Intelligent panoramic processing method and system for borehole peeping based on image processing

Abstract

The invention relates to the technical field of borehole peeping video processing, in particular to a borehole peeping intelligent panoramic processing method and system based on image processing, and the method comprises the steps: obtaining a peeping video in a borehole, and obtaining rectangular coordinates of all pixel points of circles with different radiuses; constructing a pixel rectangular strip corresponding to each circle according to the rectangular coordinates of all the pixel points of each circle; the sequence of the pixel points in the circle from 0 degree to 360 degrees is the sequence of the pixel points in the pixel rectangular strip from left to right; each circle obtains a pixel rectangular strip; the pixel rectangular strips are sequentially spliced from top to bottom according to the sequence of circle radiuses from small to large, and a step-shaped reconstructed image is obtained; performing interpolation processing on the stepped reconstructed image to obtain a reconstructed rectangular image; and carrying out repeated region detection on the reconstructed rectangular image, and removing an overlapped region to obtain a panoramic image of the drilled hole. A high-quality panoramic image is generated, and technical support is provided for geological exploration in tunnel engineering.

Description

Technical Field

[0001] The present invention relates to the technical field of borehole peep video processing, and particularly to an intelligent panoramic processing method and system for borehole peeping based on image processing. Background Art

[0002] In tunnel engineering, the borehole peeping technology is an important geological exploration means for obtaining the internal conditions of the surrounding rock of the tunnel or the rock mass in front of the heading face to help technicians evaluate and design the construction plan of the tunnel.

[0003] The borehole information obtained by borehole peeping is presented in the form of a continuous video. The data volume obtained in this way is huge and requires professional personnel for analysis and interpretation. When technicians analyze the internal conditions of the rock mass through the borehole peeping technology, they need to watch the peeping video to identify cracks, faults, etc. in the borehole. This analysis method of watching the borehole video cannot intuitively understand the comprehensive information inside the borehole and may result in misjudgment, omission, or error.

[0004] Common panoramic processing methods for borehole peeping videos usually only simply expand the peeping video. However, during the process of peeping into the borehole, since manual operation cannot ensure that the peeping probe enters the borehole completely uniformly and stably, when there are pauses and position offsets in the peeping video, ordinary panoramic processing methods will produce overlapping or incorrect images. And because the borehole peeping video is generally of low brightness, the images extracted by traditional panoramic processing methods are not clear, resulting in low-quality images after panoramic processing. Summary of the Invention

[0005] To solve the deficiencies of the prior art, the present invention provides an intelligent panoramic processing method and system for borehole peeping based on image processing; taking the distance that the borehole peeping probe enters the borehole as a standard, video frames are extracted from the peeping video at fixed intervals and saved as images, and the images are subjected to clarification, standardization, and contour recognition processing. The annular surrounding rock image in the image is transformed into a rectangular image through coordinate transformation and pixel assignment, and the rectangular images processed at different distances are spliced, and the overlapping areas between every two images are detected and removed through an image overlapping area detection algorithm to form a panoramic image of the entire borehole.

[0006] On the one hand, an intelligent panoramic processing method for borehole peeping based on image processing is provided, including:

[0007] Obtain the peeping video inside the borehole, and perform image enhancement processing on each frame of the image in the peeping video; perform edge detection processing on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock;

[0008] Taking a single pixel point in the image as a unit, starting from the outer circle of the annular surrounding rock, reducing the pixel points by one unit each time until reaching the inner circle of the annular surrounding rock, obtaining a circle each time of reduction, and finally getting circles with different radii; converting each pixel point of each circle from polar coordinates to rectangular coordinates in the order from 0 degrees to 360 degrees to obtain the rectangular coordinates of all pixel points of each circle;

[0009] According to the rectangular coordinates of all pixel points of each circle, constructing a pixel rectangular bar corresponding to each circle; the order of pixel points from 0 degrees to 360 degrees in the circle is the order of pixel points from left to right in the pixel rectangular bar; each circle obtains a pixel rectangular bar;

[0010] Splicing the pixel rectangular bars in sequence from top to bottom in the order of increasing circle radius to obtain a stepped reconstructed image; performing interpolation processing on the stepped reconstructed image to obtain a reconstructed rectangular image; performing repeated region detection on the reconstructed rectangular image to remove overlapping regions to obtain a panoramic image of the borehole.

[0011] On the other hand, a borehole peep intelligent panoramic processing system based on image processing is provided, including:

[0012] An image processing module, which is configured to: acquire a peep video inside the borehole and perform image enhancement processing on each frame of the image in the peep video; perform edge detection processing on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock;

[0013] A coordinate conversion module, which is configured to: take a single pixel point in the image as a unit, start from the outer circle of the annular surrounding rock, reduce the pixel points by one unit each time until reaching the inner circle of the annular surrounding rock, obtain a circle each time of reduction, and finally get circles with different radii; convert each pixel point of each circle from polar coordinates to rectangular coordinates in the order from 0 degrees to 360 degrees to obtain the rectangular coordinates of all pixel points of each circle;

[0014] A rectangular bar construction module, which is configured to: construct a pixel rectangular bar corresponding to each circle according to the rectangular coordinates of all pixel points of each circle; the order of pixel points from 0 degrees to 360 degrees in the circle is the order of pixel points from left to right in the pixel rectangular bar; each circle obtains a pixel rectangular bar;

[0015] A panoramic image reconstruction module, which is configured to: splice the pixel rectangular bars in sequence from top to bottom in the order of increasing circle radius to obtain a stepped reconstructed image; perform interpolation processing on the stepped reconstructed image to obtain a reconstructed rectangular image; perform repeated region detection on the reconstructed rectangular image to remove overlapping regions to obtain a panoramic image of the borehole.

[0016] The above technical solution has the following advantages or beneficial effects:

[0017] Through image processing technology, coordinate transformation, pixel assignment, and duplicate area detection, the borehole peep video can be processed efficiently and intelligently to generate high-quality panoramic images, providing strong technical support for geological exploration in tunnel engineering. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings forming a part of this invention are used to provide a further understanding of the invention. The schematic embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0019] Figure 1 Schematic diagram of borehole peeping for Example 1;

[0020] Figure 2 Schematic diagram of the annular surrounding rock for Example 1;

[0021] Figure 3 Schematic diagram of the image reconstruction process for Example 1;

[0022] FIG. 4(a) and FIG. 4(b) are schematic diagrams of detecting the repeated part of the image for Example 1;

[0023] Among them, 1. Cable; 2. Pushing rod; 3. Limiting roller; 4. Probe; 5. Borehole. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs.

[0025] Example 1. This example provides an intelligent panoramic processing method for borehole peeping based on image processing, including:

[0026] S101: Obtain the peeping video in the borehole, perform image enhancement processing on each frame of the peeping video; perform edge detection processing on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock;

[0027] S102: Taking a single pixel point in the image as a unit, starting from the outer circle of the annular surrounding rock, reducing one unit of pixel points each time until reaching the inner circle of the annular surrounding rock, obtaining a circle each time of reduction, and finally obtaining circles with different radii; converting the polar coordinates of each pixel point of each circle to rectangular coordinates in the order from 0 degrees to 360 degrees to obtain the rectangular coordinates of all pixel points of each circle;

[0028] S103: Construct a pixel rectangle bar corresponding to each circle according to the rectangular coordinates of all the pixels in each circle; the order of the pixels from 0 degrees to 360 degrees in the circle is the order of the pixels from left to right in the pixel rectangle bar; each circle obtains a pixel rectangle bar.

[0029] S104: Splice the pixel rectangle bars in ascending order of the circle radius from top to bottom to obtain a stepped reconstructed image; perform interpolation processing on the stepped reconstructed image to obtain a reconstructed rectangular image; perform duplicate region detection on the reconstructed rectangular image and remove the overlapping regions to obtain a panoramic image of the drill hole.

[0030] Further, as Figure 1 shown, the S101: Obtain the endoscopic video inside the drill hole, including: Install a box body at the front end of the push rod 2, install a probe 4 at the front end of the box body, install limit rollers 3 on both sides of the box body, the push rod 2 pushes the box body to move forward at a constant speed in the drill hole 5 under the action of an external force, the limit rollers assist the box body to be at the center position of the drill hole, and the camera on the lift head collects the video during the forward movement, and the camera transmits the collected video to the upper computer through the cable 1.

[0031] Further, the S101: Perform image enhancement processing on each frame of the endoscopic video, including:

[0032] Regard the original image as I 1 (x i , y i ), which is represented by the following formula:

[0033] I 1 (x i , y i ) = L 1 (x i , y i ) * R 1 (x i , y i );

[0034] Among them, R 1 (x i , y i ) is the reflection component; L 1 (x i , y i ) is the illumination component, and * is the convolution operation.

[0035] Perform filtering processing on the basis of the original image through a two-dimensional Gaussian function to obtain a new illumination component:

[0036]

[0037] Among them, L 2(x i , y i ) is the light component after filtering processing, and σ is the standard deviation of the Gaussian function.

[0038] By taking multiple different standard deviation values σ in the Gaussian function, the reflection component R at multiple scales can be obtained MSR (x i , y i ) is:

[0039]

[0040] where w j is the weight at different scales, and w j is Considering from high, medium, and low three scales, σ takes three values of 64, 128, and 256 here.

[0041] By transformation, the pixel values of the reflection component R 2 (x i , y i ) are in the range of 0 - 255:

[0042]

[0043] Thus, the enhanced image I 2 (x, y) is further obtained:

[0044] ln(I 2 (x i , y i )) = ln(L 2 (x i , y i )) + ln(R 2 (x i , y i ).

[0045] It should be understood that the low - light image extracted from the enhanced peeping video is enhanced in clarity, and the black circular cavity in the drilling image is identified.

[0046] Furthermore, the S101: performing edge detection processing on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock includes:

[0047] Performing grayscale processing on the enhanced image I 2 (x, y) to convert it into a grayscale image I_gray(x, y);

[0048] Calculating the horizontal gradient and vertical gradient of the grayscale image, and calculating the gradient amplitude value of each pixel point according to the horizontal gradient and vertical gradient;

[0049] Determine the contour edge points according to the gradient magnitude value of each pixel point; determine the outer radius and inner radius of the annular surrounding rock according to the contour edge points.

[0050] Further, the calculating the horizontal gradient and vertical gradient of the grayscale image, and calculating the gradient magnitude value of each pixel point according to the horizontal gradient and vertical gradient includes:

[0051] Use the Sobel operator to calculate the horizontal gradient G x (x, y) and the vertical gradient G y (x, y):

[0052]

[0053] where S x (i, j) and S y (i, j) are the convolution kernels of the Sobel operator:

[0054]

[0055] Calculate the gradient magnitude value G(x, y) of each pixel point in the image:

[0056]

[0057] Further, the determining the contour edge points according to the gradient magnitude value of each pixel point; determining the outer radius and inner radius of the annular surrounding rock according to the contour edge points includes:

[0058] Set a threshold, and mark the pixel points higher than the threshold as the contour edge points E(x, y):

[0059]

[0060] where θ is the threshold, which is determined by manual optimization;

[0061] The contour E(x i , y j ) is circular. Calculate the coordinate interpolation at different x at the same y coordinate, and take the maximum value as the radius of the circular cavity:

[0062] r = max|E(x i , y j ) - E(x i , y j+n )|;

[0063] In subsequent image processing, ignore the circular cavity area and only process the annular surrounding rock part, where the inner radius r j = r + 1; as Figure 2 shown;

[0064] Normalize all the processed images. By translation and cropping, make all the images into squares of the same size (the number of pixels in the side length must be odd). The center point of the square is the dot in the inner circle of the annular surrounding rock, and ensure that the center of the circular cavity in the image is located at the center of the image to avoid obtaining null values during the subsequent conversion between polar coordinates and rectangular coordinates. Take half of the side length of the square as the outer radius r of the annular surrounding rock 0 .

[0065] Further, S102: For each pixel point on circles with different radii, convert from polar coordinates to rectangular coordinates in the order from 0° to 360°, and obtain the rectangular coordinates of all pixel points on circles with different radii, including:

[0066] Take a single pixel point in the image as a unit, with the center of the image (x r , y r ) as the origin, and the outer radius r of the annular surrounding rock 0 as the polar coordinate radius. Increase by 1° each time within the range of 0 - 360°. Through the conversion formula between polar coordinates and rectangular coordinates, calculate the rectangular coordinates of all pixel points on the pixel circle with a radius of r 0 , and obtain the pixel value of this point according to its coordinates. Conversion formula:

[0067] x = x r + r 0 cos(α)

[0068] y = y r + r 0 sin(α).

[0069] Among them, if the x and y values are not integers, perform rounding processing.

[0070] Further, S103: As Figure 3 shown, according to the rectangular coordinates of all pixel points of each circle, construct a pixel rectangle bar corresponding to each circle; the order of pixel points from 0° to 360° in the circle is the order of pixel points from left to right in the pixel rectangle bar; each circle obtains a pixel rectangle bar, including:

[0071] Arrange the pixel points horizontally in the order of acquisition from 0 - 360°, with coordinates (0, 0), (1, 0)…(l, 0) respectively, and assign their corresponding pixel values;

[0072] Start from the outer radius r of the annular surrounding rock 0 and repeat the pixel acquisition and horizontal arrangement and recombination process by reducing one unit each time. When the radius is r iWhen it is, the rearranged coordinates are: (0, i), (1, i) … (m, i), until it is reduced to the inner radius r of the annular surrounding rock j up to this point, the rearranged coordinates are: (0, n), (1, n) … (n, j).

[0073] Furthermore, S104: Splice the pixel rectangular strips in order from the smallest to the largest circle radius, from top to bottom in sequence to obtain a stepped reconstructed image; perform interpolation processing on the stepped reconstructed image to obtain a reconstructed rectangular image, including:

[0074] In the annular surrounding rock area, for the radius r j < r i < r 0 , according to the circumference calculation formula of the circle, it can be obtained that: n < m < l. Therefore, the image constructed based on this result is a stepped reconstructed image. To construct a rectangular image, interpolation processing needs to be performed on the stepped reconstructed image, and pixel values are assigned to the interpolated pixel points;

[0075] Taking the number of pixels l + 1 obtained from the pixel circle with radius r 0 when as a benchmark, perform interpolation on other rows with the number of pixels less than l + 1. For example, when the radius is r i when, the interpolation number and interpolation interval of the pixel circle are:

[0076] a i = l - m;

[0077] wherein, a i is the interpolation number, rounded to an integer; b i is the interpolation interval, and m is the total number of pixel points obtained from the pixel circle with radius r i when.

[0078] Starting from the starting point (0, i), perform interpolation every b i pixel points. If after performing a i-1 times of interpolation, the number of subsequent pixel points is less than b i , then directly perform interpolation after the original (m, i) point.

[0079] The pixel value at the interpolated pixel point takes the average value of the pixel values of the four pixel points above, below, left, and right of it:

[0080]

[0081] According to the interpolated pixel point coordinates and their pixel values, the image can be reconstructed, and its size is

[0082] (n + 1) × (j + 1).

[0083] Further, for the reconstructed rectangular image, performing duplicate region detection and removing overlapping regions to obtain a panoramic image of the drill hole, including:

[0084] Reconstruct the image according to the rearranged pixel point coordinates and their pixel values, arrange them in the extraction order from the video, starting from the first image, detect and remove the overlapping parts between every two adjacent images, and then splice all the images to form the panoramic image of the entire drill hole.

[0085] Further, as shown in FIGS. 4(a) and 4(b), the detecting and removing the overlapping parts between every two adjacent images includes:

[0086] In the order of extracting images in the drill hole video, the shooting time of S1 is earlier than that of S2;

[0087] Perform grayscale processing on the reconstructed image, and retrieve the overlapping part in S2 through row b of image S1. j Starting from row d in S2, calculate the interpolation ΔG of each pixel point in row d 0 with each pixel point in row b 0 : j ΔG i×0 :

[0088] ΔG i×0 =|G(a i ,b j ) - G(c i ,d 0 )|;

[0089] wherein, G(a i ,b j ) represents the grayscale value of each pixel point (a i ,b j ); i ∈ [0, n];

[0090] When the interpolation ΔG i between the pixel point (a j ,b i ) and the pixel point (c 0 ,d i×0 ) is less than 20, determine that the pixel point (a i ,b j ) and the pixel point (c i ,d 0 ) are similar points, and calculate the similarity rate X j between row b 0 and row d i×0 :

[0091]

[0092] wherein, p is for row d0 The number of similarity points in a row;

[0093] If b of S1 j The row and d in S2 0 The similarity rate X of the row i×0 Is less than 95%, it is determined as non-repetitive, and continue to calculate b of S1 j The row and d in S2 1 The repetition rate X between the rows i×1 , to determine whether there is repetition, until the repetition rate X between b of S1 j The row and a certain row d in S2 c Is reached 95%, it is determined that from d in S2 i×c The row to d c The row 0 The row (d c , d c-1 , d c-2 , …, d 0 ) belongs to the repeated area. After deleting the repeated area, splice S1 and S2. If b of S1 j The row is not repeated with any row in S2, directly splice S1 and S2.

[0094] Embodiment 2

[0095] This embodiment provides a drilling peep intelligent panoramic processing system based on image processing, including:

[0096] An image processing module, which is configured to: obtain the peep video in the drill hole, perform image enhancement processing on each frame of the image in the peep video; perform edge detection processing on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock;

[0097] A coordinate conversion module, which is configured to: take a single pixel point in the image as a unit, start from the outer circle of the annular surrounding rock, reduce one unit of pixel points each time until it reaches the inner circle of the annular surrounding rock, and get a circle each time it is reduced. Finally, get circles with different radii; convert each pixel point of each circle from polar coordinates to rectangular coordinates in the order from 0 degrees to 360 degrees to obtain the rectangular coordinates of all pixel points of each circle;

[0098] A rectangular bar construction module, which is configured to: construct a pixel rectangular bar corresponding to each circle according to the rectangular coordinates of all pixel points of each circle; the order of pixel points from 0 degrees to 360 degrees in the circle is the order of pixel points from left to right in the pixel rectangular bar; each circle gets a pixel rectangular bar;

[0099] A panoramic image reconstruction module, which is configured to: splice pixel rectangular bars in ascending order of the circle radius from top to bottom to obtain a stepped reconstruction image; perform interpolation processing on the stepped reconstruction image to obtain a reconstructed rectangular image; perform duplicate region detection on the reconstructed rectangular image and remove overlapping regions to obtain a panoramic image of the drill hole.

[0100] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent panoramic processing method for drilling hole voyeurism based on image processing, characterized in that: include: Obtain the borehole peep video, and perform image enhancement processing on each frame of the peep video; Perform edge detection on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock; Take a single pixel in the image as a unit, start from the outer circle of the annular surrounding rock, reduce the pixel by one unit each time until it reaches the inner circle of the annular surrounding rock, and obtain a circle each time, and finally obtain circles with different radii; convert each pixel of the circles with different radii from polar coordinates to rectangular coordinates in the order from 0 degrees to 360 degrees, and obtain the rectangular coordinates of all pixel points of the circles with different radii; According to the rectangular coordinates of all the pixels of each circle, a pixel rectangle strip corresponding to each circle is constructed; the order of the pixels from 0 degrees to 360 degrees in the circle is the order of the pixels from left to right in the pixel rectangle strip; each circle gets a pixel rectangle strip; The pixel rectangular strips are stitched from top to bottom in the order of the circle radius from small to large to obtain a stepped reconstructed image; the stepped reconstructed image is interpolated to obtain a reconstructed rectangular image; the reconstructed rectangular image is detected for repeated areas, and the overlapping areas are removed to obtain a panoramic image of the borehole.

2. The method for drilling hole peek intelligent panoramic processing based on image processing according to claim 1, characterized in that: Perform image enhancement processing on each frame of the peek video, including: Consider the original image as I1(x i ,y i ), expressed by the following formula: I1(x i ,and i )=L1(x i ,and i )*R1(x i ,and i ); Among them, R1(x i ,y i ) is the reflection component; L1(x i ,y i ) is the illumination component, * is the convolution operation; The new illumination component is obtained by filtering the original image through a two-dimensional Gaussian function: Among them, L2(x i ,y i ) is the illumination component after filtering, σ is the standard deviation of the Gaussian function; By taking multiple different standard deviation values ​​σ in the Gaussian function, the multi-scale reflection component R can be obtained. MSR (x i ,y i ): Among them, w j are weights of different scales, w j for Considering the three scales of high, medium, and low, σ takes the values ​​of 64, 128, and 256 here; By transforming the reflected component R2(x i ,y i ) has a pixel value in the range of 0 to 255: So as to further obtain the enhanced image I2(x,y): ln(I2(x i ,y i ))=ln(L2(x i ,y i ))+ln(R2(x i ,y i ))。 3. The method for intelligent panoramic processing of borehole peek based on image processing according to claim 1, characterized in that: Perform edge detection on the enhanced image to determine the outer and inner radii of the annular surrounding rock, including: Grayscale the enhanced image I2(x,y) and convert it into a grayscale image I_gray(x,y); Calculate the horizontal gradient and vertical gradient of the grayscale image, and calculate the gradient amplitude value of each pixel based on the horizontal gradient and vertical gradient; According to the gradient amplitude value of each pixel point, the contour edge point is determined; according to the contour edge point, the outer circle radius and the inner circle radius of the annular surrounding rock are determined.

4. The method for drilling hole peek intelligent panoramic processing based on image processing as claimed in claim 3, characterized in that: The step of calculating the horizontal gradient and the vertical gradient of the grayscale image and calculating the gradient amplitude value of each pixel point according to the horizontal gradient and the vertical gradient includes: Use the Sobel operator to calculate the horizontal gradient G of the grayscale image I_gray(x,y) x (x,y) and the vertical gradient G y (x,y): Among them, S x (i,j) and S y (i,j) is the convolution kernel of the Sobel operator: Calculate the gradient magnitude G(x,y) of each pixel in the image:

5. The method for intelligent panoramic processing of borehole peek based on image processing according to claim 3 is characterized in that: Determining the contour edge point according to the gradient amplitude value of each pixel point; According to the contour edge points, determine the outer radius and inner radius of the annular surrounding rock, including: Set the threshold and mark the pixels above the threshold as contour edge points E(x,y): Among them, θ is the threshold, which is determined by manual optimization; Contour E(x i ,y j ) is a circle, calculate the interpolation of coordinates at different x positions on the same y coordinate, and take the maximum value as the radius of the circular cavity: r=max|E(x i ,y j )-E(x i ,y j+n )|; The inner radius of the ring surrounding rock is r j = r + 1; All processed images are standardized, and all images are made into squares of uniform size through translation and cropping. The center point of the square is the dot of the inner circle of the annular surrounding rock, and half of the side length of the square is the outer circle radius r0 of the annular surrounding rock.

6. The method for intelligent panoramic processing of borehole peek based on image processing according to claim 1, characterized in that: Convert each pixel point of circles with different radii from polar coordinates to rectangular coordinates in the order from 0 degrees to 360 degrees to obtain the rectangular coordinates of all pixel points of circles with different radii, including: Take a single pixel in the image as a unit and take the image center (x r ,y r ) is the origin, the outer radius of the ring surrounding rock r0 is the polar coordinate radius, and it increases by 1° each time within the range of 0-360°. The rectangular coordinates of all pixel points on the pixel circle with a radius of r0 are calculated through the conversion formula between polar coordinates and rectangular coordinates, and the pixel value of the point is obtained according to its coordinates; conversion formula: x=x r +r0 cos(α) y=y r +r0 sin(α); If the x and y values ​​are non-integer, they will be rounded.

7. The method for intelligent panoramic processing of borehole peek based on image processing according to claim 1, characterized in that: According to the rectangular coordinates of all the pixel points of each circle, a pixel rectangle strip corresponding to each circle is constructed; The order of pixels from 0 to 360 degrees in the circle is the order of pixels from left to right in the pixel rectangle; Each circle gets a rectangular strip of pixels consisting of: Arrange the pixels horizontally in the order of acquisition from 0-360°, with coordinates of (0, 0), (1, 0) ... (l, 0), and assign corresponding pixel values; Starting from the outer radius r0 of the ring surrounding rock, the pixel acquisition and horizontal arrangement and reorganization process is repeated each time a unit is reduced. When the radius is r i When the coordinates are rearranged, they are: (0, i), (1, i) ... (m, i), until they are reduced to the inner radius r of the ring surrounding rock. j So far, the rearranged coordinates are: (0, n), (1, n)...(n, j).

8. The method for intelligent panoramic processing of borehole peek based on image processing according to claim 1, characterized in that: The pixel rectangular strips are stitched together from top to bottom in the order of the circle radius from small to large to obtain a stepped reconstructed image; The staircase reconstructed image is interpolated to obtain a reconstructed rectangular image, including: In the annular surrounding rock area, the radius r j < r i < r0. According to the circumference calculation formula of a circle, it can be obtained that: n < m < l. Therefore, the image constructed based on this result is a stepped reconstruction image. To construct a rectangular image, interpolation processing needs to be performed on the stepped reconstruction image, and pixel values are assigned to the interpolated pixel points; Taking the number of pixels l+1 obtained by the pixel circle when the radius is r0 as the benchmark, interpolate the rows where the number of pixels is less than l+1. For example, when the radius is r i The number of pixel circle interpolation and the interpolation interval are: a i =l-m; Among them, a i is the number of interpolation values, rounded to the nearest integer; b i is the interpolation interval, m is the radius r i The total number of pixels obtained by the pixel circle at the time; Starting from the starting point (0,i), every interval b i Pixels are interpolated once. If a i-1 After the interpolation, the number of subsequent pixels is less than b i , then interpolation is performed directly after the original point (m,i); The pixel value at the interpolation pixel point is the average value of the pixel values ​​of the four pixels above, below, left and right: The image can be reconstructed based on the interpolated pixel coordinates and their pixel values, and its size is (n+1)×(j+1).

9. The method for intelligent panoramic processing of borehole peek based on image processing according to claim 1, characterized in that: The reconstructed rectangular image is subjected to repeated area detection, and the overlapping area is removed to obtain a panoramic image of the borehole, including: Reconstruct the image according to the rearranged pixel coordinates and their pixel values, arrange them in the order of extraction from the video, start from the first image, detect and remove the overlapping parts between every two adjacent images, and then splice all the images to form a panoramic image of the entire borehole; The detecting and removing the overlapping part between every two adjacent images comprises: In the order of extracting images from the drilling video, S1 was shot earlier than S2; The reconstructed image is grayed out by using the b j The overlapping part in S2 is retrieved by row; starting from row d0 in S2, the overlap between each pixel in row d0 and b is calculated. j The interpolation ΔG of each pixel in the row i×0 : ΔG i×0 =|G(a i ,b j )-G(c i ,d0)|; Among them, G(a i ,b j ) represents each pixel (a i ,b j )’s grayscale value; i∈[0,n]; When the pixel (a i ,b j ) and pixel (c i ,d0) between the interpolation ΔG i×0 When it is less than 20, the pixel (a i ,b j ) and pixel (c i ,d0) is a similar point, calculate b j The similarity X between row d0 and row d1 i×0 : Among them, p is the number of similar points in row d0; If S1's b j The similarity X between row d0 and row d0 in S2 i×0 If it is less than 95%, it is considered as non-repetitive and the calculation of b of S1 is continued. j The repetition rate X between rows and rows d1 in S2 i×1 , determine whether to repeat until the b of S1 is detected for the first time j row and a row d in S2 c The repetition rate between i×c When it reaches 95%, it is determined that S2 c Rows from d0 to d1 belong to the repeated region. After deleting the repeated region, S1 and S2 are concatenated. If b of S1 j If the row does not overlap with any row in S2, S1 and S2 are directly concatenated.

10. The drilling peek intelligent panoramic processing system based on image processing is characterized by: include: An image processing module is configured to: obtain a borehole peep video, and perform image enhancement processing on each frame of the peep video; Perform edge detection on the enhanced image to determine the outer radius and inner radius of the annular surrounding rock; The coordinate conversion module is configured as follows: taking a single pixel point in the image as a unit, starting from the outer circle of the annular surrounding rock, reducing the pixel point by one unit each time until it is reduced to the inner circle of the annular surrounding rock, obtaining a circle each time it is reduced, and finally obtaining circles of different radii; converting each pixel point of each circle from polar coordinates to rectangular coordinates in the order from 0 degrees to 360 degrees, and obtaining the rectangular coordinates of all pixel points of each circle; A rectangular strip construction module is configured to: construct a pixel rectangular strip corresponding to each circle according to the rectangular coordinates of all pixel points of each circle; the order of the pixel points from 0 degrees to 360 degrees in the circle is the order of the pixel points from left to right in the pixel rectangular strip; each circle obtains a pixel rectangular strip; The panoramic image reconstruction module is configured as follows: pixel rectangular strips are stitched in order from top to bottom in the order of circle radius from small to large to obtain a stepped reconstructed image; the stepped reconstructed image is interpolated to obtain a reconstructed rectangular image; and repeated area detection is performed on the reconstructed rectangular image to remove overlapping areas to obtain a panoramic image of the borehole.

Images