A method and system for extracting the profile of anchor drill holes based on profile geometric constraints
By using a contour geometry constraint-based method and image processing technology to extract the anchor hole contour, the problem of low efficiency and poor safety of manually determining the anchor hole location is solved. This achieves efficient and accurate identification of the anchor hole contour, improving the automation and safety of support operations.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-30
- Publication Date
- 2026-03-06
AI Technical Summary
In existing technologies, the location of anchor holes is determined manually, which results in low support efficiency and difficulty in ensuring safety. The process of extracting the anchor hole contour also involves non-effective contours, affecting accuracy and efficiency.
An anchor hole contour is determined by using a contour geometry constraint-based method. The anchor hole image is acquired by the camera and subjected to threshold segmentation, noise reduction and contrast enhancement. Canny edge detection and Hough line detection are used to determine the steel strip edge information. Combined with Hough circle detection and least squares fitting, the anchor hole contour is determined by the functional relationship between the distance between the camera and the steel strip.
It improves the accuracy and efficiency of anchor hole contour extraction, reduces interference from non-target contours, and enhances the automation and safety of roadway anchoring operations.
Smart Images
Figure CN116152483B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image processing, and in particular to a method and system for extracting the contour of anchor drill holes based on contour geometric constraints. Background Technology
[0002] Coal mine roadway formation mainly includes alternating operations of roadway cutting and roadway support. Among them, the alternating operation of roadway support accounts for about 70% of the roadway formation time. It mainly relies on manual determination of anchor drill hole positions and operation of single drilling rigs to complete the support work, resulting in low support efficiency and inability to guarantee personnel safety.
[0003] Improving the automation level of support systems has become an effective way to improve support efficiency and alleviate mining imbalance. Currently, the spatial location of anchor boreholes can be automatically determined using visual measurement methods; however, many ineffective contours exist during the anchor borehole contour extraction process, affecting the accuracy and efficiency of contour extraction. Therefore, research on anchor borehole contour extraction methods is of great significance for improving the efficiency and safety of support operations. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for extracting the contour of anchor drill holes based on contour geometry constraints, which can improve the accuracy of anchor drill hole contour extraction.
[0005] To achieve the above objectives, the present invention provides the following solution:
[0006] A method for extracting the contour of an anchor drill hole based on contour geometry constraints, comprising:
[0007] Use a camera to acquire images of the anchor drill holes on the steel strip;
[0008] The image of the anchor drill hole on the steel strip is preprocessed; the preprocessing includes: threshold segmentation, noise reduction and contrast enhancement.
[0009] The Canny edge detection method was used to determine the image edge information of the preprocessed anchor borehole image;
[0010] Based on the image edge information, the upper and lower edge line information of the steel strip in the image is determined using the Hough line detection method, and the upper and lower edge line information of the steel strip in the image is taken as the region of interest.
[0011] The circular contour within the region of interest is determined using a circle fitting method;
[0012] Based on the circular contour and contour geometric constraints, the contour of the anchor drill hole is determined; the contour geometric constraints are the corresponding functional relationship between the distance between the camera and the steel strip and the radius of the anchor drill hole; the camera is the same model as the camera used to acquire the image of the anchor drill hole on the steel strip.
[0013] Optionally, the threshold segmentation process employs the Otsu method.
[0014] Optionally, the noise reduction process employs a median filtering method.
[0015] Optionally, the circle fitting method is the Hough circle detection method.
[0016] Optionally, the process for determining the contour geometric constraints is as follows:
[0017] Images of the steel strip are acquired using a camera; the radius of the anchor drill hole on the steel strip image under different distance conditions is determined using image measurement methods, and the least squares method is used to fit the distance and the corresponding anchor drill hole radius to determine the functional relationship; the distance condition is the distance between the camera and the steel strip.
[0018] Optionally, the functional relationship is:
[0019] r1 = f(d);
[0020] Where d represents the distance between the camera and the steel strip, r1 represents the radius of the anchor drill hole in the acquired image, and f() represents the functional relationship.
[0021] An anchor borehole profile extraction system based on profile geometry constraints, comprising:
[0022] Anchor hole image acquisition module, used to acquire images of anchor holes on steel strips using a camera;
[0023] The image preprocessing module is used to preprocess the image of the anchor drill hole on the steel strip; the preprocessing includes: threshold segmentation, noise reduction and contrast enhancement.
[0024] The image edge information determination module is used to determine the image edge information of the preprocessed anchor borehole image using the Canny edge detection method.
