CN105184792A - Circular saw web wear extent online measuring method - Google Patents

Abstract

The invention discloses an on-line measurement method for the amount of wear of a circular saw blade. The implementation steps are as follows: an industrial computer triggers an image acquisition card, obtains an image of a circular saw blade through an industrial camera; preprocesses the image; Domain gray similarity screening method to find the candidate corners of the circular saw blade; judge whether the candidate corners are the only corners in the neighborhood or have the largest corner response function value to eliminate false corners; judge whether the corners are extremely large value point, otherwise it is eliminated, thereby determining the integer pixel coordinates of the circular saw blade tip point; using the cubic surface fitting method to perform sub-pixel positioning of the tip point; using the least square method to solve the radius value of the circle where the tip point is located, by The camera calibration relationship yields the actual amount of wear on the circular saw blade. The invention has good real-time performance and high detection precision, is an effective online detection method for the amount of wear of the circular saw blade, and the detection result provides a basis for the compensation mechanism to perform compensation.

Description

A method for online measurement of circular saw blade wear

technical field

The invention belongs to the technical field of image processing, and relates to a method for visually detecting the wear state of a tool, and more specifically, relates to an online measurement method for the amount of wear of a circular saw blade. The method is to identify the edge corner of the image, and then calculate the wear amount of the circular saw blade according to the position of the corner.

Background technique

As an emerging detection technology, machine vision has been widely used for its fast, real-time, intelligent and low-cost characteristics. The measurement based on machine vision is a non-contact measurement method. It can not only measure the characteristics of the workpiece in real time, improve the efficiency of measurement, but also adjust the focal length of the industrial camera and other parameters according to the size of the workpiece to achieve a wider range of dimensional measurements. It can avoid the measurement error caused by the change of the measurement personnel's own psychological factors.

There are mainly the following methods for the detection of tool wear. ①Monitor the vibration signal and motor current signal, construct the relationship between the vibration signal and the motor current signal and the wear amount of the tool, so as to detect the wear state of the tool; ②Monitor the acoustic emission signal during the processing, and establish the relationship between the acoustic emission signal and the wear amount of the tool, Detect the wear state of the tool; ③With the rapid development of CCD sensor and its application technology, non-contact detection technology based on machine vision is widely used in the fields of size, displacement, surface shape detection and so on. There are three ways to use machine vision to detect tool wear: ① detect tool surface images; ② detect workpiece surface texture images; ③ detect chip images.

The above methods are also commonly used for monitoring the wear of circular saw blades. Zhao Ling from Hangzhou Dianzi University and others built a circular saw blade geometric parameter measurement system based on machine vision. Based on the optimization of circular saw blade profile, this method proposes an improved quadratic polynomial interpolation sub-pixel positioning method for the inner circular hole of the circular saw blade, and uses the improved least squares method to fit the two straight lines of the tooth tip, which improves the detection efficiency. Accuracy, but this method must obtain the entire image of the circular saw blade, so the online measurement of the wear amount of the circular saw blade cannot be realized. Swedish Ekevad et al constructed the relationship between the wear amount of the circular saw blade and the vibration signal of the saw blade in the process of sawing beech. It is difficult to find the exact quantitative relationship of the blade vibration signal, and only the qualitative detection of the wear amount of the circular saw blade can be carried out.

Since the objects to be measured vary greatly and their structural characteristics are very different, there is no general method for measurement based on machine vision, and different methods need to be adopted for different objects. At present, the circular saw blade wear measurement method based on the classic Harris method has poor real-time performance, and some non-knife-tip points are often misjudged as knife-tip points. However, some non-knife-tip points are still often misjudged as knife-tip points, and it is impossible to accurately locate the knife-tip points of different circular saw blades, and the measurement error is too large, which cannot be applied to the actual measurement process.

Contents of the invention

The purpose of the present invention is to overcome the shortcomings of the existing circular saw blade wear measurement method, and propose an online measurement method for circular saw blade wear based on machine vision, so as to improve the accuracy of online measurement of circular saw blade wear.

In order to achieve the above object, the technical solution adopted by the present invention to realize the object is:

A method for online measurement of circular saw blade wear, comprising the following steps:

1) Acquire the image of the circular saw blade: manually adjust the industrial camera installed on the bracket so that the industrial camera is facing the circular saw blade under test, and the industrial computer triggers the image acquisition card to obtain the image of the circular saw blade;

2) The image is preprocessed by median filtering for noise reduction;

3) Based on the adaptive threshold, use the 8-neighborhood gray similarity screening method to find out the candidate corner points of the circular saw blade;

Specifically, the grayscale change E(u,v) caused by the movement of the window edge translation vector (u,v) centered on (x,y) is:

$\mathrm{<span\; class="notranslate">\; E.</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; \&omega;</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>{<span\; class="notranslate">\; \&lsqb;</span>\mathrm{<span\; class="notranslate">\; I</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; I</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&rsqb;</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

I(x+u,y+v) is the gray value after translation, I(x,y) is the gray value before translation, ω(x,y) is the Gaussian window function,

Its differential form is

$\mathrm{<span\; class="notranslate">\; E.</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}\mathrm{<span\; class="notranslate">\; \&omega;</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}\mathrm{<span\; class="notranslate">\; u</span>}\mathrm{<span\; class="notranslate">\; \&nu;</span>}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; \&nu;</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>$

in $I_x=\frac{\&part;I}{\&part;x},I_{\mathrm{the\; y}}=\frac{\&part;I}{\&part;\mathrm{the\; y}}$

Its matrix form is

$\mathrm{<span\; class="notranslate">\; E.</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span><span\; class="notranslate">\; \&lsqb;</span>\begin{array}{cc}\mathrm{<span\; class="notranslate">\; u</span>}& \mathrm{<span\; class="notranslate">\; v</span>}\end{array}<span\; class="notranslate">\; \&rsqb;</span>\mathrm{<span\; class="notranslate">\; m</span>}\left[\begin{array}{c}\mathrm{<span\; class="notranslate">\; u</span>}\\ \mathrm{<span\; class="notranslate">\; v</span>}\end{array}\right]$

Among them, M is the autocorrelation function matrix of the target pixel point (x, y)

$\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}\mathrm{<span\; class="notranslate">\; \&omega;</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>\left[\begin{array}{cc}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}& {\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}\\ {\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}& {\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}\end{array}\right]$

Gaussian window function $\mathrm{\&omega;}(x,\mathrm{the\; y})=e^{(x^2+{\mathrm{the\; y}}^2)/{\mathrm{\&sigma;}}^2}$

The corner response function value of the target pixel point (x, y):

CRF(x,y)=det(M)-k(trace(M)) ²

Where det(M) represents the determinant of the matrix M, trace(M) represents the trace of the matrix, and k is 0.04 to 0.06;

The standard deviation of the gray value of each pixel image in the target point (x, y) and its 8 neighborhoods is used as the gray similarity judgment threshold t of the 8 neighborhoods, and one percent of the maximum corner response function value CRF _max is used as the corner point response detection threshold T,

The difference △I between the gray value of the target point (x, y) and each pixel in its 8 neighborhoods, and count the number n of pixels in △I in the range of [-t, t], satisfying 2≤n≤ 6 and its corner response function value is greater than T and the local maximum target point is the candidate corner point.

4) For the candidate corner point, judge whether it is the only corner point in the neighborhood or its corner point response function value is the largest, and remove the false corner point;

Keep those candidate angles that are the only corner points in their 5×5 neighborhood or the candidate angles with the largest CRF value in their 5×5 neighborhood.

5) Determine whether the corner point is the maximum value point on the curve to eliminate the tooth root point, thereby determining the integer pixel coordinates of the circular saw blade tip point

The slope k _i1 of the line connecting the corner point to the previous corner point

${\mathrm{<span\; class="notranslate">\; k</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}$

The slope k _i2 of the line connecting the corner point and the next corner point

${\mathrm{<span\; class="notranslate">\; k</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}$

(x _i , y _i ) is the pixel coordinate of the i-th corner point, (x _i-1 , y _i-1 ) is the pixel coordinate of the previous corner point of the i-th corner point, (x _i+1 , y _{i +1} ) is the next corner pixel coordinate of the i-th corner point,

If k _i1 <0 and k _i2 >0, it is judged that the point is not a tool point, and it will be removed.

6) Use the cubic surface fitting method to perform sub-pixel positioning on the tool tip point

The binary cubic function form of the CRF of the whole pixel knife tip point (x, y) and each point in a certain neighborhood:

$\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 00</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 01</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 02</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 03</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 10</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 20</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 30</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 11</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; twenty\; one</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 12</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

Fitted error sum of squares

$\mathrm{<span\; class="notranslate">\; \&epsiv;</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 25</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

Calculate a ₀₀ , a ₀₁ , a ₀₂ , a ₀₃ , a ₁₀ , a ₂₀ , a ₃₀ , a ₁₁ , a ₂₁ , a ₁₂

Using the determined cubic surface expression to solve the CRF of the entire pixel tip point subdivided into 3×3 sub-pixel points, the sub-pixel coordinate corresponding to the maximum CRF value among the 9 sub-pixel points is taken as the coordinate of the tool tip point.

7) Use the least square method to solve the radius value of the circle where the tool tip point is located, and obtain the actual wear amount of the circular saw blade through the camera calibration relationship

definition

$\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; b</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; c</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; N</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; N</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; b</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; d</span>}}{\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; b</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$

$\mathrm{<span\; class="notranslate">\; B</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; b</span>}\mathrm{<span\; class="notranslate">\; c</span>}}{{\mathrm{<span\; class="notranslate">\; b</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; d</span>}}$

$\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; no</span>}}<span\; class="notranslate">\; (</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; A</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; B</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>$

r ² =(A ² +B ² -4C)/4

Then, according to the calibration relationship of the camera, the actual radius value of the tool is obtained, and the difference between the two detection results is the wear amount of the circular saw blade.

Compared with the prior art, the present invention has the following advantages and beneficial effects:

1. Through the two screenings of step 3 and step 4, false corner points are eliminated, avoiding the corner clustering phenomenon of the existing method.

2. Through the above-mentioned step 5, the dedendum point is eliminated, thereby determining the integer pixel coordinates of the circular saw blade tip point, avoiding the deviation of the circle fitting caused by the existing method from misjudging the dedendum point as the tool tip point. mistake.

Description of drawings

Fig. 1 is a schematic block diagram of a measuring device according to an embodiment of the present invention,

Fig. 2 is the schematic diagram of industrial camera installation of the embodiment of the present invention,

Fig. 3 is the realization flowchart of the embodiment of the present invention,

Fig. 4 uses the present invention and existing method to the knife tip point extraction comparison figure of the circular saw blade of smooth transition between adjacent sawtooth,

Fig. 5 is a comparison diagram of the extraction of the tip point of a circular saw blade with a sharp transition between adjacent saw teeth by using the present invention and the existing method.

Detailed ways

In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

An on-line measurement method for the wear amount of a circular saw blade according to the present invention is to calibrate the industrial camera before the online measurement of the wear amount of the circular saw blade. The computer triggers the image acquisition card to obtain the image of the calibration object, calculates the pixel value of the known size according to the obtained image, divides the known size by the pixel value to obtain the actual size value represented by each pixel. As shown in Figure 3, the specific steps are as follows:

Step 1. Install the industrial camera on the bracket, and adjust it manually so that the industrial camera faces the circular saw blade under test;

As shown in Figure 1, the entire measurement device includes industrial cameras, image acquisition cards, industrial computers and measurement software. As shown in Figure 2, before measuring the wear amount of the circular saw blade, install the industrial camera 3 on the bracket 4, manually adjust the industrial camera 3 to face the circular saw blade 2 on the machine tool 1, connect the industrial camera with the network cable 5 and The image acquisition card (not shown in the figure) in the industrial computer 6 is connected.

Step 2. The industrial computer triggers the image acquisition card, and obtains the image of the circular saw blade through the industrial camera;

The industrial computer is used as the main controller, and the image acquisition card communicates with the industrial computer through the PCI-e bus. The industrial camera is facing the circular saw blade under test, and the circular saw blade under test is imaged on the industrial camera after being irradiated by the transmitted light source. The collected digital image is transmitted to the industrial computer to obtain the image of the circular saw blade.

Step 3, preprocessing the image;

In order to suppress the influence of noise, the original image collected by the industrial camera is processed for noise reduction. Median filtering is used for noise reduction processing, so that the object and background are uniform and single, with high contrast, without other lines and details that are difficult to distinguish.

Step 4. Based on the adaptive threshold, use the 8-neighborhood gray similarity screening method to find out the candidate corner points of the circular saw blade;

In order to improve the overall adaptability of the method and reduce the misdetection and missed detection of corner points caused by unreasonable threshold setting, an adaptive threshold selection method is used in the circular saw blade tip point detection method. The standard deviation of the image gray value is used as the 8-neighborhood gray similarity judgment threshold t; one percent of the maximum corner response function value CRF _max of the image is used as the corner response detection threshold T.

The grayscale change E(u,v) caused by the movement of the window edge translation vector (u,v) centered on (x,y) is:

$\mathrm{<span\; class="notranslate">\; E.</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; \&omega;</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>{<span\; class="notranslate">\; \&lsqb;</span>\mathrm{<span\; class="notranslate">\; I</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; I</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&rsqb;</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

I(x+u,y+v) is the gray value after translation, I(x,y) is the gray value before translation, ω(x,y) is the Gaussian window function,

Its differential form is

$\mathrm{<span\; class="notranslate">\; E.</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}\mathrm{<span\; class="notranslate">\; \&omega;</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}\mathrm{<span\; class="notranslate">\; u</span>}\mathrm{<span\; class="notranslate">\; \&nu;</span>}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; \&nu;</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>$

in $I_x=\frac{\&part;I}{\&part;x},I_{\mathrm{the\; y}}=\frac{\&part;I}{\&part;\mathrm{the\; y}}$

Its matrix form is

$\mathrm{<span\; class="notranslate">\; E.</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; v</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span><span\; class="notranslate">\; \&lsqb;</span>\begin{array}{cc}\mathrm{<span\; class="notranslate">\; u</span>}& \mathrm{<span\; class="notranslate">\; v</span>}\end{array}<span\; class="notranslate">\; \&rsqb;</span>\mathrm{<span\; class="notranslate">\; m</span>}\left[\begin{array}{c}\mathrm{<span\; class="notranslate">\; u</span>}\\ \mathrm{<span\; class="notranslate">\; v</span>}\end{array}\right]$

Among them, M is the autocorrelation function matrix of the target pixel point (x, y)

$\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}\mathrm{<span\; class="notranslate">\; \&omega;</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>\left[\begin{array}{cc}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}& {\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}\\ {\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}& {\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}\end{array}\right]$

Gaussian window function $\mathrm{\&omega;}(x,\mathrm{the\; y})=e^{(x^2+{\mathrm{the\; y}}^2)/{\mathrm{\&sigma;}}^2}$

The corner response function value of the target pixel point (x, y):

CRF(x,y)=det(M)-k(trace(M)) ²

Among them, det(M) represents the determinant of matrix M, trace(M) represents the trace of matrix, and k takes 0.04～0.06.

The standard deviation of the gray value of each pixel image in the target point (x, y) and its 8 neighborhoods is used as the gray similarity judgment threshold t of the 8 neighborhoods, and one percent of the maximum corner response function value CRF _max is used as the corner point response detection threshold T,

The difference △I between the gray value of the target point (x, y) and each pixel in its 8 neighborhoods, and count the number n of pixels in △I in the range of [-t, t], satisfying 2≤n≤ 6 and its corner response function value is greater than T and the local maximum target point is the candidate corner point.

Step 5. For the candidate corner point, judge whether it is the only corner point in the neighborhood or its corner point response function value is the largest, and remove the false corner point;

The authenticity of the candidate corners is judged. Take the 5×5 neighborhood of each target point as the region of interest, and judge whether the target point is the only corner point. If so, save the target point as a real corner point; if not, judge again. Search out other corners in its 5×5 neighborhood and save the pixel with the largest CRF among these corners as the real corner.

Step 6, judging whether the corner point is the maximum value point on the curve to remove the tooth root point, thereby determining the integer pixel coordinates of the circular saw blade tip point;

Extract all the corner points on the circular saw blade, but these corner points not only include the tip point of the circular saw blade, but also may include the tooth root points between adjacent teeth, and these non-knife tip points will cause the deviation of the circle fitting It is even wrong, so it needs to be screened again to eliminate non-tip points. The edge profile of the circular saw blade is regarded as a continuous curve, the point of the knife tip is the maximum value point on the curve, and the tooth root point between adjacent saw teeth is the minimum value point of the curve.

The slope k _i1 of the line connecting the corner point and the previous corner point

${\mathrm{<span\; class="notranslate">\; k</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}$

The slope k _i2 of the line connecting the corner point and the next corner point

${\mathrm{<span\; class="notranslate">\; k</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}}$

(x _i , y _i ) is the pixel coordinate of the i-th corner point, (x _i-1 , y _i-1 ) is the pixel coordinate of the previous corner point of the i-th corner point, (x _i+1 , y _{i +1} ) is the next corner pixel coordinate of the i-th corner point,

If k _i1 <0 and k _i2 >0, it is judged that the point is not a tool point, and it will be removed.

Step 7, using the cubic surface fitting method to perform sub-pixel positioning on the tool tip point;

In order to improve the detection accuracy without changing the hardware equipment, sub-pixel positioning is performed on the tool tip. Sub-pixel is k subdivision of physical pixels. If the original image has n rows and m columns, after k subdivision, it becomes kn rows and km columns, which means that each pixel is divided into smaller units, so that These smaller units perform interpolation operations to increase the accuracy of the method.

The binary cubic function representation of the whole pixel knife point (x, y) and the CRF of each point in a certain neighborhood:

$\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 00</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 01</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 02</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 03</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 10</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 20</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 30</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 11</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; twenty\; one</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; a</span>}}_{\mathrm{<span\; class="notranslate">\; 12</span>}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

Fitted error sum of squares

$\mathrm{<span\; class="notranslate">\; \&epsiv;</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 25</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

Calculate a ₀₀ , a ₀₁ , a ₀₂ , a ₀₃ , a ₁₀ , a ₂₀ , a ₃₀ , a ₁₁ , a ₂₁ , a ₁₂

Using the determined cubic surface expression to solve the CRF of the entire pixel tip point subdivided into 3×3 sub-pixel points, the sub-pixel coordinate corresponding to the maximum CRF value among the 9 sub-pixel points is taken as the coordinate of the tool tip point.

Step 8. Use the least square method to solve the radius value of the circle where the tool tip point is located, and obtain the actual wear amount of the circular saw blade through the camera calibration relationship

definition

$\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; b</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; c</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; N</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; N</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; -</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

$\mathrm{<span\; class="notranslate">\; A</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; b</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; d</span>}}{\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; b</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$

$\mathrm{<span\; class="notranslate">\; B</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; e</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; b</span>}\mathrm{<span\; class="notranslate">\; c</span>}}{{\mathrm{<span\; class="notranslate">\; b</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; d</span>}}$

$\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; -</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; no</span>}}<span\; class="notranslate">\; (</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; A</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; B</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span>$

according to

r ² =(A ² +B ² -4C)/4

Calculate the actual radius value of the tool, and the difference between the two detection results is the pixel value of the wear amount of the circular saw blade.

The beneficial effects of the present invention can be further illustrated by the following experiments

1. Experimental content

Tested with two kinds of circular saw blades, the transition between adjacent saw teeth of the circular saw blade in Fig. 4a is gentle, and the transition between adjacent saw teeth of the circular saw blade in Fig. The tip point of the circular saw blade.

2. Experimental device

The industrial computer adopts Taiwan Advantech industrial computer IPC-610H, the CPU is E5300, and the memory is 2G; the image acquisition card adopts the PCIe-GIE64+ image acquisition card of Taiwan ADLINK; the industrial camera adopts the 5 million-pixel acA2500-14gm industrial camera of the German BASLER company, the lens The M5018-MP2 fixed-focus lens of Japanese computar company is adopted.

3. Experimental results

In order to verify the effectiveness of the present invention, a circular saw blade tip point detection effect comparison experiment is designed. The experiment selects two kinds of circular saw blades with different shape characteristics, respectively adopts the classical Harris method, the improved Harris method and the method of the present invention to extract the knife tip point of the circular saw blade, and the list of the detection results is shown in Table 1 and Table 2. The renderings are shown in Figure 4 and Figure 5.

Table 1 Circular saw blade detection parameters with smooth transition between adjacent saw teeth

running time(s) Number of tip points The number of corners detected Classic Harris method 5.25 10 10 Improved Harris method 1.078 10 14 The method of the invention 1.571 10 10

Table 2 Detection parameters of circular saw blades with rapid transition between adjacent teeth

running time(s) Number of tip points The number of corners detected Classic Harris method 4.39 12 twenty four Improved Harris method 1.031 12 32 The method of the invention 1.304 12 12

The running time of the improved Harris method is the shortest, less than 20% of the classic Harris method; the running time of the method of the present invention is also less than 35% of the classic Harris method. The method of the present invention has the best effect of extracting the tip point; the classic Harris method has a good effect on extracting the tip point of the circular saw blade with a gentle transition between adjacent saw teeth, but the corner point extracted by the method is good for the circular saw blade with a rapid transition between adjacent saw teeth. It includes not only the tip point, but also the root point between adjacent saw teeth; the corner points extracted by the improved Harris method have serious clustering phenomenon, and the detection effect is the worst. It can be seen that the method of the present invention is more effective in the application of circular saw blade wear detection.

Claims (8)

1. a saw blade wear extent On-line Measuring Method, is characterized in that, comprises the following steps:

(1) saw blade image is obtained;

(2) noise reduction pre-service is carried out to the image obtained;

(3) based on adaptive threshold, use 8 neighborhood gray scale similarity screening techniques, find out the candidate angular of saw blade;

(4) for candidate angular, judge whether it is that the interior unique angle point of neighborhood or its angle point response function value are maximum, weeds out pseudo-angle point; Retaining those is candidate angular maximum for the angle point response function value in the candidate angular of unique angle point or its 5 × 5 neighborhood in its 5 × 5 neighborhood;

(5) judge that whether angle point is that on curve, maximum point, to reject tooth root point, thus determines the Integer Pel coordinate of saw blade point of a knife point;

(6) cubic surface fitting process tool setting cusp is utilized to carry out sub-pixel positioning;

(7) use least square method to solve point of a knife point place radius of a circle value, demarcate by industrial camera the actual wear amount that relation draws saw blade.

2. saw blade wear extent On-line Measuring Method according to claim 1, it is characterized in that, the method that described step 1 obtains saw blade image is: by rack-mount industrial camera, pass through manual shift, industrial camera is made to face measured circle saw blade, industrial computer trigger image capture card, obtains saw blade image.

3. saw blade wear extent On-line Measuring Method according to claim 1, is characterized in that, described step 2 is carried out the pretreated method of noise reduction to the image obtained and is: adopt mean filter, medium filtering or Wavelet Denoising Method.

4. saw blade wear extent On-line Measuring Method according to claim 1, is characterized in that, the defining method of described step 3 candidate angular is:

The mobile grey scale change E (u, v) caused of windowsill translation vector (u, v) centered by (x, y) is:

$E(u,v)=\underset{x,y}{\mathrm{\&Sigma;}}\mathrm{\&omega;}\left(x,y\right){\&lsqb;I\left(x+u,y+v\right)-I\left(x,y\right)\&rsqb;}^2$

In formula: I (x+u, y+v) is the gray-scale value after translation, I (x, y) is the gray-scale value before translation, and ω (x, y) is Gauss's window function,

Its differential form is

$E(u,v)=\underset{x,y}{\&Sigma;}\mathrm{\&omega;}(x,y)(I_x^2{u}^2+2I_x{I}_{y}u\mathrm{\&nu;}+I_y^2{\mathrm{\&nu;}}^2)$

Wherein $I_x=\frac{\&part;I}{\&part;x},I_y=\frac{\&part;I}{\&part;y}$

Its matrix form is

$E(u,v)=\&lsqb;\begin{array}{cc}u& v\end{array}\&rsqb;M\left[\begin{array}{c}u\\ v\end{array}\right]$

Wherein, M is the autocorrelation function matrix of target pixel points (x, y)

$M=\underset{x,y}{\&Sigma;}\mathrm{\&omega;}(x,y)\left[\begin{array}{cc}{I}_x^2& I_x{I}_y\\ I_x{I}_y& I_y^2\end{array}\right]$

Gauss's window function $\mathrm{\&omega;}(x,y)=e^{(x^2+y^2)/{\mathrm{\&sigma;}}^2}$

Angle point response function value CRF (x, y) of target pixel points (x, y):

CRF(x,y)＝det(M)-k(trace(M)) ²

The wherein determinant of det (M) representing matrix M, the mark of trace (M) representing matrix, k gets 0.04 ~ 0.06,

Using the standard deviation of impact point (x, y) and each pixel image intensity value in its 8 contiguous range as the similar decision threshold t of 8 neighborhood gray scale, maximum angle point response function value CRF _maxone of percentage as angle point response detection threshold T,

Impact point (x, y) with the difference △ I of gray-scale value of each pixel in its 8 contiguous range, the statistics pixel number n of △ I in [-t, t] scope, meets 2≤n≤6 and its angle point response function value is greater than T and the maximum impact point in local is candidate angular.

5. saw blade wear extent On-line Measuring Method according to claim 1, is characterized in that, the method that described step 5 rejects saw blade tooth root point is as follows:

The slope k of angle point and previous angle point line _i1

$k_{i1}=\frac{y_i-y_{i-1}}{x_i-x_{i-1}}$

The slope k of angle point and a rear angle point line _i2

$k_{i2}=\frac{y_i-y_{i+1}}{x_i-x_{i+1}}$

(x _i, y _i) be the pixel coordinate of i-th angle point, (x _i-1, y _i-1) be the previous corner pixels coordinate of i-th angle point, (x _i+1, y _i+1) be the rear corner pixels coordinate of i-th angle point,

Reject those k _i1<0 and k _i2the angle point of >0.

6. saw blade wear extent On-line Measuring Method according to claim 1, is characterized in that, the method that described step 6 tool setting cusp carries out sub-pixel positioning is as follows:

The CRF binary cubic function representation of each point in Integer Pel point of a knife point (x, y) and certain neighborhood thereof:

$CRF(x_i,y_i)=a_{00}+a_{01}{y}_i+a_{02}{y}_i^2+a_{03}{y}_i^3+a_{10}{x}_i+a_{20}{x}_i^2+a_{30}{x}_i^3+a_{11}{x}_i{y}_i+a_{21}{x}_i^2{y}_i+a_{12}{x}_i{y}_i^2$

The error sum of squares of matching

$\mathrm{\&epsiv;}=\underset{i=1}{\overset{25}{\mathrm{\&Sigma;}}}{\left(CRF\right(x,y)-CRF(x_i,y_i\left)\right)}^2$

try to achieve a ₀₀, a ₀₁, a ₀₂, a ₀₃, a ₁₀, a ₂₀, a ₃₀, a ₁₁, a ₂₁, a ₁₂

Utilize the cubic surface expression formula determined to solve the CRF that Integer Pel point of a knife point is subdivided into 3 × 3 sub-pix points, get the coordinate of the subpixel coordinates in 9 sub-pix points corresponding to CRF maximal value as this point of a knife point.

7. saw blade wear extent On-line Measuring Method according to claim 1, is characterized in that, the computing method that described step 7 solves point of a knife point place radius of a circle value are as follows:

Definition

$a=n\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i^2-\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i$

$b=n\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i{y}_i-\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i$

$c=n\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i^3+n\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i{y}_i^2-\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}(x_i+y_i)\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i$

$d=n\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i^2-\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i$

$e=N\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i^2{y}_i+N\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i^3-\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}(x_i^2+y_i^2)\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i$

$A=\frac{be-cd}{ad-b^2}$

$B=\frac{ae-bc}{b^2-ad}$

$C=-\frac{1}{n}\left(\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}\right(x_i^2+y_i^2)+A\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{x}_i+B\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{y}_i)$

According to formula r ²=(A ²+ B ²-4C)/4, calculate the sub-pixel values of point of a knife point place radius of circle.

8. saw blade wear extent On-line Measuring Method according to claim 1, is characterized in that, the computing method of the actual wear amount of the saw blade of described step 7 are as follows:

(1) camera calibration, at the demarcation thing that the position installation dimension of installing saw blade is known, industrial computer trigger image capture card obtains the image demarcating thing, according to the image obtained, calculate the pixel value of known dimensions, known dimensions obtains the physical size value of each pixel representative divided by pixel value;

(2) according to the radius value obtaining cutter reality, the difference of twice testing result is the pixel value of saw blade wear extent, then is multiplied by the physical size value of each pixel representative, obtains the size of the wearing and tearing value of saw blade.