CN113962956B - Foreign matter detection method for coal conveying belt conveyor - Google Patents
Foreign matter detection method for coal conveying belt conveyor Download PDFInfo
- Publication number
- CN113962956B CN113962956B CN202111223902.8A CN202111223902A CN113962956B CN 113962956 B CN113962956 B CN 113962956B CN 202111223902 A CN202111223902 A CN 202111223902A CN 113962956 B CN113962956 B CN 113962956B
- Authority
- CN
- China
- Prior art keywords
- image
- foreign matter
- frame
- coal
- detecting
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 108
- 238000012545 processing Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 24
- 230000000877 morphologic effect Effects 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 7
- 238000005520 cutting process Methods 0.000 claims abstract description 5
- 238000003708 edge detection Methods 0.000 claims abstract description 5
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 11
- 230000006872 improvement Effects 0.000 description 8
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007797 corrosion Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 241000519995 Stachys sylvatica Species 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—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
- G06T7/11—Region-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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method for detecting foreign matters of a coal conveyor belt, and belongs to the technical field of image detection. The method comprises the following steps: 1) Acquiring a real-time image of the belt conveyor through a monitoring camera; 2) Cutting each frame of image and converting the image into a gray level image; 3) Performing binarization processing on an input video sequence by using a threshold segmentation method; 4) Acquiring non-coal foreign matter information by adopting an improved algorithm fused by an inter-frame difference method and a background difference method; 5) Processing the image by adopting morphological opening operation; 6) Edge detection is carried out by adopting a canny operator; 7) Foreign object information is extracted from the processed image using a contour detection algorithm. The method is based on a computer image processing technology, and in the whole process, the collected real-time video is processed, the characteristics of the foreign matters are enhanced, and meanwhile, various interference factors in real-time monitoring are removed, so that the result of extracting the foreign matters of the coal conveyor by the later contour detection is more accurate.
Description
Technical Field
The invention belongs to the technical field of image detection, and particularly relates to a method for detecting foreign matters of a coal conveyor belt.
Background
The production of industrial raw coal is 39 hundred million tons in the world, and the total energy consumption is 49.8 hundred million tons of standard coal in the year of 2020, and meanwhile, the natural gas and petroleum resources of the country are relatively less, and other energy development has a plurality of restriction factors. Therefore, the coal industry has an important supporting function in the process of promoting the economic development of China and the living standard of people.
Along with the continuous expansion of the production scale of coal mines in China, the demand for coal resources is continuously increased, and the belt conveyor is used as main conveying equipment of coal and plays an important role in coal transportation. However, during the exploitation and transportation of raw coal, some foreign matters such as stone, wood, iron blocks, anchor rods and the like are often mixed in the coal, so that special people have to be arranged for inspection, and the foreign matters are prevented from entering the next working procedure. However, the manual inspection is adopted to leak the foreign matters, so that the leaked foreign matters not only can lead to the improvement of transportation cost, but also can easily damage equipment in the subsequent process, and meanwhile, the foreign matters can also lead to the blocking of a nozzle of coal injection equipment, and the tearing of a belt conveyor is serious, so that the production efficiency of a factory is influenced. Therefore, the machine identification is used for replacing manual detection, so that the identification precision of foreign matters is improved, the quality of coal is improved, and the production cost and human resources are saved.
At present, the traditional detection method mainly comprises manual detection, metal detection, radar detection and the like. Wherein, as mentioned in the above, manual detection is time-consuming and labor-consuming, and has potential safety hazard. The metal detection deployment is difficult, and the application range is small. The radar monitoring has the problems of high cost, difficult maintenance and low accuracy. Therefore, the conventional methods have limitations, and are difficult to be widely applied to detecting the foreign matters in the coal conveyor belt.
With the development of modern computers, computer vision technology is increasingly being used in various fields of industrial production. After investigation and analysis, if the actual images of the workshops can be identified and detected by adopting an algorithm based on computer vision, then the result information is timely returned to an operator and the operator is informed to carry out corresponding next treatment, so that the detection efficiency and detection precision of the foreign matters of the belt conveyor can be effectively increased, the quality of coal is improved, the labor intensity of workers is reduced, and the production cost of factories is saved. However, due to the complex working environment of the coal transporting workshop, the variety of foreign matters is great, and the existing computer vision-based algorithm is difficult to apply in such complex scene.
Disclosure of Invention
1. Problems to be solved
Aiming at the problems that the conventional algorithm is large in limitation in detecting the foreign matters in the transportation of the belt conveyor and the conventional algorithm based on computer vision is difficult to apply to the transportation of the belt conveyor in the complex scene, the invention provides the detection method for the foreign matters in the transportation of the coal conveyor, which is used for acquiring images of the transportation condition of the belt conveyor to obtain real-time videos and effectively improving the accuracy of the finally obtained foreign matters images by adopting an improved algorithm fused with an inter-frame difference method and a background difference method.
2. Technical proposal
In order to solve the problems, the invention adopts the following technical scheme.
A method for detecting foreign matters of a coal conveyor belt comprises the following steps:
Step 1), carrying out real-time video acquisition on the transportation condition of a coal transportation belt conveyor through an image acquisition device;
step 2), carrying out image cutting and gray level map conversion on each frame of image of the acquired video, wherein the gray level map conversion process adopts the following formula:
g(x,y)=(R*0.299+G*0.587+B*0.114+500)/1000
Wherein g (x, y) represents the output gray value; r represents red in the input pixel, G represents green in the input pixel, and B represents blue in the input pixel;
Step 3), processing the cut image by using a threshold segmentation method to convert the cut image into a binary image, wherein the process is as follows:
wherein f (x, Y) is g (x, Y) in step 2), Y' n (x, Y) is the processed pixel, and T is the threshold;
and 4) processing the video sequence by adopting an inter-frame difference method to obtain a detection image, wherein the processing process is as follows:
bn(x,y)=f(j,j-1)(x,y)∩f(j+1,j)(x,y)
Dn(x,y)=f(j+1,j-1)(x,y)∪bn(x,y)
Wherein I J-1(x,y),IJ(x,y),IJ+1 (x, y) is a previous frame, a current frame and a next frame in the video respectively, f (j,j-1)(x,y)、f(j+1,j) (x, y) and f (j+1,j-1) (x, y) are image frames generated by dividing g (j,j-1)(x,y)、g(j+1,j) (x, y) and g (j+1,j-1) (x, y) by threshold values respectively, g (j,j-1)(x,y)、g(j+1,j) (x, y) and g (j+1,j-1) (x, y) are gray values of the previous frame, the current frame and the next frame in the video respectively, b n (x, y) is a result obtained by an inter-frame difference method, and D n (x, y) is an improved foreign object feature enhancement result;
Then, the video sequence is processed by adopting a background difference method, and the process is as follows:
Bn(x,y)=||Fn(x,y)-Pn(x,y)||
Cn(x,y)=Dn(x,y)∪Bn(x,y)
Wherein F n (x, y) is a background image, P n (x, y) is a current frame, B n (x, y) is a result obtained after a background difference method operation, and C n (x, y) is a result of a background difference method and an interframe difference fusion operation;
If the detected image obtained by the inter-frame difference method has no foreign matter, updating P n (x, y) into F n (x, y), and if the inter-frame difference method detects the foreign matter, performing OR operation on the current frame and the background difference method to obtain a processed image;
step 5), processing the processed image again by adopting a morphological method, wherein the process is as follows:
Wherein A is the step, B is the structural element, A.sup.X is the result of morphological processing of the image;
step 6), carrying out edge detection on the image obtained in the step 5) by adopting a canny operator to obtain an image with object edge information;
Step 7), extracting foreign matter information from the image obtained in the step 6) by using a contour detection algorithm.
As a further improvement of the technical scheme, in the step 1), an image acquisition device is arranged right above the coal conveying belt conveyor.
As a further improvement of the technical scheme, the image acquisition device comprises a camera and a light source.
As a further improvement of the technical solution, in the step 1), the image frame rate of the collected video is 18fps.
As a further improvement of the technical scheme, the device also comprises an alarm device, wherein in the step 7), when the foreign matter information is extracted, the alarm system alarms, and meanwhile, the current frame is stored in the computer folder.
As a further improvement of the technical scheme, the method further comprises the following steps: in the step 7), after the foreign matter information is obtained, the parameters of the obtained foreign matter information are processed, and the foreign matter information meeting the conditions is stored in a database according to the set parameter range of the foreign matter to be detected.
As a further improvement of the technical scheme, the method further comprises the following steps: and through pyqt, calling a label component, and displaying the image processed in the step 5) on a user interface in a real-time picture.
As a further improvement of the technical scheme, the structural element templates adopted in the step 5) are as follows:
3. Advantageous effects
Compared with the prior art, the invention has the beneficial effects that:
(1) The method for detecting the foreign matters of the coal conveyor comprises the steps of acquiring images of the conveying condition of the conveyor to obtain real-time video, processing the obtained video by adopting an improved algorithm fused with an inter-frame difference method and a background difference method, and removing various interference factors in real-time monitoring while enhancing the characteristics of the foreign matters, so that the result of extracting the foreign matters of the conveyor of the coal conveyor by the later profile detection is more accurate, and the accuracy of the finally obtained foreign matters is effectively improved;
(2) The method for detecting the foreign matters of the coal conveyor belt comprises the steps of preprocessing collected videos frame by frame, namely image cutting and gray level diagram conversion, wherein areas needing to be identified are cut out through the images, interference of surrounding factors is reduced, convenience is provided for subsequent inter-frame processing through gray level diagram conversion, and subsequent processing precision is improved;
(3) The method for detecting the foreign matters of the coal conveyor uses a threshold segmentation method to process and convert the image into a binary image, and because the chromaticity of the coal is lower, the foreign matters can be relatively highlighted, and the moving coal blocks can be ignored after the threshold processing, so that the interference of the moving coal blocks on the recognition of the foreign matters is eliminated, and the accuracy of the subsequent algorithm recognition is ensured;
(4) The method for detecting the foreign matters of the coal conveyor uses an improved algorithm combining an inter-frame difference method and a background difference method to process adjacent frames, solves the problems that double shadows, hollows and omission are generated when the independent inter-frame difference method is used for identifying foreign matters images and the independent background difference method is difficult to apply to a moving scene, combines the advantages of the two algorithms to improve, and greatly improves the accuracy and the anti-interference capability of the later foreign matter detection;
(5) The foreign matter image obtained by the algorithm is processed by adopting a morphological method, so that the large-area object is not influenced, and meanwhile, small white spots caused by other interferences in the image are eliminated, the interferences are reduced, and the subsequent detection is facilitated;
(6) A foreign matter detection method for a coal conveying belt conveyor is characterized in that an obtained image is processed, the processed image is fed back to a user interface in real time by using a lable component, a current detection result is displayed in real time, on-site staff can check the detection result at any time, clear the foreign matter and shut down a conveyor belt, the production efficiency is improved, and the economic effect of enterprises is increased.
Drawings
FIG. 1 is a flow chart of a method for detecting foreign matter on a coal conveyor belt;
Fig. 2 is a current frame image without foreign matter;
FIG. 3 is an image of FIG. 2 without morphological processing;
FIG. 4 is an image of the morphological treatment of FIG. 2;
FIG. 5 is a flow chart of step 4);
FIG. 6 is a stick diagram of inclusions in coal identified using a conventional algorithm;
FIG. 7 is a stick diagram of inclusions in coal identified using the algorithm of step 4);
FIG. 8 is a graph of foreign matter entrained in coal identified using a conventional algorithm;
FIG. 9 is a graph of foreign matter entrained in coal identified using the algorithm of step 4).
Detailed Description
The invention is further described below in connection with specific embodiments and the accompanying drawings.
Example 1
Because the foreign matters in the coal easily cause the damage of the coal conveying equipment, the current situations of shutdown of a factory production line, economic loss and the like are caused, raw coal is generally required to be filtered through a screening device when being input into a belt conveyor and is removed by site workers, but occasionally, partial foreign matters are blocked and fail, so that the belt conveyor is torn, the coal conveying device is damaged and the like. With the continuous development of technology, detection methods such as metal detection and radar detection are generated, and the adoption of the detection methods has a plurality of limitations, so that the detection methods are difficult to deploy and maintain, and foreign matters cannot be detected well.
In order to solve the above problems, as shown in fig. 1, the embodiment provides a method for detecting a foreign matter of a coal conveyor belt, which includes the following steps:
step 1), carrying out real-time video acquisition on the transportation condition of the coal transportation belt conveyor through an image acquisition device, wherein the image acquisition device is arranged right above the coal transportation belt conveyor and comprises a camera and a light source, and the image frame rate of the acquired video is 18fps.
The network camera is arranged right above the coal conveying belt conveyor and the light source is assembled, so that interference factors outside a target area can be reduced, and the collected video is more convenient to detect.
Step 2), preprocessing the acquired video frame by frame, namely cutting each frame of image and converting a gray level map, wherein the gray level map conversion process adopts the following formula:
g(x,y)=(R*0.299+G*0.587+B*0.114+500)/1000
wherein g (x, y) represents the output gray value; r represents red in the input pixel, G represents green in the input pixel, and B represents blue in the input pixel.
The region to be identified is cut out through the image, the interference of surrounding factors is reduced, the gray level image conversion provides convenience for the subsequent inter-frame processing, and the subsequent processing precision is improved.
Step 3), processing the cut image by using a threshold segmentation method to convert the cut image into a binary image, wherein the process is as follows:
Where f (x, Y) is g (x, Y) of step 2), Y n' (x, Y) is the processed pixel, and T is the threshold. The size of T can be manually adjusted according to the field environment, and T in the embodiment is 130; for Y 'n (x, Y), the system developed a corresponding interface, Y n' (x, Y) was set to 1 for pixel gray value of 255, denoted as foreground, 0 for pixel gray value of 0, denoted as background, the foreground representing the area where the foreign object needs to be detected, and the background being the normal area without the foreign object.
The defect of the inter-frame difference method and the background difference method for detecting the foreign matters on the belt conveyor is that all moving objects can be captured, and the images are processed and converted into binary images by using a threshold segmentation method, so that the foreign matters can be highlighted relatively due to lower chromaticity of coal, and moving coal blocks can be ignored after threshold processing, thereby eliminating the interference of the moving coal blocks on the recognition of the foreign matters and ensuring the accuracy of the recognition of a subsequent algorithm.
And 4) processing the video sequence by adopting an inter-frame difference method to obtain a detection image, wherein the processing process is as follows:
bn(x,y)=f(j,j-1)(x,y)∩f(j+1,j)(x,y)
Dn(x,y)=f(j+1,j-1)(x,y)∪bn(x,y)
Wherein I J-1(x,y),IJ(x,y),IJ+1 (x, y) is a previous frame, a current frame and a next frame in the video, f (j,j-1)(x,y)、f(j+1,j) (x, y) and f (j+1,j-1) (x, y) are image frames generated by threshold segmentation of g (j,j-1)(x,y)、g(j+1,j) (x, y) and g (j+1,j-1) (x, y), g (j,j-1)(x,y)、g(j+1,j) (x, y) and g (j+1,j-1) (x, y) are gray values of the previous frame, the current frame and the next frame in the video, b n (x, y) is a result obtained by an inter-frame difference method, and D n (x, y) is an improved foreign object feature enhancement result.
Then, according to the result of the detected image by the inter-frame difference method, the video sequence is processed by the background difference method, and the processed image is obtained, wherein the process is as follows:
Bn(x,y)=||Fn(x,y)-Pn(x,y)||
Cn(x,y)=Dn(x,y)∪Bn(x,y)
Wherein F n (x, y) is a background image, P n (x, y) is a current frame, B n (x, y) is a result obtained after the background difference method operation, and C n (x, y) is a result of the background difference method and the interframe difference fusion operation.
If the detected image obtained by the inter-frame difference method has no foreign matter, updating P n (x, y) to F n (x, y), and if the inter-frame difference method detects the foreign matter, performing OR operation on the current frame and the background difference method to obtain a processed image.
The common three-frame difference method can cause the generation of a cavity in the foreign object image, when the motion trail of the foreign object covers up the self in three frames, the object can be missed by the algorithm processing, and in order to solve the problems and improve the recognition rate, a series of fusion can be carried out on the images generated by the three frames of difference to strengthen the foreign object information in the images. However, although the foreign matters can be accurately detected without interference, the recognition rate is improved, the fused image outline is far from the original image, and one foreign matter can be detected into a plurality of foreign matters during edge detection, so that the foreign matter information is not only influenced to be stored in a database, but also the production requirement is not met, and redundant data is generated.
Aiming at the problems, the embodiment adopts an improved algorithm which fuses an inter-frame difference method and a background difference method to extract the foreign object image, and combines the advantages of the two algorithms to process the image. Firstly, an improved frame difference method is adopted to obtain a detection image, then contour detection is adopted to judge the detection image, if no foreign matter is detected, the current frame is updated into a background image of the background difference method in the background difference method, and if an object is detected, the processed image is obtained by using the background difference method for the current frame. Through the processing process, the system can accurately identify the non-coal foreign matters, reduce false detection and improve production efficiency.
Step 5), processing the processed image again by adopting morphological opening operation methods such as corrosion, expansion and the like, wherein the process is as follows:
wherein A is the step, B is the structural element, A.sup.X is the result of morphological processing of the image; the structural elements are the most basic components of expansion and corrosion operation, the operation effect depends on the size content of the structural elements, and the structural element templates adopted by the method are as follows:
the embodiment ensures that a large-area object is not affected by morphological processing such as corrosion and expansion, and simultaneously eliminates small white spots caused by other interferences in the image, reduces the interferences and is convenient for subsequent detection.
And 6) adopting a canny operator to perform edge detection on the image obtained in the step 5) to obtain an image with object edge information.
The embodiment can well describe the foreign object edge in the image processed by the algorithm, and is favorable for the subsequent contour detection algorithm processing.
And 7) performing contour detection and labeling on the image obtained in the step 6) by adopting a findContours algorithm method to obtain the size and position information of the foreign matters.
In summary, according to the method for detecting the foreign matters of the coal conveyor belt in the embodiment, the image acquisition is performed on the conveyor belt transportation condition to obtain the real-time video, and the inter-frame difference method and the background difference method are fused to process the obtained video, so that the accuracy of the finally obtained foreign matter image is effectively improved.
Example 2
The foreign matter detection method of the coal conveying belt conveyor of the embodiment is improved on the basis of the embodiment 1:
Because of the change of environment or illumination in the whole detection process, the detection accuracy rate is relatively dependent on the setting of the threshold value in the step 3), however, the system may need to be applied to a plurality of belt conveyors for detection on site, and the system cannot be adjusted in time, so that the problems of inaccurate identification and the like may be caused.
In order to avoid the problems, the threshold value in the step 3) can be stored in a database, and a worker can select and adjust the threshold value in the database in real time according to the corresponding belt conveyor in a user interface, so that the production efficiency is improved as much as possible while the accuracy is ensured, and the smooth implementation of the actual production process is ensured.
In addition, in order to be convenient for on-the-spot staff more directly perceivedly look over testing result, still include:
In step 7), after the foreign matter information is obtained, the obtained data is processed, through screening the size range of the foreign matter preset by workers, when the foreign matter meeting the requirements is detected, the workers are warned through a warning system music, meanwhile, the screenshot of the foreign matter is put into a single folder, and the information of the size, the detection time, the position of the foreign matter and the like of the foreign matter is stored in a database.
In addition, the lambel component is called through pyqt, the image processed in the step 5) is displayed on a user interface in a real-time picture for displaying detection information, so that on-site staff can observe the image on the user interface intuitively, and corresponding measures can be taken timely.
The examples of the present invention are merely for describing the preferred embodiments of the present invention, and are not intended to limit the spirit and scope of the present invention, and those skilled in the art should make various changes and modifications to the technical solution of the present invention without departing from the spirit of the present invention.
Claims (8)
1. A method for detecting foreign matters of a coal conveyor belt comprises the following steps:
Step 1), carrying out real-time video acquisition on the transportation condition of a coal transportation belt conveyor through an image acquisition device;
step 2), carrying out image cutting and gray level map conversion on each frame of image of the acquired video, wherein the gray level map conversion process adopts the following formula:
g(x,y)=(R*0.299+G*0.587+B*0.114+500)/1000
Wherein g (x, y) represents the output gray value; r represents red in the input pixel, G represents green in the input pixel, and B represents blue in the input pixel;
Step 3), processing the cut image by using a threshold segmentation method to convert the cut image into a binary image, wherein the process is as follows:
wherein f (x, Y) is g (x, Y) in step 2), Y' n (x, Y) is the processed pixel, and T is the threshold;
and 4) processing the video sequence by adopting an inter-frame difference method to obtain a detection image, wherein the processing process is as follows:
bn(x,y)=f(j,j-1)(x,y)∩f(j+1,j)(x,y)
Dn(x,y)=f(j+1,j-1)(x,y)∪bn(x,y)
Wherein I J-1(x,y),IJ(x,y),IJ+1 (x, y) is a previous frame, a current frame and a next frame in the video respectively, f (j,j-1)(x,y)、f(j+1,j) (x, y) and f (j+1,j-1) (x, y) are image frames generated by dividing g (j,j-1)(x,y)、g(j+1,j) (x, y) and g (j+1,j-1) (x, y) by threshold values respectively, g (j,j-1)(x,y)、g(j+1,j) (x, y) and g (j+1,j-1) (x, y) are gray values of the previous frame, the current frame and the next frame in the video respectively, b n (x, y) is a result obtained by an inter-frame difference method, and D n (x, y) is an improved foreign object feature enhancement result;
Then, the video sequence is processed by adopting a background difference method, and the process is as follows:
Bn(x,y)=||Fn(x,y)-Pn(x,y)||
Cn(x,y)=Dn(x,y)∪Bn(x,y)
Wherein F n (x, y) is a background image, P n (x, y) is a current frame, B n (x, y) is a result obtained after a background difference method operation, and C n (x, y) is a result of a background difference method and an interframe difference fusion operation;
If the detected image obtained by the inter-frame difference method has no foreign matter, updating P n (x, y) into F n (x, y), and if the inter-frame difference method detects the foreign matter, performing OR operation on the current frame and the background difference method to obtain a processed image;
step 5), processing the processed image again by adopting a morphological method, wherein the process is as follows:
Wherein A is the step, B is the structural element, A.sup.X is the result of morphological processing of the image;
step 6), carrying out edge detection on the image obtained in the step 5) by adopting a canny operator to obtain an image with object edge information;
Step 7), extracting foreign matter information from the image obtained in the step 6) by using a contour detection algorithm.
2. The method for detecting the foreign matters of the coal conveyor belt according to claim 1, wherein the method comprises the following steps: in the step 1), an image acquisition device is arranged right above the coal conveying belt conveyor.
3. The method for detecting the foreign matter of the coal conveyor belt according to claim 2, wherein: the image acquisition device comprises a camera and a light source.
4. The method for detecting the foreign matter of the coal conveyor belt according to claim 3, wherein: in the step 1), the image frame rate of the collected video is 18fps.
5. The method for detecting the foreign matter of the coal conveyor belt according to claim 3, wherein: the system also comprises an alarm device, wherein in the step 7), when the foreign matter information is extracted, the alarm system alarms, and meanwhile, the current frame is stored in a computer folder.
6. The method for detecting the foreign matter of the coal conveyor belt according to any one of claims 1 to 5, characterized by: the method also comprises the following steps: in the step 7), after the foreign matter information is obtained, the parameters of the obtained foreign matter information are processed, and the foreign matter information meeting the conditions is stored in a database according to the set parameter range of the foreign matter to be detected.
7. The method for detecting the foreign matter of the coal conveyor belt according to any one of claims 1 to 5, characterized by: the method also comprises the following steps: and through pyqt, calling a label component, and displaying the image processed in the step 5) on a user interface in a real-time picture.
8. The method for detecting the foreign matter of the coal conveyor belt according to any one of claims 1 to 5, characterized by: the structural element templates adopted in the step 5) are as follows:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111223902.8A CN113962956B (en) | 2021-10-18 | 2021-10-18 | Foreign matter detection method for coal conveying belt conveyor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111223902.8A CN113962956B (en) | 2021-10-18 | 2021-10-18 | Foreign matter detection method for coal conveying belt conveyor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113962956A CN113962956A (en) | 2022-01-21 |
CN113962956B true CN113962956B (en) | 2024-04-19 |
Family
ID=79465158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111223902.8A Active CN113962956B (en) | 2021-10-18 | 2021-10-18 | Foreign matter detection method for coal conveying belt conveyor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113962956B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846359A (en) * | 2017-01-17 | 2017-06-13 | 湖南优象科技有限公司 | Moving target method for quick based on video sequence |
CN107176432A (en) * | 2017-06-15 | 2017-09-19 | 西安科技大学 | A kind of anchor pole foreign matter and belt tearing detecting system based on machine vision |
CN110015553A (en) * | 2019-04-17 | 2019-07-16 | 华夏天信(北京)智能低碳技术研究院有限公司 | Travelling belt system foreign bodies detection guard method based on video analysis |
CN113469071A (en) * | 2021-07-06 | 2021-10-01 | 西安科技大学 | Video detection method for foreign matters in coal conveying belt for embedded equipment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6410118B1 (en) * | 2017-03-29 | 2018-10-24 | パナソニックIpマネジメント株式会社 | Vehicle door monitoring system and vehicle door monitoring method |
-
2021
- 2021-10-18 CN CN202111223902.8A patent/CN113962956B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846359A (en) * | 2017-01-17 | 2017-06-13 | 湖南优象科技有限公司 | Moving target method for quick based on video sequence |
CN107176432A (en) * | 2017-06-15 | 2017-09-19 | 西安科技大学 | A kind of anchor pole foreign matter and belt tearing detecting system based on machine vision |
CN110015553A (en) * | 2019-04-17 | 2019-07-16 | 华夏天信(北京)智能低碳技术研究院有限公司 | Travelling belt system foreign bodies detection guard method based on video analysis |
CN113469071A (en) * | 2021-07-06 | 2021-10-01 | 西安科技大学 | Video detection method for foreign matters in coal conveying belt for embedded equipment |
Also Published As
Publication number | Publication date |
---|---|
CN113962956A (en) | 2022-01-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111754466B (en) | Intelligent detection method for damage condition of conveyor belt | |
CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN111289538A (en) | PCB element detection system and detection method based on machine vision | |
CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
CN109911550A (en) | Scratch board conveyor protective device based on infrared thermal imaging and visible light video analysis | |
CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
CN110473184A (en) | A kind of pcb board defect inspection method | |
CN115601355A (en) | Method and device for detecting and classifying product surface defects and storage medium | |
CN110519566B (en) | Belt motion state monitoring method based on video processing | |
CN116188459B (en) | Line laser rapid identification method and system for belt tearing detection | |
CN116228651A (en) | Cloth defect detection method, system, equipment and medium | |
CN113361420A (en) | Mine fire monitoring method, device and equipment based on robot and storage medium | |
CN105619741B (en) | A kind of mould intelligent detecting method based on Tegra K1 | |
CN106872477A (en) | Car engine seal open defect fault detection system | |
CN113962956B (en) | Foreign matter detection method for coal conveying belt conveyor | |
CN113469938A (en) | Pipe gallery video analysis method and system based on embedded front-end processing server | |
CN106370673A (en) | Automatic lens flaw detection method | |
CN208155893U (en) | binocular vision scratch detection system based on high speed camera | |
CN109272480B (en) | Detection method for boundary of immiscible solution | |
CN114782808A (en) | Scrap steel grading identification method and system based on machine vision algorithm | |
CN105095897A (en) | Gradient image and similarity weight based digit identification method | |
Wang et al. | Visual defect detection for substation equipment based on joint inspection data of camera and robot | |
Xu et al. | Detection method of edge position of belt conveyor based on complex environment | |
CN110674754A (en) | Online intermittent hollow filter stick visual defect detection and identification system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |