CN110015553B - Foreign matter detection and protection method for conveyor belt system based on video analysis - Google Patents
Foreign matter detection and protection method for conveyor belt system based on video analysis Download PDFInfo
- Publication number
- CN110015553B CN110015553B CN201910309980.6A CN201910309980A CN110015553B CN 110015553 B CN110015553 B CN 110015553B CN 201910309980 A CN201910309980 A CN 201910309980A CN 110015553 B CN110015553 B CN 110015553B
- Authority
- CN
- China
- Prior art keywords
- belt
- camera
- conveyor belt
- image
- belt system
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
Landscapes
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Control Of Conveyors (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a foreign matter detection and protection method of a conveyor belt system based on video analysis, which comprises the steps of collecting image information of materials of two adjacent conveyor belts of the conveyor belt system, carrying out analysis processing by using an algorithm engine module on a main control industrial personal computer, carrying out image denoising and image enhancement preprocessing by adopting Gaussian filtering, detecting scale-invariant feature points by adopting a Gaussian scale space, drawing a foreign matter contour according to the feature points, giving an alarm by the algorithm engine module and recording an abnormal contour when the abnormal contour appears, and simultaneously rapidly sending a control signal to the conveyor belt system according to the severity of the abnormality. According to the method, the camera is used for collecting the belt image, the image characteristics are extracted, the foreign matter condition is found through video analysis, an alarm is generated in time, and the belt is stopped in time under the serious condition, so that the functions of alarming the foreign matter and protecting the belt are realized, and the safe and orderly production of a coal mine is guaranteed.
Description
Technical Field
The invention relates to a safety protection method for a coal mine monitoring video, in particular to a foreign matter detection protection method for a conveyor belt system based on video analysis.
Background
In the process of production on mines, coal transportation mainly depends on a transportation belt system, but various foreign matters are mixed in the coal in the process of mining, and the foreign matters are different in shape and can cause serious damage to the belt in the process of transportation, so that the transportation and production of the belt are influenced.
Disclosure of Invention
The invention provides a foreign matter detection and protection method of a conveyor belt system based on video analysis, which solves the problem of detecting foreign matters on a conveyor belt through a camera and adopts the following technical scheme:
a foreign matter detection and protection method of a conveyor belt system based on video analysis comprises the following steps:
(1) a first camera is arranged right above one certain upstream belt of the conveying belt system, acquires image information of the upstream belt and transmits video streams to the master industrial personal computer;
(2) the downstream belt is adjacent to the upstream belt, receives the materials of the upstream belt, is provided with a second camera right above the upstream belt, collects corresponding image information of the downstream belt, and transmits the video stream to the master control industrial personal computer for analysis and processing;
(3) an algorithm engine module is arranged in the master control industrial personal computer, and image denoising and image enhancement preprocessing are performed on image information of the same region acquired by the first camera and the second camera by adopting Gaussian filtering;
(4) detecting scale-invariant feature points by adopting a Gaussian scale space, and then drawing a foreign body contour according to the feature points;
(5) when an abnormal profile occurs, the algorithm engine module alarms and records the abnormal profile, and simultaneously, a control signal is rapidly sent to the conveyor belt system according to the severity of the abnormality.
The first camera and the second camera are connected to the master control industrial personal computer through the switch.
The upstream belt and the downstream belt are correspondingly provided with power control systems, and the power control systems are connected to a master control industrial personal computer through a switch; when the conveyor belt is loaded with coal for transport, the power control system activates the algorithm engine module of the conveyor belt system.
In the step (3), the gaussian filtering is to scan each pixel in the image by using a template, and replace the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template.
In the step (3), the laplacian operator performs image enhancement according to that when the gray level of the central pixel of the neighborhood is lower than the average gray level of other pixels in the domain where the central pixel is located, the gray level of the central pixel is further reduced, and when the gray level of the central pixel of the neighborhood is higher than the average gray level of other pixels in the neighborhood where the central pixel is located, the gray level of the central pixel is further improved, so that the image enhancement processing is realized.
In step (4), invariant feature points in the scale are detected by using a gaussian scale space, the kernel which can only generate the scale space is a gaussian kernel function, and the scale space of the image is represented as a function L (x, y, σ), which is generated by convolving a gaussian function G (x, y, σ) with an image I (x, y), namely L (x, y, σ) ═ G (x, y, σ) · I (x, y). Where x, y represent the horizontal and vertical coordinates of the pixels in the image and σ represents the gaussian smoothing factor.
In the step (5), the foreign body outline is identified by using a machine learning mode, when no foreign body exists, the coal briquette is filtered when the characteristic extraction is carried out, and at the moment, the belt can normally run.
In the step (5), when the abnormal contour is not serious, the conveyer belt system informs a worker; when the foreign matters seriously exceed the limit, the conveying belt system controls the corresponding power control system to decelerate or stop the belts at all levels in time.
The method collects image information of multi-stage belts for continuous material conveying and sequentially detects foreign matters of adjacent belts.
According to the method, the camera is used for collecting the belt image, the image characteristics are extracted, the foreign matter condition is found through video analysis, an alarm is generated in time, and the belt is stopped in time under the serious condition, so that the functions of alarming the foreign matter and protecting the belt are realized, and the safe and orderly production of a coal mine is guaranteed.
Drawings
FIG. 1 is a schematic view of the installation structure of the present invention relating to the relevant apparatus;
FIG. 2 is a flow chart of a foreign object detection protection method provided by the present invention;
fig. 3 is a flowchart of an algorithm engine module of the foreign object detection protection method provided by the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
As shown in figure 1, the related device applied to the conveying belt system comprises cameras which are arranged right above two adjacent conveying belts, and the cameras and power control systems corresponding to the conveying belts are connected with a master control industrial personal computer through a switch.
A first camera 1 is mounted directly above the upstream belt 3 and a second camera 2 is mounted directly above the downstream belt 4 of the upstream belt 3. The corresponding regions photographed by the first camera 1 and the second camera 2 are the same.
For this purpose, the first camera 1 photographs the zone D1 of the upstream belt 3, which zone D1, when the material is conveyed to the downstream belt 4, forms the zone D2 correspondingly, and the second camera 2 photographs the zone D2, that is to say, the captured image zones in which the first camera 1 and the second camera 2 are mounted correspond. This can be achieved by setting the distance, position and speed of belt transport of the camera relative to the belt.
Two cameras pass through fiber connection to switch 7, and switch 7 passes through on fiber connection to master control industrial computer 8.
The upstream belt 3 corresponds to a first belted power control system 5 and the downstream belt 4 corresponds to a second belted power control system 6. The first power control system 5 and the second power control system 6 are also connected to a main control industrial personal computer 8 through optical fibers and an exchanger 7.
The first camera 1 collects image information of materials of the upstream belt 3, the materials fall onto the downstream belt 4 from the upstream belt 3 to be conveyed continuously, abnormal objects cannot exist during normal production, and therefore the materials cannot be influenced by shape change in the transportation process. Then, the video stream is transmitted to an algorithm engine module of the master control industrial personal computer 8 for analysis and processing through image information of the belt surface shot by the two cameras.
When foreign matters such as anchor rods, iron rods, huge stones and the like appear in the conveying process of the belt, the anchor rods and the iron rods are special in shape and are strip-shaped relative to the coal blocks, metal objects are easy to reflect light and are easy to identify, and the huge stones are much larger than normal coal blocks in size. Therefore, the foreign matters can change the shape of the material, and then are analyzed by the algorithm engine module.
The master control industrial computer 8 can judge according to the size and the severity of foreign matter to in time report to the police near the staff, can remind the staff in time to clear up when the foreign matter is less, can send the control signal of scram to belt power control system at different levels when the foreign matter is great, in time stop the belt, wait for the staff to open the transportation belt again after having cleared up the foreign matter, guaranteed that the belt is not damaged in process of production.
The invention relates to a monocular camera-based transportation belt vision measurement method, which is implemented according to the following steps as shown in figure 2:
an explosion-proof industrial network camera fixed above a conveyor belt is adopted to collect videos, when the conveyor belt stops, the situation near a monitoring point can be monitored through a system interface of the system, and at the moment, an algorithm engine module is in a dormant state; the algorithm engine module is activated by feedback from the belt power control system when the conveyor belt is loaded with coal for transport.
As shown in fig. 3, a processing flow chart of the algorithm engine module is that image information acquired by two cameras is subjected to image denoising by gaussian filtering and image enhancement preprocessing by a laplacian operator. The specific operation of gaussian filtering is: each pixel in the image is scanned using a template (or convolution, mask), and the weighted average gray value of the pixels in the neighborhood determined by the template is used to replace the value of the pixel in the center of the template.
The image enhancement by the laplacian operator is realized by that when the gray level of the central pixel of the neighborhood is lower than the average gray level of other pixels in the domain where the central pixel is located, the gray level of the central pixel is further reduced, and when the gray level of the central pixel of the neighborhood is higher than the average gray level of other pixels in the neighborhood where the central pixel is located, the gray level of the central pixel is further improved.
And then detecting invariant feature points in the scale by adopting a Gaussian scale space, wherein the kernel which can only generate the scale space is a Gaussian kernel function, so that the scale space of the image is represented as a function L (x, y, sigma), which is generated by convolution of a Gaussian function G (x, y, sigma) with the image I (x, y) in a variable scale. That is, L (x, y, σ) ═ G (x, y, σ) × I (x, y). Where x, y represent the horizontal and vertical coordinates of the pixels in the image and σ represents the gaussian smoothing factor. And then drawing the contour of the detection target according to the feature points, identifying the foreign body contour by using a machine learning mode, not detecting the foreign body feature when no foreign body exists, enabling the belt to normally run at the moment, generating an alarm and recording the abnormal contour when the abnormal contour occurs, and simultaneously rapidly sending a control signal to a belt power system to protect the transport belt through a strong real-time communication protocol according to the severity of the abnormality.
Furthermore, the method can be used for sequentially detecting the foreign matters of the adjacent belts by acquiring the image information of the multi-stage belts for continuously conveying the materials.
Under the condition that the conveying belt runs under a load, foreign matters in the middle of coal on the conveying belt can be accurately identified, and the foreign matters can quickly respond through a strong real-time communication protocol, so that production equipment is protected. The invention integrates a machine vision technology, a computer network strong real-time communication technology, a machine learning technology and an automatic control technology, can automatically complete the detection of various foreign matters in the video monitoring image of the coal conveying belt, provides guarantee for the coal mine conveying belt system, and has important significance for the safe and normal operation of the conveying belt system.
Claims (5)
1. A foreign matter detection and protection method of a conveyor belt system based on video analysis comprises the following steps:
(1) a first camera is arranged right above one certain upstream belt of the conveying belt system, acquires image information of the upstream belt and transmits video streams to the master industrial personal computer;
(2) the downstream belt is adjacent to the upstream belt, receives the materials of the upstream belt, is provided with a second camera right above the upstream belt, collects corresponding image information of the downstream belt, and transmits the video stream to the master control industrial personal computer for analysis and processing;
(3) an algorithm engine module is arranged in the master control industrial personal computer, and image denoising and image enhancement preprocessing are performed on image information of the same region acquired by the first camera and the second camera by adopting Gaussian filtering;
(4) detecting scale-invariant feature points by adopting a Gaussian scale space, and then drawing a foreign body contour according to the feature points; detecting invariant feature points in a scale by using a Gaussian scale space, wherein the kernel which can only generate the scale space is a Gaussian kernel function, and the scale space of an image is expressed as a function L (x, y, sigma), which is generated by convolution of a Gaussian function G (x, y, sigma) with the image I (x, y), wherein L (x, y, sigma) is G (x, y, sigma) I (x, y), x and y represent horizontal and vertical coordinates of pixels in the image, and sigma represents a Gaussian smoothing factor;
(5) when an abnormal contour occurs, the algorithm engine module gives an alarm and records the abnormal contour, and simultaneously, the control signal is rapidly sent to the conveyor belt system through a strong real-time communication protocol according to the severity of the abnormality; the foreign body outline is identified by using a machine learning mode, when no foreign body exists, the coal briquette can be filtered when the characteristic extraction is carried out, and the belt can normally run at the moment;
the method comprises the steps of collecting image information of multi-stage belts for continuous material conveying, and sequentially detecting foreign matters on adjacent belts;
the method is a visual measurement method of a conveyor belt based on a monocular camera, wherein the first camera and the second camera are both explosion-proof industrial network cameras;
first camera, second camera pass through the switch and are connected to the main control industrial computer, and wherein, first camera, second camera pass through optical fiber connection to the switch, and the switch passes through optical fiber connection to the main control industrial computer.
2. The video analysis-based foreign object detection protection method for a conveyor belt system according to claim 1, wherein: the upstream belt and the downstream belt are correspondingly provided with power control systems, and the power control systems are connected to a master control industrial personal computer through a switch; when the conveyor belt is loaded with coal for transport, the power control system activates the algorithm engine module of the conveyor belt system.
3. The video analysis-based foreign object detection protection method for a conveyor belt system according to claim 1, wherein: in the step (3), the gaussian filtering is to scan each pixel in the image by using a template, and replace the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template.
4. The video analysis-based foreign object detection protection method for a conveyor belt system according to claim 1, wherein: in the step (3), the laplacian operator performs image enhancement according to that when the gray level of the central pixel of the neighborhood is lower than the average gray level of other pixels in the domain where the central pixel is located, the gray level of the central pixel is further reduced, and when the gray level of the central pixel of the neighborhood is higher than the average gray level of other pixels in the neighborhood where the central pixel is located, the gray level of the central pixel is further improved, so that the image enhancement processing is realized.
5. The video analysis-based foreign object detection protection method for a conveyor belt system according to claim 1, wherein: in the step (5), when the abnormal contour is not serious, the conveyer belt system informs a worker; when the foreign matters seriously exceed the limit, the conveying belt system controls the corresponding power control system to decelerate or stop the belts at all levels in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910309980.6A CN110015553B (en) | 2019-04-17 | 2019-04-17 | Foreign matter detection and protection method for conveyor belt system based on video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910309980.6A CN110015553B (en) | 2019-04-17 | 2019-04-17 | Foreign matter detection and protection method for conveyor belt system based on video analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110015553A CN110015553A (en) | 2019-07-16 |
| CN110015553B true CN110015553B (en) | 2020-07-03 |
Family
ID=67191644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910309980.6A Active CN110015553B (en) | 2019-04-17 | 2019-04-17 | Foreign matter detection and protection method for conveyor belt system based on video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110015553B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814678B (en) * | 2020-07-08 | 2024-06-18 | 江苏三恒科技股份有限公司 | Method and system for identifying coal flow in conveyor belt based on video monitoring |
| CN112781494A (en) * | 2020-12-24 | 2021-05-11 | 中标慧安信息技术股份有限公司 | Method and system for detecting existence state of foreign matter on surface of conveying belt |
| CN112928966A (en) * | 2021-03-26 | 2021-06-08 | 中国矿业大学(北京) | Belt conveyor speed regulating system based on video signals and control method thereof |
| CN113962956B (en) * | 2021-10-18 | 2024-04-19 | 安徽工业大学 | Foreign matter detection method for coal conveying belt conveyor |
| CN116612423B (en) * | 2023-03-20 | 2024-05-03 | 华洋通信科技股份有限公司 | AI video identification method for coal mine transportation system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3910427A (en) * | 1972-08-01 | 1975-10-07 | Hitachi Ltd | Conveyance control apparatus and method |
| CN102320457A (en) * | 2011-08-23 | 2012-01-18 | 北京纵横兴业科技发展有限公司 | Intelligent monitoring system for monitoring coal conveying belt for of coal conveying system |
| CN105217271A (en) * | 2015-08-31 | 2016-01-06 | 西安华光信息技术有限责任公司 | Based on the self-adaptation control method of the belt transportation system of video identification |
| CN107043000A (en) * | 2017-06-15 | 2017-08-15 | 西安科技大学 | A kind of belt conveyer safe and intelligent safeguards system based on machine vision |
| 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 |
-
2019
- 2019-04-17 CN CN201910309980.6A patent/CN110015553B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3910427A (en) * | 1972-08-01 | 1975-10-07 | Hitachi Ltd | Conveyance control apparatus and method |
| CN102320457A (en) * | 2011-08-23 | 2012-01-18 | 北京纵横兴业科技发展有限公司 | Intelligent monitoring system for monitoring coal conveying belt for of coal conveying system |
| CN105217271A (en) * | 2015-08-31 | 2016-01-06 | 西安华光信息技术有限责任公司 | Based on the self-adaptation control method of the belt transportation system of video identification |
| CN107043000A (en) * | 2017-06-15 | 2017-08-15 | 西安科技大学 | A kind of belt conveyer safe and intelligent safeguards system based on machine vision |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110015553A (en) | 2019-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110015553B (en) | Foreign matter detection and protection method for conveyor belt system based on video analysis | |
| CN101986143B (en) | Machine vision belt tear detection and protective device | |
| CN110171691B (en) | Belt tearing state detection method and detection system for belt conveyor | |
| CN109359594B (en) | Mine belt abnormity detection method and device based on video processing | |
| CN201890600U (en) | Machine vision belt tearing detecting device | |
| CN107176432A (en) | A kind of anchor pole foreign matter and belt tearing detecting system based on machine vision | |
| CN113283344A (en) | Mining conveying belt deviation detection method based on semantic segmentation network | |
| CN110765848A (en) | Chemical plant personnel safety guarantee system and early warning method based on artificial intelligence image processing algorithm | |
| CN103383361A (en) | Steel wire core conveyer belt detection device and method | |
| CN104792796A (en) | On-line monitoring system for mining adhesive tape operation condition based on machine vision | |
| CN105321289B (en) | A kind of round-the-clock monitoring image intellectual analysis and warning system and method | |
| KR20100121020A (en) | Apparatus for detecting a obstacle in a road crossing and controlling method thereof using a moving track of an object | |
| CN111506011A (en) | Construction safety monitoring method and device | |
| CN109255798A (en) | Monitoring alarm method is used in a kind of safety in production | |
| CN114348581A (en) | Belt tearing detection method and system | |
| CN107200274A (en) | A kind of anti-container truck based on machine vision is lifted method | |
| CN110441320A (en) | A kind of gangue detection method, apparatus and system | |
| CN110597165B (en) | Steel piling monitoring system and steel piling monitoring method | |
| Li et al. | Intelligent monitoring system of coal conveyor belt based on computer vision technology | |
| CN115082850A (en) | Template support safety risk identification method based on computer vision | |
| CN215624882U (en) | Belt foreign matter monitoring devices in pit based on machine vision | |
| CN113469974A (en) | Method and system for monitoring grate plate state of pellet chain grate | |
| CN111573200B (en) | Visual detection system and detection method for blocking of underground belt transfer joint | |
| CN111291728A (en) | Detection system, detection equipment and detection method for illegal crossing of transmission belt behavior | |
| CN115504187B (en) | Intelligent speed regulation and protection system and control method for mining belt |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100102 room 1703, 7 / F, building 3, No.203, zone 2, Lize Zhongyuan, Chaoyang District, Beijing Patentee after: Huaxia Tianxin IOT Technology Co.,Ltd. Address before: 100102 room 1703, 7 / F, building 3, No.203, zone 2, Lize Zhongyuan, Chaoyang District, Beijing Patentee before: HUAXIA TIANXIN (BEIJING) INTELLIGENT LOW CARBON TECHNOLOGY RESEARCH INSTITUTE CO.,LTD. |