Machine vision calibration board with multiple horizontal and vertical sine curves

Abstract

The utility model discloses a machine vision calibration board with a plurality of horizontal and vertical sine curves, which comprises a rectangular substrate, the surface of the rectangular substrate is provided with uniformly distributed checkerboard patterns, the area of the checkerboard patterns is provided with a plurality of sine curves parallel to the horizontal and vertical directions to form a gridding fluctuation characteristic line structure, and the sine curves are arranged on the rectangular substrate. Four corners of the rectangular substrate are provided with concentric circle positioning marks. According to the utility model, after a sine curve is introduced as a characteristic line, continuous curve characteristics can be provided, and modeling of nonlinear distortion and visual angle change is facilitated. The four-corner concentric circle positioning marks are used for assisting image rapid positioning and direction verification.

Description

Technical Field

[0001] This utility model relates to the field of image processing and machine vision technology, and in particular to a machine vision calibration plate with multiple horizontal and vertical sine curves. Background Technology

[0002] Visual measurement technology is well adapted to the new standards and requirements of modern industry for the inspection of workpiece dimensions. It is a non-contact shape inspection method that combines accuracy and efficiency.

[0003] Checkerboard calibration targets are widely used for camera calibration in vision measurement imaging systems. The process typically involves taking multiple photographs of the calibration target in different poses using the vision measurement imaging system. By extracting and comparing the pixel coordinates of the corner points on the calibration target with the known world coordinates of those corner points, the internal and external parameters of the camera model of the vision measurement imaging system are determined, thus completing the calibration of the system. Therefore, the accuracy of the corner point extraction from the checkerboard calibration target directly affects the final calibration accuracy of the camera.

[0004] However, traditional chessboard calibration boards have a simple structure and rely solely on corner points for camera parameter estimation, making it difficult to achieve high-precision fitting in the presence of complex distortions. Utility Model Content

[0005] To solve the above-mentioned technical problems, this utility model designs a machine vision calibration plate with multiple horizontal and vertical sine curves.

[0006] The present invention adopts the following technical solution:

[0007] A machine vision calibration board with multiple horizontal and vertical sine curves includes a rectangular substrate. The surface of the rectangular substrate is provided with a uniformly distributed checkerboard pattern. Multiple sine curves parallel to the horizontal and vertical directions are provided on the area of ​​the checkerboard pattern to form a gridded undulating feature line structure.

[0008] Preferably, concentric circle positioning marks are provided at the four corners of the rectangular substrate.

[0009] Preferably, the number of sine curves parallel to the horizontal and vertical directions is 3-6.

[0010] Preferably, the spacing between the plurality of sine curves parallel to the horizontal and vertical directions is uniform.

[0011] Preferably, the amplitude of the sine curve is 1-2 times the width of the checkerboard pattern, and the wavelength is 8-10 times the width of the checkerboard pattern.

[0012] The calibration method for this machine vision calibration board with multiple horizontal and vertical sine curves is as follows:

[0013] (1) Obtain image data of the calibration board in different poses;

[0014] (2) Extract the corner points of the chessboard, the peak and trough feature points on multiple sine curves, and the center of the four corners;

[0015] (3) Fit camera intrinsic and extrinsic parameters based on spatially distributed feature points;

[0016] (4) Complete the camera model establishment and distortion correction.

[0017] By introducing a sine curve as a feature line, this invention provides continuous curve features, which helps in modeling nonlinear distortion and viewpoint changes. Concentric circle positioning markers at the four corners are used to assist in rapid image positioning and orientation verification.

[0018] The beneficial effects of this utility model are: (1) increasing the density of feature points and improving the fitting accuracy; (2) enhancing the image modeling capability through horizontal and vertical fluctuations; (3) improving the ease of operation and automatic recognition efficiency through concentric circle positioning marks; and (4) improving the stability of distortion parameter estimation in complex vision systems. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the structure of this utility model;

[0020] In the diagram: 1. Rectangular substrate, 2. Checkerboard pattern, 3. Sine curve, 4. Concentric circle positioning marks. Detailed Implementation

[0021] The technical solution of this utility model will be further described in detail below through specific embodiments and with reference to the accompanying drawings:

[0022] Example: Figure 1 As shown, a machine vision calibration board with multiple horizontal and vertical sine curves includes a rectangular substrate 1. The surface of the rectangular substrate is provided with a uniformly distributed checkerboard pattern 2. Multiple sine curves 3 parallel to the horizontal and vertical directions are provided on the area of ​​the checkerboard pattern to form a gridded undulating feature line structure.

[0023] Concentric circle positioning marks 4 are set at the four corners of the rectangular substrate.

[0024] There are 5 sine curves parallel to both the horizontal and vertical directions. The spacing between the multiple sine curves parallel to both the horizontal and vertical directions is uniform.

[0025] The amplitude of the sine curve is 1.5 times the width of the checkerboard pattern, and the wavelength is 10 times the width of the checkerboard pattern.

[0026] The calibration method for this machine vision calibration board with multiple horizontal and vertical sine curves is as follows:

[0027] (1) Obtain image data of the calibration board in different poses;

[0028] (2) Extract the corner points of the chessboard, the peak and trough feature points on multiple sine curves, and the center of the four corners;

[0029] (3) Fit camera intrinsic and extrinsic parameters based on spatially distributed feature points;

[0030] (4) Complete the camera model establishment and distortion correction.

[0031] By introducing a sine curve as a feature line, this invention provides continuous curve features, which helps in modeling nonlinear distortion and viewpoint changes. Concentric circle positioning markers at the four corners are used to assist in rapid image positioning and orientation verification.

[0032] The embodiments described above are merely preferred solutions of this utility model and are not intended to limit this utility model in any way. Other variations and modifications are possible without departing from the technical solutions described in the claims.

Claims

1. A machine vision calibration board with multiple horizontal and vertical sinusoidal curves, comprising a rectangular substrate, the surface of the rectangular substrate is provided with a chessboard pattern uniformly distributed, characterized in that, The chessboard pattern region is provided with a plurality of sinusoidal curves parallel to the horizontal and vertical directions, forming a grid wave feature line structure.

2. The machine vision calibration board with multiple horizontal and vertical sinusoidal curves of claim 1, wherein, The rectangular substrate is provided with concentric circle positioning marks at four corners.

3. The machine vision calibration board with multiple horizontal and vertical sinusoidal curves of claim 1, wherein, The number of the sinusoidal curves parallel to the horizontal and vertical directions is 3-6 respectively.

4. The machine vision calibration board with multiple horizontal and vertical sinusoidal curves of claim 1, wherein, The intervals between the plurality of sinusoidal curves parallel to the horizontal and vertical directions are uniform.

5. The machine vision calibration panel with multiple horizontal and vertical sinusoidal curves of claim 1, wherein, The wave amplitude of the sinusoidal curve is 1-2 chessboard pattern widths, and the wavelength is 8-10 chessboard pattern widths.

Images