CN113674301A - Method and system for identifying material flow strength, electronic equipment and medium - Google Patents
Method and system for identifying material flow strength, electronic equipment and medium Download PDFInfo
- Publication number
- CN113674301A CN113674301A CN202110989455.0A CN202110989455A CN113674301A CN 113674301 A CN113674301 A CN 113674301A CN 202110989455 A CN202110989455 A CN 202110989455A CN 113674301 A CN113674301 A CN 113674301A
- Authority
- CN
- China
- Prior art keywords
- image
- width
- acquiring
- edge
- belt
- 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
- 239000000463 material Substances 0.000 title claims abstract description 194
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 52
- 239000011159 matrix material Substances 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000005260 corrosion Methods 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000003723 Smelting Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 3
- 230000010339 dilation Effects 0.000 description 3
- 239000010959 steel Substances 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000109 continuous material Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention is suitable for the field of image processing and identification, and provides a method, a system, electronic equipment and a medium for identifying the material flow intensity, wherein the method comprises the following steps: acquiring an image to be identified of the belt conveyor, identifying the belt edge position of the image to be identified, and acquiring a belt area according to the belt edge position; identifying the material edge contour of the image to be identified, and acquiring a material area according to the material edge contour; acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring the width ratio of the second width to the first width, and acquiring the material flow strength according to the width ratio, wherein the first width is the width of the belt area, and the second width is the width of the material area; comparing the material flow strength with a preset strength threshold value to obtain a material flow strength identification result; the problem of can't carry out accurate discernment to the material stream intensity of belt feeder among the prior art is solved.
Description
In the technical field of
The present invention relates to the field of image processing and recognition, and in particular, to a method and a system for recognizing a material flow intensity, an electronic device, and a medium.
Background
In the iron and steel smelting industry, belt conveyors are one of the common material transport means. If in the transportation, disposable blanking is too much, causes the transportation material overfill, may cause the belt to skid because of transporting the too big, the motor is overheated or transmit the unrestrained scheduling problem of material, causes inconvenience to production operation.
At present, the problem of the overfilling of materials conveyed by a belt conveyor is not effectively judged during steel smelting, so that the overfilling of the conveyed materials cannot be well avoided, and the additional loss of production operation is easily caused.
Disclosure of Invention
The invention provides a method, a system, electronic equipment and a medium for identifying material flow strength, and aims to solve the problem that the material flow strength of a belt conveyor cannot be accurately identified in the prior art.
The invention provides a method for identifying the material flow strength, which comprises the following steps:
acquiring an image to be identified of a belt conveyor, identifying the belt edge position of the image to be identified, and acquiring a belt area according to the belt edge position;
identifying the material edge contour of the image to be identified, and acquiring a material area according to the material edge contour;
acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring a width ratio of the second width to the first width, and acquiring material flow strength according to the width ratio, wherein the first width is the width of the belt area, and the second width is the width of the material area;
and comparing the material flow strength with a preset strength threshold value to obtain a material flow strength identification result.
Optionally, the step of obtaining a width ratio of the second width to the first width and obtaining the material flow strength according to the width ratio specifically includes:
acquiring the material density of the material area;
and if the material density is greater than a preset density threshold value, acquiring the width ratio of the second width to the first width, and acquiring the material flow strength according to the width ratio.
Optionally, before the step of obtaining the material density of the material region, the method further includes:
carrying out binarization processing on the image to be identified according to a preset pixel threshold value to obtain a pixel value of the image after binarization processing;
acquiring the material density according to the pixel value of the image after binarization processing;
the mathematical expression of the binarization process is as follows:
wherein p2(x, y) is the pixel value of the image after binarization processing, p2(x, y) is the pixel value of the image to be identified, n is a preset pixel threshold value, 255 represents a white pixel value, and 0 represents a black pixel value.
Optionally, the step of identifying the material edge contour of the image to be identified specifically includes:
preprocessing the image to be identified to obtain a gray scale image, wherein the preprocessing comprises the following steps: graying processing and histogram equalization processing;
identifying the material edge contour of the gray scale image to obtain a first edge contour;
performing expansion operation processing on the first edge profile to obtain a second edge profile;
and carrying out corrosion operation processing on the second edge contour to obtain the material edge contour of the image to be identified.
Optionally, the mathematical expression of the histogram equalization processing is as follows:
wherein n iskIs the number of pixels per gray level k (the kth gray level, where the pixel value is k), N is the total number of pixels of the image subjected to the graying process, L is the number of gray levels of the image (L is 256), and P (r)k) For the probability of each gray level appearing in the grayed image, njIs the number of pixels per gray level j, SkThe gray level image after histogram equalization is obtained.
Optionally, the step of performing material edge contour identification on the grayscale map to obtain a first edge contour specifically includes:
respectively setting a first convolution kernel and a second convolution kernel, wherein the first convolution kernel is a convolution kernel in the x direction of the image, and the second convolution kernel is a convolution kernel in the y direction of the image;
obtaining an image matrix of the gray-scale image, and performing convolution operation on the first convolution kernel and the image matrix of the gray-scale image to obtain a first edge matrix;
performing convolution operation on the second convolution kernel and the image matrix of the gray image to obtain a second edge matrix;
and linearly mixing the first edge matrix and the second edge matrix to obtain an edge image matrix, and obtaining the first edge profile according to the edge image matrix.
Optionally, the step of identifying the belt edge position of the image to be identified specifically includes:
acquiring a sample image of the belt conveyor, and forming a sample data set according to the sample image;
constructing an initial identification model, training the initial identification model by adopting the sample data set, and acquiring a belt edge identification model;
and inputting the image to be recognized into the belt edge recognition model, and acquiring the belt edge position of the image to be recognized.
The invention also provides a system for identifying the material flow strength, which comprises:
the belt area acquisition module is used for acquiring an image to be identified of the belt conveyor, identifying the belt edge position of the image to be identified and acquiring a belt area according to the belt edge position;
the material area acquisition module is used for identifying the material edge contour of the image to be identified and acquiring a material area according to the material edge contour;
the material flow strength acquisition module is used for acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring a width ratio of the second width to the first width, and acquiring material flow strength according to the width ratio, wherein the first width is the width of the belt area, and the second width is the width of the material area;
and the identification result acquisition module is used for comparing the material flow strength with a preset strength threshold value to acquire a material flow strength identification result.
The present invention also provides an electronic device comprising: a processor and a memory;
the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory so as to enable the electronic equipment to execute the identification method of the material flow strength.
The present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for identifying the strength of a material flow as described above.
The invention has the beneficial effects that: according to the identification method of the material flow strength, firstly, a belt area and a material area are extracted according to an image to be identified of a belt conveyor, then the width of the belt area and the width of the material area are obtained, the material flow strength is obtained according to the width ratio of the width of the material area and the width of the belt conveyor, and the material flow strength is compared with a preset strength threshold value to obtain a material flow strength identification result; according to the method, the material flow strength condition of the belt conveyor in conveying the materials can be judged better through the obtained material flow strength identification result, so that the purpose of avoiding production operation loss caused by overfilling of the conveyed materials is achieved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow diagram of a method for identifying strength of a material flow in an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method of obtaining a belt edge position in an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a first method for obtaining an edge profile according to an embodiment of the present invention;
fig. 4 is a block diagram of a flow intensity identification system in an embodiment of the invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
First embodiment
Fig. 1 is a schematic flow diagram of a method for identifying stream strength provided in an embodiment of the present invention.
As shown in fig. 1, the method for identifying the strength of the material flow includes steps S110 to S140:
s110, acquiring an image to be identified of the belt conveyor, identifying the belt edge position of the image to be identified, and acquiring a belt area according to the belt edge position;
s120, identifying the material edge contour of the image to be identified, and acquiring a material area according to the material edge contour;
s130, acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring a width ratio of the second width to the first width, and acquiring material flow strength according to the width ratio;
s140, comparing the material flow strength with a preset strength threshold value to obtain a material flow strength identification result.
In step S110 of this embodiment, the image to be identified of the belt conveyor may be obtained according to a working video of the belt conveyor, and the working video of the belt conveyor may be a working video of the belt conveyor in the steel smelting industry. The working video of the belt conveyor can be a real-time working video of the belt conveyor, and the image to be identified, which is acquired through the real-time working video of the belt conveyor, reflects the real-time working state of the belt conveyor. The material flow strength identification result in the conveying process of the belt conveyor is acquired through the image to be identified, so that the working state of the belt conveyor is monitored in real time, the abnormal working state of the belt conveyor is conveniently and rapidly adjusted, and the purpose of avoiding production operation loss caused by over-full conveying materials is achieved.
In an embodiment, a specific implementation method for identifying the belt edge position of the image to be identified may refer to fig. 2, and fig. 2 is a flowchart illustrating a method for acquiring the belt edge position according to an embodiment of the present invention.
As shown in fig. 2, the method for acquiring the edge position of the belt may include the following steps S210 to S230:
s210, obtaining a sample image of the belt conveyor, and forming a sample data set according to the sample image;
s220, constructing an initial identification model, training the initial identification model by adopting a sample data set, and acquiring a belt edge identification model;
and S230, inputting the image to be recognized into the belt edge recognition model, and acquiring the belt edge position of the image to be recognized.
In step S210, a sample image of the belt may be acquired according to the belt image or the video. In order to improve the multi-scene universality of the belt edge identification model, the sample images are derived from belt images or belt videos of various machine positions and different light scenes. Before forming the sample data set according to the sample image, marking the belt edge position of the sample image, and forming the sample data set according to the marked sample image.
In step S220 of the present embodiment, the initial recognition model includes, but is not limited to, a neural network model for image target detection, such as SSD, YOLO series, RCNN, CNN, centrnet, etc. Specifically, a sample data set is divided into a training data set and a testing data set, a training data set is adopted to forward propagate a training neural network model, a testing data set is input into the trained neural network model, a testing result is obtained, and if the testing result is not in line with the edge position of a labeling belt of a sample image, the neural network model is updated through backward propagation. Updating the neural network model using back propagation includes: and determining the error back propagation of the predicted belt edge position and the marked belt edge position of the training data set according to the cross entropy loss function, and updating the neural network model.
In one embodiment, the step of obtaining a belt region based on a belt edge position comprises: inputting an image to be recognized into an edge detection recognition model, acquiring two recognition frames (a first recognition frame and a second recognition frame) with the highest confidence degree, and acquiring a belt region according to the first recognition frame and the second recognition frame. The coordinates of the upper left corner of the first recognition box are represented as (x1, y1) and the coordinates of the lower right corner are represented as (x2, y2), the coordinates of the upper left corner of the second recognition box are represented as (x3, y3) and the coordinates of the lower right corner are represented as (x4, y4), the abscissa of the upper left corner of the belt region is represented as (x1+ x3)/2, the ordinate of the upper left corner of the belt region is represented as (y1+ y3)/2, the abscissa of the lower right corner of the belt region is represented as (x2+ x4)/2, and the ordinate of the lower right corner of the belt region is represented as (y2+ y 4)/2.
In step S120 of this embodiment, the step of identifying the material edge contour of the image to be identified includes: preprocessing an image to be recognized to obtain a gray scale image, wherein the preprocessing comprises the following steps: graying processing and histogram equalization processing; identifying the material edge contour of the gray scale image to obtain a first edge contour; performing expansion operation processing on the first edge profile to obtain a second edge profile; and carrying out corrosion operation processing on the second edge contour to obtain the material edge contour of the image to be identified.
Specifically, the grayscale processing and the histogram equalization processing are performed on the image to be recognized to enhance the image contrast, so that a finer grayscale image is obtained. Firstly, carrying out graying processing on an image to be recognized, and then carrying out histogram equalization processing on the image to be recognized after graying processing, wherein the mathematical expression of the histogram military equalization processing is as follows:
wherein n iskIs the number of pixels per gray level k (the kth gray level, where the pixel value is k), N is the total number of pixels of the image subjected to the graying process, L is the number of gray levels of the image (L is 256), and P (r)k) For the probability of each gray level appearing in the grayed image, njIs the number of pixels per gray level j, SkThe gray level image after histogram equalization is obtained.
Specifically, the gray image is subjected to material edge contour recognition to obtain a first edge contour, each part of continuous material image corresponds to one section of independent edge contour, and the edges are stored in a point set mode, namely if the materials in the belt conveyor working video are discontinuous materials, the material edge contour of the image to be recognized corresponds to each pile of materials. Referring to fig. 3, fig. 3 is a schematic flowchart illustrating a method for acquiring a first edge contour according to an embodiment of the present invention.
As shown in fig. 3, the method for acquiring the first edge profile may include the following steps S310 to S350:
s310, respectively setting a first convolution kernel and a second convolution kernel;
s320, acquiring an image matrix of the gray image, and performing convolution operation on the first convolution kernel and the image matrix of the gray image to acquire a first edge matrix;
s330, performing convolution operation on the second convolution kernel and the image matrix of the gray image to obtain a second edge matrix;
s340, performing linear mixing on the first edge matrix and the second edge matrix to obtain an edge image matrix, and obtaining a first edge profile according to the edge image matrix.
Specifically, the first convolution kernel Gx is a convolution kernel of 3 × 3 in the x direction of the image, and the second convolution kernel Gy is a convolution kernel of 3 × 3 in the y direction of the image; the first image pixels are image pixels in the x-direction of the gray scale image, and the second image pixels are image pixels in the y-direction of the gray scale image.
The mathematical expression of the first edge matrix Dx is:
the mathematical expression of the second edge matrix Dy is:
wherein Dx is a first edge matrix, Gx is a first convolution kernel,
for convolution operation, A is an image matrix of the gray scale image, Dy is a second edge matrix, and Gy is a second convolution kernel.
The mathematical expression of the edge image matrix D is:
D＝αDx+βDy；
α+β＝1；
wherein D is an edge image matrix, alpha and beta are linear mixing parameters, alpha is more than 0 and less than 1, and beta is more than 0 and less than 1.
In an embodiment, the performing the dilation operation on the first edge profile and obtaining the second edge profile specifically includes: and performing expansion operation processing on the first edge profile, and connecting the closer edge profiles to form a complete profile to obtain a second edge profile. Specifically, the first edge profile is subjected to dilation operation, and for each point in the image, n pixels are expanded outwards, so that a dilated image is obtained, wherein adjacent gap portions are connected together.
In one embodiment, the second edge contour is subjected to erosion operation processing, and the expanded part of the second edge contour is restored to obtain the material edge contour of the image to be identified. Specifically, the second edge profile is subjected to corrosion operation processing, n pixels are reduced inwards, and the expansion part of the n pixels is restored; but for the connected pixel region, 1 pixel still remains during corrosion, and the connection contour is not disconnected; thereby obtaining an effective edge image which is roughly distributed the same as the original edge image but is in gap communication.
In one embodiment, the material edge profile is based onThe material acquisition area specifically comprises: making a minimum external rectangle for the edge profile of the material, namely making the minimum external rectangle for each section of continuous profile of the obtained material on the belt conveyor; and acquiring a circumscribed rectangle with the largest area, and taking the circumscribed rectangle as a material area. The coordinates of the top left corner of the circumscribed rectangle may be represented as (x)min,ymin) The coordinate of the lower right corner of the circumscribed rectangle can be expressed as (x)max,ymax) Wherein x ismin、xmax、yminAnd ymaxFor four extreme points in each segment of the continuous edge profile: (x)min,yxmin)、(xmax,yxmax)、(xymin,yxmin) And (x)ymax,ymax). Specifically, (x)min,yxmin) Taking the coordinate corresponding to the minimum value for the coordinate x of the material edge profile, (x)max,yxmax) Taking the coordinate corresponding to the maximum value for the coordinate x of the material edge profile, (x)ymin,yxmin) Taking the coordinate corresponding to the minimum value for the coordinate y of the material edge profile, (x)ymax,ymax) And taking the coordinate corresponding to the maximum value for the coordinate y of the material edge profile. The length of the circumscribed rectangle is xmax-xminThe width of the circumscribed rectangle is ymax-ymin。
In step S130 of this embodiment, the material density of the material region needs to be obtained before the material flow strength is obtained according to the width ratio, and if the material density is greater than the preset density threshold, the width ratio of the second width to the first width is obtained, and the material flow strength is obtained according to the width ratio. By obtaining the material density in the material region and presetting the density threshold value, the false detection condition that the material in the region is excessively distributed and scattered, the distribution area is wider, but the flow is smaller is avoided.
Before the material density of the material area is obtained, binarization processing is carried out on an image to be identified according to a preset pixel threshold value, and a pixel value of the image after binarization processing is obtained; and acquiring the material density according to the pixel value of the image after binarization processing. The binarization processing of the image to be recognized according to the preset pixel threshold specifically comprises the following steps: carrying out graying processing on the image to be recognized, and then carrying out binarization processing on the image to be recognized after graying processing according to a preset pixel threshold. The mathematical expression of the binarization process is:
wherein p2(x, y) is the pixel value of the image after binarization processing, p2(x, y) is the pixel value of the image to be identified, n is a preset pixel threshold value, 255 represents a white pixel value, and 0 represents a black pixel value.
The binarization processing converts the gray level image distributed at all levels of the image into black-white two-color distribution by taking a preset pixel threshold value as a reference, so that the material part and the belt part in the image are clearly divided, and the material density is convenient to obtain. The step of obtaining the material density according to the pixel value of the image after binarization processing specifically comprises the following steps: and acquiring the number of nonzero pixel points of the image after binarization processing, and acquiring the material density according to the number of the nonzero pixel points.
In step S140 of this embodiment, the preset intensity threshold may be divided into a light overfill threshold and a heavy overfill threshold according to the actual working condition of the belt conveyor. The material flow strength recognition results comprise normal work, light overfill of materials and heavy overfill of materials. If the material flow strength acquired according to the image to be identified is smaller than the material slight overfill threshold, the material flow strength identification result is normal work; if the material flow strength acquired according to the image to be identified is greater than the material slight overfill threshold and less than the material severe overfill threshold, the material flow strength identification result is that the material is slightly overfilled; and if the material flow strength acquired according to the image to be identified is greater than the material gravity overfill threshold value, the material flow strength identification result is the material gravity overfill.
In one embodiment, in order to avoid production operation loss caused by overfilling of transported materials, after the step of obtaining the material flow strength identification result, whether the material flow strength identification result meets a preset condition is judged, and if the material flow strength identification result does not meet the preset condition, early warning information is generated. The early warning information comprises first early warning information and second early warning information, and the first early warning information and the second early warning information are used for reminding workers of adjusting the material flow strength of the belt conveyor. If the material flow strength identification result does not meet the preset condition, generating early warning information specifically comprises: if the material flow strength identification result is that the material is slightly overfilled, generating first early warning information; and if the material flow strength identification result is that the material is heavily overfilled, generating second early warning information.
Second embodiment
Based on the same inventive concept as the method in the first embodiment, correspondingly, the embodiment also provides a belt conveyor charge level deviation identification system.
Fig. 4 is a block diagram of a flow intensity identification system provided by the present invention.
As shown in fig. 4, the flow intensity identification system includes: 41 a belt area acquisition module, 42 a material area acquisition module, 43 a material flow strength acquisition module and 44 a recognition result acquisition module.
The belt area acquisition module is used for acquiring an image to be identified of the belt conveyor and identifying a belt area of the image to be identified;
the material area acquisition module is used for identifying the material edge contour of the image to be identified and acquiring a material area according to the material edge contour;
the material flow strength acquisition module is used for acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring a width ratio of the second width to the first width, and acquiring material flow strength according to the width ratio, wherein the first width is the width of the belt area, and the second width is the width of the material area;
and the identification result acquisition module is used for comparing the material flow strength with a preset strength threshold value to acquire a material flow strength identification result.
In some exemplary embodiments, the belt region acquisition module includes:
the system comprises a sample data set acquisition unit, a sample data set generation unit and a sample data set generation unit, wherein the sample data set acquisition unit is used for acquiring a sample image of the belt conveyor and forming a sample data set according to the sample image;
the identification model establishing unit is used for establishing an initial identification model, training the initial identification model by adopting the sample data set and acquiring a belt edge identification model;
the edge position acquiring unit is used for inputting the image to be recognized into the belt edge recognition model and acquiring the belt edge position of the image to be recognized;
and the belt area acquisition unit is used for acquiring a belt area according to the belt edge position.
In some exemplary embodiments, the material region acquisition module includes:
the preprocessing unit is used for preprocessing the image to be identified to obtain a gray scale image, and the preprocessing comprises the following steps: graying processing and histogram equalization processing;
the mathematical expression of the histogram equalization process is:
wherein n iskIs the number of pixels per gray level k (the kth gray level, where the pixel value is k), N is the total number of pixels of the image subjected to the graying process, L is the number of gray levels of the image (L is 256), and P (r)k) For the probability of each gray level appearing in the grayed image, njIs the number of pixels per gray level j, SkA gray level image after histogram equalization is obtained;
the first edge contour acquisition unit is used for carrying out material edge contour identification on the gray level image to acquire a first edge contour;
a second edge contour acquiring unit, configured to perform dilation operation on the first edge contour to acquire a second edge contour;
and the material edge contour unit is used for carrying out corrosion operation processing on the second edge contour to obtain the material edge contour of the image to be identified.
In some exemplary embodiments, the first edge profile acquiring unit includes:
a convolution kernel setting unit, configured to set a first convolution kernel and a second convolution kernel respectively, where the first convolution kernel is a convolution kernel in an x direction of an image, and the second convolution kernel is a convolution kernel in a y direction of the image;
the first edge matrix acquisition unit is used for acquiring an image matrix of the gray image, and performing convolution operation on the first convolution kernel and the image matrix of the gray image to acquire a first edge matrix;
the second edge matrix obtaining unit is used for performing convolution operation on the second convolution kernel and the image matrix of the gray-scale image to obtain a second edge matrix;
and the first edge profile acquiring subunit is configured to perform linear mixing on the first edge matrix and the second edge matrix to acquire an edge image matrix, and acquire the first edge profile according to the edge image matrix.
In some exemplary embodiments, the flow stream strength acquisition module comprises:
the material density acquisition unit is used for acquiring the material density of the material area;
and the material flow strength obtaining unit is used for obtaining the width ratio of the second width to the first width if the material density is greater than a preset density threshold value, and obtaining the material flow strength according to the width ratio.
In some exemplary embodiments, the flow stream strength acquisition module further comprises:
the pixel value acquisition unit is used for carrying out binarization processing on the image to be identified according to a preset pixel threshold value and acquiring the pixel value of the image after binarization processing;
the material density obtaining subunit is used for obtaining the material density according to the pixel value of the image after the binarization processing;
the mathematical expression of the binarization process is as follows:
wherein p2(x, y) is the pixel value of the image after binarization processing, p2(x, y) is the pixel value of the image to be identified, n is a preset pixel threshold value, 255 represents a white pixel value, and 0 represents a black pixel value.
The present embodiment also provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements any of the methods in the present embodiments.
The present embodiment also provides an electronic device, including: a processor and a memory;
the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the electronic equipment to execute the method in the embodiment.
The computer-readable storage medium in the present embodiment can be understood by those skilled in the art as follows: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The electronic device provided by the embodiment comprises a processor, a memory, a transceiver and a communication interface, wherein the memory and the communication interface are connected with the processor and the transceiver and are used for realizing mutual communication, the memory is used for storing a computer program, the communication interface is used for carrying out communication, and the processor and the transceiver are used for operating the computer program to enable the electronic device to execute the steps of the method.
In this embodiment, the Memory may include a Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In the above-described embodiments, references in the specification to "the present embodiment," "an embodiment," "another embodiment," "in some exemplary embodiments," or "other embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least some embodiments, but not necessarily all embodiments. The various appearances of the phrase "the present embodiment," "one embodiment," or "another embodiment" are not necessarily all referring to the same embodiment.
In the embodiments described above, although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory structures (e.g., dynamic ram (dram)) may use the discussed embodiments. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing embodiments are merely illustrative of the principles of the present invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A method for identifying the strength of a material flow is characterized by comprising the following steps:
acquiring an image to be identified of a belt conveyor, identifying the belt edge position of the image to be identified, and acquiring a belt area according to the belt edge position;
identifying the material edge contour of the image to be identified, and acquiring a material area according to the material edge contour;
acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring a width ratio of the second width to the first width, and acquiring material flow strength according to the width ratio, wherein the first width is the width of the belt area, and the second width is the width of the material area;
and comparing the material flow strength with a preset strength threshold value to obtain a material flow strength identification result.
2. The method for identifying the strength of the material flow according to claim 1, wherein the step of obtaining the width ratio of the second width to the first width and obtaining the strength of the material flow according to the width ratio specifically comprises:
acquiring the material density of the material area;
and if the material density is greater than a preset density threshold value, acquiring the width ratio of the second width to the first width, and acquiring the material flow strength according to the width ratio.
3. The method for identifying material flow strength according to claim 2, wherein the step of obtaining the material density of the material area is preceded by the step of:
carrying out binarization processing on the image to be identified according to a preset pixel threshold value to obtain a pixel value of the image after binarization processing;
acquiring the material density according to the pixel value of the image after binarization processing;
the mathematical expression of the binarization process is as follows:
wherein p2(x, y) is the pixel value of the image after binarization processing, p2(x, y) is the pixel value of the image to be identified, n is a preset pixel threshold value, 255 represents a white pixel value, and 0 represents a black pixel value.
4. The method for identifying the material flow strength according to claim 1, wherein the step of identifying the material edge profile of the image to be identified specifically comprises:
preprocessing the image to be identified to obtain a gray scale image, wherein the preprocessing comprises the following steps: graying processing and histogram equalization processing;
identifying the material edge contour of the gray scale image to obtain a first edge contour;
performing expansion operation processing on the first edge profile to obtain a second edge profile;
and carrying out corrosion operation processing on the second edge contour to obtain the material edge contour of the image to be identified.
5. The method for identifying stream strength as recited in claim 4, wherein the mathematical expression of histogram equalization is:
wherein n iskIs the number of pixels per gray level k (the kth gray level, where the pixel value is k), N is the total number of pixels of the image subjected to the graying process, L is the number of gray levels of the image (L is 256), and P (r)k) For the probability of each gray level appearing in the grayed image, njIs the number of pixels per gray level j, SkThe gray level image after histogram equalization is obtained.
6. The method for identifying material flow strength according to claim 4, wherein the step of performing material edge contour identification on the gray-scale map to obtain a first edge contour specifically comprises:
respectively setting a first convolution kernel and a second convolution kernel, wherein the first convolution kernel is a convolution kernel in the x direction of the image, and the second convolution kernel is a convolution kernel in the y direction of the image;
obtaining an image matrix of the gray-scale image, and performing convolution operation on the first convolution kernel and the image matrix of the gray-scale image to obtain a first edge matrix;
performing convolution operation on the second convolution kernel and the image matrix of the gray image to obtain a second edge matrix;
and linearly mixing the first edge matrix and the second edge matrix to obtain an edge image matrix, and obtaining the first edge profile according to the edge image matrix.
7. The method for identifying the material flow strength according to claim 1, wherein the step of identifying the belt edge position of the image to be identified specifically comprises:
acquiring a sample image of the belt conveyor, and forming a sample data set according to the sample image;
constructing an initial identification model, training the initial identification model by adopting the sample data set, and acquiring a belt edge identification model;
and inputting the image to be recognized into the belt edge recognition model, and acquiring the belt edge position of the image to be recognized.
8. A system for identifying a flow intensity, the system comprising:
the belt area acquisition module is used for acquiring an image to be identified of the belt conveyor, identifying the belt edge position of the image to be identified and acquiring a belt area according to the belt edge position;
the material area acquisition module is used for identifying the material edge contour of the image to be identified and acquiring a material area according to the material edge contour;
the material flow strength acquisition module is used for acquiring a first width according to the belt area, acquiring a second width according to the material area, acquiring a width ratio of the second width to the first width, and acquiring material flow strength according to the width ratio, wherein the first width is the width of the belt area, and the second width is the width of the material area;
and the identification result acquisition module is used for comparing the material flow strength with a preset strength threshold value to acquire a material flow strength identification result.
9. An electronic device comprising a processor, a memory, and a communication bus;
the communication bus is used for connecting the processor and the memory;
the processor is configured to execute a computer program stored in the memory to implement the method of identifying strength of a flow according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon for causing a computer to execute the method for identifying a stream intensity according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110989455.0A CN113674301A (en) | 2021-08-26 | 2021-08-26 | Method and system for identifying material flow strength, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110989455.0A CN113674301A (en) | 2021-08-26 | 2021-08-26 | Method and system for identifying material flow strength, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674301A true CN113674301A (en) | 2021-11-19 |
Family
ID=78546821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110989455.0A Pending CN113674301A (en) | 2021-08-26 | 2021-08-26 | Method and system for identifying material flow strength, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674301A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913032A (en) * | 2016-04-15 | 2016-08-31 | 天地（常州）自动化股份有限公司 | Detection method and system for working state of mining belt |
| CN110766743A (en) * | 2019-10-23 | 2020-02-07 | 中冶赛迪重庆信息技术有限公司 | Material flow detection method, device, equipment and medium based on image recognition |
| CN111285052A (en) * | 2020-03-16 | 2020-06-16 | 河北金波嘉源测控技术有限公司 | Belt material flow control system |
| CN111325787A (en) * | 2020-02-09 | 2020-06-23 | 天津博宜特科技有限公司 | Mobile belt deviation and transportation amount detection method based on image processing |
| CN113192037A (en) * | 2021-05-06 | 2021-07-30 | 中冶赛迪重庆信息技术有限公司 | Belt conveyor monitoring method, system, medium and electronic terminal |
-
2021
- 2021-08-26 CN CN202110989455.0A patent/CN113674301A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913032A (en) * | 2016-04-15 | 2016-08-31 | 天地（常州）自动化股份有限公司 | Detection method and system for working state of mining belt |
| CN110766743A (en) * | 2019-10-23 | 2020-02-07 | 中冶赛迪重庆信息技术有限公司 | Material flow detection method, device, equipment and medium based on image recognition |
| CN111325787A (en) * | 2020-02-09 | 2020-06-23 | 天津博宜特科技有限公司 | Mobile belt deviation and transportation amount detection method based on image processing |
| CN111285052A (en) * | 2020-03-16 | 2020-06-16 | 河北金波嘉源测控技术有限公司 | Belt material flow control system |
| CN113192037A (en) * | 2021-05-06 | 2021-07-30 | 中冶赛迪重庆信息技术有限公司 | Belt conveyor monitoring method, system, medium and electronic terminal |
Non-Patent Citations (1)
| Title |
|---|
| 苏强: "矿用带式输送机智能物料超限识别及安全防护系统研究", 优秀硕士论文全文库工程科技Ⅰ辑;信息科技, pages 1 - 110 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11275961B2 (en) | Character image processing method and apparatus, device, and storage medium | |
| CN110309824B (en) | Character detection method and device and terminal | |
| US20160314368A1 (en) | System and a method for the detection of multiple number-plates of moving cars in a series of 2-d images | |
| CN108121982B (en) | Method and device for acquiring facial single image | |
| CN110533023B (en) | Method and device for detecting and identifying foreign matters of railway wagon | |
| CN113592886B (en) | Drawing examining method and device for building drawing, electronic equipment and medium | |
| CN113112485A (en) | Belt conveyor deviation detection method, system, equipment and medium based on image processing | |
| CN111767915A (en) | License plate detection method, device, equipment and storage medium | |
| CN101599172A (en) | The illumination compensation splitting method of the text image of inhomogeneous illumination | |
| CN110930087A (en) | Inventory checking method and device | |
| Huang et al. | A real-time algorithm for aluminum surface defect extraction on non-uniform image from CCD camera | |
| CN113674301A (en) | Method and system for identifying material flow strength, electronic equipment and medium | |
| CN104951755B (en) | A kind of Intelligent file image block detection method based on EMD | |
| CN111461152B (en) | Cargo detection method and device, electronic equipment and computer readable medium | |
| CN113674259B (en) | Belt conveyor slip detection method, system, electronic equipment and medium | |
| CN116402771A (en) | Defect detection method and device and model training method and device | |
| CN113284115B (en) | Steel coil tower shape identification method, system, medium and terminal | |
| US10592724B2 (en) | Information output method and information processing device | |
| Bourja et al. | Speed estimation using simple line | |
| CN113674302B (en) | Belt conveyor material level deviation identification method, system, electronic equipment and medium | |
| CN114529555A (en) | Image recognition-based efficient cigarette box in-and-out detection method | |
| CN114120109A (en) | Belt longitudinal tearing detection method based on neural network | |
| CN113901941A (en) | Cargo vehicle checking method and device, electronic device and storage medium | |
| CN112991294A (en) | Foreign matter detection method, apparatus and computer readable medium | |
| CN113343866A (en) | Identification method and device of form information and electronic equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd. Address before: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information |