CN107131837A - A kind of rocker arm of coal mining machine mining height vision measuring method - Google Patents

Abstract

The invention discloses a method for visually measuring the mining height of the rocker arm of a coal shearer. A square positioning mark is respectively installed on the rocker arm of the coal shearer and the machine body, and the image of the shearer is collected by a camera; the collected target image is Carry out noise reduction processing, and extract the positioning marks in the image after the noise reduction processing; carry out edge straight line fitting on each positioning mark, and obtain the four vertex coordinates of each positioning mark; The included angle between the two positioning marks is based on the length of the rocker arm and the angle between the two positioning marks, and the rocker mining height of the shearer. The invention uses non-contact visual measurement technology to automatically measure the inclination angle of the rocker arm relative to the fuselage in the video image of the coal mining machine. Technical support, with significant economic benefits and high engineering application value.

Description

A visual measurement method for mining height of rocker arm of coal mining machine

technical field

The invention belongs to the field of mining equipment operation state monitoring, and in particular relates to a visual measurement method for mining height of a rocker arm of a coal mining machine.

Background technique

The mining height of the shearer is an important parameter of the working condition of the shearer, so the detection of the inclination angle of the rocker arm of the shearer is very necessary. At present, the mining height measurement of coal mining machines generally adopts contact measurement methods, among which, the rotary encoder is used to measure the inclination angle of its rocker arm, which is difficult to install; there is also the use of magnetic telescopic sensors to measure the displacement of the rocker arm cylinder. The inclination angle of the rocker arm is calculated indirectly, but because the rocker arm of the shearer has a large forced vibration when it is working, the service life of these two sensors is very short, which seriously limits the development of intelligent control of the shearer.

Contents of the invention

Aiming at the defects and deficiencies of the existing preparation technology, the purpose of the present invention is to provide a method for visually measuring the mining height of the rocker arm of a coal shearer, which solves the problems of difficulty in installing the detection device and low detection accuracy in the existing detection method.

In order to achieve the above object, the present invention adopts the following technical solutions to achieve:

A method for visually measuring the mining height of a rocker arm of a coal shearer, comprising the following steps:

Step 1: Install square positioning marks on the rocker arm and body of the shearer respectively, and collect images of the shearer through the camera;

Step 2: Perform noise reduction processing on the acquired target image, and extract the positioning mark in the image after the noise reduction processing;

Step 3: Perform edge straight line fitting for each positioning mark to obtain the four vertex coordinates of each positioning mark. The specific steps are:

Step 3.1: Distribute the receptive field for the jth positioning mark according to the set center distance and size, use the mask of (r*2+1)*(r*2+1), j=1, 2, N is the positioning The number of identification plates, r is the radius of the receptive field cell, and the center of the mask coincides with the center of the receptive field cell;

Step 3.2: Use the gradient operator to calculate the gradient direction of each receptive field mask, and make a qualitative judgment on each receptive field direction through the gradient direction of the mask, so as to divide the upper edge, lower edge, left edge and right edge of the positioning mark respectively Receptive field cells distributed on

Step 3.3: Use the receptive field model to calculate the response value of each receptive field in the direction of the upper edge, and determine the relationship between the center of each receptive field and the contrast edge in the receptive field to Feel the distance from the center of the field, and then use the constrained least squares model to fit the straight line where the edge of the signboard is located;

Step 3.4: Repeat step 3.3 to fit the straight lines where the lower edge, left edge, and right edge of the positioning mark are located;

Step 3.5: Obtain the coordinates of the four vertices of the jth positioning mark according to the four straight line equations of the fitted upper edge, lower edge, left edge and right edge;

Step 3.6: Repeat steps 3.1 to 3.5 to obtain the four vertex coordinates of all positioning marks.

