Visual calibration device, radial line calibration plate and visual calibration method

By working together with the radial line calibration board and the processor, the calibration point and the photo point are automatically found, which solves the problem of manually adjusting the fine photo point position of the traditional calibration board and realizes an efficient and low-cost calibration process.

CN117252929BActive Publication Date: 2025-12-19FU TAI HUA IND SHENZHEN +2
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210656258.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-10
Publication Date
2025-12-19
Estimated Expiration
2042-06-10

AI Technical Summary

Technical Problem

Traditional calibration boards require manual adjustment of precise photo points when robots are paired with camera devices for hand-eye calibration and visual point calculation. This lack of scalability leads to problems such as patterns not being able to match perfectly.

Method used

Using a radial line calibration plate, the robot and the imaging device work together to automatically find calibration points and shooting points. The processor calculates the coordinates of the radial line intersection points in the image and adjusts the shooting angle and position to achieve automated calibration.

Benefits of technology

It enables an automated, fast, and efficient calibration process for calibration boards, reducing manufacturing costs and improving calibration accuracy and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117252929B_ABST
    Figure CN117252929B_ABST
Patent Text Reader

Abstract

The application provides a visual calibration device, a radial line calibration plate and a visual calibration method. The visual calibration device works in combination with the radial line calibration plate. The radial line calibration plate comprises a plurality of radial lines, and the center points of the radial lines are consistent with the center point of the radial line calibration plate. The visual calibration device comprises a robot, a shooting device and a processor. The shooting device is used to obtain a first image of the radial line calibration plate. The processor is used to capture any two radial lines in the first image and calculate first pixel coordinates according to the any two radial lines in the first image. The processor is further used to process the first pixel coordinates and calculate first physical coordinates. The processor is further used to control the robot to drive the shooting device to move and adjust the shooting angle or position of the shooting device according to the first physical coordinates.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of visual positioning, in particular to a visual calibration device, a radial line calibration board and a visual calibration method. BACKGROUND

[0002] The calibration board is a flat plate with a fixed interval pattern array, which is widely used in machine vision, image measurement, photogrammetry, three-dimensional reconstruction and other applications to determine the relationship between the pixel and the actual physical size of the shooting device. Currently commonly used calibration boards include chessboard, circular grid and Charuco.

[0003] In the process of hand-eye calibration and visual point calculation of the robot combined with the shooting device, the traditional calibration board needs to be manually adjusted to fine-tune the shooting point, so that the patterns on the calibration board are completely within the field of view of the shooting device, otherwise the patterns cannot be completely matched, which lacks expansibility. SUMMARY

[0004] Therefore, it is necessary to provide a visual calibration device, a radial line calibration board and a visual calibration method to solve the above problems.

[0005] The present application provides a visual calibration device for working with a radial line calibration board, wherein the radial line calibration board includes a plurality of radial lines, and the center points of the plurality of radial lines are consistent with the center point of the radial line calibration board; the visual calibration device includes a robot, a shooting device and a processor, the processor is electrically connected with the robot and the shooting device to form a communication connection with each other; the shooting device is used to acquire a first image of the radial line calibration board; the processor is used to acquire the first image to capture any two radial lines in the first image, and calculate a first pixel coordinate according to the any two radial lines in the first image; wherein the first pixel coordinate is the pixel coordinate of the intersection of the any two radial lines in the first image; the processor is further used to process the first pixel coordinate to calculate a first physical coordinate; wherein the first physical coordinate is the physical coordinate of the intersection of the any two radial lines in the first image; the processor is further used to control the robot to move the shooting device according to the first physical coordinate, and adjust the shooting angle or position of the shooting device.

[0006] Further, the robot includes a mechanical arm; the processor is used to control the mechanical arm to move according to the first physical coordinate, adjust the shooting angle of the shooting device and perform shooting, and control the shooting device to obtain a second image.

[0007] Further, the radial line calibration board comprises a calibration board; the processor acquires a second image from the photographing device, detects whether the calibration board is completely in the second image; when the processor detects that the calibration board is completely in the second image, the vision calibration device performs hand-eye calibration on the calibration board, and acquires a hand-eye calibration parameter; the processor is further configured to process the hand-eye calibration parameter, and obtain a conversion relationship between pixel coordinates of the photographing device and actual physical coordinates.

[0008] Further, the radial line calibration board further comprises a radial line plate arranged around the calibration board, the radial line plate comprising a plurality of radial lines, and the intersection points of the radial lines being consistent with the center point of the calibration board; the photographing device is further configured to acquire a third image; the processor is further configured to receive the third image, capture any two radial lines in the third image, and then calculate second pixel coordinates according to the any two radial lines in the third image; wherein the second pixel coordinates are pixel coordinates of the intersection points of the any two radial lines in the third image; the processor is further configured to process the second pixel coordinates to calculate second physical coordinates; wherein the second physical coordinates are physical coordinates of the intersection points of the any two radial lines in the third image.

[0009] Further, the processor is further configured to process the second pixel coordinates according to the conversion relationship between the pixel coordinates of the photographing device and the actual physical coordinates, to obtain the second physical coordinates and third physical coordinates; wherein the second physical coordinates are the physical coordinates of the intersection points of the any two radial lines in the third image, and the third physical coordinates are physical coordinates of the position of the photographing device.

[0010] Further, the processor is further configured to control the mechanical arm to drive the photographing device to move to the third physical coordinates according to the second physical coordinates and the third physical coordinates, and control the photographing device to acquire a fourth image.

[0011] Further, the processor acquires the fourth image from the photographing device, detects whether the calibration board is completely in the fourth image; when the processor detects that the calibration board is completely in the fourth image, the vision calibration device performs vision point calculation.

[0012] The application further provides a radial line calibration board applied to a vision calibration device, the radial line calibration board comprising a calibration board and a radial line plate, the radial line plate being arranged around the calibration board; the radial line plate comprising a plurality of radial lines, and the intersection points of the radial lines being consistent with the center point of the calibration board.

[0013] The application further provides a vision calibration method applied to the vision calibration device, the vision calibration method comprising: acquiring a first image, capturing any two radial lines in the first image, and calculating first pixel coordinates according to the any two radial lines in the first image; processing the first pixel coordinates to calculate first physical coordinates; and controlling the robot to move the shooting device according to the first physical coordinates, so as to adjust the shooting angle or position of the shooting device.

[0014] Further, the vision calibration method further comprises: controlling the mechanical arm to move according to the first physical coordinates, adjusting the shooting angle of the shooting device and shooting, and controlling the shooting device to shoot a second image; confirming whether the calibration board is completely in the second image; when confirming that the calibration board is completely in the second image, performing hand-eye calibration to acquire hand-eye calibration parameters; and processing the hand-eye calibration parameters to obtain the conversion relationship between the pixel coordinates of the shooting device and the actual physical coordinates.

[0015] Further, the vision calibration method further comprises: acquiring a third image, capturing any two radial lines in the third image, and calculating second pixel coordinates according to the any two radial lines in the third image; processing the second pixel coordinates to calculate second physical coordinates; processing the second pixel coordinates according to the conversion relationship between the pixel coordinates of the shooting device and the actual physical coordinates to obtain the second physical coordinates and third physical coordinates; and controlling the mechanical arm to move the shooting device to the third physical coordinates according to the second physical coordinates and the third physical coordinates, and controlling the shooting device to shoot a fourth image.

[0016] Further, the vision calibration method further comprises: confirming whether the calibration board is completely in the fourth image; and when the processor detects that the calibration board is completely in the fourth image, performing visual point calculation.

[0017] The vision calibration device, the radial line calibration board and the vision calibration method provided by the application can automatically find the calibration point and the shooting point through the any two radial lines in the image shot by the shooting device, and the whole process is efficient and fast. Moreover, the radial line calibration board can be expanded from the calibration board, and the manufacturing process is simple and the cost is low. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a structural schematic diagram of the vision calibration device provided by the embodiment of the application;

[0019] Figure 2 is a structural schematic diagram of the radial line calibration board provided by the embodiment of the application;

[0020] Figure 3 is a schematic diagram of the vision calibration device working with the radial line calibration board;

[0021] Figure 4 is a flowchart of one embodiment of a visual calibration method;

[0022] Figure 5 is a flowchart of another embodiment of a visual calibration method.

[0023] Explanation of main element symbols

[0024] Visual calibration device 10

[0025] Robot 11

[0026] Mechanical arm 111

[0027] Imaging device 12

[0028] Radial line calibration plate 20

[0029] Calibration plate 21

[0030] Radial line plate 22

[0031] Radial line 221

[0032] The following detailed description will further describe the present application with reference to the above-mentioned drawings. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing the specific embodiments only and is not intended to be limiting of the application.

[0035] The terms "first" and "second" and the like in the description of the present application and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the term "comprising" and any variation thereof is intended to cover the non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or modules is not limited to the listed steps or modules, but can optionally include steps or modules not listed, or can optionally include other steps or modules inherent to the process, method, product or device.

[0036] Some embodiments of the present application will be described in detail with reference to the drawings. The following embodiments and features of the embodiments described below can be combined with each other without conflict.

[0037] A calibration board is a flat plate with a fixed-pitch pattern array, which is widely used in machine vision, image measurement, photogrammetry, three-dimensional reconstruction and other applications to determine the relationship between camera pixels and actual physical size. In the process of hand-eye calibration and visual point calculation of robots combined with cameras, the camera shooting point position needs to be debugged first to make the patterns on the calibration board completely within the camera field of view.

[0038] Referring to Figure 1 , a structural schematic diagram of a visual calibration device 10 provided by an embodiment of the present application is shown. The visual calibration device 10 includes a robot 11, a shooting device 12, and a processor (not shown in the figure). The robot 11 includes a mechanical arm 111, and the shooting device 12 is arranged at an end of the mechanical arm 111 away from the robot 11. It can be understood that in the embodiment, the shooting device 12 can be a camera.

[0039] The processor can be a computer, a computer, a notebook computer, or the like. The processor is electrically connected to the robot 11 and the shooting device 12 to form a communication connection with each other. The processor is configured to receive and process images shot by the shooting device 12. The processor is also configured to control the mechanical arm 111 to move the shooting device 12 according to information obtained by processing the images, so as to switch the shooting angle or position of the shooting device 12.

[0040] Referring to Figure 2 , a structural schematic diagram of a radial line calibration board 20 proposed by an embodiment of the present application is shown. The radial line calibration board 20 includes a calibration board 21 and a radial line board 22. The calibration board 21 can be any kind of calibration board (for example, a chessboard, a circular grid, Charuco). The radial line board 22 has a plurality of radial lines 221 drawn thereon. The radial line board 22 is arranged around the calibration board 21, and the center point of the radial line 221 coincides with the center point of the calibration board 21. In some embodiments, the length of the radial line 221 can be adjusted according to actual conditions, that is, the size of the radial line board 22 can be adjusted according to actual conditions.

[0041] In some embodiments, the radial line calibration board 20 can be a whole, that is, the radial line 221 is drawn around the calibration board 21 to form the radial line calibration board 20. The radial line calibration board 20 can also be a combination, that is, the calibration board 21 is arranged on the radial line board 22, and the center of the calibration board 21 coincides with the center of the radial line 221 to form the radial line calibration board 20. As Figure 2 shown, the radial line calibration board 20 can be expanded from the calibration board 21, and the manufacturing process is simple and the cost is low.

[0042] Referring to Figure 3 In specific embodiments, the visual calibration device 10 is equipped with the radial line calibration board 20, and automatically finds the calibration point for hand-eye calibration and the shooting point for visual point calculation. The calibration point is the center point of the calibration board 21. The shooting point is the position of the calibration board 21 when it is in the shooting field of view of the shooting device 12.

[0043] Specifically, when the visual calibration device 10 is equipped with the radial line calibration board 20 and automatically finds the calibration point, the processor controls the mechanical arm 111 to drive the shooting device 12 to move to the first initial shooting point. The distance between the first initial shooting point and the radial line calibration board 20 does not exceed the visual range of the shooting device 12. After the shooting device 12 moves to the first initial shooting point, the radial line calibration board 20 is shot, and a first image is obtained. The processor obtains the first image from the shooting device 12, captures any two radial lines 221 in the first image, and calculates the first pixel coordinates according to the captured two radial lines 221. The first pixel coordinates are the pixel coordinates of the intersection of any two radial lines 221 in the first image.

[0044] The processor stores a coordinate equation calculation program. When the processor captures any two radial lines 221 in the radial line calibration board 20, the coordinate equation calculation program is enabled to calculate the first pixel coordinates.

[0045] Further, the processor obtains the parameter value (e.g., pixel, resolution) of the shooting device 12, and processes the first pixel coordinates according to the parameter value of the shooting device 12 to obtain the first physical coordinates. The first physical coordinates are the physical coordinates of the intersection of any two radial lines 221 in the first image. Further, the processor controls the mechanical arm 111 to move according to the first physical coordinates, adjusts the shooting angle of the shooting device 12 and performs shooting, and controls the shooting device 12 to obtain a second image. The processor obtains the second image from the shooting device 12, and detects whether the calibration board 21 is completely in the second image, that is, whether the calibration board 21 is completely in the shooting field of view of the shooting device 12.

[0046] The processor stores a visual detection program. When the processor obtains the second image from the shooting device 12, the visual detection program is enabled to detect whether the calibration board 21 is completely in the second image.

[0047] When the processor detects that the calibration board 21 is not completely in the second image, that is, detects that the calibration board 21 is not completely in the shooting field of view of the shooting device 12, the processor captures any two radial lines 221 in the second image, and calculates the second pixel coordinates according to the two captured radial lines 221. The second pixel coordinates are the pixel coordinates of the intersection of any two radial lines 221 in the second image.

[0048] Further, the processor processes the second pixel coordinates according to the parameter values of the shooting device 12 to obtain the second physical coordinates. The second physical coordinates are the physical coordinates of the intersection of any two radial lines 221 in the second image. Then, the processor controls the mechanical arm 111 to move according to the second physical coordinates, adjusts the shooting angle of the shooting device 12, and performs shooting.

[0049] Further, the processor again acquires the image shot by the shooting device 12, and detects whether the calibration board 21 is completely in the shooting field of view of the shooting device 12. If it is detected that the calibration board 21 is not completely in the shooting field of view of the shooting device 12, the above operations are repeated until it is detected that the calibration board 21 is completely in the shooting field of view of the shooting device 12.

[0050] When the processor detects that the calibration board 21 is completely in the second image, that is, detects that the calibration board 21 is completely in the shooting field of view of the shooting device 12, it means that the vision calibration device 10 finds the calibration point, and then the vision calibration device 10 performs hand-eye calibration on the calibration board 21 to obtain the hand-eye calibration parameters. Then, the processor processes the hand-eye calibration parameters to obtain the conversion relationship between the pixel coordinates and the actual physical coordinates of the shooting device 12.

[0051] In some embodiments, the vision calibration device 10 performs three times of hand-eye calibration in cooperation with the radial line calibration board 20, that is, the processor acquires at least three sets of hand-eye calibration parameters, and then the processor can calculate the conversion relationship between the pixel coordinates and the actual physical coordinates of the shooting device 12 according to the at least three sets of hand-eye calibration parameters.

[0052] The processor stores a coordinate conversion program. When the processor acquires at least three hand-eye calibration parameters, the coordinate conversion program is enabled to calculate the conversion relationship between the pixel coordinates and the actual physical coordinates of the shooting device 12.

[0053] Specifically, when performing hand-eye calibration, the initial shooting point of the shooting device 12 is changed to shoot the radial line calibration board 20 at different angles, and then the processor can acquire different hand-eye calibration parameters through the images of the radial line calibration board 20 shot by the shooting device 12 at different angles. In specific embodiments, the more times of hand-eye calibration, the more accurate the conversion relationship between the pixel coordinates and the actual physical coordinates of the shooting device 12 obtained by the processor.

[0054] In some embodiments, after the conversion relationship between the pixel coordinates and the actual physical coordinates of the photographing device 12 is obtained by performing the hand-eye calibration, the visual calibration device 10 automatically finds the photographing point in combination with the radial line calibration board 20 to perform the visual calculation point.

[0055] Specifically, the processor controls the mechanical arm 111 to move the photographing device 12 to a second initial photographing point. The distance between the second initial photographing point and the radial line calibration board 20 does not exceed the visual range of the photographing device 12. After the photographing device 12 moves to the second initial photographing point, the radial line calibration board 20 is photographed to obtain a third image. The processor acquires the third image from the photographing device 12, captures any two radial lines 221 in the third image, and calculates third pixel coordinates according to the captured two radial lines 221. The third pixel coordinates are the pixel coordinates of the intersection of any two radial lines 221 in the third image.

[0056] Further, the processor processes the third pixel coordinates according to the conversion relationship between the pixel coordinates and the actual physical coordinates of the photographing device 12 to obtain third physical coordinates and fourth physical coordinates. The third physical coordinates are the physical coordinates of the intersection of any two radial lines 221 in the third image. The fourth physical coordinates are the physical coordinates of the position of the photographing device 12.

[0057] Further, the processor controls the mechanical arm 111 to move the photographing device 12 to the fourth physical coordinates according to the third physical coordinates and the fourth physical coordinates, and controls the photographing device 12 to capture a fourth image. The processor acquires the fourth image from the photographing device 12, and detects whether the calibration board 21 is completely in the fourth image, that is, whether the calibration board 21 is completely in the photographing field of view of the photographing device 12.

[0058] When the processor detects that the calibration board 21 is not completely in the fourth image, that is, the calibration board 21 is not completely in the photographing field of view of the photographing device 12, the processor captures any two radial lines 221 in the fourth image, and calculates fourth pixel coordinates according to the captured two radial lines 221. The fourth pixel coordinates are the pixel coordinates of the intersection of any two radial lines 221 in the fourth image. Then, the processor processes the fourth pixel coordinates according to the parameter values of the photographing device 12 to obtain fifth physical coordinates. The fifth physical coordinates are the physical coordinates of the intersection of any two radial lines 221 in the fourth image. Further, the processor controls the mechanical arm 111 to move and adjust the photographing angle of the photographing device 12 according to the fifth physical coordinates and performs photographing.

[0059] Further, the processor acquires again the image captured by the photographing device 12, and detects whether the calibration board 21 is completely within the photographing field of view of the photographing device 12. If it is detected that the calibration board 21 is not completely within the photographing field of view of the photographing device 12, the above operation is repeated until it is detected that the calibration board 21 is completely within the photographing field of view of the photographing device 12.

[0060] When the processor detects that the calibration board 21 is completely in the fourth image, that is, detects that the calibration board 21 is completely within the photographing field of view of the photographing device 12, it indicates that the vision calibration device 10 finds the calibration point, and then the vision calibration device 10 performs vision calibration.

[0061] Referring to Figure 4 is a flowchart of an embodiment of the vision calibration method. The specific steps of the vision calibration method include:

[0062] Step S401: Control the mechanical arm 111 to move the photographing device 12 to a first initial photographing point.

[0063] In some embodiments, the distance between the first initial photographing point and the radial line calibration board 20 does not exceed the range of the photographing device 12.

[0064] Step S402: Photograph the radial line calibration board 20 to acquire an image of the first initial photographing point.

[0065] Step S403: Capture any two radial lines 221 in the image, and calculate the pixel coordinates of the intersection of the two radial lines 221 according to the captured two radial lines 221, that is, the pixel coordinates of the center point of the calibration board 21.

[0066] In some embodiments, the processor acquires the image captured by the photographing device 12 from the photographing device 12, captures any two radial lines 221 in the image, and calculates the pixel coordinates of the center point of the calibration board 21 according to the captured two radial lines 221.

[0067] The processor stores a coordinate equation calculation program. When the processor captures any two radial lines 221 in the radial line calibration board 20, the coordinate equation calculation program is enabled to calculate the pixel coordinates of the intersection of the two radial lines 221.

[0068] Step S404: Acquire the parameter value of the photographing device 12, and process the pixel coordinates of the center point of the calibration board 21 according to the parameter value of the photographing device 12 to obtain the physical coordinates of the center point of the calibration board 21.

[0069] In some embodiments, the processor acquires the parameter value of the photographing device 12, and processes the pixel coordinates of the center point of the calibration board 21 according to the parameter value of the photographing device 12, to obtain the physical coordinates of the center point of the calibration board 21.

[0070] Step S405: The mechanical arm 111 is controlled to move, and the photographing angle of the photographing device 12 is adjusted.

[0071] In some embodiments, the processor controls the mechanical arm 111 to move according to the physical coordinates of the center point of the calibration board 21, and adjusts the photographing angle of the photographing device 12, to ensure that the calibration board 21 is completely within the photographing field of view of the photographing device 12.

[0072] Step S406: The radial line calibration board 20 is photographed, and an image after the photographing angle is adjusted is acquired.

[0073] Step S407: Whether the calibration board 21 is completely within the photographing field of view of the photographing device 12 is confirmed.

[0074] In some embodiments, the processor acquires the photographed image from the photographing device 12, and detects whether the calibration board 21 is completely within the photographing field of view of the photographing device 12. The processor stores a visual judgment program. When the processor acquires the image from the photographing device 12, the visual judgment program is started to detect whether the calibration board 21 is completely within the photographing field of view of the photographing device 12.

[0075] When the processor detects that the calibration board 21 is not completely within the photographing field of view of the photographing device 12, step S403 is performed.

[0076] When the processor detects that the calibration board 21 is completely within the photographing field of view of the photographing device 12, step S408 is performed.

[0077] Step S408: Hand-eye calibration is performed, hand-eye calibration parameters are acquired and processed, to obtain the conversion relationship between the pixel coordinates and the actual physical coordinates of the photographing device 12.

[0078] When the processor detects that the calibration board 21 is completely within the photographing field of view of the photographing device 12, that is, the visual calibration device 10 finds the calibration point, and then the visual calibration device 10 performs hand-eye calibration on the calibration board 21 to acquire hand-eye calibration parameters. The processor processes the hand-eye calibration parameters, to obtain the conversion relationship between the pixel coordinates and the actual physical coordinates of the photographing device 12.

[0079] Please refer to Figure 5 for the flowchart of another embodiment of the visual calibration method. The specific steps of the visual calibration method include:

[0080] Step S501: Obtain the conversion relationship between the pixel coordinates of the photographing device 12 and the actual physical coordinates.

[0081] In some embodiments, the vision calibration device 10 performs hand-eye calibration on the calibration board 21 to obtain hand-eye calibration parameters. The processor then processes the hand-eye calibration parameters to obtain the conversion relationship between the pixel coordinates of the photographing device 12 and the actual physical coordinates.

[0082] Step S502: Control the mechanical arm 111 to move the photographing device 12 to a second initial photographing point.

[0083] In some embodiments, the distance between the second initial photographing point and the radial line calibration board 20 does not exceed the range of the photographing device 12.

[0084] Step S503: Photograph the radial line calibration board 20 to obtain an image at the second initial photographing point.

[0085] Step S504: Capture any two radial lines 221 in the image, and calculate the pixel coordinates of the intersection of the two radial lines 221, i.e., the pixel coordinates of the center point of the calibration board 21, according to the captured two radial lines 221.

[0086] In some embodiments, the processor obtains the image photographed by the photographing device 12 from the photographing device 12, captures any two radial lines 221 in the image, and calculates the pixel coordinates of the center point of the calibration board 21 according to the captured two radial lines 221.

[0087] The processor stores a coordinate equation calculation program. When the processor captures any two radial lines 221 in the radial line calibration board 20, the coordinate equation calculation program is enabled to calculate the pixel coordinates of the intersection of the two radial lines 221.

[0088] Step S505: Process the pixel coordinates of the center point of the calibration board 21 to obtain the physical coordinates of the center point of the calibration board 21 and the physical coordinates of the location of the photographing device 12.

[0089] In some embodiments, the processor processes the pixel coordinates of the center point of the calibration board 21 according to the conversion relationship between the pixel coordinates of the photographing device 12 and the actual physical coordinates to obtain the physical coordinates of the center point of the calibration board 21 and the physical coordinates of the location of the photographing device 12.

[0090] Step S506: Control the mechanical arm 111 to move the photographing device 12 to the physical coordinates of the center point of the calibration board 21.

[0091] In some embodiments, the processor controls the mechanical arm 111 to move the photographing device 12 to the physical coordinates of the center point of the calibration plate 21 according to the physical coordinates of the center point of the calibration plate 21 and the physical coordinates of the position where the photographing device 12 is located, and controls the photographing device 12 to take a photograph.

[0092] Step S507: Take a photograph of the radial line calibration plate 20 to obtain an image at the physical coordinates of the center point of the calibration plate 21.

[0093] Step S508: Determine whether the calibration plate 21 is completely within the photographing field of view of the photographing device 12.

[0094] In some embodiments, the processor obtains the photographed image from the photographing device 12, and detects whether the calibration plate 21 is completely within the photographing field of view of the photographing device 12. The processor stores a visual judgment program. When the processor obtains the image from the photographing device 12, the visual judgment program is started to detect whether the calibration plate 21 is completely within the photographing field of view of the photographing device 12.

[0095] When the processor detects that the calibration plate 21 is not completely within the photographing field of view of the photographing device 12, step S504 is performed.

[0096] When the processor detects that the calibration plate 21 is completely within the photographing field of view of the photographing device 12, step S509 is performed.

[0097] Step S509: Perform visual calculation.

[0098] In some embodiments, when the processor detects that the calibration plate 21 is completely within the photographing field of view of the photographing device 12, that is, the visual calibration device 10 finds the calibration point, the visual calibration device 10 performs visual calculation.

[0099] In the embodiments of the present application, the visual calibration device 10 is matched with a radial line calibration plate 20 with a length and a width of 20 cm and a calibration plate 21 with a length and a width of 10 cm to find the photographing point. According to experiments, when the initial photographing point of the photographing device 12 is within the range of the photographing device 12, at most three adjustments are needed to accurately find the photographing point. Therefore, the visual calibration device 10 matched with the radial line calibration plate 20 is fast and efficient in the whole process of finding the photographing point.

[0100] The visual calibration device, the radial line calibration plate and the visual calibration method provided in the present application can automatically find the calibration point and the photographing point by obtaining any two radial lines 221 in the image taken by the photographing device 12, and the whole process is efficient and fast. In addition, the radial line calibration plate 20 can be expanded from the calibration plate 21, and the manufacturing process is simple and the cost is low.

[0101] Those skilled in the art will realize that the embodiments described herein are merely illustrative and are not intended to limit the scope of the application. Changes and modifications can be made to the embodiments without departing from the spirit and scope of the application.

Claims

1. A vision calibration device for working in conjunction with a radial line calibration plate, wherein, The radial line calibration board comprises a plurality of radial lines, and the center point of the radial lines is consistent with the center point of the radial line calibration board. The visual calibration device comprises a robot, a shooting device and a processor, the processor is electrically connected with the robot and the shooting device to form a communication connection with each other. The shooting device is used to acquire a first image of the radial line calibration board. The processor is used to acquire the first image to capture any two radial lines in the first image, and calculate a first pixel coordinate according to any two radial lines in the first image; wherein the first pixel coordinate is the pixel coordinate of the intersection of any two radial lines in the first image. The processor is also used to process the first pixel coordinate to calculate a first physical coordinate; wherein the first physical coordinate is the physical coordinate of the intersection of any two radial lines in the first image. The robot comprises a mechanical arm; the processor is used to control the mechanical arm to move according to the first physical coordinate, adjust the shooting angle of the shooting device and shoot, and control the shooting device to shoot to obtain a second image; the radial line calibration board comprises a calibration board; the processor acquires the second image from the shooting device, detects whether the calibration board is completely in the second image; when the processor detects that the calibration board is completely in the second image, the visual calibration device performs hand-eye calibration on the calibration board to acquire hand-eye calibration parameters; the processor is also used to process the hand-eye calibration parameters to obtain the conversion relationship between the pixel coordinate and the actual physical coordinate of the shooting device.

2. The visual calibration device of claim 1, wherein, The radial line calibration board further comprises a radial line plate arranged around the calibration board, the radial line plate comprises a plurality of radial lines, and the intersection of the radial lines is consistent with the center point of the calibration board. The shooting device is also used to acquire a third image. The processor is also used to receive the third image and capture any two radial lines in the third image, and then the processor calculates a second pixel coordinate according to any two radial lines in the third image; wherein the second pixel coordinate is the pixel coordinate of the intersection of any two radial lines in the third image. The processor is also used to process the second pixel coordinate to calculate a second physical coordinate; wherein the second physical coordinate is the physical coordinate of the intersection of any two radial lines in the third image.

3. The visual calibration device of claim 2, wherein, The processor is also used to process the second pixel coordinate according to the conversion relationship between the pixel coordinate and the actual physical coordinate of the shooting device to obtain a second physical coordinate and a third physical coordinate; wherein the second physical coordinate is the physical coordinate of the intersection of any two radial lines in the third image, and the third physical coordinate is the physical coordinate of the position of the shooting device.

4. The visual calibration device of claim 3, wherein, The processor is also used to control the mechanical arm to drive the shooting device to move to the third physical coordinate according to the second physical coordinate and the third physical coordinate, and control the shooting device to shoot to obtain a fourth image.

5. The visual calibration device of claim 4, wherein, The processor acquires a fourth image from the photographing device, and detects whether the calibration board is completely in the fourth image; When the processor detects that the calibration board is completely in the fourth image, the visual calibration device performs visual point calculation.

6. A radial line calibration plate for use in a vision calibration device as claimed in any one of the claims 1 to 5, characterized in that The radial line calibration board comprises a calibration board and a radial line board, and the radial line board is arranged around the calibration board; The radial line board comprises a plurality of radial lines, and the intersection of the radial lines is consistent with the center point of the calibration board.

7. A visual calibration method applied to the visual calibration device according to any one of claims 1 to 5, characterized in that, The visual calibration method comprises: acquiring the first image, capturing any two radial lines in the first image, and calculating a first pixel coordinate according to any two radial lines in the first image; processing the first pixel coordinate to calculate a first physical coordinate; controlling the robot to move the photographing device according to the first physical coordinate, so as to adjust the shooting angle or position of the photographing device.

Citation Information

Patent Citations

  • Hand-eye vision calibration method for robot hole boring system

    CN101630409A

  • A hand-eye camera calibration method and device

    CN109671122A