CN113674302B - Belt conveyor material level deviation identification method, system, electronic equipment and medium - Google Patents
Belt conveyor material level deviation identification method, system, electronic equipment and medium Download PDFInfo
- Publication number
- CN113674302B CN113674302B CN202110993261.8A CN202110993261A CN113674302B CN 113674302 B CN113674302 B CN 113674302B CN 202110993261 A CN202110993261 A CN 202110993261A CN 113674302 B CN113674302 B CN 113674302B
- Authority
- CN
- China
- Prior art keywords
- belt conveyor
- image
- edge
- belt
- central line
- 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.)
- Active
Links
- 239000000463 material Substances 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000002372 labelling Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 10
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000003723 Smelting Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 239000010959 steel Substances 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000000109 continuous material Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
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
-
- 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
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention is suitable for the field of image processing and identification, and provides a belt conveyor material level deviation identification method, a system, electronic equipment and a medium, wherein the method comprises the following steps: acquiring an image to be identified of a belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt area according to the edge position of the belt conveyor; identifying the material edge position of the image to be identified, and acquiring a material surface area according to the material edge position; acquiring a first central line according to the belt region, acquiring a second central line according to the material surface region, and comparing the first central line with the second central line to acquire a material surface deviation identification result; the first central line is the central line of the belt area, and the second central line is the central line of the material surface area; the belt conveyor material level deviation identification method solves the problem that the belt conveyor material level deviation cannot be effectively identified in the prior art.
Description
Technical Field
The invention relates to the field of image processing and identification, in particular to a method, a system, electronic equipment and a medium for identifying the offset of a material level of a belt conveyor.
Background
Belt conveyors are one of the most common material transport means in the steel smelting industry. Because the belt surface width is large, the transportation operation is stable, and the belt conveyor is often adopted in bulk cargo transportation. Belt conveyor material level offset is one of the common problems in the operation of its conveyor. The transportation material level deviation easily causes the belt off tracking, and the material takes place unrestrained when the transmission, when causing material loss, its clearance is received and is put in order also comparatively inconvenient, leads to the production of extra labor.
In the current iron and steel smelting scene, the problem of material level deviation of the belt conveyor transportation materials is not effectively judged, the belt conveyor transportation is not guaranteed to be in a normal state, the material level deviation condition cannot be well avoided, and the material loss is easy to cause.
Disclosure of Invention
The invention provides a method, a system, electronic equipment and a medium for identifying the deviation of a material level of a belt conveyor, which are used for solving the problem that the deviation of the material level of the belt conveyor cannot be effectively identified in the prior art.
The invention provides a belt conveyor material level deviation identification method, which comprises the following steps:
acquiring an image to be identified of a belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt area according to the edge position of the belt conveyor;
identifying the material edge position of the image to be identified, and acquiring a material surface area according to the material edge position;
acquiring a first central line according to the belt region, acquiring a second central line according to the material surface region, and comparing the first central line with the second central line to acquire a material surface deviation identification result; the first center line is the center line of the belt area, and the second center line is the center line of the material surface area.
Optionally, the identifying the edge position of the belt conveyor in the image to be identified specifically includes:
acquiring a sample image of the belt conveyor, and performing edge labeling on the sample image to acquire a sample data set;
training a neural network by adopting the sample data set to obtain a belt conveyor edge recognition model;
inputting the image to be identified into the belt conveyor edge identification model to obtain the edge position of the belt conveyor.
Optionally, the step of performing edge labeling on the sample image to obtain a sample data set specifically includes:
acquiring a central line of the sample image, and rotating the sample image until the central line of the sample image is vertical;
cutting the rotated sample image until the rotating edge completely disappears, reserving the maximum image area, and obtaining a first image;
adjusting the size of the first image according to the preset image size to obtain a second image;
and carrying out edge labeling on the second image to obtain a sample data set.
Optionally, the edge labeling includes left and right edge labeling, and the step of extracting the belt area according to the edge position of the belt conveyor specifically includes:
acquiring left edge coordinates and right edge coordinates of the belt conveyor according to the edge position of the belt conveyor, wherein the left edge coordinates comprise left upper corner coordinates (x 1, y 1) and right lower corner coordinates (x 2, y 2) of the left edge, and the right edge coordinates comprise left upper corner coordinates (x 3, y 3) and right lower corner coordinates (x 4, y 4) of the right edge;
extracting a belt area according to the left edge coordinate and the right edge coordinate;
the mathematical expression of the image pixel values for the belt region is:
x left ＝(x1+x2)/2；
x right ＝(x3+x4)/2；
wherein x is left Is the left edge x coordinate, x of the belt conveyor right Is the right edge x coordinate of the belt conveyor, img (x, y) is the belt areaSrc (x, y) is the image pixel value before extraction.