Step 4: According to the vertex coordinates of the positioning marks obtained in step 3, the angle between the two positioning marks is obtained, and the mining height h of the rocker arm of the shearer is calculated by the following formulas (1) and (2)

h＝L*sin(θ-θ ₀ ) (1)

Among them, L is the arm length of the rocker arm, and θ is the angle between the two positioning marks;

n _j is the vector formed by the vertex ξ and the vertex υ of the jth positioning mark, j=1, 2, i=1, 2, 3, 4, and the vertex at the upper left corner of each positioning mark is taken as the first coordinate P ₁ , the remaining coordinates are distributed in a clockwise direction, ξ∈i,υ∈i, ξ≠υ; (x _ji ,y _ji ) is the image coordinate of the i-th vertex of the j-th location identification vertex, (X _ji ,Y _ji , Z _ji ) are the optical center coordinates of the i-th vertex of the j-th location identification vertex;

B _j1 = x _j2 y _j3 -x _j4 y _j3 +x _j4 y _j2 -x _j2 y _j4 +x _j3 y _j4 -x _j3 y _j2

B _j2 = x _j3 y _j4 -x _j4 y _j3 -x _j1 y _j4 -x _j4 y _j1 +x _j1 y _j3 -x _j3 y _j1

B _j3 ＝x _j1 y _j2 -x _j4 y _j2 -x _j2 y _j1 -x _j1 y _j4 +x _j4 y _j1 -x _j2 y _j4

B _j4 ＝x _j3 y _j2 -x _j2 y _j3 +x _j1 y _j3 -x _j2 y _j1 -x _j1 y _j2 -x _j3 y _j1

Among them, l _j is the distance between the vertex ξ and the vertex υ of the jth positioning mark, and C is the effective focal length of the camera.

Further, the second step includes:

Step 2.1: Perform adaptive binarization preprocessing on each frame of the acquired target image;

Step 2.2: Using a method based on connected components to extract the location markers in the preprocessed target image.

Compared with prior art, the beneficial effect of the present invention is:

The invention uses non-contact visual measurement technology to automatically measure the inclination angle of the rocker arm relative to the fuselage in the video image of the coal mining machine. Technical support, with significant economic benefits and high engineering application value.

Description of drawings

Fig. 1 is a flowchart of the present invention.

Fig. 2 is a diagram of the installation position of the positioning mark of the present invention in the coal shearer.

Fig. 3 is the image collected by the method of the present invention and the processed image thereof, (a) the original image, (b) the image after binarization preprocessing, and (c) the extracted positioning mark.

The specific content of the present invention will be further explained in detail below in conjunction with the examples.

detailed description

The present invention first explains the coordinate system used in the text:

Optical center coordinate system (camera coordinate system): take the optical center of the camera as the coordinate origin, the X-axis and Y-axis are parallel to the two vertical sides of the CCD plane, and the Z-axis coincides with the optical axis of the camera; image coordinate system: coordinate origin At the center of the CCD image plane, the X-axis and Y-axis are parallel to the two vertical sides of the CCD plane; pixel coordinate system: the coordinate origin is at the upper left corner of the CCD image plane, and the U-axis and V-axis are parallel to the X-axis of the image coordinates , Y axis.

A method for visually measuring the mining height of a rocker arm of a coal mining machine according to the present invention comprises the following steps:

Step 1: Install a square positioning mark on the rocker arm and the pin shaft of the fuselage of the shearer respectively, and collect images of the shearer through a camera. Generally, the camera is installed on the shearer, see Figure 2 for details;

Step 2: Perform noise reduction processing on the collected target image, and extract the positioning marks in the pre-processed image, where there are two positioning marks in each image;

Step 2.1: Perform adaptive binarization preprocessing on each frame of the acquired target image;

Step 2.2: using a method based on connected components to extract the location markers in the preprocessed target image;

Step 3: Perform edge straight line fitting for each positioning mark to obtain the four vertex coordinates of each positioning mark, specifically:

Step 3.1: Distribute the receptive field for the jth positioning mark according to the set center distance and size, and use the mask of (r*2+1)*(r*2+1), j=1, 2, r is the receptive field Field cell radius, the center of the mask coincides with the center of the receptive field cell;

Step 3.2: Use the gradient operator to calculate the gradient direction of each receptive field mask;

Qualitatively judge the direction of each receptive field through the gradient direction of the mask, so as to divide the receptive field cells distributed on the upper edge, lower edge, left edge and right edge of the positioning mark;

Step 3.3: Using the receptive field model, calculate the response value S of each receptive field in the direction of the upper edge,

S＝S ₁ -S ₂ (2)

Among them, σ _D ＝r _D /4, σ _S ＝r _S /4; r _D and r _S represent the radii of the central area and the peripheral area (also including the great circle of the central area) of the receptive field respectively, h(u,v, η) represents the stimulus intensity of the pixel point located in the pixel (u, v) when the contrast stimulus coverage rate is η, the value of the point with a pixel value of 255 in the binary image is 1, and the value of a point with a pixel value of 0 is 0 ;

S ₁ is the response value of the central area of the receptive field, S ₂ is the response value of the surrounding area of the receptive field, D _l is the pixel point located in the central area of the receptive field, _Se is the pixel point located in the peripheral area of the receptive field, l=0,1 ,2,...,f, e=1,2,...,m, f is the pixel located in the center of the receptive field, m is the number of pixels located in the peripheral area of the receptive field.

