A synchronous detection method for machine vision equipment

Abstract

This invention discloses a synchronous detection method for machine vision devices, relating to the field of synchronous detection technology, comprising the following steps: constructing a scene screen; setting the placement position of the machine vision device based on the scene screen; acquiring a real-time target image based on the scene screen and the machine vision device; acquiring a grayscale segmentation threshold based on the real-time target image; acquiring a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructing a real-time reference value based on the real-time target region; determining whether the machine vision devices are synchronized based on the real-time reference value; if the machine vision devices are not synchronized, acquiring the time deviation between the two machine vision devices based on the real-time reference value; this invention addresses the problem that existing synchronous detection technologies fail to analyze whether synchronization is achieved based on image results, leading to low accuracy of synchronous detection results.

Description

Technical Field

[0001] This invention relates to the field of synchronous detection technology, specifically to a synchronous detection method for machine vision equipment. Background Technology

[0002] In modern industrial automation, intelligent transportation, scientific research, and national defense, collaborative perception systems based on multiple machine vision devices are increasingly widely used. These systems achieve comprehensive, high-precision measurement and analysis of target objects or scenes by synchronously collecting data from different spatial perspectives or using different modal sensors. Examples include online 3D inspection of high-speed production lines and multi-sensor environmental perception of autonomous vehicles. If the acquisition actions of each device are not synchronized, there will be a time difference in the recording of the same dynamic process. If the data lacks a unified time reference for alignment, accurate fusion and 3D calculation cannot be performed. Therefore, synchronous detection by machine vision devices is required.

[0003] Existing synchronization detection relies on electronic signals and metadata to infer synchronization, but cannot be verified through the final image data. This may result in synchronized signal data but asynchronous actual images. If this continues to operate, the output error data will gradually increase. For example, patent application CN105511315A discloses a method to keep machine vision detection and controller synchronized. This scheme determines whether synchronization is achieved through data signals, without verifying through image results, resulting in low accuracy of synchronization detection results. Existing synchronization detection technologies fail to analyze whether synchronization is achieved based on image results, leading to low accuracy of synchronization detection results. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art by constructing a scene screen; setting the placement position of the machine vision device based on the scene screen; acquiring a real-time target image based on the scene screen and the machine vision device; acquiring a grayscale segmentation threshold based on the real-time target image; acquiring a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructing a real-time reference value based on the real-time target region; determining whether the machine vision device is synchronized based on the real-time reference value; and if the machine vision device is not synchronized, acquiring the time deviation between the two machine vision devices based on the real-time reference value. This addresses the problem that existing synchronization detection technologies fail to analyze whether synchronization is achieved based on image results, resulting in low accuracy of synchronization detection results.

[0005] To achieve the above objectives, this application provides a synchronous detection method for a machine vision device, comprising the following steps:

[0006] Build scene screens;

[0007] The placement of machine vision equipment is determined based on the scene screen;

[0008] Real-time target images are acquired using scene screens and machine vision devices;

[0009] Gray-scale segmentation threshold is obtained based on real-time target images;

[0010] Real-time target region is obtained based on grayscale segmentation threshold and real-time target image;

[0011] Construct real-time reference values ​​based on the real-time target region;

[0012] Determine whether machine vision devices are synchronized based on real-time reference values;

[0013] If the machine vision devices are not synchronized, the time deviation between the two machine vision devices is obtained based on the real-time reference value.

[0014] Furthermore, constructing the scene screen includes the following sub-steps:

[0015] Set up a screen, labeled as the scene screen; make the background of the scene screen white, and display a black circle in the center of the screen with a fixed center position and a gradually increasing diameter, labeled as the reference changing circle; the rate of change of the diameter of the reference changing circle is a fixed value, labeled as the first rate of change.

[0016] Furthermore, setting the placement of the machine vision device based on the scene screen includes the following sub-steps:

[0017] Obtain the face of the scene screen and mark it as the first plane;

[0018] Obtain the plane that is parallel to the first plane and at a distance of the first length, and mark it as the second plane;

[0019] Draw a perpendicular line from the center of the reference circle to the first plane, and mark it as the first perpendicular line;

[0020] Obtain the intersection point of the first perpendicular line and the second plane, and mark it as the first intersection point;

[0021] On the second plane, draw a circle with the first intersection point as the center and the second length as the radius, and mark it as the second drawn circle;

[0022] Obtain the number of machine vision devices to be inspected, and label it as n;

[0023] The placement interval degree is obtained as: J = 360° / n; where J is the placement interval degree;

[0024] Set one direction of the center of the second drawing circle to 0°, and place machine vision devices on the outline of the second drawing circle at 0°, J, 2×J, ..., (n-1)×J respectively, so that the machine vision devices face the first plane.