Optionally, before the step of identifying the material edge position of the image to be identified, the method further includes:
preprocessing the image to be identified, wherein the preprocessing comprises the following steps: gray map conversion, histogram equalization, and image closure operations.
Optionally, the step of obtaining the material surface area according to the material edge position specifically includes:
the edge outline of the material is subjected to minimum circumscribed rectangle;
acquiring the area of the circumscribed rectangle;
if the area of the circumscribed rectangle is larger than a preset area threshold, selecting two circumscribed rectangles with the largest areas, and taking the circumscribed rectangles as a material surface area;
and if the area of the circumscribed rectangle is smaller than a preset area threshold, selecting two circumscribed rectangles with the largest area, and then, taking the circumscribed rectangles with the two circumscribed rectangles with the largest area as circumscribed rectangles to obtain a material surface area.
Optionally, the step of comparing the first center line with the second center line to obtain a material level deviation recognition result specifically includes:
comparing the first central line with the second central line to obtain a charge level pixel offset value;
and converting the charge level pixel offset value into an actual distance, and obtaining a charge level offset value to obtain a charge level offset identification result.
The invention also provides a belt conveyor material level deviation recognition system, which comprises:
the belt region acquisition module is used for acquiring an image to be identified of the belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt region according to the edge position of the belt conveyor;
the material surface area acquisition module is used for identifying the material edge position of the image to be identified and acquiring a material surface area according to the material edge position;
the recognition result acquisition module is used for acquiring a first central line according to the belt area, acquiring a second central line according to the material surface area, comparing the first central line with the second central line, and acquiring a material surface deviation recognition result; the first central line is the central line of the belt area, the second central line is the central line of the material surface area, and the belt area acquisition module, the material surface area acquisition module and the material surface area acquisition module are connected.
The present invention also provides an electronic device including: a processor and a memory;
the storage is used for storing a computer program, and the processor is used for executing the computer program stored in the storage, so that the electronic equipment executes the belt conveyor material level offset identification method.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a belt conveyor level offset identification method as described above.
The invention has the beneficial effects that: according to the belt conveyor material level deviation recognition method, firstly, a belt area and a material level area are extracted according to an image to be recognized of the belt conveyor, then, the center line of the belt area and the center line of the material level area are obtained, and finally, the center line of the belt area and the center line of the material level area are compared to obtain a material level deviation recognition result; according to the invention, the deviation condition of the material level of the transported material on the belt conveyor can be well judged through the obtained material level deviation recognition result, meanwhile, the loss caused by the material level deviation can be reduced, the human risk factors possibly caused by manual participation are avoided, and the safety of the material level deviation recognition is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art 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 other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for identifying belt conveyor level offset in an embodiment of the invention;
fig. 2 is a flowchart of a method for acquiring an edge position of a belt conveyor according to an embodiment of the present invention;
FIG. 3 is a block diagram of a belt conveyor level offset identification system in accordance with an embodiment of the present invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
First embodiment
Fig. 1 is a schematic flow chart of a belt conveyor level deviation recognition method according to an embodiment of the present invention.
As shown in fig. 1, the method for identifying the offset of the material level of the belt conveyor comprises the following steps S110-S130:
s110, acquiring an image to be identified of the belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt area according to the edge position of the belt conveyor;
s120, identifying the material edge position of the image to be identified, and acquiring a material surface area according to the material edge position;
s130, acquiring a first central line according to the belt area, acquiring a second central line according to the material surface area, and comparing the first central line with the second central line to acquire a material surface offset 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 iron and steel smelting industry. The working video of the belt conveyor can be real-time working video of the belt conveyor, the image to be identified is obtained through the real-time video, and then the material level deviation identification result is obtained after the image to be identified is processed, so that the real-time monitoring of the working state of the belt conveyor is realized, the abnormal working state of the belt conveyor is conveniently and rapidly adjusted, and the purpose of reducing the loss caused by the material level deviation is achieved.