According to the relationship between the contrast edge position formed by the pixels in a single receptive field and the distance from the center of the receptive field, determine the distance d _h from the center of each receptive field to the fitted contrast edge in the receptive field, h=1,2,...,n, where n represents the number of receptive field cells.

Assuming that the line equation of the edge is (a,b)(u,v) ^T +c=0, according to the distance formula from the point to the line:

Among them, (u _h , v _h ) is the coordinate point of the center of the receptive field on the pixel coordinate system.

Fit the straight line where the edge is located using a constrained least squares model;

Among them, L(a, b, c, λ) represents the Lagrangian function, λ is a parameter; a, b, c are the coefficients of the line equation where the fitted edge is located, and U and V represent the pixel at the center of the receptive field cell An n*1 matrix composed of coordinates, D represents an n*1 matrix composed of d _h ;

Under the constraint condition a ² +b ² =1, find the optimal solution of a, b, c (a ^* , b ^* , c ^* );

Step 3.4: Repeat step 3.3 to fit the straight lines where the lower edge, left edge, and right edge of the positioning mark are located;

Step 3.5: Obtain the coordinates of the four vertices of the jth positioning mark according to the four straight line equations of the fitted upper edge, lower edge, left edge and right edge;

Step 3.6: Repeat steps 3.1 to 3.5 to obtain the vertex coordinates of the two positioning marks;

Step 4: According to the respective vertex coordinates of the two positioning marks obtained in step 3, the angle between the two positioning marks is obtained, and the rocking arm mining height of the shearer is obtained according to the length of the rocker arm and the angle between the two positioning marks .

Step 4.1: Convert the coordinates of the four vertices obtained in Step 3 into the image coordinates (x _ji , y _ji ), and calculate the jth one according to the relationship between the image coordinates and the optical center coordinates (X _ji , Y _ji , Z _ji ). Vector n _j formed by vertex ξ and vertex υ in the positioning mark;

Among them, n _j is the vector formed by the vertex ξ and the vertex υ of the jth location marker, j=1,2, i=1,2,3,4, ξ∈i,υ∈i, ξ≠υ; (x _ji ,y _ji ) is the image coordinates of the i-th vertex of the j-th location marker vertex, (X _ji ,Y _ji , Z _ji ) is the optical center coordinate of the i-th vertex of the j-th location marker vertex, and each The vertex in the upper left corner of a positioning mark is taken as the first coordinate P ₁ , and the rest of the coordinates are distributed in a clockwise direction, as shown in Figure 2;

B _j1 = x _j2 y _j3 -x _j4 y _j3 +x _j4 y _j2 -x _j2 y _j4 +x _j3 y _j4 -x _j3 y _j2

B _j2 = x _j3 y _j4 -x _j4 y _j3 -x _j1 y _j4 -x _j4 y _j1 +x _j1 y _j3 -x _j3 y _j1

B _j3 ＝x _j1 y _j2 -x _j4 y _j2 -x _j2 y _j1 -x _j1 y _j4 +x _j4 y _j1 -x _j2 y _j4

B _j4 ＝x _j3 y _j2 -x _j2 y _j3 +x _j1 y _j3 -x _j2 y _j1 -x _j1 y _j2 -x _j3 y _j1

Wherein, l _j is the distance between the vertex ξ and the vertex υ of the jth positioning mark, and C is the effective focal length of the camera;

Step 4.2: Calculate the mining height h of the rocker arm of the shearer through the following formulas (1) and (2),

h＝L*sin(θ-θ ₀ ) (1)

Among them, L is the arm length of the rocker arm, θ is the angle between the two positioning marks during the movement of the rocker arm of the shearer, and _θ0 is the axis of the rocker arm of the shearer and the axis of the body of the shearer When parallel, the angle between two positioning marks.

Specific embodiments of the present invention are provided below, and it should be noted that the present invention is not limited to the following specific embodiments, and all equivalent transformations done on the basis of the technical solutions of the present application all fall within the scope of protection of the present invention.

Example

This embodiment provides a method for visual measurement and detection of the mining height of the rocker arm of a coal mining machine, including:

Install square positioning marks on the rocker arm and the fuselage of the shearer respectively. When the rocker arm of the shearer is parallel to the fuselage, the image acquisition of the shearer is carried out through the camera installed on the shearer body, as shown in the figure As shown in 2, the camera is suspended on a certain position of the fuselage between the two positioning marks through a cross bar, so that the camera can capture the two positioning marks at the same time, and the length of the rocker arm is 500mm.

Adaptive binarization preprocessing is performed on each frame of target image acquired, and the processing result is shown in Figure 3(a); the connected components in the hydraulic support image after binarization preprocessing are extracted; the long and short axes of the connected components are used to Ratio and area information extraction and segmentation of positioning marks in the hydraulic support image, the extracted image is shown in Figure 3(b);

Use the gradient operator to calculate the gradient direction of each receptive field mask, and make a qualitative judgment on each receptive field direction through the gradient direction, so as to divide the receptive field cells distributed on any edge of the positioning mark, as shown in Figure 3(c) As shown; using the receptive field model, calculate the response value of each receptive field in the edge direction of the positioning mark, and determine the fitting from the center of each receptive field to the receptive field according to the relationship between the contrast edge position formed by a single receptive field pixel and the distance from the receptive field center Compare the distance of the edge;

Use the constrained least squares model to fit the straight line where the edge is located; calculate the pixel coordinates of the four vertices of the positioning marks in the roadheader image according to the four straight line equations of the fitted upper edge, lower edge, left edge and right edge .

Using the above calculation formulas (1) to (5), when the rocker arm is parallel to the fuselage, the angle between the two positioning marks is 1.5413°;

Adjust the rocker arm of the shearer. When the rocker arm is raised by 19.1892° and the mining height is 164.3443mm, carry out image acquisition, repeat the above steps, and calculate that the angle between the two positioning marks on the shearer is 20.6979°. Considering the initial The included angle is 1.5413°, and finally the actual included angle between the rocker arm and the fuselage of the shearer is 19.1566°, and the mining height is 164.0756mm. This value is very close to the actual value. The mining height measurement of the rocker arm of the coal mining machine provides the necessary technical support.

Claims (2)

1. a kind of rocker arm of coal mining machine mining height vision measuring method, it is characterised in that comprise the following steps：

Step one：Square positioning mark is installed on rocker arm of coal mining machine and fuselage respectively, and coal-winning machine carried out by video camera IMAQ；

Step 2：Noise reduction process is carried out to the target image collected, the positioning mark after noise reduction process in image is extracted；

Step 3：Edge lines fitting is carried out to each positioning mark, four apex coordinates of each positioning mark are obtained, specifically Step is：

Step 3.1：To center spacing and size distribution receptive field of j-th of positioning mark according to setting, using (r*2+1) * (r* Mask 2+1), j=1,2, N be the number of positioning marking plate, and r is receptive field cell radius, mask center and receptive field cell Center superposition；

Step 3.2：Each receptive field mask gradient direction is calculated using gradient operator, by mask gradient direction to each impression Wild direction is qualitatively judged, and is distributed so as to be respectively divided out on top edge, lower edge, left hand edge and the right hand edge of positioning mark Receptive field cell；

Step 3.3：Using receptive field model, the response of each receptive field of top edge direction is calculated, according in single receptive field The relation of contrast fringes position and the receptive field centre distance of pixel formation, it is determined that each receptive field center is to right in receptive field Than the distance at edge to receptive field center, then marking plate top edge place is fitted using the LEAST SQUARES MODELS FITTING of belt restraining Straight line；

Step 3.4：Repeat step 3.3, is fitted to straight line where the lower edge, left hand edge, right hand edge of positioning mark respectively；

Step 3.5：According to the top edge of fitting, lower edge, four linear equations of left hand edge and right hand edge, j-th of positioning is obtained Four apex coordinates of mark；

Step 3.6：3.1~step 3.5 of repeat step, obtains four apex coordinates of all positioning marks.

Step 4：The positioning obtained according to step 3 identifies respective apex coordinate and obtains two angles positioned between mark, leads to Cross following formula (1) and (2) calculate the mining height h of rocker arm of coal mining machine

H=L*sin (θ-θ₀) (1)

<mrow> <mi>&amp;theta;</mi> <mo>=</mo> <msup> <mi>cos</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msup> <mrow> <mo>(</mo> <mfrac> <mrow> <mover> <msub> <mi>n</mi> <mn>1</mn> </msub> <mo>&amp;RightArrow;</mo> </mover> <mo>*</mo> <mover> <msub> <mi>n</mi> <mn>2</mn> </msub> <mo>&amp;RightArrow;</mo> </mover> </mrow> <mrow> <mo>|</mo> <mover> <msub> <mi>n</mi> <mn>1</mn> </msub> <mo>&amp;RightArrow;</mo> </mover> <mo>|</mo> <mo>*</mo> <mo>|</mo> <mover> <msub> <mi>n</mi> <mn>2</mn> </msub> <mo>&amp;RightArrow;</mo> </mover> <mo>|</mo> </mrow> </mfrac> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>2</mn> <mo>)</mo> </mrow> </mrow>

Wherein, L is the brachium of rocking arm, and θ is the angle between two positioning marks；

n_jThe vector formed for the summit ξ and summit υ of j-th of positioning mark, j=1,2, i=1,2,3,4, it will each position mark The summit in the upper left corner is used as first coordinate P₁, remaining coordinate is sequentially distributed in the direction of the clock, ξ ∈ i, υ ∈ i, ξ ≠ υ；(x_ji, y_ji) for j-th positioning mark summit i-th of summit image coordinate, (X_ji,Y_ji,Z_ji) identify summit for j-th of positioning The photocentre coordinate on i-th of summit；

<mrow> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> </mrow> <mi>C</mi> </mfrac> <mo>,</mo> <msub> <mi>Y</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> </mrow> <mi>C</mi> </mfrac> <mo>,</mo> <msub> <mi>Z</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> <mo>=</mo> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mi>i</mi> </mrow> </msub> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>5</mn> <mo>)</mo> </mrow> </mrow>

<mrow> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>Cl</mi> <mi>j</mi> </msub> </mrow> <msqrt> <mrow> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <msup> <mi>C</mi> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> </mrow> 1

<mrow> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>Cl</mi> <mi>j</mi> </msub> </mrow> <msqrt> <mrow> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <msup> <mi>C</mi> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> </mrow>

<mrow> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mn>3</mn> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>3</mn> </mrow> </msub> <msub> <mi>Cl</mi> <mi>j</mi> </msub> </mrow> <msqrt> <mrow> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <msup> <mi>C</mi> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> </mrow>

<mrow> <msub> <mi>t</mi> <mrow> <mi>j</mi> <mn>4</mn> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>4</mn> </mrow> </msub> <msub> <mi>Cl</mi> <mi>j</mi> </msub> </mrow> <msqrt> <mrow> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>x</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>2</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>B</mi> <mrow> <mi>j</mi> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <msup> <mi>C</mi> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> </mrow>

B_j1=x_j2y_j3-x_j4y_j3+x_j4y_j2-x_j2y_j4+x_j3y_j4-x_j3y_j2

B_j2=x_j3y_j4-x_j4y_j3-x_j1y_j4-x_j4y_j1+x_j1y_j3-x_j3y_j1

B_j3=x_j1y_j2-x_j4y_j2-x_j2y_j1-x_j1y_j4+x_j4y_j1-x_j2y_j4

B_j4=x_j3y_j2-x_j2y_j3+x_j1y_j3-x_j2y_j1-x_j1y_j2-x_j3y_j1

Wherein, l_jThe distance between summit ξ and summit υ for j-th of positioning mark, C are the effective focal length of video camera.

2. rocker arm of coal mining machine mining height vision measuring method as claimed in claim 1, it is characterised in that：Described step two is wrapped Include：

Step 2.1：Self-adaption binaryzation pretreatment is carried out to the every frame target image collected；

Step 2.2：The positioning mark in pretreated target image is extracted using the method based on connected component.