CN111003446A - Belt deviation detection method - Google Patents
Belt deviation detection method Download PDFInfo
- Publication number
- CN111003446A CN111003446A CN201911262037.0A CN201911262037A CN111003446A CN 111003446 A CN111003446 A CN 111003446A CN 201911262037 A CN201911262037 A CN 201911262037A CN 111003446 A CN111003446 A CN 111003446A
- Authority
- CN
- China
- Prior art keywords
- belt
- deviation
- pixel
- gradient
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a belt deviation detection method, which comprises the following steps: installing a plurality of cameras above the belt according to the length of the belt; setting electronic limits and deviation grade thresholds for two sides of a belt in each camera video image; acquiring a video image of each camera in real time through a network and an RTSP (real time streaming protocol); performing edge extraction on two sides of a belt in the video image; comparing the extracted edge with a preset electronic limit to obtain a deviation value; and comparing the obtained deviation value with a preset deviation grade threshold value, and judging whether the belt deviates and the deviation degree. Compared with the prior art, the method can realize real-time intelligent detection on the belt deviation condition, improves the detection efficiency and accuracy, and is beneficial to safe and smooth production.
Description
Technical Field
The invention relates to the technical field of belt transportation, in particular to a belt deviation detection method.
Background
Belt conveyor systems are an important means of transporting materials in modern industrial processes. In the belt transportation process, if the condition of belt off tracking appears, not only influence the quality of transported substance material, polluted environment, can cause trouble such as machine scram moreover, bring certain potential safety hazard.
The belt deviation condition is detected mainly by a manual inspection mode in the prior art, inspectors regularly inspect the belt, and when the belt deviation is found, the inspectors can stop the machine for maintenance and gradually adjust the position of the belt by manually adjusting the position of a tail shaft of the machine. However, the inspection mode cannot monitor the belt deviation condition in real time, so that the detection efficiency is low, certain hysteresis is achieved, and the requirement of modern production is difficult to meet.
Disclosure of Invention
The invention aims to provide a belt deviation detection method, which is used for realizing real-time intelligent inspection of belt deviation and improving detection efficiency and accuracy.
In order to solve the technical problem, an embodiment of the invention provides a belt deviation detection method, which comprises the following steps:
s1, mounting a plurality of cameras above the belt according to the length of the belt;
s2, setting electronic limits and deviation grade thresholds for two sides of a belt in each camera video image;
s3, acquiring the video image of each camera in real time through a network and an RTSP protocol;
s4, extracting edges of two sides of the belt in the video image;
s5, comparing the extracted edge with a preset electronic limit to obtain a deviation value;
and S6, comparing the obtained deviation value with a preset deviation level threshold value, and judging whether the belt deviates and the deviation degree.
Preferably, the step S1 includes:
installing a camera at preset intervals from a belt head according to the length of a belt;
and adjusting the irradiation angle of the camera to enable the irradiation angle to be vertical to the running direction of the belt.
Preferably, the step S4 includes:
s401, acquiring a belt area in the video image through a Mask image Mask generated in advance;
s402, eliminating noise by convolution of a Gaussian smoothing filter;
s403, calculating gradient amplitude and direction by using a Sobel filter;
s404, carrying out gradient edge thinning by using a non-maximum value inhibition method;
and S405, extracting edges according to a preset hysteresis threshold value.
Preferably, the step S403 includes:
the following convolution arrays are applied to the x-direction and the y-direction, respectively:
gradient magnitude and direction were calculated using the following formulas:
the gradient direction is approximated to one of four angles: 0 °, 45 °, 90 °, 135 °.
Preferably, the step S404 includes:
comparing the gradient amplitude of the current pixel with the gradient amplitudes of other pixels in the positive and negative gradient directions;
if the gradient amplitude of the current pixel is the maximum compared with the gradient amplitudes of other pixels in the same direction, the value of the current pixel is kept; otherwise, inhibit, i.e., set to 0.
Preferably, the step S405 includes:
presetting two hysteresis thresholds which are respectively a high threshold and a low threshold;
if the amplitude of a certain pixel is larger than the high threshold value, the pixel is reserved as an edge pixel;
if the amplitude of a pixel is less than the low threshold, the pixel is excluded;
if a pixel has an amplitude between the high and low thresholds, the pixel is retained only when connected to a pixel having an amplitude greater than the high threshold.
Preferably, the ratio of the high threshold to the low threshold is between 2:1 and 3: 1.
Preferably, the step S5 includes:
respectively calculating the distances between the four end points of the extracted two side edges and the corresponding electronic boundary;
the maximum value among the four distances is selected as a deviation value for judgment.
Preferably, the detection method further includes, after the step S6:
when the belt deviation is judged, alarming is carried out on the staff, and the alarming mode comprises audible and visual alarming, monitoring screen display alarming and mobile terminal information pushing alarming.
Preferably, the detection method further includes, after the step S6:
when the belt deviation is judged, an instruction is sent to a belt motor controller to control the belt motor to stop or adjust the operation parameters.
The technical scheme of the invention has the following beneficial effects:
in the scheme, the plurality of cameras are arranged above the belt to acquire the video images of the belt during transportation in real time, the belt edge is extracted and compared with the preset electronic limit to obtain the deviation value, then the deviation value is compared with the preset deviation grade threshold value to judge whether the belt deviates or not and the deviation degree, and the alarm and equipment linkage are carried out when the belt deviation is judged, so that the real-time intelligent detection of the belt deviation condition is realized, the detection efficiency and accuracy are improved, and the safe and smooth production is facilitated.
Drawings
FIG. 1 is a flow chart of a belt deviation detecting method provided by the embodiment of the invention;
FIG. 2 is a diagram illustrating edge extraction results according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating the calculation of the deviation value in an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following detailed description is made with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides a belt deviation detection method, as shown in fig. 1, the method comprises the following steps:
s1, mounting a plurality of cameras above the belt according to the length of the belt;
s2, setting electronic limits and deviation grade thresholds for two sides of a belt in each camera video image;
s3, acquiring the video image of each camera in real time through a network and an RTSP protocol;
s4, extracting edges of two sides of the belt in the video image;
s5, comparing the extracted edge with a preset electronic limit to obtain a deviation value;
and S6, comparing the obtained deviation value with a preset deviation level threshold value, and judging whether the belt deviates and the deviation degree.
In the scheme, the plurality of cameras are arranged above the belt to acquire the video images of the belt during transportation in real time, the belt edge is extracted and compared with the preset electronic limit to obtain the deviation value, then the deviation value is compared with the preset deviation grade threshold value to judge whether the belt deviates or not and the deviation degree, so that the real-time intelligent detection of the belt deviation condition is realized, and the detection efficiency and the accuracy are improved.
Further, step S1 includes:
installing a camera at preset intervals from a belt head according to the length of a belt;
and adjusting the irradiation angle of the camera to be vertical to the running direction of the belt.
For example, one camera is installed every 20 meters from the head of the belt, and the transportation condition of the belt is monitored. The camera supports RTSP and ONVIF protocols, and according to a video image shot by the camera, when the deviation value of the left deviation or the right deviation of the belt edge and the corresponding electronic boundary line exceeds the deviation level valve value, the severity of belt deviation is judged according to the threshold value of which level is specifically exceeded.
Further, the algorithm for acquiring the real-time video image of the camera in step S3 is as follows:
wherein cv2 is an opencv library,
rtsp/admin: admin @192.168.1.45:554// Streaming/Channels/1 is the rtsp Streaming media address of the camera, and is acquired according to the actual camera, and the frame is the video image acquired in real time.
Further, step S4 includes:
s401, acquiring a belt area in a video image through a Mask image Mask generated in advance;
s402, eliminating noise by convolution of a Gaussian smoothing filter;
s403, calculating gradient amplitude and direction by using a Sobel filter;
s404, carrying out gradient edge thinning by using a non-maximum value inhibition method;
and S405, extracting edges according to a preset hysteresis threshold value.
Specifically, step S401 is implemented by the following algorithm:
selecting a region of interest (here a belt region):
the method comprises the following steps of obtaining interested places of a region related to a belt in a video image by generating a Mask image Mask in advance, wherein the specific algorithm is as follows:
import cv2
import numpy as np
sss＝np.zeros([1280,720],dtype＝np.uint8)
sss[600:120,1200:700]＝255
image＝cv2.add(img0,np.zeros(np.shape(img0),dtype＝np.uint8),mask＝sss)
for example, a picture of 1280 × 720 size may be generated by the above algorithm, filled with 0, and then at 500: 120, 1200: the 700 area is filled to 255 completely, then this area is the area of interest, and the belt area is initially obtained by this algorithm.
Further, step S402 specifically includes:
convolution noise reduction using a gaussian smoothing filter, an example of a gaussian kernel with size 5 is shown below:
the gaussian filtering algorithm implements the code as follows:
further, step S403 includes:
following the procedure of the Sobel filter, the following convolution arrays were applied to the x-direction and y-direction, respectively:
gradient magnitude and direction were calculated using the following formulas:
the gradient direction is approximated to one of four angles: 0 °, 45 °, 90 °, 135 °.