[0025] The region of interest determination module is used to determine the upper and lower edge straight line information of the steel strip in the image based on the image edge information and the Hough line detection method, and to take the upper and lower edge straight line information of the steel strip in the image as the region of interest;
[0026] The circular contour determination module is used to determine the circular contour within the region of interest using a circle fitting method.
[0027] The anchor hole contour determination module is used to determine the anchor hole contour based on a circular contour and contour geometric constraints; the contour geometric constraints are the corresponding functional relationship between the distance between the camera and the steel strip and the radius of the anchor hole; the camera is the same model as the camera used to acquire the image of the anchor hole on the steel strip.
[0028] An anchor borehole contour extraction system based on contour geometry constraints includes: at least one processor, at least one memory, and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the anchor borehole contour extraction method based on contour geometry constraints is implemented.
[0029] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0030] The present invention provides a method and system for extracting anchor borehole contours based on contour geometric constraints. By utilizing the upper and lower edge information of the steel strip, the straight line information of the upper and lower edges of the steel strip in the extracted image is effectively used as the region of interest (ROI), which effectively reduces the difficulty of image processing, speeds up image processing, and avoids interference from information other than the steel strip. The contour extraction method based on contour geometric constraints can effectively reduce non-target contours and improve the efficiency and accuracy of anchor borehole contour recognition. The present invention can effectively improve the accuracy and efficiency of automatic anchor borehole recognition and improve the efficiency of roadway anchoring operations. Attached Figure Description
[0031] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0032] Figure 1 A schematic diagram of the process for extracting the contour of an anchor drill hole based on contour geometry constraints provided by the present invention;
[0033] Figure 2 A schematic diagram of a camera capturing images of a steel strip;
[0034] Figure 3 This is a schematic diagram of the binarized image obtained by thresholding the acquired image;
[0035] Figure 4 This is a schematic diagram of the filtered image obtained using the median filtering method;
[0036] Figure 5 This is a schematic diagram obtained from edge detection processing;
[0037] Figure 6 This is a schematic diagram obtained from Hough line detection;
[0038] Figure 7 This is a schematic diagram of the circular hole obtained by circle fitting;
[0039] Figure 8 This is a schematic diagram of the anchor drill hole profile based on geometric constraints.
[0040] Figure 9 This is a schematic diagram of an anchor borehole contour extraction system based on contour geometry constraints provided by the present invention. Detailed Implementation
[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0042] The purpose of this invention is to provide a method and system for extracting the contour of anchor drill holes based on contour geometry constraints, which can improve the accuracy of anchor drill hole contour extraction.
[0043] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0044] Figure 1 This is a schematic diagram of the process for extracting the contour of an anchor drill hole based on contour geometric constraints provided by the present invention, as shown below. Figure 1 As shown, the present invention provides a method for extracting the contour of an anchor drill hole based on contour geometric constraints, comprising:
[0045] S101, using a camera to acquire images of the anchor drill holes on the steel strip. And as... Figure 2 As shown;
[0046] S102, preprocess the image of the anchor drill hole on the steel strip; the preprocessing includes: threshold segmentation, noise reduction and contrast enhancement.
[0047] As a specific embodiment, the threshold segmentation process uses the Otsu algorithm. In the Otsu algorithm, the global threshold of the image is set to K, the total number of pixels less than or equal to the threshold is num1, the total number of pixels greater than the threshold is num2, and the total number is num = num1 + num2. The mean value of all pixel values less than or equal to the threshold is small. m The mean of all pixel values greater than the threshold is large. m The mean value of all pixels in the entire image is global. m ,in:
[0048]
[0049]
[0050]
[0051] Therefore, the formula for between-class variance is: σ 2 =p1*[small m -globle m ] 2 +p2*[l arge m -globle m ] 2 ,in,
[0052]
[0053] n represents the number of pixels in the image; k represents the total number of pixels less than or equal to the threshold, which is equal to num1; pixelCount i Globle represents the pixel value of the i-th pixel. m This represents the average pixel value of the image.
[0054] The possible pixel values obtained by iterating through the image are used as a threshold T, such that σ 2 The T value that yields the maximum value is considered the most suitable threshold. Image thresholding is then performed accordingly, setting all pixels with values less than or equal to the threshold to 0, and setting all pixels with values greater than the threshold to the other pixel value of 1. This completes the image binarization process. Figure 3 As shown.
[0055] As a specific embodiment, the noise reduction process employs a median filtering method. Figure 4 As shown, the median filtering method processes binarized images, specifically including:
[0056] g(x,y)=median[f(xi,yi),...,f(x,y),...f(x+i,y+i)], i∈Z (1)
[0057] In the formula, (x, y) represents the center position of the window, and f(x, y) represents the value of the corresponding pixel. (Z is an integer representing a certain region. For example, Z = 1 means that the processing is performed within a 3*3 neighborhood centered at (x, y). median means that the middle gray value is taken from the gray values of the pixels in parentheses. As mentioned above, Z = 1 means that there are a total of nine pixels in the 3*3 neighborhood. The middle value is g(x, y) = median(……..)).
[0058] S103, the Canny edge detection method is used to determine the image edge information of the preprocessed anchor borehole image. The image edge information is as follows: Figure 5 As shown.
[0059] S104, Based on the image edge information, the upper and lower edge line information of the steel strip in the image is determined using the Hough line detection method, and the upper and lower edge line information of the steel strip in the image is taken as the region of interest, and so on. Figure 6 As shown.
[0060] S105, the circular contour within the region of interest is determined using a circle fitting method, and as shown... Figure 7 As shown;
[0061] As a specific embodiment, the circle fitting method is the Hough circle detection method. The Hough circle detection method is used to fit the anchor drill hole circle, determining the center coordinates and radius. Its principle is as follows:
[0062] The formula for a circle is: (xa) 2 +(yb) 2 =r 2 (2)
[0063] In equation (2), x and y are the coordinates of the edge point; (a, b) are the coordinates of the center of the circle; and r is the radius.
[0064] Suppose there is an edge point (x, y), then the circle passing through this edge point satisfies (xa). 2 +(yb) 2 =r 2 Furthermore, there are infinitely many circles that satisfy this condition. Since a, b, and r are all variables, they can be represented by a three-dimensional parameter space abr (where a is the x-coordinate, b is the y-coordinate, and r is the y-coordinate):
[0065] When r = 0, from (xa) 2 +(yb) 2 =r 2 We can obtain a = x and b = y, where (a, b, r) represents a point in the three-dimensional parameter space;
[0066] When r = 1, from (xa) 2 +(yb) 2 =r 2 A set of values can be calculated, all of which satisfy (xa). 2 +(yb) 2 =r 2 And it forms a circle in the three-dimensional parameter space;
[0067] Similarly, different circles can be obtained for different r values, which, when drawn in parameter space, form a conical surface.
[0068] Different edge points will result in different conical surfaces. If two conical surfaces intersect at a point, then that point represents a circle that passes through two edge points at the same time. The center coordinates a, b and the radius r can be determined based on the coordinates of that point. In this embodiment, a preset threshold is set. If the number of conical surfaces intersecting at a point exceeds the preset threshold, then the set of parameters is considered to be a circle.
[0069] S106, Based on the circular profile and geometric constraints, determine the anchor hole profile, and as follows: Figure 8 As shown; the contour geometric constraint is a function relating the distance between the camera and the steel strip to the radius of the anchor drill hole; the camera is the same model as the camera used to acquire images of the anchor drill hole on the steel strip.
[0070] The process for determining the contour geometric constraints is as follows:
[0071] Images of the steel strip are acquired using a camera; the radius of the anchor drill hole on the steel strip image under different distance conditions is determined using image measurement methods, and the least squares method is used to fit the distance and the corresponding anchor drill hole radius to determine the functional relationship; the distance condition is the distance between the camera and the steel strip.
[0072] Under laboratory conditions, the distance between the camera and the steel strip was adjusted, and images of the steel strip were acquired at different distances using the same image acquisition device. Image processing methods were used to measure the radius of the anchor drill holes in the images at different distances, and a distance-radius function relationship was fitted based on the least squares method. This function relationship allows us to obtain the range of anchor drill hole radii in the images near the corresponding distances, which is then used as a constraint to filter out invalid contours.
[0073] The functional relationship is as follows:
[0074] r1 = f(d);
[0075] Where d represents the distance between the camera and the steel strip, r1 represents the radius of the anchor drill hole in the acquired image, and f() represents the functional relationship.
[0076] Figure 9 This is a schematic diagram of an anchor borehole contour extraction system based on contour geometry constraints provided by the present invention, as shown below. Figure 9 As shown, the present invention provides an anchor borehole contour extraction system based on contour geometry constraints, comprising:
[0077] Anchor hole image acquisition module 901 is used to acquire images of anchor holes on steel strips using a camera;
[0078] Image preprocessing module 902 is used to preprocess the image of the anchor drill hole on the steel strip; the preprocessing includes: threshold segmentation processing, noise reduction processing and contrast enhancement processing;
[0079] The image edge information determination module 903 is used to determine the image edge information of the preprocessed anchor borehole image using the Canny edge detection method;
[0080] The region of interest determination module 904 is used to determine the upper and lower edge straight line information of the steel strip in the image based on the Hough line detection method according to the image edge information, and to take the upper and lower edge straight line information of the steel strip in the image as the region of interest;
[0081] The circular contour determination module 905 is used to determine the circular contour within the region of interest using a circle fitting method.
[0082] The anchor hole contour determination module 906 is used to determine the anchor hole contour based on the circular contour and contour geometric constraints; the contour geometric constraints are the corresponding functional relationship between the distance between the camera and the steel strip and the radius of the anchor hole; the camera is the same model as the camera that acquires the image of the anchor hole on the steel strip.
[0083] In order to execute the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, the present invention also provides an anchor borehole contour extraction system based on contour geometric constraints, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, wherein when the computer program instructions are executed by the processor, the anchor borehole contour extraction method based on contour geometric constraints is implemented.
[0084] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.
[0085] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A contour geometry constraint based anchor hole contour extraction method, characterized in that, The method comprises the following steps: acquiring an anchor hole image on a steel strip by using a camera; preprocessing the anchor hole image on the steel strip; the preprocessing comprises threshold segmentation processing, noise reduction processing, and contrast enhancement processing; determining image edge information of the preprocessed anchor hole image by using a Canny edge detection method; determining upper and lower edge straight line information of the steel strip in the image based on a Hough straight line detection method according to the image edge information, and taking the upper and lower edge straight line information of the steel strip in the image as a region of interest; determining a circular contour in the region of interest by using a circle fitting method; determining an anchor hole contour based on a contour geometric constraint according to the circular contour; the contour geometric constraint is a corresponding functional relationship between a distance between the camera and the steel strip and a radius of the anchor hole; the camera is the same as the camera used for acquiring the anchor hole image on the steel strip; the contour geometric constraint is determined in the following process: collecting a steel strip image by using a camera; determining the radius of the anchor hole on the steel strip image under different distance conditions by using an image measurement method, and fitting the distance and the corresponding radius of the anchor hole by using a least square method to determine the functional relationship; the distance condition is the distance between the camera and the steel strip; the functional relationship is: ； wherein d represents the distance between the camera and the steel strip, represents the radius of the anchor hole on the acquired image, f () represents a functional relationship.
2. The anchor hole profile extraction method based on contour geometric constraints according to claim 1, characterized in that, the threshold segmentation processing adopts the Otsu method.
3. The anchor hole profile extraction method based on contour geometric constraints according to claim 1, characterized in that, the noise reduction processing adopts the median filtering method.
4. The anchor hole profile extraction method based on contour geometric constraints according to claim 1, characterized in that, the circle fitting method is the Hough circle detection method.
5. A contour geometry constraint based anchor hole contour extraction system for implementing a contour geometry constraint based anchor hole contour extraction method according to any one of claims 1-4, characterized in that, The method comprises the following steps: an anchor hole image acquisition module is configured to acquire an anchor hole image on a steel strip by using a camera; an image preprocessing module is configured to preprocess the anchor hole image on the steel strip; the preprocessing comprises threshold segmentation processing, noise reduction processing, and contrast enhancement processing; an image edge information determination module is configured to determine image edge information of the preprocessed anchor hole image by using a Canny edge detection method; a region of interest determination module is configured to determine upper and lower edge straight line information of the steel strip in the image based on a Hough straight line detection method according to the image edge information, and take the upper and lower edge straight line information of the steel strip in the image as a region of interest; a circular contour determination module is configured to determine a circular contour in the region of interest by using a circle fitting method; an anchor hole contour determination module is configured to determine an anchor hole contour based on a contour geometric constraint according to the circular contour; the contour geometric constraint is a corresponding functional relationship between a distance between the camera and the steel strip and a radius of the anchor hole; the camera is the same as the camera used for acquiring the anchor hole image on the steel strip.
6. A contour geometry constraint based anchor hole contour extraction system, characterized in that, The method comprises the following steps: at least one processor, at least one memory, and computer program instructions stored in the memory, when the computer program instructions are executed by the processor, realize a contour geometric constraint-based anchor hole contour extraction method according to any one of claims 1-4.