CN110015553A - Travelling belt system foreign bodies detection guard method based on video analysis - Google Patents
Travelling belt system foreign bodies detection guard method based on video analysis Download PDFInfo
- Publication number
- CN110015553A CN110015553A CN201910309980.6A CN201910309980A CN110015553A CN 110015553 A CN110015553 A CN 110015553A CN 201910309980 A CN201910309980 A CN 201910309980A CN 110015553 A CN110015553 A CN 110015553A
- Authority
- CN
- China
- Prior art keywords
- belt
- travelling belt
- scale
- 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.)
- Granted
Links
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 present invention provides a kind of travelling belt system foreign bodies detection guard method based on video analysis, the acquisition of image information is carried out by the material of adjacent two conveyor belt to travelling belt system, it is analyzed and processed in master control industrial personal computer using algorithm engine module, image denoising is carried out using gaussian filtering first and Laplace operator carries out image enhancement pretreatment, scale invariant feature point is detected using Gaussian scale-space again, then foreign matter profile is depicted according to characteristic point, when there is abnormal profile, algorithm engine module alarms and records abnormal profile, travelling belt system is promptly sent to for signal is controlled according to abnormal severity simultaneously.This method acquires belt image using camera, extracts characteristics of image, finds foreign matter situation by video analysis, and generate alarm in time, shuts down belt in time under serious conditions, to realize foreign matter alarm and protection belt function, ensures that safety of coal mines orderly produces.
Description
Technical field
The present invention relates to a kind of method for security protection of mine supervision video, more particularly, to a kind of based on video analysis
Travelling belt system foreign bodies detection guard method.
Background technique
In mine in production process, transport coal relies primarily on travelling belt system, but the meeting in coal in recovery process
Mixed with various impurity foreign matters, these foreign matters may cause belt seriously to hurt during transportation due to different
Evil, influences belt-conveying and production.
Summary of the invention
The travelling belt system foreign bodies detection guard method based on video analysis that the present invention provides a kind of, solves and passes through
The problem of foreign matter on camera detection travelling belt, it is described that its technical solution is as follows:
A kind of travelling belt system foreign bodies detection guard method based on video analysis, including the following steps:
(1) right above a certain upstream belt of travelling belt system, the first camera is installed, the first camera acquires institute
Video is streamed to master control industrial personal computer by the image information for stating upstream belt；
(2) and the adjacent downstream belt of upstream belt, receive the material of upstream belt, right above the second camera shooting is installed
Head, second camera acquire the correspondence image information of the downstream belt, and video is streamed to master control industrial personal computer and is analyzed
Processing；
(3) it is provided with algorithm engine module in master control industrial personal computer, the phase acquired for the first camera and second camera
With the image information in region, image denoising is carried out using gaussian filtering and Laplace operator carries out image enhancement pretreatment；
(4) scale invariant feature point is detected using Gaussian scale-space, and foreign matter profile is then depicted according to characteristic point；
(5) when there is abnormal profile, algorithm engine module alarms and records abnormal profile, while according to the serious of exception
Degree is promptly sent to travelling belt system for signal is controlled.
First camera, second camera are connected to master control industrial personal computer by interchanger.
Upstream belt and downstream belt, which all correspond to, is equipped with power control system, and power control system passes through interchanger and connects
To master control industrial personal computer；When travelling belt loads Coal Transport, power control system activates the algorithm of travelling belt system
Engine modules.
In step (3), gaussian filtering is the neighborhood determined with template with each of template scan image pixel
The weighted average gray value of interior pixel goes the value of alternate template central pixel point.
In step (3), it is according to when centre of neighbourhood pixel grey scale is lower than where it that Laplace operator, which carries out image enhancement,
Field in other pixels average gray when, the gray scale of this center pixel should be further reduced, when centre of neighbourhood pixel ash
Degree is higher than when the average gray of other pixels, the gray scale of this center pixel should be further improved, with this in the neighborhood where it
Realize image enhancement processing.
In step (4), using characteristic point constant in Gaussian scale-space detection scale, scale space can be uniquely generated
Core is gaussian kernel function, and the scale space of image is expressed as a function L (x, y, σ), is by the Gaussian function of a mutative scale
Number G (x, y, σ) and image I (x, y) convolution generate, i.e. L (x, y, σ)=G (x, y, σ) * I (x, y).Wherein x, y are indicated in image
The transverse and longitudinal coordinate of pixel, σ indicate the Gaussian smoothing factor.
In step (5), foreign matter profile is identified in the way of machine learning, when foreign matter is not present, coal cinder exists
Will be filtered when feature extraction, belt can operate normally at this time.
In step (5), when abnormal profile is not serious, travelling belt system notifies staff；When foreign matter seriously transfinites, fortune
Defeated belt system controls corresponding power control system, slows down or stop in time belts at different levels.
This method all carries out image information collecting to the multi-stage, belt that moving material transmits, and successively carries out to adjacent belt
Foreign bodies detection.
This method acquires belt image using camera, extracts characteristics of image, finds foreign matter situation by video analysis, and
Alarm is generated in time, shuts down belt in time under serious conditions, to realize foreign matter alarm and protection belt function, ensures coal mine peace
Complete orderly production.
Detailed description of the invention
Fig. 1 is the mounting structure schematic diagram the present invention relates to relevant apparatus；
Fig. 2 is the flow chart of foreign bodies detection guard method provided by the invention；
Fig. 3 is the flow chart of the algorithm engine module of foreign bodies detection guard method provided by the invention.
Specific embodiment
The following describes the present invention in detail with reference to the accompanying drawings and specific embodiments.
As shown in Figure 1, the relevant apparatus that the present invention applies in travelling belt system, including in two adjacent conveying skins
The camera that the surface of band is all installed, the corresponding power control system of camera, conveyor belt all pass through interchanger and master control
Industrial personal computer is connected.
In upstream, first camera 1, the surface of the downstream belt 4 of belt 3 in upstream are installed in the surface of belt 3
One second camera 2 is installed.First camera 1 is identical with the corresponding region that second camera 2 is shot.
For this purpose, the region D1 of the first camera 1 shooting upstream belt 3, the material transmission of region D1 to downstream belt 4
When, it is correspondingly formed region D2,2 shooting area D2 of second camera, that is to say, that the first camera 1 and second camera 2 are installed
The image interval of acquisition be corresponding.In this regard, can be passed by the way that distance, position and the belt of camera opposed belts is arranged
The velocity interpolation sent.
Two cameras are connected to interchanger 7 by optical fiber, and interchanger 7 is connected on master control industrial personal computer 8 by optical fiber.
Upstream belt 3 is corresponding with the first power control system 5 of belt, and downstream belt 4 is corresponding with the second power of belt
Control system 6.First power control system 5, the second power control system 6 are equally connected to master control work by optical fiber, interchanger 7
On control machine 8.
First camera 1 acquires the image information of the material of upstream belt 3, and material falls on downstream belt 4 from upstream belt 3
On continue to convey, there is no abnormal objects during normal production, therefore material is during transportation, will not occur shape change
The influence of change.Then, the image information of the belt surface shot by two cameras, is streamed to master control industrial personal computer for video
8 algorithm engine module is analyzed and processed.
When foreign matter such as anchor pole, iron rod, the foreign matters such as megalith, the shape ratio of anchor pole and iron rod occurs during transportation in belt
It is more special, be strip for coal cinder, metal object it is easily reflective be easier to identify, megalith is since volume is relative to normal
It is much larger for coal cinder.Thus foreign matter enables to the shape of material to change, and then is gone out by algorithm engine module analysis
Come.
Master control industrial personal computer 8 can be judged according to the size and seriousness of foreign matter, and and alarm give neighbouring work people
Member, can remind staff to clear up in time, can send the control signal of emergency stop to respectively when foreign matter is larger when foreign matter is smaller
Grade belt power control system, stops belt in time, reopens travelling belt again after waiting staff to clean up foreign matter, protects
Belt has been demonstrate,proved not to be damaged in process of production.
The present invention is the travelling belt vision measuring method based on monocular cam, as shown in Fig. 2, real according to the following steps
It applies:
Using the acquisition for being fixed on industrial network camera progress video explosion-proof above travelling belt, stop in travelling belt
, can be by the situation near the system interface purpose monitoring point of this system when only, algorithm engine module is in suspend mode shape at this time
State；When travelling belt loads Coal Transport, algorithm engine module can be swashed by the feedback of belt power control system
It is living.
The process flow diagram of algorithm engine module is as shown in figure 3, the image information acquired first to two cameras, uses
Gaussian filtering carries out image denoising and Laplace operator carries out image enhancement pretreatment.The concrete operations of gaussian filtering are: using
Each of one template (or convolution, mask) scan image pixel, the weighting with pixel in the determining neighborhood of template are flat
Equal gray value goes the value of alternate template central pixel point.
Laplace operator carry out image enhancement be according to when centre of neighbourhood pixel grey scale lower than in the field where it its
When the average gray of its pixel, the gray scale of this center pixel should be further reduced, when centre of neighbourhood pixel grey scale is higher than its institute
Neighborhood in other pixels average gray when, the gray scale of this center pixel should be further improved, with this realize image increase
Strength reason.
Then using characteristic point constant in Gaussian scale-space detection scale, the core of scale space can uniquely be generated as height
This kernel function, so the scale space of image is expressed as a function L (x, y, σ), it is by the Gaussian function of a mutative scale
What number G (x, y, σ) and image I (x, y) convolution generated.That is L (x, y, σ)=G (x, y, σ) * I (x, y).Wherein x, y indicate image
The transverse and longitudinal coordinate of middle pixel, σ indicate the Gaussian smoothing factor.Then the profile of detection target, and benefit are depicted according to characteristic point
Foreign matter profile is identified with the mode of machine learning, not will detect that foreign matter feature when foreign matter is not present, at this time belt
It can operate normally, when there is abnormal profile, algorithm engine, which can generate, alarms and records abnormal profile, while according to exception
Severity will control signal and be promptly sent to belt drive system protection travelling belt by hard real time communications protocol.
Further, this method can all carry out image information collecting by the multi-stage, belt transmitted to moving material, according to
It is secondary that foreign bodies detection is carried out to adjacent belt.
The present invention can accurately identify on travelling belt among coal in the case where travelling belt load running
Foreign matter, and made a response rapidly by hard real time communications protocol, and then protect production equipment.The present invention merges machine vision skill
Art, computer network hard real time mechanics of communication, machine learning techniques, automatic control technology, can be automatically performed Coal Transport skin
Various foreign bodies detections in the video surveillance image of band provide guarantee for Coal Transportation belt system, to travelling belt system
Safety, which operates normally, important meaning.
Claims (9)
1. a kind of travelling belt system foreign bodies detection guard method based on video analysis, including the following steps:
(1) right above a certain upstream belt of travelling belt system, the first camera is installed, the first camera acquires on described
The image information for swimming belt, is streamed to master control industrial personal computer for video；
(2) and the adjacent downstream belt of upstream belt, receive the material of upstream belt, right above second camera is installed,
Second camera acquires the correspondence image information of the downstream belt, and video is streamed to master control industrial personal computer and is carried out at analysis
Reason；
(3) it is provided with algorithm engine module in master control industrial personal computer, the same zone acquired for the first camera and second camera
The image information in domain carries out image denoising using gaussian filtering and Laplace operator carries out image enhancement pretreatment；
(4) scale invariant feature point is detected using Gaussian scale-space, and foreign matter profile is then depicted according to characteristic point；
(5) when there is abnormal profile, algorithm engine module alarms and records abnormal profile, while according to abnormal severity
Control signal is promptly sent to travelling belt system.
2. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: the first camera, second camera are connected to master control industrial personal computer by interchanger.
3. the travelling belt system foreign bodies detection guard method according to claim 2 based on video analysis, feature exist
In: upstream belt and downstream belt all correspondences are equipped with power control system, and power control system is connected to master by interchanger
Control industrial personal computer；When travelling belt loads Coal Transport, power control system activates the algorithm engine of travelling belt system
Module.
4. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: in step (3), gaussian filtering is the picture in the neighborhood that is determined with template with each of template scan image pixel
The weighted average gray value of element goes the value of alternate template central pixel point.
5. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: in step (3), it is according to when centre of neighbourhood pixel grey scale is lower than the field where it that Laplace operator, which carries out image enhancement,
When the average gray of interior other pixels, the gray scale of this center pixel should be further reduced, when centre of neighbourhood pixel grey scale is higher than
In neighborhood where it when the average gray of other pixels, the gray scale of this center pixel should be further improved, and realize figure with this
Image intensifying processing.
6. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: in step (4), using characteristic point constant in Gaussian scale-space detection scale, the core that can uniquely generate scale space is
The scale space of image is expressed as a function L (x, y, σ), is by the Gaussian function G of a mutative scale by gaussian kernel function
(x, y, σ) and image I (x, y) convolution generate, i.e. L (x, y, σ)=G (x, y, σ) * I (x, y), wherein x, and y indicates pixel in image
Transverse and longitudinal coordinate, σ indicate the Gaussian smoothing factor.
7. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: in step (5), foreign matter profile is identified in the way of machine learning, when foreign matter is not present, coal cinder is carrying out spy
Sign will be filtered when extracting, and belt can operate normally at this time.
8. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: in step (5), when abnormal profile is not serious, travelling belt system notifies staff；When foreign matter seriously transfinites, skin is transported
Band system controls corresponding power control system, slows down or stop in time belts at different levels.
9. the travelling belt system foreign bodies detection guard method according to claim 1 based on video analysis, feature exist
In: this method all carries out image information collecting to the multi-stage, belt that moving material transmits, and successively carries out foreign matter to adjacent belt
Detection.
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 true CN110015553A (en) | 2019-07-16 |
| CN110015553B 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) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814678A (en) * | 2020-07-08 | 2020-10-23 | 江苏三恒科技股份有限公司 | Video monitoring-based method and system for identifying coal flow in conveyor belt |
| 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 |
| CN113962956A (en) * | 2021-10-18 | 2022-01-21 | 安徽工业大学 | Foreign matter detection method for coal conveying belt conveyor |
| CN116612423A (en) * | 2023-03-20 | 2023-08-18 | 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 |
Non-Patent Citations (2)
| Title |
|---|
| 牛金海: "《超声原理及生物医学工程应用：生物医学超声学》", 31 January 2017, 上海交通大学出版社 * |
| 王毅: "《基于偏微分方程的遥感图像处理方法》", 30 November 2016, 中国地质大学出版社 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814678A (en) * | 2020-07-08 | 2020-10-23 | 江苏三恒科技股份有限公司 | Video monitoring-based method and system for identifying coal flow in conveyor belt |
| 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 |
| CN113962956A (en) * | 2021-10-18 | 2022-01-21 | 安徽工业大学 | Foreign matter detection method for coal conveying belt conveyor |
| CN113962956B (en) * | 2021-10-18 | 2024-04-19 | 安徽工业大学 | Foreign matter detection method for coal conveying belt conveyor |
| CN116612423A (en) * | 2023-03-20 | 2023-08-18 | 华洋通信科技股份有限公司 | AI video identification method for coal mine transportation system |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110015553B (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110015553A (en) | Travelling belt system foreign bodies detection guard method based on video analysis | |
| CN107176432B (en) | A kind of anchor pole foreign matter and belt tearing detection system based on machine vision | |
| CN109359594B (en) | Mine belt abnormity detection method and device based on video processing | |
| Yang et al. | On-line conveyor belts inspection based on machine vision | |
| Xianguo et al. | Laser-based on-line machine vision detection for longitudinal rip of conveyor belt | |
| CN113658136B (en) | Deep learning-based conveyor belt defect detection method | |
| US9390333B2 (en) | System and method for robust motion detection | |
| CN107403443B (en) | A kind of more rope multi-lay windings row's rope form state online test method and device based on machine vision | |
| CN105575027B (en) | It is a kind of to invade and boundary defence method and device | |
| CN110765848A (en) | Chemical plant personnel safety guarantee system and early warning method based on artificial intelligence image processing algorithm | |
| CN103101741B (en) | Implementation method of laser vision conveyer belt damage detection device | |
| CN106951838B (en) | A kind of overboard alarm system and its method based on image water wave | |
| CN107301375A (en) | A kind of video image smog detection method based on dense optical flow | |
| CN106815831B (en) | Method and device for detecting abrasion of steel wire rope | |
| CN110441320A (en) | A kind of gangue detection method, apparatus and system | |
| CN112818753A (en) | Pit falling object detection method, device and system | |
| CN109255798A (en) | Monitoring alarm method is used in a kind of safety in production | |
| CN115620192A (en) | Method and device for detecting wearing of safety rope in aerial work | |
| CN115082850A (en) | Template support safety risk identification method based on computer vision | |
| CN114002228A (en) | Belt crack detection method based on image recognition | |
| CN117315593A (en) | Recognition method for foreign matter invasion of underground coal mine transportation system | |
| Huang et al. | A real-time algorithm for aluminum surface defect extraction on non-uniform image from CCD camera | |
| CN115504187B (en) | Intelligent speed regulation and protection system and control method for mining belt | |
| CN109726750B (en) | Passenger fall detection device, passenger fall detection method and passenger conveying device | |
| CN115171006B (en) | Detection method for automatically identifying person entering electric power dangerous area based on deep learning |
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 |
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. |
|
| CP01 | Change in the name or title of a patent holder |