CN113838011A - Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient - Google Patents
Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient Download PDFInfo
- Publication number
- CN113838011A CN113838011A CN202111067115.9A CN202111067115A CN113838011A CN 113838011 A CN113838011 A CN 113838011A CN 202111067115 A CN202111067115 A CN 202111067115A CN 113838011 A CN113838011 A CN 113838011A
- Authority
- CN
- China
- Prior art keywords
- rock
- color
- gradient
- channel
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a system, a terminal and a readable storage medium for acquiring rock block degree and/or distribution rules based on digital image color gradients. The method provides a new method for optimizing train of thought about rock boundary feature extraction and rock block degree calculation, and simultaneously can draw a frequency histogram and an accumulative distribution curve according to the actual equivalent diameter, visually display the quantity and distribution condition of the rock block degree, promote the improvement of the rock block degree calculation method and realize the effectiveness research and application of the digital image technology in geotechnical engineering.
Description
Technical Field
The invention belongs to the technical field of rock fragment or rock material particle boundary and block degree correlation technology in geotechnical engineering, and particularly relates to a method, a system, a terminal and a readable storage medium for acquiring rock block degree and/or distribution rule based on digital image color gradient.
Background
Rock breaking is one of important process flows in the process of mine resource development. In most non-coal mines in China, the blasting technology is often adopted to crush ore bodies. In rock blasting engineering, the blasting effect of ore rock is measured by indexes such as the rock block size and the like, and meanwhile, the operation efficiency of loading, transportation, secondary crushing and the like in the production process of mines is also influenced. The research on the rock block size in the crushed rock is helpful for promoting the development of various problems such as the selection of a crushing method, the research on a crushing mechanism, the proposal of a mining scheme and the like in the enterprise production. In order to ensure the construction safety, the method can also carry out quantitative evaluation on the flying stone lumpiness generated in the blasting process, thereby being convenient for formulation of a safety emergency plan and the proposal of related safety standards. The cause of the rock fragments is generated by cutting or penetrating of cracks which exist in the rock fragments or are newly generated by external force, and from the viewpoint, the size of the rock fragments can reflect the cuttability of the rock; on the economic aspect, the initial lump size of broken rock is little, then is convenient for subsequent ore rock transportation, ore dressing, has improved the economic input cost of enterprise very appreciably. Therefore, the research on the rock block size distribution rule can improve the parameters of the blasting process, provide a basis for making a mining scheme and a safety emergency rescue plan, and have important significance for saving the production investment cost of enterprises and improving the economic benefit.
Rock block size is one of the main evaluation parameters of the blasting effect of the rock, and experts and scholars at home and abroad carry out a great deal of research on the rock block size for a long time, and generally, the method for evaluating the rock block size distribution can be basically divided into a direct method and an indirect method. The direct method directly tests the rock block size characteristic through a certain device and instrument, and the three commonly used methods are respectively: the method comprises a screening method, a secondary blasting rock block statistical method and a blasting pile measuring method, wherein the screening method is high in accuracy and more in application, but the screening method is often used as a correction means in the actual production process. The indirect method mainly comprises a data measurement method, a numerical simulation method, an empirical distribution function method and the like, wherein the data measurement method indirectly reflects the rock block degree rule according to indexes such as loading cycle time, crusher production capacity and the like, and the numerical simulation method simulates and calculates input parameters by a BLASAP model, a Harreis model, a BMMC blasting mathematical model and the like to obtain a corresponding rock block degree distribution rule.
The prior art rock boundary identification and blockiness calculation methods are as follows:
CN109544624A discloses a rock block image analysis system, which performs image processing such as graying, smoothing filtering, image segmentation and the like by obtaining RGB images of rock block, and calculates the volume of rock by using watershed algorithm. The technology does not visually present the corresponding area calculation result and accuracy when the shape of the rock target is irregular, and the adopted image processing technology is simple and cannot fully highlight the boundary characteristics of the rock object, so that the recognized rock target segmentation result is not ideal.
CN108305263B discloses an image statistical method for rock block degrees after blasting, which is to use photoshop software to carry out edge delineation on collected rock pictures, and then use the image processing technology in matlab to calculate and count the rock block degrees in the pictures. The technology needs to use software such as photoshop and matlab at the same time, the operation process is complex and time-consuming, more time and energy are needed to be consumed for processing a large number of pictures, and certain software operation proficiency requirements are provided for operators. And the method does not fully perform certain image processing on the acquired image, so that the characteristics of the target object in the image are not outstanding enough, and the interference on rock mass identification and calculation is caused.
Disclosure of Invention
The invention aims to solve the problem of calculating the block size of a rock block, and provides a method, a system, a terminal and a readable storage medium for acquiring the rock block size and/or the distribution rule based on the color gradient of a digital image. The method comprises the steps of identifying the color gradient of an original image of the rock fragment, identifying the boundary and the connected region of an object in the image, and taking the actual equivalent diameter of the connected region as an evaluation index of the rock fragment block degree. The method provides a new method for optimizing train of thought about rock boundary feature extraction and rock block size calculation, and can draw a frequency histogram and an accumulative distribution curve according to the actual equivalent diameter, so that the number and distribution condition of the rock block sizes are visually displayed, and the improvement of the rock block size calculation method and the effective research and application of the digital image technology in geotechnical engineering are promoted.
On one hand, the invention provides a rock block degree and/or distribution rule obtaining method based on digital image color gradient, which comprises the following steps:
s1: acquiring and reading a digital original color image of the rock fragment, and respectively constructing a single-channel data matrix by using three color values of R-G-B;
s2: respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color chart;
s3: fusing based on the three gradient color maps to obtain a single-channel color gradient map of the rock fragment;
s4: carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
s5: carrying out boundary extraction and identification on the binary image of the rock fragment to identify a connected region and form a rock boundary extraction image, wherein each complete closed region is a rock individual;
s6: and calculating the equivalent diameter of each individual rock in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock granularity by taking the actual equivalent diameter as a representation of the rock granularity of the rock fragment.
Wherein, the frequency histogram represents the occurrence frequency corresponding to each block degree of the rock; the cumulative distribution curve represents the sum of the frequencies of a certain block size and the following block sizes of the rock object.
Alternatively, the calculation formula of the color gradient value in step S2 is as follows:
in the formula, grayr、grayg、graybR, G, B pixels [ i, j ] in a single-channel data matrix, respectively]Corresponding to the calculated color gradient value ri,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value R in the R single-channel data matrixi+Δi,jRepresenting the target pixel [ i, j]The value of the next pixel point in the R single-channel data matrix after the same row is moved by the step length delta i; gi,j+ΔjRepresenting the target pixel [ i, j]In the same column, and the next pixel point shifted by step Δ j corresponds to the value in the G single-channel data matrix, Gi+Δi,jRepresenting the target pixel [ i, j]The value of the next pixel point in the G single-channel data matrix after the same row is moved by the step length delta i; bi,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value in the B single-channel data matrix, Bi+Δi,jRepresenting the target pixel [ i, j]And in the same row, the next pixel point after the movement by the step length delta i corresponds to the value in the B single-channel data matrix, and delta j and delta i are the difference step lengths taken in the horizontal direction and the vertical direction when the pixel gradient value is calculated respectively.
Optionally, the process of performing the fused single-channel color gradient map of the rock fragment based on the three gradient color maps in step S3 is as follows:
carrying out weighted average calculation on the three gradient color images to obtain a color gradient single-channel matrix;
visualizing the color gradient single-channel matrix to obtain a rock fragment color gradient single-channel diagram;
the weighting formula is as follows:
Grayij＝a1*grayr+a2*grayg+a3*grayb
Grayijrepresenting a color gradient single channel matrix; a is1、a2、a3Respectively represent R, G, B three-channel weights, and a1+a2+a3＝1； gradr、grayg、graybNamely the color gradient level matrix corresponding to the R, G, B gradient color map.
Optionally, in step S6, for each individual rock block in the rock block boundary extraction map, the process of calculating the equivalent diameter thereof is:
and determining a mass point Z corresponding to the connected region for each individual rock block, and calculating the area of the equivalent circle by taking the mass point Z as the center of the circle on the basis of the area of the connected region to obtain the equivalent diameter.
In a second aspect, the invention provides a method for acquiring rock block size and/or distribution rule based on digital image color gradient, which comprises:
the image acquisition module is used for acquiring digital original color images of the rock fragments;
the single-channel data matrix construction module is used for reading digital original color images of the rock fragments and respectively constructing single-channel data matrices by using three color values of R-G-B;
the gradient color image acquisition module is used for respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color image;
the rock fragment color gradient single-channel image acquisition module is used for performing fusion on the basis of the three gradient color images;
the binarization processing module is used for carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
the boundary extraction module is used for carrying out boundary extraction and identification on the binary image of the rock fragments to form a rock boundary extraction image, wherein each complete closed region is an individual rock;
and the calculating module is used for calculating the equivalent diameter of each rock individual in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock lumpiness by taking the actual equivalent diameter as a representation of the rock lumpiness.
In a third aspect, the present invention provides a terminal, comprising:
one or more processors;
a memory storing one or more programs;
the processor calls the program to perform:
a method for acquiring rock block degree and/or distribution rule based on digital image color gradient.
In a fourth aspect, the present invention provides a readable storage medium storing a computer program for execution by a processor to:
a method for acquiring rock block degree and/or distribution rule based on digital image color gradient.