In an embodiment, a specific implementation method for identifying an edge position of a belt conveyor in an image to be identified may refer to fig. 2, and fig. 2 is a flow chart of a method for acquiring an edge position of a belt conveyor according to an embodiment of the present invention.
As shown in fig. 2, the method for acquiring the edge position of the belt conveyor may include the following steps S210 to S230:
s210, acquiring a sample image of the belt conveyor, and performing edge labeling on the sample image to acquire a sample data set;
s220, training a neural network by adopting a sample data set to obtain a belt conveyor edge recognition model;
s230, inputting the image to be identified into a belt conveyor edge identification model to obtain the edge position of the belt conveyor.
In step S210 of the present embodiment, a sample image of the belt conveyor may be acquired from an image or video of the belt conveyor. The step of carrying out edge labeling on the sample image to obtain a sample data set comprises the following steps: acquiring a central line of a sample image, and rotating the sample image until the central line of the sample image is vertical; cutting the rotated sample image until the rotating edge completely disappears, reserving the maximum image area, and obtaining a first image; adjusting the size of the first image according to the preset image size to obtain a second image; and carrying out edge labeling on the second image to obtain a sample data set. Specifically, the sizes of all the images in the sample data set are the same as the preset image size. Edge labeling the second image includes: and marking the left and right edges of the belt conveyor in the second image, and completely containing the edge curves of the belt conveyor.
In one embodiment, the neural network model includes, but is not limited to, SSD, YOLO series, RCNN, centerNet, and the like neural network models for image object detection.
In step S230 of the present embodiment, the step of inputting the image to be recognized into the belt conveyor edge recognition model to obtain the edge position of the belt conveyor includes: acquiring a central line of an image to be identified, and rotating the image to be identified until the central line of the image to be identified is vertical; cutting the rotated image to be identified until the rotating edge completely disappears, reserving the maximum image area, and obtaining a third image; adjusting the size of the third image according to the preset image size to obtain a fourth image; inputting the fourth image into a belt conveyor edge recognition model to obtain the edge position of the belt conveyor.
In one embodiment, the step of extracting the belt area based on the edge position of the belt conveyor comprises: acquiring left edge coordinates and right edge coordinates of the belt conveyor according to the edge position of the belt conveyor, wherein the left edge coordinates comprise left upper corner coordinates (x 1, y 1) and right lower corner coordinates (x 2, y 2) of the left edge, and the right edge coordinates comprise left upper corner coordinates (x 3, y 3) and right lower corner coordinates (x 4, y 4) of the right edge;
extracting a belt area according to the left edge coordinate and the right edge coordinate;
the mathematical expression of the image pixel values for the belt region is:
x left ＝(x1+x2)/2；
x right ＝(x3+x4)/2；
wherein x is left Is the left edge x coordinate, x of the belt conveyor right Is the right edge x coordinate of the belt conveyorImg (x, y) is the image pixel value of the belt region and src (x, y) is the image pixel value before extraction. The extracted belt area is rectangular.
The left edge and the right edge of the belt conveyor in the second image are marked, namely the left edge identification frame and the right edge identification frame of the belt conveyor in the second image are marked, so that the left edge coordinates and the right edge coordinates are the coordinates of the left edge identification frame and the coordinates of the right edge identification frame in sequence.
In order to ensure the accuracy of the material level deviation recognition result, after the coordinates of the left and right edge recognition frames of the belt conveyor are obtained, whether the coordinates of the recognition frames are the same edge recognition frame is further required to be judged, and if the left side of the recognition frame meets the following mathematical expression:
the acquired identification frames belong to the same edge; where k-pixel is the scaling of the image pixel distance and the actual distance, t is the distance threshold, and b is the belt width.
In order to improve accuracy of material level area identification, before identifying the material edge position of the image to be identified in the step, the method further comprises: and preprocessing the image to be identified. The pretreatment comprises the following steps: gray map conversion, histogram equalization, and image closure operations. Converting a gray level diagram, namely converting an image to be identified into a single-channel image from an RGB color three-channel image; histogram equalization, namely changing the original images to be identified with more concentrated gray level distribution into approximately uniform distribution so as to increase the contrast of the images; and (3) performing image closing operation, namely performing one-time expansion and one-time corrosion operation on the image to be identified, and closing a smaller gap on the premise of keeping the general distribution of the image unchanged so as to ensure that adjacent material images on the belt conveyor are connected together.
In particular, the process of histogram equalization can be expressed as:
wherein, the equize Hist is after equalizationN is the total number of image pixels, N j Is the number of pixels per gray level j, and L is the number of gray levels of the image (l=256).
The processing of the image closing operation comprises the following steps:
performing expansion processing on the image, setting a convolution kernel k with the size of n x n, and performing convolution processing on the equalized image G to be identified to obtain an image G', wherein mathematical expression of performing convolution processing on the image G is as follows:
performing corrosion treatment on the image G ', and performing convolution treatment on the image G' by adopting the convolution kernel k to obtain an image G ', wherein mathematical expression of performing convolution treatment on the image G' is as follows:
for image G', n pixels are scaled inward, but the connected pixel areas are not broken; this results in a processed image G which is substantially identical in distribution to the original image G, but which is in gap communication.
In step S130 of the present embodiment, the material edge position of the image to be identified is identified, and an operator for edge detection or a filter is used to identify the material edge position of the image to be identified. The operator or filter for edge detection includes, but is not limited to, canny, roberts, sobel, laplacian operator, scharr filter, and the like. In addition, a trained material edge recognition model can be used for recognizing the material edge position of the image to be recognized. Each part of continuous material image corresponds to a section of independent edge outline, and the edges are stored in a point set, namely if the materials in the working video of the belt conveyor are discontinuous materials, the material edge outline of the image to be identified corresponds to each pile of materials.
In one embodiment, the step of obtaining the level region based on the material edge location comprises: the edge contour of the material is subjected to a minimum circumscribed rectangle; acquiring the area of an external rectangle; if the area of the circumscribed rectangle is larger than a preset area threshold, selecting two circumscribed rectangles with the largest areas, and taking the circumscribed rectangles as a material surface area; if the area of the circumscribed rectangle is smaller than the preset area threshold, selecting two circumscribed rectangles with the largest area, and then performing circumscribed rectangles with the two circumscribed rectangles with the largest area to obtain the material surface area.
Specifically, the minimum circumscribed rectangle is made on the edge profile of the material, namely, the minimum circumscribed rectangle is made on each section of continuous profile of the material on the acquired belt conveyor; the upper left corner coordinates of the bounding rectangle may be represented as (x min ,y min ) The lower right corner coordinates of the bounding rectangle may be represented as (x max ,y max ) Wherein x is min 、x max 、y min And y max For four extreme points in each segment of the continuous edge profile: (x) min ,y xmin )、(x max ,y xmax )、(x ymin ,y xmin ) And (x) ymax ,y max ). Specifically, (x) min ,y xmin ) Taking the coordinate corresponding to the minimum value of the coordinate x of the material edge profile, (x) max ,y xmax ) Taking the coordinate corresponding to the maximum value of the coordinate x of the material edge profile (x) ymin ,y xmin ) Taking the coordinate corresponding to the minimum value for the coordinate y of the material edge profile, (x) ymax ,y max ) And taking the coordinate corresponding to the maximum value of the coordinate y of the material edge profile. The length of the circumscribed rectangle is x max -x min The width of the circumscribed rectangle is y max -y min 。
In step S130 of this embodiment, the first center line is the center line of the belt area, and the second center line is the center line of the burden surface area. Acquiring the center line of the belt region includes acquiring the upper left angular coordinates (X1, Y1) and the lower right angular coordinates (X2, Y2) of the belt region, and then the abscissa of the center line of the belt region is (x1+x2)/2. The center line of the material level region is obtained by obtaining the left upper corner coordinates (X3, Y3) and the right lower corner coordinates (X4, Y4) of the material level region, and then the horizontal coordinate of the center line of the belt region is (X3 + X4)/2.
In an embodiment, the step compares the center line of the charge level region with the center line of the charge level region to obtain a charge level pixel offset value, converts the charge level pixel offset value into an actual distance, and obtains the charge level offset value to obtain a charge level offset identification result. The mathematical expression of the charge level pixel offset value is:
s1＝|X5-X6|；
where s1 is the level pixel offset value, X5 is the abscissa of the belt area centerline, and X6 is the abscissa of the level area centerline.
The mathematical expression of the level offset value is:
s2＝s1*k-pixel；
where s1 is the level pixel offset value, s2 is the level offset value, and k-pixel is the scaling of the image pixel distance and the actual distance.
In an embodiment, if the deviation recognition result does not meet the preset condition, generating the alarm information, that is, the material level deviation value is greater than the preset deviation threshold value, and generating the alarm information. According to the embodiment, the deviation condition of the material level of the transported material on the belt conveyor can be well judged through the obtained material level deviation recognition result, if the material level deviation value of the belt conveyor is in an abnormal state, alarm information is generated, the abnormal state can be conveniently processed as soon as possible, so that loss caused by the material level deviation can be reduced, personal risk factors possibly brought by manual participation are avoided, and the safety of the material level deviation recognition is ensured.
Second embodiment
Based on the same inventive concept as the method in the first embodiment, correspondingly, the embodiment also provides a belt conveyor material level deviation recognition system.
Fig. 3 is a block diagram of a belt conveyor material level deviation recognition system provided by the invention.
As shown in fig. 3, the illustrated system 3 comprises: the device comprises a belt region acquisition module 31, a material surface region acquisition module 32 and a recognition result acquisition module 33.
The belt region acquisition module is used for acquiring an image to be identified of the belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt region according to the edge position of the belt conveyor;
the material surface area acquisition module is used for identifying the material edge position of the image to be identified and acquiring a material surface area according to the material edge position;
the recognition result acquisition module is used for acquiring a first central line according to the belt area, acquiring a second central line according to the material surface area, comparing the first central line with the second central line, and acquiring a material surface deviation recognition result; the first central line is the central line of the belt area, the second central line is the central line of the material surface area, and the belt area acquisition module, the material surface area acquisition module and the material surface area acquisition module are connected.
In some exemplary embodiments, the belt region acquisition module includes:
the data set acquisition unit is used for acquiring a sample image of the belt conveyor, and carrying out edge labeling on the sample image to acquire a sample data set;
the recognition model acquisition unit is used for training the neural network by adopting the sample data set to obtain a belt conveyor edge recognition model;
and the edge position acquisition unit is used for inputting the image to be identified into the belt conveyor edge identification model to acquire the edge position of the belt conveyor.
In some exemplary embodiments, the data set acquisition unit includes:
a rotation subunit, configured to acquire a center line of the sample image, and rotate the sample image until the center line of the sample image is vertical;
the first image acquisition subunit is used for cutting the rotated sample image until the rotating edge completely disappears, reserving the maximum image area and acquiring a first image;
the second image acquisition subunit is used for adjusting the size of the first image according to the preset image size to acquire a second image;
and the data set acquisition subunit is used for carrying out edge labeling on the second image to acquire a sample data set.
In some exemplary embodiments, the belt region acquisition module further comprises:
a coordinate acquiring unit configured to acquire a left edge coordinate and a right edge coordinate of the belt conveyor according to an edge position of the belt conveyor, wherein the left edge coordinate includes an upper left corner coordinate (x 1, y 1) and a lower right corner coordinate (x 2, y 2) of a left edge, and the right edge coordinate includes an upper left corner coordinate (x 3, y 3) and a lower right corner coordinate (x 4, y 4) of a right edge;
the belt unit extraction unit is used for extracting a belt area according to the left edge coordinate and the right edge coordinate;
the mathematical expression of the image pixel values for the belt region is:
x left ＝(x1+x2)/2；
x right ＝(x3+x4)/2；
wherein x is left Is the left edge x coordinate, x of the belt conveyor right For the belt conveyor right edge x coordinate, img (x, y) is the image pixel value of the belt region, and src (x, y) is the image pixel value before extraction.
In some exemplary embodiments, the belt conveyor charge level offset identification system further comprises:
the preprocessing module is used for preprocessing the image to be identified, and the preprocessing comprises the following steps: gray map conversion, histogram equalization, and image closure operations.
In some exemplary embodiments, the charge level region acquisition module includes:
the circumscribed rectangle acquisition unit is used for making a minimum circumscribed rectangle for the edge outline of the material;
an area acquisition unit for acquiring the area of the circumscribed rectangle;
the first execution unit is used for selecting two circumscribed rectangles with the largest area as a material surface area if the area of the circumscribed rectangles is larger than a preset area threshold value;
and the second execution unit is used for selecting two circumscribed rectangles with the largest area if the area of the circumscribed rectangle is smaller than a preset area threshold value, and then taking the circumscribed rectangle with the largest area as the circumscribed rectangle of the two circumscribed rectangles to obtain a material surface area.
In some exemplary embodiments, the recognition result acquisition module includes:
the offset value acquisition unit is used for comparing the first central line with the second central line to acquire a charge level pixel offset value;
the identification result acquisition unit is used for converting the charge level pixel offset value into an actual distance, acquiring the charge level offset value and obtaining a charge level offset identification result.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements any of the methods of the present embodiments.
The embodiment also provides an electronic device, including: 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 that the electronic device executes any one of the methods in the embodiment.
The computer readable storage medium in this embodiment, as will be appreciated by those of ordinary skill in the art: all or part of the steps for implementing the method embodiments described above may be performed by computer program related hardware. The aforementioned computer program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The electronic device provided in this embodiment includes a processor, a memory, a transceiver, and a communication interface, where the memory and the communication interface are connected to the processor and the transceiver and perform communication therebetween, the memory is used to store a computer program, the communication interface is used to perform communication, and the processor and the transceiver are used to run the computer program, so that the electronic device performs each step of the above method.
In this embodiment, the memory may include a random access memory (Random Access Memory, abbreviated as RAM), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In the foregoing embodiments, references in the specification to "this embodiment," "one embodiment," "another embodiment," "in some exemplary embodiments," or "other embodiments" indicate that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least some, but not necessarily all, embodiments. Multiple occurrences of "this embodiment," "one embodiment," "another embodiment," and "like" do not necessarily all refer to the same embodiment.
In the above embodiments, while 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 embodiments discussed. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
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 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 above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. It is therefore intended that all equivalent modifications and changes made by those skilled in the art without departing from the spirit and technical spirit of the present invention shall be covered by the appended claims.
Claims (7)
1. The belt conveyor material level deviation identification method is characterized by comprising the following steps of:
acquiring an image to be identified of a belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt area according to the edge position of the belt conveyor;
identifying the material edge position of the image to be identified, and acquiring a material surface area according to the material edge position;
acquiring a first central line according to the belt region, acquiring a second central line according to the material surface region, and comparing the first central line with the second central line to acquire a material surface deviation identification result; the first central line is the central line of the belt area, and the second central line is the central line of the material surface area;
the identifying the edge position of the belt conveyor in the image to be identified specifically comprises the following steps:
acquiring a sample image of the belt conveyor, and performing edge labeling on the sample image to acquire a sample data set;
training a neural network by adopting the sample data set to obtain a belt conveyor edge recognition model;
inputting the image to be identified into the belt conveyor edge identification model to obtain the edge position of the belt conveyor;
the edge labeling comprises left and right edge labeling, and the step of extracting the belt area according to the edge position of the belt conveyor specifically comprises the following steps:
acquiring left edge coordinates and right edge coordinates of the belt conveyor according to the edge position of the belt conveyor, wherein the left edge coordinates comprise left upper corner coordinates (x 1, y 1) and right lower corner coordinates (x 2, y 2) of the left edge, and the right edge coordinates comprise left upper corner coordinates (x 3, y 3) and right lower corner coordinates (x 4, y 4) of the right edge;
extracting a belt area according to the left edge coordinate and the right edge coordinate;
the mathematical expression of the image pixel values for the belt region is:
x left ＝(x1+x2)/2；
x right ＝(x3+x4)/2；
wherein x is left Is the left edge x coordinate, x of the belt conveyor right For the belt conveyor right edge x coordinate, img (x, y) is the image pixel value of the belt region, and src (x, y) is the image pixel value before extraction.
2. The method for identifying the offset of the material level of the belt conveyor according to claim 1, wherein the step of performing edge labeling on the sample image to obtain a sample data set specifically comprises:
acquiring a central line of the sample image, and rotating the sample image until the central line of the sample image is vertical;
cutting the rotated sample image until the rotating edge completely disappears, reserving the maximum image area, and obtaining a first image;
adjusting the size of the first image according to the preset image size to obtain a second image;
and carrying out edge labeling on the second image to obtain a sample data set.
3. The method for identifying the material level offset of the belt conveyor according to claim 1, further comprising, before the step of identifying the material edge position of the image to be identified:
preprocessing the image to be identified, wherein the preprocessing comprises the following steps: gray map conversion, histogram equalization, and image closure operations.
4. The method for identifying the offset of the charge level of the belt conveyor according to claim 1, wherein the step of comparing the first center line with the second center line to obtain the identification result of the offset of the charge level specifically comprises:
comparing the first central line with the second central line to obtain a charge level pixel offset value;
and converting the charge level pixel offset value into an actual distance, and obtaining a charge level offset value to obtain a charge level offset identification result.
5. A belt conveyor level offset identification system, the belt conveyor level offset identification system comprising:
the belt region acquisition module is used for acquiring an image to be identified of the belt conveyor, identifying the edge position of the belt conveyor in the image to be identified, and extracting a belt region according to the edge position of the belt conveyor;
the material surface area acquisition module is used for identifying the material edge position of the image to be identified and acquiring a material surface area according to the material edge position;
the recognition result acquisition module is used for acquiring a first central line according to the belt area, acquiring a second central line according to the material surface area, comparing the first central line with the second central line, and acquiring a material surface deviation recognition result; the first central line is the central line of the belt area, the second central line is the central line of the material surface area, and the belt area acquisition module, the material surface area acquisition module and the material surface area acquisition module are connected;
the belt region acquisition module includes:
the data set acquisition unit is used for acquiring a sample image of the belt conveyor, and carrying out edge labeling on the sample image to acquire a sample data set;
the recognition model acquisition unit is used for training the neural network by adopting the sample data set to obtain a belt conveyor edge recognition model;
the edge position acquisition unit is used for inputting the image to be identified into the belt conveyor edge identification model to acquire the edge position of the belt conveyor;
the belt region acquisition module further includes:
a coordinate acquiring unit configured to acquire a left edge coordinate and a right edge coordinate of the belt conveyor according to an edge position of the belt conveyor, wherein the left edge coordinate includes an upper left corner coordinate (x 1, y 1) and a lower right corner coordinate (x 2, y 2) of a left edge, and the right edge coordinate includes an upper left corner coordinate (x 3, y 3) and a lower right corner coordinate (x 4, y 4) of a right edge;
the belt unit extraction unit is used for extracting a belt area according to the left edge coordinate and the right edge coordinate;
the mathematical expression of the image pixel values for the belt region is:
x left ＝(x1+x2)/2；
x right ＝(x3+x4)/2；
wherein x is left Is the left edge x coordinate, x of the belt conveyor right For the belt conveyor right edge x coordinate, img (x, y) is the image pixel value of the belt region, and src (x, y) is the image pixel value before extraction.
6. 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 belt conveyor level offset identification method according to any one of claims 1 to 4.
7. A computer-readable storage medium having stored thereon a computer program for causing the computer to execute the belt conveyor level offset recognition method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993261.8A CN113674302B (en) | 2021-08-26 | 2021-08-26 | Belt conveyor material level deviation identification method, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110993261.8A CN113674302B (en) | 2021-08-26 | 2021-08-26 | Belt conveyor material level deviation identification method, system, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113674302A CN113674302A (en) | 2021-11-19 |
| CN113674302B true CN113674302B (en) | 2024-03-05 |
Family
ID=78546988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110993261.8A Active CN113674302B (en) | 2021-08-26 | 2021-08-26 | Belt conveyor material level deviation identification method, system, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674302B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1162130A (en) * | 1995-09-29 | 1997-10-15 | 德克萨斯仪器股份有限公司 | Central line aliasing-removing method for digital printing |
| KR101161247B1 (en) * | 2011-04-19 | 2012-07-02 | 서강대학교산학협력단 | Method of extracting the barcode |
| JP2013037009A (en) * | 2012-10-05 | 2013-02-21 | Horon:Kk | Contour line extraction method, contour line extraction program and area measuring method |
| CN106709909A (en) * | 2016-12-13 | 2017-05-24 | 重庆理工大学 | Flexible robot vision recognition and positioning system based on depth learning |
| CN108090912A (en) * | 2017-12-13 | 2018-05-29 | 李正伟 | A kind of track detection method and system based on image identification |
| CN109969736A (en) * | 2019-01-17 | 2019-07-05 | 上海大学 | A kind of large size carrier strip deviation fault intelligent detecting method |
| CN110514669A (en) * | 2019-07-31 | 2019-11-29 | 辽宁科技大学 | A kind of belt conveyor multizone spills material detection system and method |
| CN111661593A (en) * | 2020-06-24 | 2020-09-15 | 淄博蓝达智能视觉科技有限公司 | Visual detection error prevention system and position correction method for articles conveyed by conveyor belt |
| CN112712077A (en) * | 2020-12-30 | 2021-04-27 | 中冶赛迪重庆信息技术有限公司 | Steel flow contour determination method, system, terminal and medium |
| CN113255686A (en) * | 2021-07-15 | 2021-08-13 | 恒生电子股份有限公司 | Method and device for identifying seal in image, processing equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5862623B2 (en) * | 2013-08-08 | 2016-02-16 | カシオ計算機株式会社 | Image processing apparatus, image processing method, and program |
-
2021
- 2021-08-26 CN CN202110993261.8A patent/CN113674302B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1162130A (en) * | 1995-09-29 | 1997-10-15 | 德克萨斯仪器股份有限公司 | Central line aliasing-removing method for digital printing |
| KR101161247B1 (en) * | 2011-04-19 | 2012-07-02 | 서강대학교산학협력단 | Method of extracting the barcode |
| JP2013037009A (en) * | 2012-10-05 | 2013-02-21 | Horon:Kk | Contour line extraction method, contour line extraction program and area measuring method |
| CN106709909A (en) * | 2016-12-13 | 2017-05-24 | 重庆理工大学 | Flexible robot vision recognition and positioning system based on depth learning |
| CN108090912A (en) * | 2017-12-13 | 2018-05-29 | 李正伟 | A kind of track detection method and system based on image identification |
| CN109969736A (en) * | 2019-01-17 | 2019-07-05 | 上海大学 | A kind of large size carrier strip deviation fault intelligent detecting method |
| CN110514669A (en) * | 2019-07-31 | 2019-11-29 | 辽宁科技大学 | A kind of belt conveyor multizone spills material detection system and method |
| CN111661593A (en) * | 2020-06-24 | 2020-09-15 | 淄博蓝达智能视觉科技有限公司 | Visual detection error prevention system and position correction method for articles conveyed by conveyor belt |
| CN112712077A (en) * | 2020-12-30 | 2021-04-27 | 中冶赛迪重庆信息技术有限公司 | Steel flow contour determination method, system, terminal and medium |
| CN113255686A (en) * | 2021-07-15 | 2021-08-13 | 恒生电子股份有限公司 | Method and device for identifying seal in image, processing equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113674302A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11275961B2 (en) | Character image processing method and apparatus, device, and storage medium | |
| US9384398B2 (en) | Method and apparatus for roof type classification and reconstruction based on two dimensional aerial images | |
| CN113592886B (en) | Drawing examining method and device for building drawing, electronic equipment and medium | |
| CN111898610B (en) | Card unfilled corner detection method, device, computer equipment and storage medium | |
| CN111539238A (en) | Two-dimensional code image restoration method and device, computer equipment and storage medium | |
| CN113284117B (en) | Steel coil unwinding identification method, system, medium and terminal | |
| CN113674302B (en) | Belt conveyor material level deviation identification method, system, electronic equipment and medium | |
| CN113221742B (en) | Video split screen line determining method, device, electronic equipment, medium and program product | |
| CN111047619A (en) | Face image processing method and device and readable storage medium | |
| CN116434346B (en) | Method and device for detecting customer behaviors in unattended store and storage medium | |
| CN112308848A (en) | Method and system for identifying state of baffle plate of scrap steel truck, electronic equipment and medium | |
| CN113284115B (en) | Steel coil tower shape identification method, system, medium and terminal | |
| CN112001336A (en) | Pedestrian boundary crossing alarm method, device, equipment and system | |
| CN113674259B (en) | Belt conveyor slip detection method, system, electronic equipment and medium | |
| CN112733841B (en) | Method, system, equipment and medium for judging internal disorder of steel coil | |
| CN116402771A (en) | Defect detection method and device and model training method and device | |
| CN113674301A (en) | Method and system for identifying material flow strength, electronic equipment and medium | |
| CN113780269A (en) | Image recognition method, device, computer system and readable storage medium | |
| CN112712539B (en) | Machine vision-based converter tapping buggy ladle control method, system, medium and terminal | |
| CN114119419B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN116503407B (en) | Method and device for detecting foreign object region in image and electronic equipment | |
| CN117372408A (en) | Equipment detection method, device, equipment and storage medium | |
| CN114119609B (en) | Method, device and equipment for detecting image stain concentration and storage medium | |
| CN115761375A (en) | Moving object detection method, device, equipment and medium based on ore transportation | |
| CN114820672A (en) | Image processing method, image processing device, computer equipment and storage medium |
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 | ||
| 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |