CN117129388A - Stone grain grading detection device and method based on image detection - Google Patents
Stone grain grading detection device and method based on image detection Download PDFInfo
- Publication number
- CN117129388A CN117129388A CN202311022083.XA CN202311022083A CN117129388A CN 117129388 A CN117129388 A CN 117129388A CN 202311022083 A CN202311022083 A CN 202311022083A CN 117129388 A CN117129388 A CN 117129388A
- Authority
- CN
- China
- Prior art keywords
- stone
- slope
- image
- particles
- background plate
- 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
- 239000004575 stone Substances 0.000 title claims abstract description 191
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000002245 particle Substances 0.000 claims abstract description 212
- 238000003384 imaging method Methods 0.000 claims abstract description 83
- 239000002689 soil Substances 0.000 claims abstract description 23
- 239000000463 material Substances 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000005303 weighing Methods 0.000 claims abstract description 6
- 238000003708 edge detection Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 230000002146 bilateral effect Effects 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 8
- 229910000831 Steel Inorganic materials 0.000 claims description 6
- 238000000926 separation method Methods 0.000 claims description 6
- 239000010959 steel Substances 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 238000005096 rolling process Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 239000002344 surface layer Substances 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 abstract description 5
- 239000000428 dust Substances 0.000 abstract description 5
- 230000011218 segmentation Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000005192 partition Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000005056 compaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000000572 ellipsometry Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means, e.g. by light scattering, diffraction, holography or imaging
- G01N15/0227—Investigating particle size or size distribution by optical means, e.g. by light scattering, diffraction, holography or imaging using imaging, e.g. a projected image of suspension; using holography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0272—Investigating particle size or size distribution with screening; with classification by filtering
Landscapes
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The application discloses a rock-fill dam material grain grading detection device and method based on image detection, which are characterized in that firstly, dust grains with smaller grain diameters are screened by a rock-fill dam material to be detected, the remaining larger grains fall along a slope, video images of stones in the falling are shot, the grain diameters of the stones are identified, the weight of the dust is added to convert the data into full grading data of the rock-fill dam material, and a full grading curve of the rock-fill dam material is drawn, so that the soil and stone material full grading detection device and method based on image identification are practically applied. According to the application, through realizing screening and automatic weighing of tiny stone particles and optimizing the stone particle imaging dispersion process, on the basis of avoiding segmentation errors caused by the shading and stone imaging concentration of tiny stone particles, the soil stone grading detection precision based on image recognition is greatly improved, a feasible technical scheme is provided for realizing rapid and high-precision soil stone grading detection, and the method has important engineering application reference value and significance.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a stone grain grading detection device and method based on image detection.
Background
The mechanical property and the impermeability of the rock-fill dam have very obvious influence on the safety of the dam, and the grading property of the rock-fill dam is a main factor influencing the mechanical property and the impermeability of the filled material after compaction, thereby having great significance in dam construction. The good grading can ensure the filling compaction quality of the rock-fill dam engineering and improve the impervious performance and the deformation resistance of the engineering, so that the grain size grading detection of the rock-fill dam material is an important link of the construction quality control of the rock-fill dam.
The traditional stone grading detection mainly adopts a screening method, and grading data is obtained through random sampling and manual screening and calculation. However, manual screening is time-consuming and low-efficient, and labor cost is high, so that the requirements of high speed and high efficiency of modern intelligent construction are difficult to meet. Along with the development of computer science and technology, image recognition is widely applied to various fields as a new detection means, and has better development and application in the water conservancy industry, thereby providing a new direction for rock-fill dam material grading detection.
The related research work of the image recognition technology for stone particle size detection has achieved great achievements, and related computing theory is mature day by day. However, the research theory or method cannot be suitable for complex environmental conditions of the rock-fill dam construction site, and cannot be widely applied to grading detection of rock-fill dam materials.
Disclosure of Invention
The application aims to provide a stone grain grading detection device and method based on image detection. Firstly, dust particles with smaller particle sizes are screened from rock-fill dam materials to be detected, the dust particles with smaller particle sizes are directly weighed, the remaining larger particles fall along a slope, video images of stones in the fall are shot, the particle sizes of the stones are identified, the dust weight is converted into full-grading data of the rock-fill dam materials, and a full-grading curve of the rock-fill dam materials is drawn, so that the soil and stone full-grading detection device and method based on image identification are practically applied. The test device mainly comprises: the soil and stone full-grading detection device mainly comprises a screening component and a shooting component, wherein the screening component is a linear vibrating screen which is provided with particles below 5mm and completes automatic weighing, and the shooting component comprises freely adjustable equipment such as a slope, a high-speed camera, a light supplementing lamp and the like; secondly, combining the video image shot by the rapid soil and stone grading detection device, and preprocessing the image, wherein the basic processes of the image comprise background separation, image graying treatment, image histogram equalization and bilateral filtering noise reduction; then image segmentation, motion blur correction and edge detection based on the maximum inter-class variance method are sequentially carried out, and characteristic parameters of particles are extracted and then are converted into stone equivalent particle sizes; and finally, screening the equivalent particle sizes of stones according to the partitions of the frame images, sequentially arranging and storing the equivalent particle sizes into the same set, and drawing a stone stacking grading curve by combining the weight of the stones below 5mm screened out, thereby realizing the full grading detection of the soil stones based on image identification.
In order to solve the problems, the technical scheme of the application is as follows: a stone grain composition detection method based on image detection comprises the following steps: the method comprises the following steps:
step1, separating soil and stones by using a linear vibrating screen, weighing particles below 5mm below the screen, dispersing and paving stone particles above 5mm above the screen, and conveying to an inclined slope imaging background plate;
step2, continuously shooting stone particles sliding down an imaging area of a slope imaging background plate by a shooting component to obtain a frame image;
step3, taking out frame images of stone particles of one specification from all frame images at preset optimal frame taking intervals from front to back in sequence, and storing the frame images as effective frame images of the stone particles of the specification, so that the stone particles of the specification only appear once in two effective frame images which are continuously taken out;
step4, performing image processing on the effective frame images of the stone particles with various specifications, extracting characteristic parameters of the stone particles and converting the characteristic parameters into equivalent particle diameter data of the stone particles;
step5, according to the specification of stone particles corresponding to the effective frame image, extracting equivalent particle diameter data of stone particles conforming to the specification from the equivalent particle diameter data extracted from the effective frame image, and according to the corresponding relation between the equivalent particle diameter and the mass, obtaining the equivalent mass of the stone particles;
step6, combining the equivalent particle diameter and equivalent mass of the stone particles obtained in the step5 in the same effective frame picture into the same set, and arranging according to the ascending order of the equivalent particle diameter of the particles: let i be the arrangement number and n be the total number of detected particle sizes, the set can be expressed as:
O i ＝{(d 1 ,m 1 )(d 2 ,m 2 )…(d i ,m i )…(d n ,m n )}
wherein i is the arrangement number, n is the total number of detected particle sizes, d i Is of equivalent particle diameter, m i Is equivalent mass;
step7, calculating the particle diameter d smaller than i The mass percent of all stone particles:
wherein m is p,i Is smaller than particle diameter d i The mass percentage of the stone material, m df To vibrate the weight of the undersize of the primary screen, m a For the actual total weight of the stone to be photographed,the particle size identified for step6 is not greater than d i Stone quality of->The effective mass of all stone particles identified for step 6;
and 8, drawing a stone grading curve by taking the particle size of stone particles as an abscissa and the mass percentage of the stone particles smaller than each particle size as an ordinate.
The result precision analysis model of the stone grading curve comprises two indexes, namely absolute precision and relative error, wherein the absolute precision characterizes the fitting degree of the grading curve obtained in the step 8 and a preset grading curve, and the relative error reflects the sectional deviation degree of the grading curve obtained in the step 8 and the preset grading curve;
the relative error calculation formula is as follows:
W i ＝[(y p,i -y p,i-1 )-(y s,i -y s,i-1 )]×100％
wherein i is the sequence number, which satisfies 2 < i < M, M is the length of the gradation curve data sequence obtained in step 8, y s,i For presetting the ordinate of the grading curve, y p,i The ordinate of the distribution curve obtained in the step 8;
the absolute precision calculation formula is as follows:
wherein AAC is the absolute precision of the gradation curve obtained in the step 8 relative to a preset gradation curve, and AAC is 0< 1.
The shooting frame frequency of the shooting component is F, and the number of times N of continuous occurrence of stone particles in the frame image t The method comprises the following steps:
in the formula, v 0 For the initial speed of stone entering the slope surface of the screening device, epsilon is the slope angle influence coefficient of the slope imaging background plate, epsilon=g (sin alpha-mu cos alpha), g is gravity acceleration; alpha is the slope inclination angle of the slope imaging background plate; μ is the coefficient of friction of the ramp imaging background plate; h is a 0 For the displacement of stone sliding along the slope imaging background plate to the upper edge of the imaging zone, L h Is the length of the imaging zone.
The specification comprises a large particle interval, a medium particle interval and a small particle interval: the particle size interval of the large particles is 60-100 mm; the grain size interval of the medium grains is 20-60 mm; the particle size interval of the small particles is 5-20 mm;
optimal frame taking interval N corresponding to large, medium and small particle interval b b 、N b m 、N b s Is N t The values obtained by multiplying the values with corresponding scaling factors are rounded upwards, when the slope inclination angle of the slope imaging background plate is 40 degrees, the scaling factors corresponding to the large, medium and small particle intervals are 0.34, 0.38 and 0.37 respectively, and N is equal to that of the slope imaging background plate b b 、N b m 、N b s 14, 16, 15 respectively.
The image processing step in the step4 includes: image preprocessing, and then sequentially carrying out image segmentation and edge detection based on a maximum inter-class variance method to extract particle contour features;
the image preprocessing includes: background separation, image graying treatment, image histogram equalization and bilateral filtering noise reduction.
The bilateral filtering noise reduction is combined with the similarity of the image pixel values to carry out weight superposition on the basis of considering the space distance, and the image edge information can be well reserved while the noise is removed.
The edge detection comprises edge detection based on Roberts operator and particle size identification based on circumscribed ellipsometry.
The extracting the characteristic parameters of the stone particles to convert the characteristic parameters into equivalent particle diameter data of the stone particles comprises the following steps: in the edge detection result image, extracting edge line scattered point coordinates of each stone object, obtaining the length of a long axis and a short axis of a graph formed by the edge line scattered point coordinates, and calculating the equivalent particle diameter of stone particles, wherein the equivalent particle diameter calculation formula of the stone particles is as follows:
where α is the long axis of the stone particles and β is the short axis of the stone particles.
The maximum inter-class variance algorithm divides the gray level image to form inter-class variance sigma 2 The threshold value t at the maximum is used as a binary image segmentation threshold value, and then the background area pixel value in the gray level diagram is changed to 0, and the foreground area pixel value is changed to 255. The gray mean square error of the two types of areas is as follows:
σ 2 ＝ω 0 (μ 0 -μ T ) 2 +ω 1 (μ 1 -μ T ) 2
in sigma 2 Is gray mean square error omega 0 Probability of occurrence, μ, for pixels of gray scale number 0 to t 0 Is the gray average value of the foreground region, mu 1 Is the gray average value of background area, mu T Is the gray average value omega of the whole image 1 For the probability of occurrence of pixels t +1 to L-1.
The edge detection based on the Roberts operator determines a proper threshold value after determining the gradient amplitude of the Roberts operator, wherein the point with the gradient amplitude larger than the threshold value is a step edge point, so that the particle size of stone particles is extracted, and the gradient amplitude of the Roberts operator is as follows:
wherein d x 2 (i,j)，d y 2 (i, j) are difference amounts of the binary image f (x, y) in the x and y directions, respectively.
The stone grain grading detection system based on image detection comprises a stone tiling and conveying system consisting of the linear vibrating screen and the slope imaging background plate, and an image acquisition and analysis system comprising the shooting component;
the slope imaging background plate can be manually adjusted in angle and comprises a rotary support plate, a support frame and a PVC pad, wherein the upper end of the slope imaging background plate is flexibly connected to an outlet of a linear vibration screen surface, two sides of the slope surface of the rotary support plate are provided with baffle plates for preventing stones from rolling down from two sides, one end of each slope support rod is fixed at the upper end of a steel frame and can rotate around a shaft, the other end of each slope support rod supports the slope imaging background plate, an interface is arranged at the back of the slope imaging background plate, and the slope support rods are connected in when the angle is adjusted; the slope imaging background plate surface is based on a steel wire mesh, a red PVC pad with good wear resistance is selected as a surface layer to cover an imaging area, and the angle of the slope imaging background plate can be freely adjusted to 60 degrees, 55 degrees, 50 degrees, 45 degrees, 40 degrees, 35 degrees, 30 degrees and 25 degrees;
the shooting component consists of a high-speed camera, a light supplementing lamp and an image processing system;
the linear vibrating screen is a double-shaft inertial vibrating screen and comprises: the vibration isolator comprises a screen box, a screen, a motor, a transmission device and a vibration isolator.
The high-speed camera frame is fixed in front of the slope imaging background plate, so that a shooting area of the high-speed camera frame is opposite to the slope imaging background plate, the focal length of the high-speed camera is adjusted, the width of a video recording area of the high-speed camera is overlapped with the width of the slope imaging background plate, the brightness and the irradiation angle of the light supplementing lamp are adjusted, and the uniform illumination brightness on the slope imaging background plate is ensured.
And the image acquisition and analysis system installs and executes the programs from the step3 to the step 7.
According to the application, through realizing screening and automatic weighing of tiny stone particles and optimizing the stone particle imaging dispersion process, on the basis of avoiding segmentation errors caused by the shading and stone imaging concentration of tiny stone particles, the soil stone grading detection precision based on image recognition is greatly improved, a feasible technical scheme is provided for realizing rapid and high-precision soil stone grading detection, and the method has important engineering application reference value and significance.
Drawings
The application is further described with reference to the accompanying drawings:
FIG. 1 is a flow chart of a test and method of the soil and stone grading detection device of the present application;
FIG. 2 is a schematic diagram of the overall three-dimensional structure of the soil and stone grading detection device of the application;
FIG. 3 is a three-dimensional schematic view of an adjustable falling slope of the soil and stone grading detection device of the application;
FIG. 4 is a schematic diagram of the whole soil and stone grading detection device according to the present application;
FIG. 5 is a schematic view showing the background separation effect of the soil and stone grading detection device of the present application;
FIG. 6 is a schematic view showing the effect of graying treatment on an image of the soil and stone grading detection device of the present application;
FIG. 7 is a schematic diagram showing the equalization effect of the image histogram of the soil and stone grading detection device of the present application;
FIG. 8 is a schematic diagram of bilateral filtering noise reduction effect of the soil and stone grading detection device of the application;
FIG. 9 is a schematic view showing the effect of the maximum inter-class variance algorithm of the soil and stone grading detection device for gray image segmentation;
FIG. 10 is a schematic diagram showing the effect of edge detection by the soil and stone grading detection device based on Roberts operator;
fig. 11 is a schematic view showing the moment that stone particles fall into an imaging area of a slope imaging background plate in the present application.
Detailed Description
The technical scheme and the beneficial effects of the application are described below with reference to the accompanying drawings and the specific embodiments.
As shown in fig. 2 to 4, an indoor test device for detecting the grading of soil and stone materials taking account of imaging dispersion of stone particles mainly comprises a linear vibrating screen 1, a slope imaging background plate 2 with manually adjustable angles and a shooting component 3, wherein the linear vibrating screen 1 mainly realizes the filtration and automatic weighing of particles below 5mm, the stone particles are fed to the slope imaging background plate 2 in a vibrating batch, and stone materials are dispersed and tiled uniformly as much as possible through vibration. The slope imaging background plate 2 with the manually adjustable angle mainly comprises a rotary support plate 21, support frames (23, 24 and 25), a PVC pad 21 and the like, and can realize the fixation of the slope imaging background plate 2 with the adjustable multiple angles and the optimizing adjustment of stone particle imaging dispersion; the shooting part 3 is composed of a high-speed camera, a light supplementing lamp and an image processing system, performs image preprocessing such as background separation, image graying processing, image histogram equalization, bilateral filtering noise reduction and the like on the basis of shooting video images, sequentially performs image segmentation and edge detection based on a maximum inter-class variance method, and extracts characteristic parameters of particles to convert the particles into stone equivalent particle sizes; and finally, screening the equivalent particle sizes of the stones according to the partitions of the frame images, sequentially arranging and storing the equivalent particle sizes into the same set, and drawing a stone grading curve by combining the weight of the stones below 5mm screened out, thereby realizing the soil stone grading detection taking the imaging dispersion degree of the stone particles into consideration.
In the preferred scheme, the linear vibrating screen is called a double-shaft inertial vibrating screen, and the main components of the linear vibrating screen comprise: screen box, screen cloth, motor, transmission, vibration isolation device etc.. The screen surface of the linear vibrating screen adopts a standard screen with the width of 700mm, the length of 1700mm, the height of 900mm and the screen diameter of 5mm, the lower end of the screen is connected with a storage container, and an electronic scale is arranged under the container.
The characteristic parameters of the linear vibrating screen mainly comprise a screen surface inclination angle, a vibrating direction angle, throwing strength, amplitude and vibration frequency, material movement speed, screening efficiency and the like.
In the preferred scheme, the upper end of the slope imaging background plate 2 with the manual angle adjustable is flexibly connected to the outlet of the linear vibration screen surface, the baffle plates 22 are arranged on two sides of the slope surface to prevent stones from rolling off from two sides, one end of the slope support rod 23 is fixed at the upper end of the steel frame 24 and can rotate around the shaft, the other end of the slope support rod supports the slope imaging background plate 2, an interface is arranged on the back of the slope imaging background plate 2, and the slope support rod 23 can be quickly connected in when the angle is adjusted, as shown in fig. 3.
In the preferred scheme, the surface of the slope imaging background plate 2 with the manually adjustable angle is based on a steel wire mesh, and a red PVC pad 21 with good wear resistance is selected as a surface layer. The imaging background color is obviously compared with the stone particle color, the imaging effect is better, the size of the PVC pad 21 is the same as the size of the imaging area, and the PVC pad covers the imaging area.
In a preferred scheme, the angle of the slope imaging background plate 2 with the manually adjustable angle can be freely adjusted to 60 degrees, 55 degrees, 50 degrees, 45 degrees, 40 degrees, 35 degrees, 30 degrees and 25 degrees.
In the preferred scheme, the high-speed camera frame is fixed in front of the slope imaging background plate 2 with the manually adjustable angle, so that the shooting area of the high-speed camera frame is opposite to the slope imaging background plate 2, the focal length of the high-speed camera is adjusted, the width of the video recording area of the high-speed camera is overlapped with the width of the slope imaging background plate 2, the brightness and the irradiation angle of the light supplementing lamp are adjusted, and the uniform illumination brightness on the slope imaging background plate 2 is ensured.
In a preferred scheme, the particle size range of the stone samples is considered to be 0-100mm in combination with the detection device, the mass percentage of 5mm is controlled below 5%, and the total weight of the two groups of configured stone samples is 25kg.
In a preferred embodiment, the step of grading detection experiment includes the steps of:
step1: installing a detection device and preparing a stone sample;
step2: the high-speed camera 3 is erected on the horizontal ground, so that a shooting lens of the high-speed camera is opposite to the center of the slope imaging background plate 2, the height is fixed, the focal length of the high-speed camera is adjusted, the width of a video recording area of the high-speed camera is equal to that of the slope imaging background plate 2, and a light supplementing lamp is turned on;
step3: pouring the stone sample on the screen surface of the linear vibrating screen;
step4: starting a high-speed camera to record a video, and starting a linear vibrating screen motor;
step5: after the group of stones fall completely, the high-speed camera stops recording, then the motor is turned off, and the weight of the stones in the undersize container and the weight of the stones falling along the slope are recorded;
step6: guiding out video images in the high-speed camera, and finishing the screening and shooting process of the indoor rock-fill dam material;
step7: and (5) performing rock-fill dam video image analysis and full-grading conversion.
In the preferred scheme, the rock-fill dam video image analysis and full-grading conversion comprises the steps of establishing an effective frame image comprehensive extraction model, performing image preprocessing, extracting particle outline characteristics, performing rock-fill dam full-grading conversion and drawing a rock grading curve.
And establishing an effective frame image comprehensive extraction model for taking out frame images of stone particles of one specification from all frame images at preset optimal frame taking intervals in sequence from front to back, and storing the frame images as effective frame images of the stone particles of the specification, so that the stone particles of the specification only appear once in two effective frame images which are continuously taken out.
In a preferred embodiment, the basic process of the image preprocessing includes background separation, graying processing, histogram equalization and bilateral filtering noise reduction, as shown in fig. 5 to 8.
In the preferred scheme, the bilateral filtering noise reduction combines the similarity of the pixel values of the images to carry out weight superposition on the basis of considering the space distance, and can better keep the image edge information while denoising.
In a preferred embodiment, the extracting the particle contour features includes image segmentation based on a maximum inter-class variance method, edge detection based on a Roberts operator, and particle size identification based on an external ellipsometry, as shown in FIGS. 9-10.
In a preferred embodiment, the basic process of converting the particle profile characteristics into stone equivalent particle sizes comprises:
step1: dividing the gray image by using a maximum inter-class variance algorithm to obtain an inter-class variance sigma 2 The maximum threshold t is used as a binary image segmentation threshold, and the background area pixel value in the gray level diagram is changed to 0 (black), and the foreground areaThe domain pixel value becomes 255 (white). The variance is a measure of the uniformity of the gray level distribution, and the larger the inter-class variance between the background and the foreground, the larger the difference between the two parts constituting the image, and the smaller the difference between the two parts is caused when the foreground is divided into the background or the background is divided into the foreground.
The gray mean square error of the two types of areas is as follows: sigma (sigma) 2 ＝ω 0 (μ 0 -μ T ) 2 +ω 1 (μ 1 -μ T ) 2
In sigma 2 Is gray mean square error omega 0 Probability of occurrence, μ, for pixels of gray scale number 0 to t 0 Is the gray average value of the foreground region, mu 1 Is the gray average value of background area, mu T Is the gray average value omega of the whole image 1 The probability of the occurrence of pixels of the gray level number t+1 to L-1, L being the total gray level number of the gray image.
Step2: after the gradient amplitude of the Roberts operator is determined, a proper threshold value is determined, and the point with the gradient amplitude larger than the threshold value is a step edge point, so that the particle size of stone particles is extracted, and the gradient amplitude of the Roberts operator is as follows:
wherein d x 2 (i,j)，d y 2 (i, j) are difference amounts of the binary image f (x, y) in the x and y directions, respectively.
Step3: and extracting edge line scattered point coordinates of each stone object in the edge detection result image to obtain the length of a major axis and a minor axis of a graph formed by the edge line scattered point coordinates, calculating the equivalent particle size of stone particles, and further obtaining the equivalent mass of the stone particles according to the corresponding relation between the equivalent particle size and the mass. The equivalent formula for calculating the equivalent particle diameter of the stone particles is as follows:
where α is the long axis of the stone particles and β is the short axis of the stone particles.
In a preferred embodiment, if the frame rate of the camera is theoretically set to F, the number of pictures continuously taken by the camera, i.e. the number of times N the spherical stone is continuously present in the frame map t The method comprises the following steps:
in the formula, v 0 For the initial speed of stone entering the slope surface of the screening device, epsilon is the slope angle influence coefficient of the slope imaging background plate, epsilon=g (sin alpha-mu cos alpha), g is gravity acceleration; alpha is the slope inclination angle of the slope imaging background plate; μ is the coefficient of friction of the ramp imaging background plate; h is a 0 For the displacement of stone sliding along the slope imaging background plate to the upper edge of the imaging zone, L h Is the length of the imaging zone.
As shown in FIG. 11, when the stone P is theoretically spherical 1 When entering the shooting area (i.e. sliding down to the point B), the displacement on the slope imaging background plate is h 0 The time spent when the spherical stone slides from the point A to the point B is calculated as follows:
the speed of the spherical stone rolling down to the point B is as follows:
the moment the spherical stone passes through the shooting area (i.e. slides down to point C), the total displacement of the movement on the slope is:
s c ＝L h +h 0
wherein L is h Representing the height of the view window formed by the camera on the background.
The corresponding time spent is:
the spherical stone reaches a maximum speed at this point:
based on the analysis of the movement state of the stone, the number of frames that the spherical stone may appear in an ideal situation is calculated. The time taken from the falling of the spherical stone to entering the shooting area is t b The time taken for the spherical stone to leave the shooting area from the beginning of the fall is t c . If the frame rate of the camera is F, the number of pictures continuously shot by the camera, namely the number of times N of continuous occurrence of spherical stones in the frame map t The method comprises the following steps:
wherein F is the shooting frame rate of the camera; t is t c Time spent for spherical stone to leave the shooting area from the beginning of the fall; t is t b It takes time for the spherical stone to start falling to enter the photographing region.
In practice, stone particles with different specifications have unequal sliding speeds on a slope because the stone particles are in an irregular ellipsoid shape, so that the stone particles with different specifications may not appear twice or once in adjacent frame pictures taken out at the same optimal frame taking interval.
In the preferred scheme, an effective frame image comprehensive extraction model is established for respectively setting optimal frame taking interval intervals to respectively extract three effective frame image groups according to different specification ranges of stones, and the effective frame image comprehensive extraction model is used for the grading identification of the respective particle size intervals of large, medium and small particles.
The specification comprises a large particle size section, a medium particle size section and a small particle size section: the particle size interval of the large particles is 60-100 mm; the grain size interval of the medium grains is 20-60 mm; the particle size interval of the small particles is 5-20 mm;
optimal frame taking interval N corresponding to large, medium and small particle interval b b 、N b m 、N b s Is N t And multiplying the two scaling factors respectively and then rounding the two scaling factors to obtain a numerical value, wherein the large, medium and small particle intervals respectively correspond to one scaling factor.
According to the analysis and demonstration of the frame number of the stone, an effective frame image comprehensive extraction model is established for the video image processing of the stone sliding along the inclined plane.
Firstly, according to the working condition of the shot video, the optimal frame taking interval N of the calculation theory is obtained t 。
The optimal frame taking interval N t Multiplying the scaling factors of the large, medium and small granule intervals respectively and rounding up to obtain the optimal frame taking interval N in each interval b b 、N b m 、N b s 。
Every N from the first frame image of the shot video b b One picture is stored as an effective frame image for large particle detection, the rest pictures are kept in a database for temporary processing until the last frame image, and all detection frame images of large particle particles can be selected. Every second N b m 、N b s And repeating the above processes for each image, and storing the images as effective frame images for detecting the medium and small particles.
And carrying out image recognition by using the three groups of frame images, and extracting equivalent particle sizes and equivalent volumes of stone objects with large, medium and small particle sizes according to the particle size partition, namely only storing particle data with equivalent particle sizes of 60-100mm in the large particle size partition, only storing particle data with equivalent particle sizes of 20-60mm in the medium particle size partition, and only storing particle data with equivalent particle sizes of 5-20mm in the small particle size partition.
The effective frame image extraction model can ensure that the data is not missed and mixed when the particle size of the stone object is detected, thereby improving the accuracy of the whole detection system.
When the slope inclination angle of the slope imaging background plate is 40 degrees, the corresponding scaling coefficients of the large, medium and small particle size intervals are 0.34, 0.38 and 0.37 respectively, and N is equal to that of the slope imaging background plate b b 、N b m 、N b s 14, 16, 15 respectively.
In the preferred scheme, the three groups of frame images are used for image recognition, and equivalent particle sizes and equivalent volumes of stone objects with large, medium and small particle sizes are extracted in a partitioning mode according to the particle sizes.
In a preferred scheme, the three effective frame image groups are reserved to be in accordance with the particle equivalent particle diameter data of the specification range of the partition particle diameter, and the data are integrated into the same set and are arranged according to the ascending order of the particle equivalent particle diameter: let i be the arrangement number and n be the total number of detected particle sizes, the set can be expressed as:
O i ＝{(d 1 ,m 1 )(d 2 ,m 2 )…(d i ,m i )…(d n ,m n )}
wherein i is an arrangement number, n is the total number of detected particle sizes, d is the equivalent particle size of the particles, and m is the equivalent mass.
In a preferred embodiment, a particle size d smaller than i The mass percent of all stone particles:
wherein m is p,i Is smaller than particle diameter d i The mass percentage of the stone material, m df To vibrate the weight of the undersize of the primary screen, m a For the actual total weight of the stone to be photographed,the particle size identified for step6 is not greater than d i Stone quality of->The effective mass of all stone particles identified for step 6;
wherein di>When 5mm, the equivalent mass of stone particles below 5mm which can be obtained through conversion can be written as:
the total equivalent mass of all stone particles obtained by conversion can be written as:
the weight of stone particles having a particle size less than di can be expressed as (the equivalent mass of all stone particles having a particle size less than di is):
in the preferred scheme, the stone grading data below 5mm is obtained by equally dividing the mass percentage of stone particles below 5mm according to the particle size, the section presents a straight line on a grading curve, and after the mass percentage of the stone particles smaller than a certain particle size is obtained, the stone grading curve is drawn by taking the particle size of the stone particles as an abscissa and taking the mass percentage smaller than a certain particle size as an ordinate.
In a preferred scheme, the grading detection result precision analysis model comprises two indexes of absolute precision and relative error, wherein the absolute precision represents the fitting degree of the two curves, and the relative error reflects the sectional deviation degree of the two curves.
In a preferred embodiment, the relative error calculation formula is as follows:
W i ＝[(y p,i -y p,i-1 )-(y s,i -y s,i-1 )]×100％
wherein i is the sequence number, which satisfies 2 < i < M, M is the data sequence length of the sieving grading curve, y s,i For presetting the ordinate of the grading curve, y p,i Is the ordinate of the screen grading curve.
In a preferred embodiment, the absolute precision calculation formula is as follows:
wherein AAC is the absolute precision of the video image detection gradation curve relative to the preset gradation curve, 0< AAC <1.
The above embodiments are merely preferred embodiments of the present application, and should not be construed as limiting the present application, and the embodiments and features of the embodiments of the present application may be arbitrarily combined with each other without collision. The protection scope of the present application is defined by the claims, and the protection scope includes equivalent alternatives to the technical features of the claims. I.e., equivalent replacement modifications within the scope of this application are also within the scope of the application.
Claims (9)
1. The stone grain composition detection method based on image detection is characterized by comprising the following steps of:
step1, separating soil and stones by using a linear vibrating screen, weighing particles below 5mm below the screen, dispersing and paving stone particles above 5mm above the screen, and conveying to an inclined slope imaging background plate;
step2, continuously shooting stone particles sliding down an imaging area of a slope imaging background plate by a shooting component to obtain a frame image;
step3, taking out frame images of stone particles of one specification from all frame images at preset optimal frame taking intervals from front to back in sequence, and storing the frame images as effective frame images of the stone particles of the specification, so that the stone particles of the specification only appear once in two effective frame images which are continuously taken out;
step4, performing image processing on the effective frame images of the stone particles with various specifications, extracting characteristic parameters of the stone particles and converting the characteristic parameters into equivalent particle diameter data of the stone particles;
step5, according to the specification of stone particles corresponding to the effective frame image, extracting equivalent particle diameter data of stone particles conforming to the specification from the equivalent particle diameter data extracted from the effective frame image, and according to the corresponding relation between the equivalent particle diameter and the mass, obtaining the equivalent mass of the stone particles;
step6, combining the equivalent particle diameter and equivalent mass of the stone particles obtained in the step5 in the same effective frame picture into the same set, and arranging according to the ascending order of the equivalent particle diameter of the particles: let i be the arrangement number and n be the total number of detected particle sizes, the set can be expressed as:
O i ＝{(d 1 ,m 1 )(d 2 ,m 2 )…(d i ,m i )…(d n ,m n )}
wherein i is the arrangement number, n is the total number of detected particle sizes, d i Is of equivalent particle diameter, m i Is equivalent mass;
step7, calculating the particle diameter d smaller than i The mass percent of all stone particles:
wherein m is p,i Is smaller than particle diameter d i The mass percentage of the stone material, m df To vibrate the weight of the undersize of the primary screen, m a For the actual total weight of the stone to be photographed,the particle size identified for step6 is not greater than d i Stone quality of->The effective mass of all stone particles identified for step 6;
and 8, drawing a stone grading curve by taking the particle size of stone particles as an abscissa and the mass percentage of the stone particles smaller than each particle size as an ordinate.
2. The method for detecting stone grain grading based on image detection according to claim 1, wherein the result precision analysis model of the stone grading curve comprises two indexes of absolute precision and relative error, the absolute precision represents the fitting degree of the grading curve obtained in the step 8 and a preset grading curve, and the relative error reflects the sectional deviation degree of the grading curve obtained in the step 8 and the preset grading curve;
the relative error calculation formula is as follows:
W i ＝[(y p,i -y p,i-1 )-(y s,i -y s,i-1 )]×100％
wherein i is the sequence number, which satisfies 2 < i < M, M is the length of the gradation curve data sequence obtained in step 8, y s,i For presetting the ordinate of the grading curve, y p,i The ordinate of the distribution curve obtained in the step 8;
the absolute precision calculation formula is as follows:
wherein AAC is the absolute precision of the gradation curve obtained in the step 8 relative to a preset gradation curve, and AAC is 0< 1.
3. The method for detecting stone grain composition based on image detection according to claim 1, wherein the photographing frame rate of the photographing means is F, and the number of times N of continuous occurrence of stone grains in the frame map t The method comprises the following steps:
in the formula, v 0 For the initial speed of stone entering the slope surface of the screening device, epsilon is the slope angle influence coefficient of the slope imaging background plate, epsilon=g (sin alpha-mu cos alpha), g is gravity acceleration; alpha is the slope inclination angle of the slope imaging background plate; μ is the coefficient of friction of the ramp imaging background plate; h is a 0 For the displacement of stone sliding along the slope imaging background plate to the upper edge of the imaging zone, L h Is the length of the imaging zone.
4. A stone grain size distribution detection method based on image detection according to claim 3, wherein the specifications include large, medium and small grain intervals: the particle size interval of the large particles is 60-100 mm; the grain size interval of the medium grains is 20-60 mm; the particle size interval of the small particles is 5-20 mm;
optimal frame taking interval N corresponding to large, medium and small particle interval b b 、N b m 、N b s Is N t The values obtained by multiplying the values with corresponding scaling factors are rounded upwards, when the slope inclination angle of the slope imaging background plate is 40 degrees, the scaling factors corresponding to the large, medium and small particle intervals are 0.34, 0.38 and 0.37 respectively, and N is equal to that of the slope imaging background plate b b 、N b m 、N b s 14, 16, 15 respectively.
5. The method for detecting stone grain size distribution based on image detection according to claim 1, wherein the image processing step in step4 comprises: image preprocessing, and then sequentially carrying out image segmentation, particle edge detection and particle size identification based on a maximum inter-class variance method;
the image preprocessing includes: background separation, image graying treatment, image histogram equalization and bilateral filtering noise reduction.
6. The image detection-based stone grain grading detection method according to claim 1, wherein the extracting the characteristic parameters of the stone grains to convert them into equivalent grain size data of the stone grains comprises: in the edge detection result image, extracting edge line scattered point coordinates of each stone object, obtaining the length of a long axis and a short axis of a graph formed by the edge line scattered point coordinates, and calculating the equivalent particle diameter of stone particles, wherein the equivalent particle diameter calculation formula of the stone particles is as follows:
where α is the long axis of the stone particles and β is the short axis of the stone particles.
7. A stone grain grading detection system based on image detection, which is characterized by comprising a stone tiling and conveying system consisting of a linear vibrating screen and a slope imaging background plate according to claim 1, and an image acquisition and analysis system comprising the shooting component according to claim 1;
the slope imaging background plate can be manually adjusted in angle and comprises a rotary support plate, a support frame and a PVC pad, wherein the upper end of the slope imaging background plate is flexibly connected to an outlet of a linear vibration screen surface, two sides of the slope surface of the rotary support plate are provided with baffle plates for preventing stones from rolling down from two sides, one end of each slope support rod is fixed at the upper end of a steel frame and can rotate around a shaft, the other end of each slope support rod supports the slope imaging background plate, an interface is arranged at the back of the slope imaging background plate, and the slope support rods are connected in when the angle is adjusted; the slope imaging background plate surface is based on a steel wire mesh, a red PVC pad with good wear resistance is selected as a surface layer to cover an imaging area, and the angle of the slope imaging background plate can be freely adjusted to 60 degrees, 55 degrees, 50 degrees, 45 degrees, 40 degrees, 35 degrees, 30 degrees and 25 degrees;
the shooting component consists of a high-speed camera, a light supplementing lamp and an image processing system;
the linear vibrating screen is a double-shaft inertial vibrating screen and comprises: the vibration isolator comprises a screen box, a screen, a motor, a transmission device and a vibration isolator.
8. The image detection-based stone grain composition detection system according to claim 7, wherein: the high-speed camera frame is fixed in front of the slope imaging background plate, so that a shooting area of the high-speed camera frame is opposite to the slope imaging background plate, the focal length of the high-speed camera is adjusted, the width of a video recording area of the high-speed camera is overlapped with the width of the slope imaging background plate, the brightness and the irradiation angle of the light supplementing lamp are adjusted, and the uniform illumination brightness on the slope imaging background plate is ensured.
9. The image detection-based stone grain composition detection system according to claim 7, wherein: the image acquisition and analysis system installs and executes the procedure of steps 3 to 7 according to claim 1.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311002027 | 2023-08-09 | ||
| CN202311002027X | 2023-08-09 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117129388A true CN117129388A (en) | 2023-11-28 |
Family
ID=88860861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311022083.XA Pending CN117129388A (en) | 2023-08-09 | 2023-08-14 | Stone grain grading detection device and method based on image detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117129388A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117204655A (en) * | 2023-10-14 | 2023-12-12 | 华南农业大学 | Special-shaped diamond mosaic system based on EtherCAT bus communication |
-
2023
- 2023-08-14 CN CN202311022083.XA patent/CN117129388A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117204655A (en) * | 2023-10-14 | 2023-12-12 | 华南农业大学 | Special-shaped diamond mosaic system based on EtherCAT bus communication |
| CN117204655B (en) * | 2023-10-14 | 2024-04-05 | 华南农业大学 | Special-shaped diamond mosaic system based on EtherCAT bus communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Murphy et al. | The measurement and characterisation of voids in soil thin sections by image analysis. Part I. Principles and techniques | |
| CN117129388A (en) | Stone grain grading detection device and method based on image detection | |
| CN107621435A (en) | A kind of aggregate on-Line Monitor Device | |
| CN109472822A (en) | Dimension of object measurement method based on depth image processing | |
| CN1916598A (en) | Apparatus for measuring spectrum of fog drop, and image processing device | |
| CN110118775A (en) | Plantmix's cement stabilized macadam aggregate forms rapid detection method | |
| CN108460793A (en) | The fractal dimension of radioscopic image determines the method for separating of method and bastard coal | |
| CN106521066A (en) | Blast furnace burden particle size monitoring system and distributed data on-line analysis method | |
| CN111715540B (en) | Apparatus and method for sorting coal and gangue | |
| CN107909584B (en) | Asphalt mixture gradation estimation method through cold charge monitoring | |
| CN111968173A (en) | Method and system for analyzing granularity of mixture | |
| CN108280838A (en) | A kind of intermediate plate tooth form defect inspection method based on edge detection | |
| GB2221754A (en) | Digital image processing system | |
| CN113533145A (en) | Rockfill particle size identification and monitoring device and method based on camera set three-dimensional reconstruction | |
| CN101059450A (en) | Intelligent identification method of metallurgical mine phase | |
| CN110599473A (en) | Method, device and equipment for determining digital core | |
| CN110501268A (en) | A kind of micro dust detection method based on Micrograph image processing | |
| CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
| CN111105386B (en) | Coarse aggregate quality image processing and analyzing method based on mobile equipment | |
| Cao et al. | Effects of flow rates and layer thicknesses for aggregate conveying process on the prediction accuracy of aggregate gradation by image segmentation based on machine vision | |
| CN111507980B (en) | Correction method for detecting particle size distribution of ore crushed and ground product by dynamic image method | |
| CN111307070B (en) | Method for measuring edge angle of concrete coarse aggregate based on digital image processing | |
| CN216870297U (en) | Rockfill particle size identification and monitoring device based on three-dimensional reconstruction of camera set | |
| CN109583703B (en) | Method for quantitatively defining starting critical index of non-viscous bottom sand | |
| Seyedin et al. | Designing and programming an efficient software for sizing and counting various particles using image processing technique |
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 |