Advantageous effects
The method comprises the steps of collecting digital original color images of rock fragments, and respectively constructing single-channel data matrixes according to color channels; calculating the color gradient value corresponding to each pixel point in the single-channel data matrix, and generating a gradient color map; and then fusion and binarization processing are carried out, wherein color gradient value calculation is carried out on image pixels, so that the contour characteristics of the image are more effectively retained, the edge gray level change of a rock object in the image is further strengthened, the layering sense of the object and the background is enhanced, and favorable conditions are provided for further extracting the image characteristics by image binarization. Calculating the irregular area of a connected region formed by the boundary through numerical software based on the binary image; the method comprises the steps of replacing an irregular area with an equivalent circle, determining the mass center of an image connected area, taking the mass center as the center of the equivalent circle, and taking the area of the connected area to be equal to the area of the equivalent circle, obtaining the equivalent diameter of the connected area through an area formula of the circle, and drawing a frequency histogram and a cumulative distribution curve according to the actual equivalent diameter, so that the frequency histogram and the cumulative distribution curve are used as characterization quantities related to the block sizes of rock blocks and rock materials, and the block size characteristics of the rock are described in a more aspect and all-round manner.
In conclusion, the invention provides an optimization idea about rock boundary feature extraction and a new method for rock block degree calculation, which visually displays the quantity and distribution condition of rock block degrees through a frequency histogram and a cumulative distribution curve, promotes the improvement of the rock block degree calculation method and realizes the effectiveness research and application of a digital image technology in geotechnical engineering. The invention is suitable for rock blasting engineering and tunneling work of a mining machine, has important significance for researching the procedures of loading, transportation, secondary crushing and the like in the production process, and can guide enterprises to make standards such as safe production and mining schemes, emergency rescue plans and the like, thereby improving the economic benefit of the enterprises on the whole.
Drawings
FIG. 1 is an overall flow chart of the rock boundary identification and blockiness calculation method of the present invention;
FIG. 2 (a) is a diagram of a rock fragment precursor according to an embodiment of the present invention;
in FIG. 2 (b)1～b3) A rock color channel map of an embodiment of the invention;
in FIG. 2 (c)1～c3) Is a color gradient map of a rock fragment according to an embodiment of the invention;
FIG. 2 (d) is a rock color gradient single-channel plot of an embodiment of the present invention;
FIG. 2 (e) is a binary graph of a rock boundary graph according to an embodiment of the present invention;
fig. 2 (f) is a diagram illustrating a result of identifying a rock mass connected region according to an embodiment of the present invention;
fig. 2 (g) is a frequency histogram and cumulative distribution curve of equivalent diameter of a rock mass according to an embodiment of the present invention.
Detailed Description
The method for acquiring the rock block size and/or the distribution rule based on the digital image color gradient can solve the problems of calculation of the rock block size and acquisition of the distribution rule in the rock blasting, tunneling engineering and other processes. The present invention will be further described with reference to the following examples.
Example 1:
the embodiment provides a rock block degree and/or distribution rule obtaining method based on digital image color gradient, which comprises the following steps:
s1: and acquiring and reading the digital original color image of the rock fragment, and respectively constructing a single-channel data matrix by using the R-G-B color values.
The method comprises the steps of utilizing a high-definition camera to conduct image acquisition on broken stones and debris generated in rock mechanics experiments conducted in laboratories or rock destruction of engineering sites, obtaining high-definition original-color images 1 of rock fragments, enabling the image color format to be an RGB mode, respectively representing red, green and blue color channels, and displaying the surface crushing degree and boundary characteristics of the rock fragments under a macroscopic condition through superposition of color channel values.
And then reading the digital original color images of the rock fragments to generate a single-channel data matrix. The digital original color image1 of the rock fragments collected in the step S1 is input into a computer, the computer reads the images and stores the images in a two-dimensional digital matrix form according to red, green and blue color channels, and two dimensions of a two-dimensional digital image matrix (single-channel data matrix) Array 1-3 respectively represent the width and height of the channel images. By generating a single-channel data matrix Array 1-3, the rock image characteristics are stored in a computer in the form of pixel value data so as to be convenient for further processing. The single-channel image matrices Array 1-3 are visualized to form images represented as color channel image images 2-4.
S2: respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes Array 4-6-gradr、gradg、gradbAnd visualizing the gradient level matrix to form color gradient map images 5-7 of the rock boundary.
Processing a single-channel data matrix Array 1-3 matrixed by color channel image images 2-4, performing differential calculation on corresponding values of each pixel point in the single-channel data matrix Array 1-3 to obtain corresponding color gradient values, and further forming a rock boundary color gradient matrix Array 4-6-grad by the gradient valuesr、gradg、gradbAnd visualizing the gradient level matrix to form color gradient image 5-7 of the rock boundary.
The formula for calculating the color gradient value is as follows:
in the formula, grayr、grayg、graybR, G, B pixels [ i, j ] in a single-channel data matrix, respectively]Corresponding to the calculated color gradient value ri,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value R in the R single-channel data matrixi+Δi,jRepresenting the target pixel [ i, j]The value of the next pixel point in the R single-channel data matrix after the same row is moved by the step length delta i; gi,j+ΔjRepresenting the target pixel [ i, j]In the same column, and the next pixel point shifted by step Δ j corresponds to the value in the G single-channel data matrix, Gi+Δi,jRepresenting the target pixel [ i, j]The value of the next pixel point in the G single-channel data matrix after the same row is moved by the step length delta i; bi,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value in the B single-channel data matrix, Bi+Δi,jRepresenting the target pixel [ i, j]Go in the same row andand the next pixel point after the step length delta i is moved corresponds to the value in the B single-channel data matrix, and delta j and delta i are the difference step lengths taken in the horizontal direction and the vertical direction when the pixel gradient value is calculated respectively.
S3: and performing fusion on the basis of the three gradient color maps to obtain the rock fragment color gradient single-channel map. In the embodiment, images 5-7 are selected to be subjected to channel weighted average calculation of color gradient images, and three color channel gradient matrixes gradr、gradg、gradbRespectively multiplied by a weight a1、a2、a3And summing the weight product results to obtain a fracture color gradient single-channel matrix Array 7-GrayijAnd simultaneously generating a corresponding rock fragment color gradient single-channel image 8. The corresponding formula is as follows:
Grayij＝a1*grayr+a2*grayg+a3*grayb
Grayijrepresenting a color gradient single channel matrix; a is1、a2、a3Respectively represent R, G, B three-channel weights, and a1+a2+a3＝1； gradr、grayg、graybNamely the color gradient level matrix corresponding to the R, G, B gradient color map.
S4: and carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map.
Wherein the color gradient single-channel digital matrix Gray is applied to the generated rock fragmentsijSetting a threshold value T, and if the color gradient single-channel matrix represents a pixel point [ i1, j1 ]]If the corresponding value is greater than the threshold value T, the value of the point is assigned to be 0; if the pixel point is [ i2, j2 ]]And if the corresponding value is less than or equal to T, assigning the point value as 1, thereby further highlighting the boundary characteristics of the rock, simultaneously storing the position and distribution condition of the contour of the rock in a computer, selecting the threshold value T according to the overall characteristics of the color map, and achieving the target effect of good segmentation effect on the boundary of the rock fragment and the corresponding background thereof after binarization processing. By binarizing the single-channel image, a computer generates a rock boundary graphThe binary image 9.
Wherein, the binarization formula is as follows:
s5: and carrying out boundary extraction and identification on the binary image of the rock fragment to identify a connected region, and forming a rock boundary extraction image, wherein each complete closed region is an individual rock. The boundary detection and the identification of the connected region are carried out on the individual rock blocks in the rock block boundary color gradient binary image9, and the identified connected region boundary is drawn.
S6: and calculating the equivalent diameter of each individual rock in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and an accumulated distribution curve of the rock block degree by taking the actual equivalent diameter as a characteristic quantity of the rock block degree.
In the embodiment, the rock boundaries are identified and extracted through a bwbounderies function in MatLab software, in order to more accurately complete feature extraction, 4 adjacent connection numbers are selected, a target pixel region is traversed, and extraction pixel points and corresponding coordinate positions (X) of the rock boundaries are obtainedi,Yi) (ii) a Determining a particle Z of the connected region through a regionprops function; circularly traversing boundary pixel points (X) of connected regionsi,Yi) Calculating the boundary-based connected region area SA(ii) a Using mass point Z as center of circle and equivalent circle area SOAnd (3) carrying out equivalent replacement, wherein the calculation formula is as follows:
wherein D isiIs the equivalent diameter corresponding to the equivalent circle.
In this embodiment, the process of obtaining the actual equivalent diameter is as follows: the method for determining the proportion of the size of the rock block object to the actual size in the image comprises the following steps: and setting a reference object, obtaining a scale of the rock image according to the proportion of the actual length of the reference object to the length in the picture, calculating the actual equivalent diameter D by using the scale as an evaluation parameter of the size of the rock fragment block degree, and drawing a frequency histogram and a cumulative distribution curve image11 related to the rock fragment block degree. Wherein, the frequency histogram represents the quantity of a certain block degree in the acquired rock block diagram; the cumulative distribution curve is represented as the distribution of rock block sizes in a certain range.
Application example:
in the following, the rock is taken from a laboratory as an experimental object for example application.
The strength and deformation characteristics of the rock are important mechanical properties of the rock, and can be characterized by measuring relevant parameters through a laboratory rock mechanical experiment. A rock fracturing experiment is carried out in a certain laboratory, the size of the rock block size of the broken rock blocks after rock fracturing is calculated by the method, and the image processing and calculating processes are shown in figure 2.
The method comprises the following application steps:
And 2, reading the rock block boundary graph by the computer to generate an image digital matrix. And (3) inputting the digital original color image of the rock boundary acquired in the step (S1) into a computer, reading the image by the computer and storing the image in a two-dimensional digital matrix form according to red, green and blue color channels respectively as shown in the diagram (a) of FIG. 2, wherein two dimensions of a two-dimensional digital image matrix Array 1-3 respectively represent the width and the height of the channel image. By generating the rock digital image matrix Array 1-3, the rock image characteristics are stored in the computer in the form of pixel value data for further processing. Single-channel image matrix Array 1-3 visualization formShown as (b) of FIG. 21～b3) Figure (a).
Step 3, calculating a rock color channel image map 2 (b)1～b3) The pixel color gradient value of (a). For the generated rock color channel image, for (b) of FIG. 21～b3) Processing the pixel matrix Array 1-3 of the graph corresponding matrixing, performing differential calculation on the corresponding value of each pixel point in the digital matrix to obtain corresponding color gradient values, and further forming a rock boundary color gradient matrix Array 4-6-grad by the gradient valuesr、gradg、gradbVisualizing the gradient level matrix to form a color gradient map of the rock block boundary, as in (c) of FIG. 21～c3) Figure (a).
And 4, performing weighted average calculation processing on the rock block boundary color gradient map. Performing weighted average calculation of channels on the color gradient map of the rock block boundary generated in the step S3, as shown in (c) of FIG. 21～c3) Graph, three color channel gradient matrices gradr、gradg、 gradbRespectively multiplied by a weight a1、a2、a3And summing the three weight matrixes to obtain a single-channel matrix Array 7-Gray of the color gradient of the rock massijThe single-channel matrix can be visualized as an image, and a corresponding color gradient single-channel map, such as the (d) map of fig. 2, is generated, so that the weighted average calculation of the three color channels of the image is realized.
And 5, performing binarization processing on the color gradient single-channel image. In step S4, the generated color gradient single-channel digital matrix GrayijSetting a threshold value T, and if the color gradient single-channel matrix represents a pixel point [ i1, j1 ]]If the corresponding value is greater than the threshold value T, the value of the point is assigned to be 0; if the pixel point is [ i2, j2 ]]And if the corresponding value is less than or equal to T, assigning the point value to be 1, thereby further highlighting the boundary characteristics of the rock, and simultaneously saving the position and distribution condition of the rock outline in the computer. By performing binarization processing on the single-channel image, the computer generates a rock boundary graph binary image, such as the (e) diagram of fig. 2.
And 6, extracting the rock object boundary region in the rock boundary graph binary image, and identifying a connected region. And (3) performing boundary extraction on the binary color gradient map of the rock block boundary generated after the image processing in the step S5, as shown in (e) of fig. 2, identifying a communication line with continuous characteristics of the boundary of the rock object to form a complete individual closed region, wherein the complete closed region is an individual rock block, and after the boundary extraction and identification of the rock block, forming a rock block boundary extraction map, as shown in (f) of fig. 2.
And 7, calculating an equivalent circle and an equivalent diameter, and drawing a rock block degree frequency histogram and a cumulative distribution curve. According to the rock boundary extraction diagram formed in the step S5, such as the diagram (f) in fig. 2, boundary detection is performed on the individual rock identified in the diagram, and the individual rock is covered with an equivalent circular O-shape. Equivalent diameter D corresponding to equivalent circle OiAnd (3) as a characteristic quantity of the rock fragment block size, determining the proportion of the rock block size in the image to the actual rock block size, and drawing a frequency histogram and a cumulative distribution curve of the corresponding block size according to the actual equivalent diameter D of each block recognition object in the image, such as a graph (g) in FIG. 2.
In the example, the rock boundary and block degree calculation method based on the image color gradient, which is applied to the broken rock after the fracturing experiment in the laboratory, is used for calculating the block degree of the broken rock object, and the color gradient, the binarization, the boundary identification and drawing, the block degree size calculation, the frequency histogram of the actual equivalent diameter and the drawing of the cumulative distribution curve are successfully carried out on the picture respectively. By the method, the rock block size boundary is successfully identified and calculated, and a new technical method and a new research idea are provided for the application of the image processing technology in the evaluation of the rock block size in geotechnical engineering. Especially compared with a rock block image analysis system disclosed in CN109544624A and an image statistical method of rock block after blasting disclosed in CN108305263B, the invention fully extracts rock block characteristics by using image processing steps such as image graying, color gradient, binarization and the like, and can realize depth automation better.
Example 2:
the embodiment provides a system based on the method, which includes: the device comprises an image acquisition module, a single-channel data matrix construction module, a gradient color image acquisition module, a rock fragment color gradient single-channel image acquisition module, a binarization processing module, a boundary extraction module and a calculation module.
The image acquisition module is used for acquiring digital original color images of the rock fragments. The image acquisition module may represent a hardware module, such as a high-definition camera, or may be a software module, such as a module in a computer that communicates with the high-definition camera, for receiving images transmitted by the camera.
The single-channel data matrix construction module is used for reading digital original color images of the rock fragments and respectively constructing single-channel data matrices by using three color values of R-G-B;
the gradient color image acquisition module is used for respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color image;
the rock fragment color gradient single-channel image acquisition module is used for performing fusion on the basis of the three gradient color images;
the binarization processing module is used for carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
the boundary extraction module is used for carrying out boundary extraction and identification on the binary image of the rock fragments to form a rock boundary extraction image, wherein each complete closed region is an individual rock;
and the calculating module is used for calculating the equivalent diameter of each rock individual in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock lumpiness by taking the actual equivalent diameter as a representation of the rock lumpiness.
For the specific implementation process of each unit module, refer to the corresponding process of the foregoing method. It should be understood that, the specific implementation process of the above unit module refers to the method content, and the present invention is not described herein in detail, and the division of the above functional module unit is only a division of a logic function, and there may be another division manner in the actual implementation, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be executed. Meanwhile, the integrated unit can be realized in a hardware form, and can also be realized in a software functional unit form.
Example 3:
the present embodiment provides a terminal, which includes: one or more processors, and a memory storing one or more programs. Wherein the processor calls the corresponding program to execute:
a method for acquiring rock block degree and/or distribution rule based on digital image color gradient. The method comprises the following specific steps:
s1: acquiring and reading a digital original color image of the rock fragment, and respectively constructing a single-channel data matrix by using three color values of R-G-B;
s2: respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color chart;
s3: performing fusion on the basis of the three gradient color maps to obtain a rock fragment color gradient single-channel map;
s4: carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
s5: carrying out boundary extraction and identification on the binary image of the rock fragment to identify a connected region and form a rock boundary extraction image, wherein each complete closed region is a rock individual;
s6: and calculating the equivalent diameter of each individual rock in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock lumpiness by taking the actual equivalent diameter as a representation of the rock lumpiness.
The terminal further includes: and the communication interface is used for communicating with external equipment and carrying out data interactive transmission.
The memory may include high speed RAM memory, and may also include a non-volatile defibrillator, such as at least one disk memory.
If the memory, the processor and the communication interface are implemented independently, the memory, the processor and the communication interface may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture bus, a peripheral device interconnect bus, an extended industry standard architecture bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc.
Optionally, in a specific implementation, if the memory, the processor, and the communication interface are integrated on a chip, the memory, the processor, that is, the communication interface may complete communication with each other through the internal interface.
It should be understood that in the embodiments of the present invention, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include both read-only memory and random access memory, and provides instructions and data to the processor. The portion of memory may also include non-volatile random access memory. For example, the memory may also store device type information.
Example 4:
the present invention provides a readable storage medium storing a computer program for being invoked by a processor to perform:
the invention provides a method for acquiring rock block degree and/or distribution rule based on digital image color gradient. The specific steps are as follows:
s1: acquiring and reading a digital original color image of the rock fragment, and respectively constructing a single-channel data matrix by using three color values of R-G-B;
s2: respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color chart;
s3: performing fusion on the basis of the three gradient color maps to obtain a rock fragment color gradient single-channel map;
s4: carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
s5: carrying out boundary extraction and identification on the binary image of the rock fragment to identify a connected region and form a rock boundary extraction image, wherein each complete closed region is a rock individual;
s6: and calculating the equivalent diameter of each individual rock in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock lumpiness by taking the actual equivalent diameter as a representation of the rock lumpiness.
The readable storage medium is a computer readable storage medium, which may be an internal storage unit of the controller described in any of the foregoing embodiments, for example, a hard disk or a memory of the controller. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the controller. Further, the readable storage medium may also include both an internal storage unit of the controller and an external storage device. The readable storage medium is used for storing the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store data that has been or will be output.
Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It should be emphasized that the examples described herein are illustrative and not restrictive, and thus the invention is not limited to the examples described in the specific embodiments, but rather, other embodiments may be devised by those skilled in the art without departing from the spirit and scope of the present invention, and it is intended to cover all modifications, alterations, and equivalents included within the scope of the present invention.
Claims (7)
1. A rock block degree and/or distribution rule obtaining method based on digital image color gradient is characterized in that: the method comprises the following steps:
s1: acquiring and reading a digital original color image of the rock fragment, and respectively constructing a single-channel data matrix by using three color values of R-G-B;
s2: respectively calculating color gradient values corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color chart;
s3: fusing based on the three gradient color maps to obtain a single-channel color gradient map of the rock fragment;
s4: carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
s5: carrying out boundary extraction and identification on the binary image of the rock fragment to identify a connected region and form a rock boundary extraction image, wherein each complete closed region is a rock individual;
s6: and calculating the equivalent diameter of each individual rock in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock lumpiness by taking the actual equivalent diameter as a representation of the rock lumpiness.
2. The method of claim 1, wherein: the calculation formula of the color gradient value in step S2 is as follows:
in the formula, grayr、grayg、graybR, G, B pixels [ i, j ] in a single-channel data matrix, respectively]Corresponding to the calculated color gradient value ri,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value R in the R single-channel data matrixi+Δi,jRepresenting the target pixel [ i, j]The value of the next pixel point in the R single-channel data matrix after the same row is moved by the step length delta i; gi,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value G in the G single-channel data matrixi+Δi,jRepresenting the target pixel [ i, j]The value of the next pixel point in the G single-channel data matrix after the same row is moved by the step length delta i; bi,j+ΔjRepresenting the target pixel [ i, j]In the same column, the next pixel point moved by the step length delta j corresponds to the value in the B single-channel data matrix，bi+Δi,jRepresenting the target pixel [ i, j]And in the same row, the next pixel point after the movement by the step length delta i corresponds to the value in the B single-channel data matrix, and delta j and delta i are the difference step lengths taken in the horizontal direction and the vertical direction when the pixel gradient value is calculated respectively.
3. The method of claim 1, wherein: the process of the rock fragment color gradient single channel map fused based on the three gradient color maps in step S3 is as follows:
carrying out weighted average calculation on the three gradient color images to obtain a color gradient single-channel matrix;
visualizing the color gradient single-channel matrix to obtain a rock fragment color gradient single-channel diagram;
the weighting formula is as follows:
Grayij＝a1*grayr+a2*grayg+a3*grayb
Grayijrepresenting a color gradient single channel matrix; a is1、a2、a3Respectively represent R, G, B three-channel weights, and a1+a2+a3＝1；gradr、grayg、graybNamely the color gradient level matrix corresponding to the R, G, B gradient color map.
4. The method of claim 1, wherein: in step S6, the process of calculating the equivalent diameter of each individual rock block in the rock block boundary extraction diagram is as follows:
and determining a mass point Z corresponding to the connected region for each individual rock block, and calculating the area of an equivalent circle by taking the mass point Z as the center of the circle based on the area of the connected region to obtain the equivalent diameter.
5. A system based on the method of any one of claims 1-4, characterized by: the method comprises the following steps:
the image acquisition module is used for acquiring digital original color images of the rock fragments;
the single-channel data matrix construction module is used for reading digital original color images of rock fragments and respectively constructing a single-channel data matrix according to R-G-B color values;
the gradient color image acquisition module is used for respectively calculating a color gradient value corresponding to each pixel point based on the three single-channel data matrixes to obtain three color gradient level matrixes to form a gradient color image;
the rock fragment color gradient single-channel image acquisition module is used for performing fusion on the basis of the three gradient color images;
the binarization processing module is used for carrying out binarization processing on the rock fragment color gradient single-channel map to obtain a rock fragment binary map;
the boundary extraction module is used for carrying out boundary extraction and identification on the binary image of the rock fragments to form a rock boundary extraction image, wherein each complete closed region is an individual rock;
and the calculating module is used for calculating the equivalent diameter of each rock individual in the rock boundary extraction diagram, obtaining the actual equivalent diameter by taking the equivalent diameter as a reference, and drawing a frequency histogram and/or a cumulative distribution curve of the rock lumpiness by taking the actual equivalent diameter as a representation of the rock lumpiness.
6. A terminal, characterized by: the method comprises the following steps:
one or more processors;
a memory storing one or more programs;
the processor calls the program to perform:
the process steps of any one of claims 1 to 4.
7. A readable storage medium, characterized by: a computer program is stored, which is invoked by a processor to perform:
the process steps of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111067115.9A CN113838011A (en) | 2021-09-13 | 2021-09-13 | Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111067115.9A CN113838011A (en) | 2021-09-13 | 2021-09-13 | Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113838011A true CN113838011A (en) | 2021-12-24 |
Family
ID=78959160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111067115.9A Pending CN113838011A (en) | 2021-09-13 | 2021-09-13 | Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113838011A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613531A (en) * | 2020-11-25 | 2021-04-06 | 国网四川省电力公司阿坝供电公司 | Soil and rock classification method and device based on image processing |
| CN114973207A (en) * | 2022-08-01 | 2022-08-30 | 成都航空职业技术学院 | Road sign identification method based on target detection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107314957A (en) * | 2017-06-30 | 2017-11-03 | 长安大学 | A kind of measuring method of rock fragmentation Size Distribution |
| CN107578418A (en) * | 2017-09-08 | 2018-01-12 | 华中科技大学 | A kind of indoor scene profile testing method of confluent colours and depth information |
| CN108648190A (en) * | 2018-05-15 | 2018-10-12 | 中铁工程装备集团有限公司 | A kind of slag piece Color Image Analysis device and method based on watershed |
| CN112396576A (en) * | 2019-08-14 | 2021-02-23 | 美卓矿物公司 | Computer-implemented method, server and terminal device for determining rock block size distribution of rock sample |
| CN113188975A (en) * | 2021-05-07 | 2021-07-30 | 中南大学 | Rock mass fracture and flying rock motion analysis system and method based on image processing technology |
-
2021
- 2021-09-13 CN CN202111067115.9A patent/CN113838011A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107314957A (en) * | 2017-06-30 | 2017-11-03 | 长安大学 | A kind of measuring method of rock fragmentation Size Distribution |
| CN107578418A (en) * | 2017-09-08 | 2018-01-12 | 华中科技大学 | A kind of indoor scene profile testing method of confluent colours and depth information |
| CN108648190A (en) * | 2018-05-15 | 2018-10-12 | 中铁工程装备集团有限公司 | A kind of slag piece Color Image Analysis device and method based on watershed |
| CN112396576A (en) * | 2019-08-14 | 2021-02-23 | 美卓矿物公司 | Computer-implemented method, server and terminal device for determining rock block size distribution of rock sample |
| CN113188975A (en) * | 2021-05-07 | 2021-07-30 | 中南大学 | Rock mass fracture and flying rock motion analysis system and method based on image processing technology |
Non-Patent Citations (1)
| Title |
|---|
| ZIZI PI等: "Digital Image Processing Method for Characterization of Fractures, Fragments, and Particles of Soil/Rock-Like Materials", MATHEMATICS, vol. 9, no. 8, pages 1 - 13 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613531A (en) * | 2020-11-25 | 2021-04-06 | 国网四川省电力公司阿坝供电公司 | Soil and rock classification method and device based on image processing |
| CN112613531B (en) * | 2020-11-25 | 2023-12-12 | 国网四川省电力公司阿坝供电公司 | Soil and rock classification method and device based on image processing |
| CN114973207A (en) * | 2022-08-01 | 2022-08-30 | 成都航空职业技术学院 | Road sign identification method based on target detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | RENet: Rectangular convolution pyramid and edge enhancement network for salient object detection of pavement cracks | |
| CN113838011A (en) | Rock block degree and/or distribution rule obtaining method, system, terminal and readable storage medium based on digital image color gradient | |
| CN107314957B (en) | Method for measuring rock block size distribution | |
| Barraud | The use of watershed segmentation and GIS software for textural analysis of thin sections | |
| CN104850854A (en) | Talc ore product sorting processing method and talc ore product sorting system | |
| CN113222992B (en) | Crack characteristic characterization method and system based on multi-fractal spectrum | |
| Dan et al. | Application of deep learning-based image recognition technology to asphalt–aggregate mixtures: Methodology | |
| Leng et al. | Rock mass trace line identification incorporated with grouping algorithm at tunnel faces | |
| CN110672072A (en) | Information multivariate interpretation and characterization method for fractured rock mass structure | |
| US11467301B1 (en) | Method and system for identifying pore and fracture based on two-dimensional (2D) scan image of core | |
| WO2024083261A1 (en) | Image spectrum technology-based geological sketching method and system for tunnel face | |
| Thurley et al. | Identifying, visualizing, and comparing regions in irregularly spaced 3D surface data | |
| Qu et al. | Gravelly soil uniformity identification based on the optimized Mask R-CNN model | |
| CN112561989B (en) | Recognition method for hoisting object in construction scene | |
| CN104463091A (en) | Face image recognition method based on LGBP feature subvectors of image | |
| CN116524017B (en) | Underground detection, identification and positioning system for mine | |
| Wang et al. | Establishment and extension of digital aggregate database using auxiliary classifier Wasserstein GAN with gradient penalty | |
| RU2693201C1 (en) | Propping agent identification by means of mobile device | |
| CN115359003A (en) | Two-step tunnel gray image crack identification method, system, medium and equipment | |
| Guo et al. | Size measurement of blasted rock fragments based on FRRSNet+ | |
| Su et al. | Fractal theory based identification model for surface crack of building structures | |
| Li et al. | Semi-automatic crack width measurement using an OrthoBoundary algorithm | |
| CN114936392A (en) | Method for controlling pre-cracking holes of slope angle in non-coal mine mining | |
| CN106909720B (en) | Method for rapidly extracting finite element node coordinates | |
| CN105241886A (en) | Earthen ruin crack detection method based on HVS and guide wave filter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |