Pixel boundary line matching method and device based on difference frequency signal phase locking principle

Abstract

For the technical solution described in this application, a reference distance is obtained and, based on the reference distance, the displacement value of the object to be located in the direction perpendicular to the line is determined. Since the reference distance is determined based on a preset fence-like pattern on the object to be located in the image, and the image is obtained by collecting the object to be located at a preset reference position, the fence-like pattern is composed of T lines with a pitch and width of W each, where |M*W - N*R| < 0.1*R, M and N are integers, and M < N, and R is the resolution of the camera that collects the image. It can be seen that the setting principle of the fence-like pattern enables the processing of the fence-like pattern in the image to follow the principle of differential frequency signal phase locking. Therefore, compared with the gray value, the reference distance determined by the fence-like pattern has higher accuracy, and thus the displacement value determined based on the reference distance has higher accuracy.

Description

Technical Field

[0001] The present application relates to the field of electronic information, and in particular, to a pixel boundary line matching method and device based on the principle of difference frequency signal phase locking. Background Art

[0002] Generally, vision positioning systems use industrial cameras to capture real-time images of the target object to be positioned, and find specific geometric marking points of the target object in the captured images, such as the center point of a round hole, etc. The positioning function of the target object is realized according to its position in the image.

[0003] Many industrial application scenarios have high requirements for the positioning accuracy of vision positioning systems. However, since the pixel gray level is the average value of the actual light radiation intensity within the corresponding area, the higher-frequency texture information in the image has been lost.

[0004] Therefore, how to improve the positioning accuracy has become an urgent problem to be solved at present. Summary of the Invention

[0005] The present application provides a pixel boundary line matching method and device based on the principle of difference frequency signal phase locking, aiming to solve the problem of how to improve the positioning accuracy.

[0006] To achieve the above object, the present application provides the following technical solutions:

[0007] A pixel boundary line matching method based on the principle of difference frequency signal phase locking, comprising:

[0008] Obtaining a reference distance, where the reference distance is determined according to a preset fence-like pattern on the object to be positioned in the image, the image is obtained by collecting the object to be positioned at a preset reference position, the fence-like pattern is composed of T lines with a spacing and width of W, where |M*W - N*R| < 0.1*R, M and N are integers, and M < N; R is the resolution of the camera that captures the image;

[0009] Determining a displacement value of the object to be positioned in a direction perpendicular to the lines according to the reference distance.

[0010] Optionally, the reference distance is the difference between a first physical distance and a second physical distance, the first physical distance value is the distance between a reference pixel and the leftmost pixel of a target pixel, the second physical distance is the distance between the reference pixel and the leftmost boundary edge of the fence-like pattern, the target pixel is a row of pixels perpendicular to the lines of the fence-like pattern in the image, the reference pixel is a pixel, among the selected pixels, located on the boundary edge between lines and non-lines in the fence-like pattern, the selected pixels are pixels, among the target pixels, numbered K, K+N, ..., K+M*N, where K is the index of the maximum value element in the array, and the elements in the array are Si=Di+D(i+N)+...+D(i+M*N), where i=1, 2, ...N, and Di is the grayscale value of the i-th pixel in the target pixel.

[0011] Optionally, obtaining the reference distance includes:

[0012] Acquire the image of the object to be located, wherein the image includes an image of a marking pattern set on the object; the marking pattern is a fence-like pattern;

[0013] Calculating the grayscale value of a target pixel, wherein the target pixel is a row of pixels perpendicular to the line in the image;

[0014] An array is obtained from the grayscale value, wherein the elements in the array are Si=Di+D(i+N)+…+D(i+M*N);

[0015] Determine the maximum value SK in the array;

[0016] Select pixels numbered K, K+N, ..., K+M*N from the target pixels as pixels to be selected;

[0017] Searching for pixels located on the boundary edge between lines and non-lines in the fence-like pattern from the pixels to be selected as reference pixels;

[0018] Calculating the first physical distance value and the second physical distance value;

[0019] A difference between the first physical distance value and the second physical distance value is calculated as the reference distance.

[0020] Optionally, determining the displacement value of the object to be located in a direction perpendicular to the line according to the reference distance includes:

[0021] After the object to be positioned moves to the measurement position, an image of the object to be positioned is collected, and a distance after the movement is acquired based on the fence-shaped pattern in the image;

[0022] Take the difference between the moved distance and the reference distance as the displacement value of the object to be located in the direction perpendicular to the line.

[0023] A pixel boundary line matching device based on the principle of differential frequency signal phase locking, comprising:

[0024] An acquisition module, configured to acquire a reference distance, where the reference distance is determined according to a preset fence-like pattern on an object to be located in an image, the image is obtained by collecting the object to be located at a preset reference position, the fence-like pattern is composed of T lines with a pitch and width of W, where |M*W - N*R| < 0.1*R, M and N are integers, and M < N; R is the resolution of the camera for collecting the image;

[0025] A positioning module, configured to determine the displacement value of the object to be located in the direction perpendicular to the line according to the reference distance.

[0026] Optionally, the reference distance is the difference between a first physical distance and a second physical distance. The first physical distance value is the distance between a reference pixel and the leftmost pixel of a target pixel. The second physical distance is the distance between the reference pixel and the leftmost demarcation edge of the fence-like pattern. The target pixel is a row of pixels perpendicular to the lines of the fence-like pattern in the image. The reference pixel is a pixel located on the demarcation edge between the lines and non-lines in the fence-like pattern among the candidate pixels. The candidate pixels are the pixels numbered K, K + N,..., K + M*N in the target pixel. K is the label of the maximum value element in the array. The elements in the array are Si = Di + D(i + N) +... + D(i + M*N), where i = 1, 2,..., N, and Di is the gray value of the i-th pixel in the target pixel.

[0027] Optionally, the acquisition module is configured to acquire the reference distance, including:

[0028] The acquisition module is specifically used to acquire the image of the object to be located, wherein the image includes an imaging of a marking pattern set on the object; the marking pattern is a fence-like pattern; calculate the grayscale value of the target pixel, wherein the target pixel is a row of pixels perpendicular to the line in the image; obtain an array from the grayscale value, and the elements in the array are Si=Di+D(i+N)+...+D(i+M*N); determine the maximum value SK in the array; select pixels numbered K, K+N,..., K+M*N from the target pixels as selected pixels; search for pixels located on the boundary edge between lines and non-lines in the fence-like pattern from the selected pixels as reference pixels; calculate the first physical distance value and the second physical distance value; calculate the difference between the first physical distance value and the second physical distance value as the reference distance.

[0029] Optionally, the positioning module is used to determine the displacement value of the object to be positioned in a direction perpendicular to the line according to the reference distance, including:

[0030] The positioning module is specifically used to collect an image of the object to be positioned after the object to be positioned moves to the measurement position, and obtain the distance after the movement based on the fence-like pattern in the image; and use the difference between the distance after the movement and the reference distance as the displacement value of the object to be positioned in a direction perpendicular to the line.

[0031] A pixel boundary line matching device based on the difference frequency signal phase locking principle comprises a memory and a processor; the memory is used to store a program, and the processor is used to run the program to implement the above-mentioned pixel boundary line matching method based on the difference frequency signal phase locking principle.

[0032] A computer-readable storage medium stores a computer program. When the computer program is run on a computer, the above-mentioned pixel boundary line matching method based on the difference frequency signal phase-locking principle is implemented.

[0033] For the technical solution described in this application, a reference distance is obtained and, based on the reference distance, the displacement value of the object to be located in the direction perpendicular to the line is determined. Since the reference distance is determined based on a preset fence-like pattern on the object to be located in the image, and the image is obtained by collecting the object to be located at a preset reference position, the fence-like pattern consists of T lines with a pitch and width of W each, where |M*W - N*R| < 0.1*R, M and N are integers, and M < N, and R is the resolution of the camera that captures the image. It can be seen that the setting principle of the fence-like pattern enables the processing of the fence-like pattern in the image to follow the principle of differential frequency signal phase locking. Therefore, compared with the gray value, the reference distance determined by the fence-like pattern has higher accuracy, and thus the displacement value determined based on the reference distance has higher accuracy. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0035] Figure 1 It is an example diagram of a preset marking pattern provided on the object to be located;

[0036] Figure 2 It is a flowchart of a pixel boundary line matching method based on the principle of differential frequency signal phase locking disclosed in an embodiment of the present application;

[0037] Figure 3 It is an example diagram of target pixels selected in the fence-like pattern disclosed in an embodiment of the present application;

[0038] Figure 4 It is a flowchart of another pixel boundary line matching method based on the principle of differential frequency signal phase locking disclosed in an embodiment of the present application;

[0039] Figure 5 It is a structural schematic diagram of pixel boundary line matching based on the principle of differential frequency signal phase locking disclosed in an embodiment of the present application. Detailed Embodiments

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0041] The technical solution described in the embodiments of the present application can be applied in Figure 1 the scenario shown below: Figure 1 In Figure 1 , a preset marker pattern is set on the object to be located, and the marker pattern is a fence-like pattern. Specifically, the fence-like pattern is composed of T lines with a spacing and width of W each. Assuming the camera resolution is R, the width W of the fence-like pattern satisfies the following requirement: |M*W - N*R| < 0.1*R, where M and N are integers and M < N. It should be noted that in practice, under the condition of meeting the above conditions, M and N can be set according to experience and requirements.

[0042] The positioning of the object to be located means that the object to be located is captured by the camera, and the positioning is achieved based on the image. The purpose of the technical solution described in the embodiments of the present application is to generate prior information based on the preset scale of the fence-like pattern, and then perform positioning based on the prior information to improve the accuracy of the positioning result.

[0043] Figure 2 A pixel boundary line matching method based on the principle of differential frequency signal phase locking disclosed in the embodiments of the present application includes the following steps:

[0044] S201: Use a camera (such as an industrial camera) to capture an image of the object to be located at a preset reference position.

[0045] It should be noted that since the marker pattern is used for positioning, the part of the object to be located with the marker pattern must be captured by the camera, or the above marker pattern is set on each plane of the object to be located that can be captured by the camera.

[0046] That is, the captured image includes the above marker pattern. Optionally, the captured image can be processed such as filtering and noise reduction to obtain a better-quality image.

[0047] The preset reference position can be set according to requirements. For example, it can be a position directly facing the camera.

[0048] S202: In the image, intercept the target pixels.

[0049] Among them, the target pixels are a row of pixels perpendicular to the lines in the fence-like pattern. As shown by the target pixels in Figure 3 . Figure 3 Shown by the target pixels in Figure 3 .

[0050] S203: Calculate the gray gradient value of the target pixels.

[0051] Generally, the gray gradient value of any pixel in a row of pixels is the difference between the gray value of this pixel and the gray value of the next adjacent pixel.

[0052] S204: Calculate arrays S1, S2,..., SN.

[0053] Wherein, S1=D1+D(1+N)+……+D(1+M*N);

[0054] S2=D2+D(2+N)+……+D(2+M*N);

[0055] ……;

[0056] SN=DN+D(N+N)+...+D(N+M*N).

[0057] Di is the gradient value of the i-th pixel.

[0058] S205: Determine the maximum value in the array, recorded as SK.

[0059] S206: Select pixels numbered K, K+N, ..., K+M*N from the target pixels as pixels to be selected.

[0060] S207: Find a pixel located on the boundary edge between a line and a non-line in the fence pattern from the pixels to be selected, record it as a reference pixel, and assume that the reference pixel is numbered Z in the target pixel and is located on the Hth edge from the left of the fence pattern.

[0061] S208: Calculate the first physical distance value and the second physical distance value.

[0062] The first physical distance value is the distance between the reference pixel and the leftmost pixel of the target pixel, that is, L1=Z*R. The second physical distance is the distance between the reference pixel and the leftmost boundary edge of the fence-shaped pattern, that is, L2=H*W. S209: Calculate the difference between the first physical distance value and the second physical distance value as the reference distance. That is, L01=L1-L2=Z*RH*W.

[0063] S210: After the object to be positioned moves to the measurement position, an image of the object to be positioned is collected, and based on a fence-shaped pattern in the image, a distance L02 after the movement is obtained.

[0064] Among them, the calculation process of L02 is the same as that of L01, that is, S202-S209 are executed for the collected image after the object to be located moves.

[0065] S211: Calculate L0=L02-L01 as the displacement value of the object to be located in a direction perpendicular to the fence (ie, the lines in the fence-shaped image).

[0066] from Figure 2It can be seen from the process shown that: first determine the reference distance of the object to be located at the reference position, and then determine the displacement value based on the reference distance. It can be understood that based on the setting principle of the above-mentioned fence-like pattern, the processing of the fence-like pattern in the image follows the difference frequency signal phase locking principle. Therefore, compared with the existing pixel grayscale positioning method, the accuracy is higher.

[0067] It should be noted that Figure 2 In the process shown in , the step of obtaining the reference distance of the object to be positioned at the reference position can be regarded as a preprocessing step. When the object to be positioned and the reference position remain unchanged, the reference position can be determined only once. Therefore, the technical solution described in the above embodiment can be summarized as the following process:

[0068] Figure 4 Another pixel boundary line matching method based on the difference frequency signal phase locking principle disclosed in an embodiment of the present application includes the following steps:

[0069] S401: Acquire a reference distance.

[0070] The reference distance is determined based on a preset fence pattern on the object to be located in the image, and the image is obtained by capturing the object to be located at a preset reference position. The setting principle of the fence pattern is as described above and will not be repeated here.

[0071] Specifically, the reference distance is the difference between the first physical distance and the second physical distance, the first physical distance value is the distance between the reference pixel and the leftmost pixel of the target pixel, the second physical distance is the distance between the reference pixel and the leftmost boundary edge of the fence-like pattern, the target pixel is a row of pixels perpendicular to the lines of the fence-like pattern in the image, the reference pixel is a pixel among the selected pixels, which is located on the boundary edge between the lines and non-lines in the fence-like pattern, the selected pixels are pixels among the target pixels, numbered K, K+N, ..., K+M*N, K is the label of the maximum value element in the array, the elements in the array are Si=Di+D(i+N)+...+D(i+M*N), wherein i=1, 2, ...N, and Di is the grayscale value of the i-th pixel in the target pixel.

[0072] Further, the step of obtaining the reference distance may refer to S201-S209.

[0073] S402: After the object to be positioned moves to the measurement position, an image of the object to be positioned is collected, and a distance after the movement is obtained based on a fence-shaped pattern in the image.

[0074] Specifically, the image collected when the object to be located is moved to the measurement position is P. Then, in P, the target pixels are intercepted, the gray gradient values of the target pixels are calculated, and arrays S1, S2, ……, SN are calculated based on the gray gradient values. The maximum value in the array is determined and denoted as SK. The pixels numbered K, K + N, ……, K + M * N are selected from the target pixels as the candidate pixels. The pixels located on the boundary edge between the lines and non - lines in the fence - like pattern are searched for among the candidate pixels and denoted as the reference pixels. The first physical distance value and the second physical distance value are calculated, and the difference between the first physical distance value and the second physical distance value is used as the distance after movement.

[0075] S403: Use the difference between the distance after movement and the reference distance as the displacement value of the object to be located in the direction perpendicular to the fence (i.e., the lines).

[0076] Figure 4 The shown process, in addition to having high precision, can reuse the reference distance, so it also has high convenience and efficiency.

[0077] Figure 5 A pixel boundary line matching device based on the principle of differential - frequency signal phase - locking disclosed in an embodiment of the present application includes: an acquisition module and a positioning module.

[0078] The acquisition module is used to acquire a reference distance, which is determined based on a preset fence - like pattern on the object to be located in the image. The image is obtained by collecting the object to be located at a preset reference position. The fence - like pattern is composed of T lines with a pitch and width of W each, where |M * W - N * R| < 0.1 * R, M and N are integers, and M < N; R is the resolution of the camera for collecting the image.

[0079] The positioning module is used to determine the displacement value of the object to be located in the direction perpendicular to the lines based on the reference distance.

[0080] Specifically, the reference distance is the difference between the first physical distance and the second physical distance. The first physical distance value is the distance between the reference pixel and the left - most pixel of the target pixel. The second physical distance is the distance between the reference pixel and the left - most boundary edge of the fence - like pattern. The target pixel is a row of pixels perpendicular to the lines of the fence - like pattern in the image. The reference pixel is a pixel located on the boundary edge between the lines and non - lines in the fence - like pattern among the candidate pixels. The candidate pixels are the pixels numbered K, K + N, ……, K + M * N in the target pixels. K is the label of the maximum - value element in the array. The elements in the array are Si = Di + D(i + N)+……+D(i + M * N), where i = 1, 2, …… N, and Di is the gray value of the i - th pixel in the target pixel.

[0081] Specifically, the specific implementation method of the acquisition module for acquiring the reference distance is: acquiring the image of the object to be located, the image including the imaging of a marking pattern set on the object; the marking pattern is a fence-like pattern; calculating the grayscale value of the target pixel, wherein the target pixel is a row of pixels perpendicular to the line in the image; acquiring an array from the grayscale value, the elements in the array being Si=Di+D(i+N)+…+D(i+M*N); determining the maximum value SK in the array; selecting pixels numbered K, K+N,…, K+M*N from the target pixels as selected pixels; searching for pixels located on the boundary edge between lines and non-lines in the fence-like pattern from the selected pixels as reference pixels; calculating the first physical distance value and the second physical distance value; calculating the difference between the first physical distance value and the second physical distance value as the reference distance.

[0082] The positioning module is used to determine the displacement value of the object to be positioned in the direction perpendicular to the line based on the reference distance. The specific implementation method is as follows: after the object to be positioned moves to the measurement position, an image of the object to be positioned is collected, and based on the fence-like pattern in the image, the distance after the movement is obtained; the difference between the distance after the movement and the reference distance is used as the displacement value of the object to be positioned in the direction perpendicular to the line.

[0083] Figure 5 The device shown can achieve pixel boundary line matching based on the difference frequency signal phase-locking principle through a fence-like pattern, so it has higher positioning accuracy.

[0084] An embodiment of the present application also discloses a pixel boundary line matching device based on the difference frequency signal phase-locking principle, comprising a memory and a processor; the memory is used to store programs, and the processor is used to run the programs to implement the pixel boundary line matching method based on the difference frequency signal phase-locking principle described in the above embodiment.

[0085] The embodiment of the present application further discloses a computer-readable storage medium on which a computer program is stored. When the computer program is run on a computer, a pixel boundary line matching method based on the difference frequency signal phase-locking principle is implemented.

[0086] If the functions described in the method of the embodiment of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a storage medium readable by a computing device. Based on this understanding, the part of the embodiment of the present application that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computing device (which can be a personal computer, server, mobile computing device or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0087] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0088] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A pixel boundary line matching method based on the difference frequency signal phase locking principle, characterized in that: include: Obtain an image of the object to be located, where the image includes the imaging of a marker pattern provided on the object to be located. The marker pattern is a fence-like pattern, and the fence-like pattern is composed of T lines with a pitch and width of W each. Among them, , M and N are integers, and M < N. R is the resolution of the camera that acquires the image; Calculating the grayscale value of a target pixel, wherein the target pixel is a row of pixels perpendicular to the line in the image; An array is obtained from the grayscale value, wherein the elements in the array are Si=Di+D(i+N)+...+D(i+M*N), wherein i=1, 2, ...N, and Di is the grayscale value of the i-th pixel in the target pixel; Determine the maximum value SK in the array; Select pixels numbered K, K+N, ..., K+M*N from the target pixels as pixels to be selected, where K is the number of the maximum value element in the array; Searching for pixels located on the boundary edge between lines and non-lines in the fence-like pattern from the pixels to be selected as reference pixels; Calculating a first physical distance value and a second physical distance value, wherein the first physical distance value is the distance between the reference pixel and the leftmost pixel of the target pixel, and the second physical distance is the distance between the reference pixel and the leftmost boundary edge of the fence-shaped pattern; Calculate the difference between the first physical distance value and the second physical distance value as a reference distance; According to the reference distance, a displacement value of the object to be located in a direction perpendicular to the line is determined.

2. The method according to claim 1, characterized in that The step of determining the displacement value of the object to be located in a direction perpendicular to the line according to the reference distance includes: After the object to be positioned moves to the measurement position, an image of the object to be positioned is collected, and a distance after the movement is acquired based on the fence-shaped pattern in the image; The difference between the distance after the movement and the reference distance is used as the displacement value of the object to be positioned in a direction perpendicular to the line.

3. A pixel boundary line matching device based on the difference frequency signal phase locking principle, characterized in that: include: An acquisition module, configured to acquire an image of an object to be located, where the image includes an imaging of a marking pattern disposed on the object to be located, the marking pattern being a fence-like pattern, and the fence-like pattern being composed of T lines with a pitch and a width both being W, where, , M and N are integers, and M < N, and R is the resolution of a camera that acquires the image; calculate a grayscale value of a target pixel, where the target pixel is a row of pixels perpendicular to the lines in the image; obtain an array from the grayscale value, where elements in the array are Si = Di + D(i + N) + …… + D(i + M * N), where i = 1, 2, …… N, and Di is the grayscale value of the i-th pixel in the target pixel; determine a maximum value SK in the array; select pixels numbered K, K + N, ……, K + M * N from the target pixels as candidate pixels, where K is the label of the maximum value element in the array; find pixels located on the boundary edge between the lines and non-lines in the fence-like pattern from the candidate pixels as reference pixels; calculate a first physical distance value and a second physical distance value, where the first physical distance value is the distance between the reference pixel and the leftmost pixel of the target pixel, and the second physical distance is the distance between the reference pixel and the leftmost boundary edge of the fence-like pattern; calculate a difference between the first physical distance value and the second physical distance value as a reference distance; The positioning module is used to determine the displacement value of the object to be positioned in a direction perpendicular to the line according to the reference distance.

4. The device according to claim 3, characterized in that The positioning module is used to determine the displacement value of the object to be positioned in a direction perpendicular to the line according to the reference distance, including: The positioning module is specifically used to collect an image of the object to be positioned after the object to be positioned moves to the measurement position, and obtain the distance after the movement based on the fence-like pattern in the image; and use the difference between the distance after the movement and the reference distance as the displacement value of the object to be positioned in a direction perpendicular to the line.

5. A pixel boundary line matching device based on the difference frequency signal phase locking principle, characterized in that: It comprises a memory and a processor; the memory is used to store programs, and the processor is used to run the programs to implement the pixel boundary line matching method based on the difference frequency signal phase locking principle as described in any one of claims 1-2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is run on a computer, the pixel boundary line matching method based on the difference frequency signal phase-locking principle described in any one of claims 1 to 2 is implemented.

Images