although the shooting angle has changed, the edge information of the rectangle remains relatively stable in the image. Then, on the basis of the first edge grayscale test card image pixel point set representing the edge information and eliminating the second edge grayscale test card image pixel point set, the test reference point pixel (for example, the pixel of the upper right corner vertex in the black rectangle) is screened out. Compared with the method based on feature point matching to find the reference point in the test card image, the above processing method has less dependence on a significant and stable single reference point in the image and less dependence on image quality, has strong adaptability to image changes, improves the accuracy of feature point (reference point) extraction, and thus improves the accuracy of the test reference point pixel coordinate information, reduces the number of reference point extraction failures, and reduces the waste of computer computing resources caused by re-extraction.

[0071] Step 106: Generate a test reference point pixel coordinate information sequence based on the generated pixel coordinate information of each test reference point.

[0072] In some embodiments, the execution entity may generate a test reference point pixel coordinate information sequence based on the generated pixel coordinate information of each test reference point.

[0073] In some optional implementations of some embodiments, the execution subject may generate a test reference point pixel coordinate information sequence based on the generated pixel coordinate information of each test reference point through the following steps:

[0074] The first step is to sort the above-mentioned test reference point pixel coordinate information according to the arrangement order of the test card images corresponding to the above-mentioned test reference point pixel coordinate information in the above-mentioned test card image sequence to obtain a test reference point pixel coordinate information sequence.

[0075] Step 107, based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field angle information and the preset reference point pixel coordinate information, generate an angle offset curve graph corresponding to the camera bracket.

[0076] In some embodiments, the execution entity may generate an angle offset curve corresponding to the camera bracket based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view information and the preset reference point pixel coordinate information.

[0077] In some optional implementations of some embodiments, the execution subject may generate an angle offset curve graph corresponding to the camera bracket based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view angle information and the preset reference point pixel coordinate information through the following steps:

[0078] In the first step, for the first test reference point pixel coordinate information in the test reference point pixel coordinate information sequence, the following determination steps are performed:

[0079] The first sub-step is to generate a horizontal angle offset value and a vertical angle offset value based on the test reference point pixel coordinate information, the preset reference point pixel coordinate information, the camera image resolution information, and the lens field of view angle information.

[0080] The second sub-step is to determine the acquisition time of the pixel coordinate information corresponding to the test reference point.

[0081] In the third sub-step, the horizontal angle offset value and the vertical angle offset value are determined as the offset information corresponding to the acquisition time.

[0082] The fourth sub-step is to delete the first test reference point pixel coordinate information from the test reference point pixel coordinate information sequence to update the test reference point pixel coordinate information sequence.

[0083] A fifth sub-step, in response to determining that the updated test reference point pixel coordinate information sequence is not an empty set, performing the above determination step again according to the updated test reference point pixel coordinate information sequence.

[0084] In the second step, in response to determining that the updated test reference point pixel coordinate information sequence is an empty set, a corresponding angle offset curve graph of the camera bracket is generated according to the determined offset information.

[0085] In some optional implementations of some embodiments, the execution subject may generate a horizontal angle offset value and a vertical angle offset value based on the test reference point pixel coordinate information, the preset reference point pixel coordinate information, the camera image resolution information, and the lens field of view angle information through the following steps:

[0086] The first step is to determine the horizontal coordinate value included in the above-mentioned test reference point pixel coordinate information as the target horizontal coordinate value.

[0087] In the second step, the horizontal coordinate value included in the above-mentioned preset reference point pixel coordinate information is determined as the reference horizontal coordinate value.

[0088] The third step is to determine the number of horizontal pixels of the camera included in the camera image resolution information as the target number of horizontal pixels.

[0089] The fourth step is to determine the horizontal field of view angle included in the lens field of view angle information as the target horizontal field of view angle. For example, the target horizontal field of view angle may be 60 degrees.

[0090] The fifth step is to generate a horizontal angle offset value based on the target horizontal coordinate value, the reference horizontal coordinate value, the target horizontal pixel number and the target horizontal field of view angle. In practice, the execution entity may determine the difference between the target horizontal coordinate value and the reference horizontal coordinate value as the first value. Then, the execution entity may determine the ratio of the first value to the target horizontal pixel number as the second value. Afterwards, the execution entity may determine the product of the second value and the target horizontal field of view angle as the horizontal angle offset value. For example, the target horizontal coordinate value may be 340, the reference horizontal coordinate value may be 320, the first value may be 20, the target horizontal pixel number may be 640, the second value may be (20 / 640), the target horizontal field of view angle may be 60 degrees, and the horizontal angle offset value may be (20 / 640)×60 degrees=1.875 degrees.

[0091] The sixth step is to determine the ordinate value included in the above-mentioned test reference point pixel coordinate information as the target ordinate value.

[0092] In the seventh step, the vertical coordinate value included in the above-mentioned preset reference point pixel coordinate information is determined as the reference vertical coordinate value.

[0093] In the eighth step, the number of vertical pixels of the camera included in the camera image resolution information is determined as the target number of vertical pixels.

[0094] In the ninth step, the vertical field of view angle included in the above lens field of view angle information is determined as the target vertical field of view angle.

[0095] Step 10: Generate a vertical angle offset value based on the target vertical coordinate value, the reference vertical coordinate value, the target vertical pixel number and the target vertical field of view angle. In practice, the execution entity may determine the difference between the target vertical coordinate value and the reference vertical coordinate value as a third value. Then, the execution entity may determine the ratio of the third value to the target vertical pixel number as a fourth value. Afterwards, the execution entity may determine the product of the fourth value and the target vertical field of view angle as the vertical angle offset value.

[0096] In some optional implementations of some embodiments, the execution subject may generate an angle offset curve graph corresponding to the camera bracket according to the determined offset information through the following steps:

[0097] The first step is to determine the acquisition times corresponding to the above offset information.

[0098] In the second step, each horizontal angle offset value included in each of the above offset information is determined as each target horizontal angle offset value, wherein each of the above target horizontal angle offset values ​​corresponds to each of the above acquisition times one by one.

[0099] In the third step, each vertical angle offset value included in each offset information is determined as each target vertical angle offset value, wherein each target vertical angle offset value in the above target vertical angle offset values ​​corresponds to each acquisition time in the above acquisition times.

[0100] The fourth step is to generate an angle offset curve corresponding to the camera bracket based on the above-mentioned target horizontal angle offset values, the above-mentioned target vertical angle offset values, and the above-mentioned acquisition times. In practice, the above-mentioned execution subject can call the preset drawing library interface to generate a first relationship curve about the corresponding relationship between the target horizontal angle offset value and the acquisition time according to the above-mentioned target horizontal angle offset values ​​and the above-mentioned acquisition times, and generate a second relationship curve about the corresponding relationship between the target vertical angle offset value and the above-mentioned acquisition time according to the above-mentioned target vertical angle offset values ​​and the above-mentioned acquisition times. Then, the above-mentioned execution subject can save the above-mentioned first relationship curve and the above-mentioned second relationship curve as an image as an angle offset curve through a preset drawing saving function (for example, plt.savefig() function). Among them, the above-mentioned preset drawing library interface can be a matplotlib.pyplot interface.

[0101] Step 108, displaying the generated angle offset curve graph on a preset camera bracket offset test page.

[0102] In some embodiments, the execution entity may display the generated angle offset curve graph on a preset camera bracket offset test page, wherein the preset camera bracket offset test page may be a page for displaying the angle offset curve graph.

[0103] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the camera bracket offset test method of some embodiments of the present disclosure, the accuracy of the camera bracket offset test is improved. Specifically, the reason for the poor accuracy of the camera bracket offset test is that: during the test time period, by randomly selecting a time point, the image of the reference object is captured using a camera fixed on the bracket, and the captured image is compared with the initial image of the same reference object captured at the beginning of the test to determine whether the bracket has offset. If the bracket has offset between two image captures, it just returns to the initial position before the random time point capture, and the offset between the two image captures cannot be detected, resulting in poor accuracy of the camera bracket offset test. Based on this, the camera bracket offset test method of some embodiments of the present disclosure, first, adjusts the distance between the camera bracket of the fixed camera in the preset test light box and the white background black rectangle test card to the test distance. In this way, the distance between the camera bracket of the fixed camera and the white background black rectangle test card can be adjusted so that the white background black rectangle test card occupies a larger screen in the camera screen. Then, a test card image sequence of the white-bottom black rectangular test card in a preset test time period is collected by a camera fixed on the camera support, wherein each test card image in the test card image sequence has a corresponding collection time. Thus, a test card image sequence that is more sensitive to instantaneous or intermittent offsets for detecting the offset of the camera in the preset test time period can be obtained. Then, the camera image resolution information and lens field of view angle information of the camera are obtained. Thus, the camera image resolution information and lens field of view angle information for generating the angle offset curve graph of the camera support can be obtained. Next, the preset reference point pixel coordinate information is obtained, wherein the preset reference point pixel coordinate information includes a horizontal coordinate value and a vertical coordinate value. Thus, the coordinate information of the preset reference point for testing can be obtained. Then, for each test card image in the test card image sequence, the test card image is subjected to a test reference point extraction process to obtain the test reference point pixel coordinate information corresponding to the test card image. Thus, the test card image can be subjected to a reference point extraction process to obtain the test reference point pixel coordinate information sequence for generating the test reference point pixel coordinate information sequence. Then, based on the generated pixel coordinate information of each test reference point, a test reference point pixel coordinate information sequence is generated. Thus, a test reference point pixel coordinate information sequence that characterizes the state change of the reference point in the camera image can be obtained. Afterwards, based on the above test reference point pixel coordinate information sequence, the above camera image resolution information, the above lens field of view angle information and the above preset reference point pixel coordinate information, an angle offset curve graph corresponding to the above camera bracket is generated. Thus, an angle offset curve graph that characterizes whether the camera bracket is offset can be obtained. Finally, the generated angle offset curve graph is displayed on the preset camera bracket offset test page.Also, when the camera bracket is subjected to an offset test, a test card image sequence that is more sensitive to instantaneous or intermittent offsets and characterizes the state changes of the camera bracket within a preset test time period is collected. Based on the test card image sequence that characterizes the state changes of the camera bracket, an offset test is performed on the camera bracket to generate an angle offset curve graph that characterizes whether the camera bracket is offset. The generated angle offset curve graph can capture accidental, instantaneous or periodic bracket offsets, reduce the impact of the camera bracket offset test when the offset is accidental or periodic (for example, the bracket is offset between two image acquisitions and just returns to the initial position before acquisition at a random time point), and improve the accuracy of the camera bracket offset test.

[0104] Further references Figure 2 As an implementation of the methods shown in the figures, the present disclosure provides some embodiments of a camera bracket offset test device, which are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0105] like Figure 2 As shown, the camera support offset test device 200 of some embodiments includes: an adjustment unit 201, a collection unit 202, a first acquisition unit 203, a second acquisition unit 204, an extraction processing unit 205, a first generation unit 206, a second generation unit 207 and a display unit 208. The adjustment unit 201 is configured to adjust the distance between the camera support of the camera fixed in the preset test light box and the black rectangular test card with a white background to a test distance; the collection unit 202 is configured to collect the test card image sequence of the black rectangular test card with a white background within a preset test time period through the camera fixed on the camera support; the first acquisition unit 203 is configured to obtain the camera image resolution information and the lens field of view angle information of the camera; the second acquisition unit 204 is configured to obtain the pixel coordinate information of the preset reference point; the extraction processing unit 205 is configured to generate the pixel coordinate information of the preset reference point for each test card image in the test card image sequence; The card image is subjected to test reference point extraction processing to obtain the test reference point pixel coordinate information corresponding to the test card image; the first generating unit 206 is configured to generate a test reference point pixel coordinate information sequence based on the generated test reference point pixel coordinate information; the second generating unit 207 is configured to generate an angle offset curve graph corresponding to the camera bracket based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view information and the preset reference point pixel coordinate information; the display unit 208 is configured to display the generated angle offset curve graph on the preset camera bracket offset test page.

[0106] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units contained therein, and will not be described in detail here.

[0107] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0108] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0109] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0110] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the method of some embodiments of the present disclosure are executed.

[0111] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0112] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0113] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: adjusts the distance between the camera support of the fixed camera in the preset test light box and the black rectangular test card with a white background to the test distance; collects the test card image sequence of the black rectangular test card with a white background within the preset test time period by the camera fixed on the camera support; obtains the camera image resolution information and lens field angle information of the camera; obtains the preset reference point pixel coordinate information; for each test card image in the test card image sequence, performs test reference point extraction processing on the test card image to obtain the test reference point pixel coordinate information corresponding to the test card image; generates a test reference point pixel coordinate information sequence based on the generated test reference point pixel coordinate information; generates an angle offset curve graph corresponding to the camera support based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field angle information and the preset reference point pixel coordinate information; and displays the generated angle offset curve graph on the preset camera support offset test page.

[0114] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be set in a processor, for example, may be described as: a processor includes an adjustment unit, an acquisition unit, a first acquisition unit, a second acquisition unit, an extraction processing unit, a first generation unit, a second generation unit and a display unit. The names of these units do not constitute limitations on the units themselves in certain circumstances. For example, the acquisition unit may also be described as "a unit that acquires a test card image sequence of the above-mentioned white-bottomed black rectangular test card within a preset test time period through a camera fixed on the above-mentioned camera bracket."

[0117] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0118] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of technical features, but should also cover other technical solutions formed by any combination of technical features or their equivalent features without departing from the inventive concept. For example, a technical solution formed by replacing the features with (but not limited to) the technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A camera bracket offset testing method, comprising: Adjust the distance between the camera bracket that fixes the camera in the preset test light box and the black rectangular test card with a white background to the test distance; Capturing a test card image sequence of the black rectangular test card with a white background within a preset test time period by a camera fixed on the camera bracket; Obtaining camera image resolution information and lens field of view angle information of the camera; Get the pixel coordinate information of the preset reference point; For each test card image in the test card image sequence, performing test reference point extraction processing on the test card image to obtain pixel coordinate information of the test reference point corresponding to the test card image; Generate a test reference point pixel coordinate information sequence based on the generated pixel coordinate information of each test reference point; Based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view angle information and the preset reference point pixel coordinate information, generating an angle offset curve graph corresponding to the camera bracket; The generated angle offset curve graph is displayed on the preset camera bracket offset test page.

2. The method according to claim 1, wherein: The step of adjusting the distance between the camera support for fixing the camera in the preset test light box and the black rectangular test card with a white background as the test distance comprises: Obtaining the horizontal field of view angle of the camera; Obtaining the width of the black rectangular test card with a white background as the test card width; Generate a test distance based on the horizontal field of view angle and the test card width; The distance between the camera support for fixing the camera in the preset test light box and the black rectangular test card with a white background is adjusted to the test distance.

3. The method according to claim 1, wherein: The step of generating a test reference point pixel coordinate information sequence based on the generated pixel coordinate information of each test reference point comprises: According to the arrangement order of each test card image corresponding to each test reference point pixel coordinate information in the test card image sequence, the test reference point pixel coordinate information is sorted to obtain a test reference point pixel coordinate information sequence.

4. The method according to claim 1, wherein: Each test card image in the test card image sequence has a corresponding acquisition time, and the test card image sequence of the white-bottom black rectangular test card within a preset test time period is acquired by a camera fixed to the camera bracket, including: Determine the starting time point of the preset test time period as the initial time point; Depending on the initial time point, perform the following acquisition steps: At an initial time point, the image of the black rectangular test card with a white background is captured by a camera fixed on the camera bracket as a test card image, and the initial time point is determined as the acquisition time of the test card image; Acquiring a system time after a preset time interval after the initial time point; In response to determining that the acquired system time is within the preset test time period, determining the acquired system time as an initial time point to update the initial time point; According to the updated initial time point, executing the acquisition step again; In response to determining that the acquired system time is not within the preset time period, the acquired test card images are arranged from front to back according to the acquisition time corresponding to the test card images to obtain a test card image sequence.

5. The method according to claim 1, wherein: The step of generating an angle offset curve graph corresponding to the camera bracket based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view angle information and the preset reference point pixel coordinate information comprises: For the first test reference point pixel coordinate information in the test reference point pixel coordinate information sequence, perform the following determination steps: Generate a horizontal angle offset value and a vertical angle offset value based on the test reference point pixel coordinate information, the preset reference point pixel coordinate information, the camera image resolution information, and the lens field of view angle information; Determine the acquisition time of the pixel coordinate information of the corresponding test reference point; The horizontal angle offset value and the vertical angle offset value are determined as the offset information corresponding to the acquisition time; Deleting the first test reference point pixel coordinate information from the test reference point pixel coordinate information sequence to update the test reference point pixel coordinate information sequence; In response to determining that the updated test reference point pixel coordinate information sequence is not an empty set, performing the determining step again according to the updated test reference point pixel coordinate information sequence; In response to determining that the updated test reference point pixel coordinate information sequence is an empty set, an angle offset curve graph corresponding to the camera bracket is generated according to the determined respective offset information.

6. The method according to claim 5, wherein: The camera image resolution information includes the number of horizontal pixels of the camera and the number of vertical pixels of the camera, the lens field of view angle information includes the horizontal field of view angle and the vertical field of view angle, the preset reference point pixel coordinate information includes the horizontal coordinate value and the vertical coordinate value, and the horizontal angle offset value and the vertical angle offset value are generated based on the test reference point pixel coordinate information, the preset reference point pixel coordinate information, the camera image resolution information, and the lens field of view angle information, including: Determine the horizontal coordinate value included in the pixel coordinate information of the test reference point as the target horizontal coordinate value; Determining the horizontal coordinate value included in the preset reference point pixel coordinate information as a reference horizontal coordinate value; Determining the number of horizontal pixels of the camera included in the camera image resolution information as the target number of horizontal pixels; Determine the horizontal field of view angle included in the lens field of view angle information as the target horizontal field of view angle; Generate a horizontal angle offset value based on the target horizontal coordinate value, the reference horizontal coordinate value, the target horizontal pixel number and the target horizontal field of view angle; Determine the ordinate value included in the test reference point pixel coordinate information as the target ordinate value; Determining the ordinate value included in the preset reference point pixel coordinate information as a reference ordinate value; Determine the number of vertical pixels of the camera included in the camera image resolution information as the target number of vertical pixels; Determine the vertical field of view angle included in the lens field of view angle information as the target vertical field of view angle; A vertical angle offset value is generated based on the target vertical coordinate value, the reference vertical coordinate value, the target vertical pixel number and the target vertical field of view angle.

7. The method according to claim 5, wherein: The step of generating an angle offset curve graph corresponding to the camera bracket according to each of the determined offset information includes: Determine each acquisition time corresponding to each offset information; Determine each horizontal angle offset value included in each offset information as each target horizontal angle offset value, wherein each target horizontal angle offset value in each target horizontal angle offset value corresponds to each acquisition time in each acquisition time; Determine each vertical angle offset value included in each offset information as each target vertical angle offset value, wherein each target vertical angle offset value in the target vertical angle offset values ​​corresponds to each acquisition time in the acquisition times; Based on the horizontal angle offset values ​​of each target, the vertical angle offset values ​​of each target, and the various acquisition times, an angle offset curve graph corresponding to the camera bracket is generated.

8. A camera bracket offset testing device, comprising: An adjustment unit is configured to adjust the distance between a camera support for fixing a camera in a preset test light box and a black rectangular test card with a white background to a test distance; A collection unit is configured to collect a test card image sequence of the black rectangular test card with a white background within a preset test time period through a camera fixed on the camera bracket; A first acquisition unit is configured to acquire camera image resolution information and lens field of view angle information of the camera; A second acquisition unit is configured to acquire pixel coordinate information of a preset reference point; an extraction processing unit configured to perform test reference point extraction processing on each test card image in the test card image sequence to obtain pixel coordinate information of the test reference point corresponding to the test card image; A first generating unit is configured to generate a test reference point pixel coordinate information sequence based on the generated test reference point pixel coordinate information; A second generating unit is configured to generate an angle offset curve graph corresponding to the camera bracket based on the test reference point pixel coordinate information sequence, the camera image resolution information, the lens field of view angle information and the preset reference point pixel coordinate information; The display unit is configured to display the generated angle offset curve graph on a preset camera bracket offset test page.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images