[0025] Furthermore, acquiring real-time target images based on the scene screen and machine vision equipment includes the following sub-steps:

[0026] As the reference circle changes, images are acquired synchronously using machine vision equipment and marked as real-time target images.

[0027] Furthermore, obtaining the grayscale segmentation threshold based on the real-time target image includes the following sub-steps:

[0028] Convert the real-time target image into a grayscale image and label it as a real-time target grayscale image;

[0029] Mark the grayscale value of each pixel in the real-time target grayscale image as the real-time target grayscale value;

[0030] Divide the real-time target grayscale value from 0 to 255 into a first number of intervals, and mark them as grayscale intervals;

[0031] The number of real-time target gray values ​​within each gray-level division interval is counted and marked as the gray-level division frequency.

[0032] A histogram is plotted with the real-time target grayscale value as the X-axis data, the grayscale frequency as the Y-axis data, and the grayscale intervals as the histogram intervals. This histogram is then labeled as the target grayscale histogram.

[0033] Furthermore, obtaining the grayscale segmentation threshold based on the real-time target image also includes the following sub-steps:

[0034] In the target grayscale histogram, obtain the grayscale intervals with a higher grayscale frequency than both sides and mark them as the first target interval;

[0035] Mark the middle value of the first target interval as the first middle value;

[0036] Get the number of the first target interval. If the number of the first target interval is less than 2, adjust the first quantity so that the number of the first target interval is greater than or equal to 2.

[0037] When the number of first target intervals is greater than or equal to 2, obtain the first target interval corresponding to the smallest first median value and mark it as the second target interval; obtain the first target interval with the largest first median value and mark it as the third target interval.

[0038] Find the gray-level segment with the minimum gray-level segmentation frequency between the second target segmentation and the third target segmentation, and mark it as the final target segmentation.

[0039] Obtain the median value of the final target range and mark it as the grayscale segmentation threshold.

[0040] Furthermore, obtaining the real-time target region based on the grayscale segmentation threshold and the real-time target image includes the following sub-steps:

[0041] Set the real-time target grayscale values ​​that are less than the segmentation grayscale threshold in the real-time target grayscale image to 0, and set the real-time target grayscale values ​​that are greater than or equal to the segmentation grayscale threshold to 255.

[0042] Obtain the continuous region of grayscale values ​​consisting of 0 in the real-time target grayscale image and mark it as the real-time target region.

[0043] Furthermore, constructing real-time reference values ​​based on the real-time target area includes the following sub-steps:

[0044] Establish a Cartesian coordinate system and label it as a parametric coordinate system;

[0045] Place the real-time target region in the first quadrant of the parametric coordinate system;

[0046] Obtain a second number of coordinate points on the contour of the real-time target area and mark them as real-time contour coordinate points;

[0047] The equation for the real-time fitting function is set as: (A1-z1) 2 +(A2-z2) 2 =r 2 Where z1, z2, and r are constants of the real-time fitting function, A1 is the horizontal axis value of the real-time fitting function, and A2 is the vertical axis value of the real-time fitting function.

[0048] The specific values ​​of z1, z2 and r are obtained by fitting the real-time contour coordinate points with the equation of the real-time fitting function.

[0049] Mark the specific value of r as the real-time reference value.

[0050] Furthermore, determining whether machine vision devices are synchronized based on real-time reference values ​​includes the following sub-steps:

[0051] Obtain the real-time reference values ​​of all machine vision devices; if the real-time reference values ​​of all machine vision devices are equal, it indicates that the machine vision devices are synchronized.

[0052] If the real-time reference values ​​of the machine vision devices are not equal, it indicates that the machine vision devices are out of sync.

[0053] Furthermore, if the machine vision devices are not synchronized, obtaining the time deviation between the two machine vision devices based on real-time reference values ​​includes the following sub-steps:

[0054] If the machine vision devices are not synchronized, obtain the difference between the two unequal real-time reference values ​​corresponding to the two machine vision devices and mark it as the real-time reference difference;

[0055] The real-time phase difference time is calculated as: S1 = 2 × C / v; where S1 is the real-time phase difference time, C is the real-time reference difference, and v is the first rate of change.

[0056] The real-time difference was determined to be the time deviation between the two machine vision devices.

[0057] The beneficial effects of this invention are as follows: This invention constructs a scene screen; sets the placement position of the machine vision device based on the scene screen; acquires a real-time target image based on the scene screen and the machine vision device; acquires a grayscale segmentation threshold based on the real-time target image; acquires a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructs a real-time reference value based on the real-time target region; determines whether the machine vision device is synchronized based on the real-time reference value; if the machine vision device is not synchronized, it acquires the time deviation between the two machine vision devices based on the real-time reference value. The advantage is that it analyzes whether the synchronization is achieved based on the image results, thus improving the accuracy of the synchronization detection results.

[0058] This invention constructs a real-time reference value based on a real-time target region. Its advantage lies in determining whether synchronization is achieved by converting the image into a specific value of the real-time reference value, making synchronization detection more convenient and accurate. Attached Figure Description

[0059] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0060] Figure 2 This is the placement point for the machine vision equipment of the present invention;

[0061] Figure 3 This is a schematic diagram of the grayscale segmentation threshold of the present invention;

[0062] Figure 4 This is a schematic diagram of r in the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Example 1, please refer to Figure 1 As shown, this application provides a synchronous detection method for a machine vision device, comprising the following steps:

[0065] Step S1, construct the scene screen; Step S1 includes the following sub-steps:

[0066] Step S101: Set up a screen and mark it as the scene screen; make the background of the scene screen white, and display a black circle in the middle of the screen with the center position unchanged and the diameter gradually increasing, and mark it as the reference change circle; the change rate of the diameter of the reference change circle is a fixed value and marked as the first change rate; establish the reference change circle to facilitate the detection and recognition of whether it is synchronized, for example, the first change rate is 1cm / s.

[0067] Step S2: Set the placement position of the machine vision device based on the scene screen; Step S2 includes the following sub-steps:

[0068] Step S201: Obtain the face of the scene screen and mark it as the first plane;

[0069] Step S202: Obtain a plane parallel to the first plane at a distance of a first length, and mark it as the second plane; the first length is the distance from the scene screen, for example, a distance of 100cm;

[0070] Step S203: Draw a perpendicular line to the first plane through the center of the reference circle and mark it as the first perpendicular line;

[0071] Step S204: Obtain the intersection point of the first perpendicular line and the second plane, and mark it as the first intersection point;

[0072] Step S205: On the second plane, draw a circle with the first intersection point as the center and the second length as the radius, and mark it as the second drawn circle; the second length is set to be able to accommodate the machine vision device, for example, the second length is 50cm;

[0073] Step S206: Obtain the number of machine vision devices to be inspected, and label it as n;

[0074] Step S207, obtain the placement interval degree as: J = 360° / n; where J is the placement interval degree;

[0075] Step S208: Set one direction of the center of the second drawing circle to 0°, and place machine vision devices on the outline of the second drawing circle at 0°, J, 2×J, ..., (n-1)×J respectively, so that the machine vision devices face the first plane; so that the reference change circles acquired by the machine vision devices at the same time are of the same size.

[0076] In practical applications, if the number of machine vision devices to be inspected is 6, then the placement interval is: J = 360° / 6 = 60°. The machine vision devices are placed on the outline of the second drawn circle at 0°, 60°, 120°, 180°, 240°, and 300° respectively. Please refer to [link to relevant documentation]. Figure 2 As shown, obtain the placement point for the machine vision device.

[0077] Step S3: Acquire real-time target images based on the scene screen and machine vision device; Step S3 includes the following sub-steps:

[0078] Step S301: When the reference changing circle changes, the image is synchronously acquired through the machine vision device and marked as the real-time target image.

[0079] Step S4: Obtain the grayscale segmentation threshold based on the real-time target image; Step S4 includes the following sub-steps:

[0080] Step S401: Convert the real-time target image into a grayscale image and mark it as a real-time target grayscale image;

[0081] Step S402: Mark the gray value of each pixel in the real-time target grayscale image as the real-time target grayscale value;

[0082] Step S403: Divide the real-time target grayscale values ​​from 0 to 255 into a first number of intervals and mark them as grayscale division intervals; to facilitate observation of the distribution of real-time target grayscale values, the first number cannot be too small, for example, the first number is 8;

[0083] Step S404: Count the number of real-time target gray values ​​in each gray-level division interval and mark them as gray-level division frequency;

[0084] Step S405: Draw a histogram with the real-time target grayscale value as the X-axis data, the grayscale division frequency as the Y-axis data, and the grayscale division interval as the histogram interval interval, and mark it as the target grayscale histogram.

[0085] Step S406: In the target grayscale histogram, obtain the grayscale division intervals that have a higher grayscale division frequency than both sides, and mark them as the first target interval;

[0086] Step S407: Mark the median value of the first target interval as the first median value;

[0087] Step S408: Obtain the number of the first target intervals. If the number of the first target intervals is less than 2, adjust the first quantity so that the number of the first target intervals is greater than or equal to 2.

[0088] Step S409: When the number of first target intervals is greater than or equal to 2, obtain the first target interval corresponding to the smallest first intermediate value and mark it as the second target interval; obtain the first target interval with the largest first intermediate value and mark it as the third target interval.

[0089] Step S410: Obtain the gray-level segmentation interval with the smallest gray-level segmentation frequency between the second target interval and the third target interval, and mark it as the final target interval;

[0090] Step S411: Obtain the median value of the final target interval and mark it as the grayscale segmentation threshold; since the obtained image only contains black and white, the grayscale segmentation threshold can be obtained, which is the reference change circle of black when the segmentation threshold is less than the threshold.

[0091] For practical applications, please refer to Figure 3 As shown, the first target intervals are 31 to 63 and 159 to 191, and the number of first target intervals is equal to 2. Therefore, the first target interval corresponding to the smallest first median value is 31 to 63, and 31 to 63 is the second target interval. The first target interval corresponding to the largest first median value is 159 to 191, and 159 to 191 is marked as the third target interval. The final target interval is 95 to 127, and the median value of the final target interval 95 to 127 is 111. Therefore, the grayscale segmentation threshold is 111.

[0092] Step S5: Obtain the real-time target region based on the grayscale segmentation threshold and the real-time target image; Step S5 includes the following sub-steps:

[0093] Step S501: Set the real-time target grayscale values ​​in the real-time target grayscale image that are less than the grayscale segmentation threshold to 0, and set the real-time target grayscale values ​​that are greater than or equal to the grayscale segmentation threshold to 255; Since the acquired image only contains black and white, the grayscale segmentation threshold can be obtained, and the reference change circle that is less than the segmentation threshold is black;

[0094] Step S502: Obtain a continuous region in the real-time target grayscale image consisting of grayscale values ​​of 0, and mark it as the real-time target region; the real-time target region is the region of the reference change circle.

[0095] Step S6: Construct real-time reference values ​​based on the real-time target area; Step S6 includes the following sub-steps:

[0096] Step S601: Establish a Cartesian coordinate system and label it as a parametric coordinate system;

[0097] Step S602: Place the real-time target region in the first quadrant of the parametric coordinate system;

[0098] Step S603: Obtain a second number of coordinate points on the contour of the real-time target area and mark them as real-time contour coordinate points; the second number is set to obtain the accurate contour of the real-time target area, so the second number cannot be too small, for example, the second number is 20;

[0099] Step S604: Set the equation of the real-time fitting function as: (A1-z1) 2 +(A2-z2) 2 =r 2Where z1, z2, and r are constants of the real-time fitting function, A1 is the horizontal axis value of the real-time fitting function, and A2 is the vertical axis value of the real-time fitting function; because the reference change circle is set as a circle, in order to prevent interference from individual abnormal pixels, the radius of the reference change circle can be obtained more accurately.

[0100] Step S605: Fit the real-time contour coordinate points with the equation of the real-time fitting function to obtain the specific values ​​of z1, z2 and r.

[0101] Step S606: Mark the specific value of r as the real-time reference value;

[0102] For practical applications, please refer to Figure 4 As shown, the equation of the time-fitting function is: (A1-40) 2 +(A2-40) 2 =15 2 The real-time reference value is 15.

[0103] Step S7: Determine whether the machine vision device is synchronized based on the real-time reference value; Step S7 includes the following sub-steps:

[0104] Step S701: Obtain the real-time reference values ​​of all machine vision devices. If the real-time reference values ​​of all machine vision devices are equal, it means that the machine vision devices are synchronized. Because the reference change circle changes in real time, if the machine vision devices are synchronized, the obtained reference change circles are equal, that is, the real-time reference values ​​are equal. Therefore, if the real-time reference values ​​of all machine vision devices are equal, it means that the machine vision devices are synchronized; otherwise, they are not synchronized.

[0105] In step S702, if the real-time reference values ​​of the machine vision devices are not equal, it indicates that the machine vision devices are out of sync.

[0106] Step S8: If the machine vision devices are not synchronized, obtain the time deviation between the two machine vision devices based on the real-time reference value; Step S8 includes the following sub-steps:

[0107] Step S801: If the machine vision devices are not synchronized, obtain the difference between the two unequal real-time reference values ​​corresponding to the two machine vision devices and mark it as the real-time reference difference.

[0108] Step S802, calculate the real-time phase difference time as: S1 = 2 × C / v; where S1 is the real-time phase difference time, C is the real-time reference difference, and v is the first rate of change;

[0109] Step S803: Determine that the real-time time difference is the time deviation between the two machine vision devices; by obtaining the time deviation between the two machine vision devices, it is convenient to adjust the devices.

[0110] In practical applications, the real-time reference difference is 1cm. The real-time phase difference time is calculated as: S1=2×1 / 1=1s. Therefore, the time deviation between the two machine vision devices is 1s.

[0111] Example 2: This application also provides an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps of a synchronous detection method for a machine vision device are performed to achieve the following functions: constructing a scene screen; setting the placement position of the machine vision device based on the scene screen; acquiring a real-time target image based on the scene screen and the machine vision device; acquiring a grayscale segmentation threshold based on the real-time target image; acquiring a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructing a real-time reference value based on the real-time target region; determining whether the machine vision devices are synchronized based on the real-time reference value; if the machine vision devices are not synchronized, acquiring the time deviation between the two machine vision devices based on the real-time reference value.

[0112] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0113] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a synchronization detection method for a machine vision device provided by the above methods. The method includes: constructing a scene screen; setting the placement position of the machine vision device based on the scene screen; acquiring a real-time target image based on the scene screen and the machine vision device; acquiring a grayscale segmentation threshold based on the real-time target image; acquiring a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructing a real-time reference value based on the real-time target region; determining whether the machine vision devices are synchronized based on the real-time reference value; if the machine vision devices are not synchronized, acquiring the time deviation between the two machine vision devices based on the real-time reference value.

[0114] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the above-described synchronous detection method for a machine vision device to achieve the following functions: constructing a scene screen; setting the placement position of the machine vision device based on the scene screen; acquiring a real-time target image based on the scene screen and the machine vision device; acquiring a grayscale segmentation threshold based on the real-time target image; acquiring a real-time target region based on the grayscale segmentation threshold and the real-time target image; constructing a real-time reference value based on the real-time target region; determining whether the machine vision devices are synchronized based on the real-time reference value; if the machine vision devices are not synchronized, acquiring the time deviation between the two machine vision devices based on the real-time reference value.

[0115] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0116] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A synchronous detection method for a machine vision device, characterized in that, Includes the following steps: Build scene screens; The placement of machine vision equipment is determined based on the scene screen; Real-time target images are acquired using scene screens and machine vision devices; Gray-scale segmentation threshold is obtained based on real-time target images; Real-time target region is obtained based on grayscale segmentation threshold and real-time target image; Construct real-time reference values ​​based on the real-time target region; Determine whether machine vision devices are synchronized based on real-time reference values; If the machine vision devices are not synchronized, the time deviation between the two machine vision devices is obtained based on the real-time reference value.

2. The synchronous detection method for a machine vision device according to claim 1, characterized in that, Building a scene screen involves the following sub-steps: Set up a screen, labeled as the scene screen; make the background of the scene screen white, and display a black circle in the center of the screen with a fixed center position and a gradually increasing diameter, labeled as the reference changing circle; the rate of change of the diameter of the reference changing circle is a fixed value, labeled as the first rate of change.

3. The synchronous detection method for a machine vision device according to claim 2, characterized in that, Setting the placement of machine vision equipment based on the scene screen includes the following sub-steps: Obtain the face of the scene screen and mark it as the first plane; Obtain the plane that is parallel to the first plane and at a distance of the first length, and mark it as the second plane; Draw a perpendicular line from the center of the reference circle to the first plane, and mark it as the first perpendicular line; Obtain the intersection point of the first perpendicular line and the second plane, and mark it as the first intersection point; On the second plane, draw a circle with the first intersection point as the center and the second length as the radius, and mark it as the second drawn circle; Obtain the number of machine vision devices to be inspected, and label it as n; The placement interval degree is obtained as: J = 360° / n; where J is the placement interval degree; Set one direction of the center of the second drawing circle to 0°, and place machine vision devices on the outline of the second drawing circle at 0°, J, 2×J, ..., (n-1)×J respectively, so that the machine vision devices face the first plane.

4. The synchronous detection method for a machine vision device according to claim 3, characterized in that, Acquiring real-time target images based on scene screens and machine vision devices includes the following sub-steps: As the reference circle changes, images are acquired synchronously using machine vision equipment and marked as real-time target images.

5. The synchronous detection method for a machine vision device according to claim 4, characterized in that, Obtaining the grayscale segmentation threshold based on a real-time target image includes the following sub-steps: Convert the real-time target image into a grayscale image and label it as a real-time target grayscale image; Mark the grayscale value of each pixel in the real-time target grayscale image as the real-time target grayscale value; Divide the real-time target grayscale value from 0 to 255 into a first number of intervals, and mark them as grayscale intervals; The number of real-time target gray values ​​within each gray-level division interval is counted and marked as the gray-level division frequency. A histogram is plotted with the real-time target grayscale value as the X-axis data, the grayscale frequency as the Y-axis data, and the grayscale intervals as the histogram intervals. This histogram is then labeled as the target grayscale histogram.

6. The synchronous detection method for a machine vision device according to claim 5, characterized in that, Obtaining the grayscale segmentation threshold based on the real-time target image also includes the following sub-steps: In the target grayscale histogram, obtain the grayscale intervals with a higher grayscale frequency than both sides and mark them as the first target interval; Mark the middle value of the first target interval as the first middle value; Get the number of the first target interval. If the number of the first target interval is less than 2, adjust the first quantity so that the number of the first target interval is greater than or equal to 2. When the number of first target intervals is greater than or equal to 2, the first target interval corresponding to the smallest first median value is obtained and marked as the second target interval; Find the first target interval with the largest first median value and mark it as the third target interval; Find the gray-level segment with the minimum gray-level segmentation frequency between the second target segmentation and the third target segmentation, and mark it as the final target segmentation. Obtain the median value of the final target range and mark it as the grayscale segmentation threshold.

7. The synchronous detection method for a machine vision device according to claim 6, characterized in that, Obtaining the real-time target region based on grayscale segmentation threshold and real-time target image includes the following sub-steps: Set the real-time target grayscale values ​​that are less than the segmentation grayscale threshold in the real-time target grayscale image to 0, and set the real-time target grayscale values ​​that are greater than or equal to the segmentation grayscale threshold to 255. Obtain the continuous region of grayscale values ​​consisting of 0 in the real-time target grayscale image and mark it as the real-time target region.

8. The synchronous detection method for a machine vision device according to claim 7, characterized in that, Constructing real-time reference values ​​based on the real-time target region includes the following sub-steps: Establish a Cartesian coordinate system and label it as a parametric coordinate system; Place the real-time target region in the first quadrant of the parametric coordinate system; Obtain a second number of coordinate points on the contour of the real-time target area and mark them as real-time contour coordinate points; The equation of the real-time fitting function is set as: (A1-z1) 2 + (A2-z2) 2 = r 2 ; wherein z1, z2 and r are constants of the real-time fitting function, A1 is a horizontal axis value of the real-time fitting function, and A2 is a vertical axis value of the real-time fitting function. The specific values ​​of z1, z2 and r are obtained by fitting the real-time contour coordinate points with the equation of the real-time fitting function. Mark the specific value of r as the real-time reference value.

9. The synchronous detection method for a machine vision device according to claim 8, characterized in that, Determining whether machine vision devices are synchronized based on real-time reference values ​​includes the following sub-steps: Obtain the real-time reference values ​​of all machine vision devices; if the real-time reference values ​​of all machine vision devices are equal, it indicates that the machine vision devices are synchronized. If the real-time reference values ​​of the machine vision devices are not equal, it indicates that the machine vision devices are out of sync.

10. The synchronous detection method of a machine vision device according to claim 9, characterized in that, If the machine vision devices are not synchronized, obtaining the time difference between the two machine vision devices based on real-time reference values ​​includes the following sub-steps: If the machine vision devices are not synchronized, obtain the difference between the two unequal real-time reference values ​​corresponding to the two machine vision devices and mark it as the real-time reference difference; The real-time phase difference time is calculated as: S1 = 2 × C / v; where S1 is the real-time phase difference time, C is the real-time reference difference, and v is the first rate of change. The real-time difference was determined to be the time deviation between the two machine vision devices.

Images