Method and apparatus for testing stability of vision system
View Patent ↗Embodiments of this application provide a method and apparatus for testing stability of a vision system, which can test whether the vision system is stable, so as to report a fault in a timely manner when the vision system is unstable, thereby guaranteeing accuracy of a measurement result of the vision system. The method includes: obtaining first position information of a spot inspection piece in a current image under the vision system; performing affine transformation on a reference contour model of the spot inspection piece for a position of the spot inspection piece in the current image based on the first position information, and obtaining, through fitting, a current contour model of the spot inspection piece in the current image based on the reference contour model; and determining stability of the vision system based on the reference contour model and the current contour model.
1 . A method for testing stability of a vision system, characterized by comprising:
obtaining first position information of a spot inspection piece in a current image under the vision system;
performing an affine transformation on a reference contour model of the spot inspection piece for a position of the spot inspection piece in the current image based on the first position information, and obtaining, through fitting, a current contour model of the spot inspection piece in the current image based on the reference contour model; and
determining stability of the vision system based on the reference contour model and the current contour model,
wherein the spot inspection piece comprises at least one rectangular frame, and each rectangular frame comprises a circle and a grayscale region outside the circle, and
wherein the reference contour model and the current contour model comprise contours of the rectangular frame and the circle.
2 . The method according to claim 1 , wherein before performing the affine transformation on a reference contour model of the spot inspection piece for a position of the spot inspection piece in the current image, the method further comprises:
obtaining the reference contour model based on a reference image of the spot inspection piece; and
obtaining second position information of the spot inspection piece in the reference image;
wherein performing the affine transformation on a reference contour model of the spot inspection piece for a position of the spot inspection piece in the current image comprises:
performing the affine transformation on the reference contour model of the spot inspection piece for the position of the spot inspection piece in the current image based on the first position information and the second position information.
3 . The method according to claim 1 , wherein a plurality of rectangular frames are present, a plurality of circles corresponding to the plurality of rectangular frames have different diameters, and a plurality of grayscale regions corresponding to the plurality of rectangular frames have different grayscale values.
4 . The method according to claim 1 , wherein one rectangular frame in the spot inspection piece comprises a notch, and the notch is configured to indicate a direction of the spot inspection piece.
5 . The method according to claim 1 , wherein the obtaining, through fitting, a current contour model based on the reference contour model comprises:
obtaining, through fitting, a second circle of the current contour model based on a first circle in the reference contour model.
6 . The method according to claim 5 , wherein the obtaining, through fitting, a second circle of the current contour model based on a first circle in the reference contour model comprises:
obtaining a plurality of pixel points with significant grayscale value changes in the current image based on a contour of the first circle, wherein the plurality of pixel points with significant grayscale value changes form the second circle.
7 . The method according to claim 5 , wherein the determining stability of the vision system based on the reference contour model and the current contour model comprises:
obtaining a diameter of the first circle based on the reference contour model;
obtaining a diameter of the second circle based on the current contour model; and
determining, based on the diameter of the first circle and the diameter of the second circle, whether a camera position of the vision system has changed.
8 . The method according to claim 7 , wherein the determining, based on the diameter of the first circle and the diameter of the second circle, whether a camera position of the vision system has changed comprises:
if a difference between the diameter of the first circle and the diameter of the second circle is greater than a first threshold, determining that the camera position has changed.
9 . The method according to claim 7 , wherein the obtaining a diameter of the second circle based on the current contour model comprises:
calculating a size of each pixel based on the diameter of the first circle and the number of pixels comprised in the diameter of the first circle;
obtaining the number of pixels comprised in the diameter of the second circle based on a contour of the second circle; and
calculating the diameter of the second circle based on the number of pixels comprised in the diameter of the second circle and the size of each pixel.
10 . The method according to claim 7 , wherein the determining stability of the vision system based on the reference contour model and the current contour model further comprises:
obtaining, based on the reference contour model, a first grayscale value of a grayscale region corresponding to the first circle;
obtaining, based on the current contour model, a second grayscale value of a grayscale region corresponding to the second circle; and
determining, based on the first grayscale value and the second grayscale value, whether illumination in the vision system has changed.
11 . The method according to claim 10 , wherein the determining, based on the first grayscale value and the second grayscale value, whether illumination in the vision system has changed comprises:
if a difference between the first grayscale value and the second grayscale value is greater than a second threshold, determining that the illumination has changed.
12 . The method according to claim 1 , wherein the first position information and the second position information comprise row information, column information, and angle information of the spot inspection piece, and the angle information is used to indicate the direction of the spot inspection piece.
13 . An apparatus for testing stability of a vision system, comprising a processor and a memory, wherein the memory is configured to store a program, and the processor is configured to call and run the program from the memory to perform the method for testing stability of a vision system according to claim 1 .
14 . A non-transitory computer-readable storage medium, comprising a computer program, wherein when the computer program runs on a computer, the computer is enabled to perform the method for testing stability of a vision system according to claim 1 .