The algorithm is implemented as follows:
further, step S404 includes:
comparing the gradient amplitude of the current pixel with the gradient amplitudes of other pixels in the positive and negative gradient directions;
if the gradient amplitude of the current pixel is the maximum compared with the gradient amplitudes of other pixels in the same direction, the value of the current pixel is kept; otherwise, inhibit, i.e., set to 0.
Non-maxima suppression is an edge refinement method, and typically results in gradient edges that are more than one pixel wide, but rather multiple pixels wide. For example, the Sobel operator has a thick and bright edge, so that the gradient map is still "blurred". The method of the present invention requires that the edge have only one exact dot width. Non-maximum suppression can help preserve the local maximum gradient while suppressing all other gradient values, which means that only the sharpest positions in the gradient change are preserved.
For example, the direction of the current pixel is directed 90 ° above, which is compared to the vertical direction, the pixel directly above and below.
The algorithm is implemented as follows:
further, step S405 includes:
presetting two hysteresis thresholds which are respectively a high threshold and a low threshold;
if the amplitude of a certain pixel is larger than the high threshold value, the pixel is reserved as an edge pixel;
if the amplitude of a pixel is less than the low threshold, the pixel is excluded;
if a pixel has an amplitude between the high and low thresholds, the pixel is retained only when connected to a pixel having an amplitude greater than the high threshold.
Preferably, the ratio of the high threshold to the low threshold is between 2:1 and 3: 1. The edge extraction results are shown in fig. 2.
Further, step S5 includes:
respectively calculating the distances between the four end points of the extracted two side edges and the corresponding electronic boundary;
the maximum value among the four distances is selected as a deviation value for judgment.
As shown in fig. 3, the thick lines are preset electronic boundary lines, the thin lines are two side edge lines of the belt obtained by a belt edge extraction algorithm, the distances between the two lines at positions 1, 2, 3 and 4 are respectively calculated, the maximum value is taken as a deviation value for judgment, the deviation value is compared with a deviation grade threshold value, and the deviation grade is obtained, so that whether the belt deviates or not and the severity of the deviation is detected.
Further, the detection method further includes, after the step S6:
when the belt deviation is judged, alarming is carried out on the staff, and the alarming mode comprises audible and visual alarming, monitoring screen display alarming and mobile terminal information pushing alarming.
Further, the detection method further includes, after the step S6:
when the belt deviation is judged, an instruction is sent to a belt motor controller to control the belt motor to stop or adjust the operation parameters.
In conclusion, compared with the prior art, the method disclosed by the invention can realize real-time intelligent detection on the belt deviation condition, improve the detection efficiency and accuracy, can alarm and adjust in time, and is favorable for safe and smooth production.
The foregoing is a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements should be considered as the protection scope of the present invention.
Claims (10)
1. A belt deviation detection method is characterized by comprising the following steps:
s1, mounting a plurality of cameras above the belt according to the length of the belt;
s2, setting electronic limits and deviation level thresholds for two sides of a belt in each camera video image;
s3, acquiring the video image of each camera in real time through a network and an RTSP protocol;
s4, extracting edges of two sides of the belt in the video image;
s5, comparing the extracted edge with a preset electronic limit to obtain a deviation value;
and S6, comparing the obtained deviation value with a preset deviation level threshold value, and judging whether the belt deviates and the deviation degree.
2. The belt deviation detecting method as claimed in claim 1, wherein said step S1 includes:
installing a camera at preset intervals from a belt head according to the length of a belt;
and adjusting the irradiation angle of the camera to enable the irradiation angle to be vertical to the running direction of the belt.
3. The belt deviation detecting method as claimed in claim 1, wherein said step S4 includes:
s401, acquiring a belt area in the video image through a Mask image Mask generated in advance;
s402, eliminating noise by convolution of a Gaussian smoothing filter;
s403, calculating gradient amplitude and direction by using a Sobel filter;
s404, carrying out gradient edge thinning by using a non-maximum value inhibition method;
and S405, extracting edges according to a preset hysteresis threshold value.
4. The belt deviation detecting method according to claim 3, wherein the step S403 includes:
the following convolution arrays are applied to the x-direction and the y-direction, respectively:
gradient magnitude and direction were calculated using the following formulas:
the gradient direction is approximated to one of four angles: 0 °, 45 °, 90 °, 135 °.
5. The belt deviation detecting method as claimed in claim 3, wherein the step S404 includes:
comparing the gradient amplitude of the current pixel with the gradient amplitudes of other pixels in the positive and negative gradient directions;
if the gradient amplitude of the current pixel is the maximum compared with the gradient amplitudes of other pixels in the same direction, the value of the current pixel is kept; otherwise, inhibit, i.e., set to 0.
6. The belt deviation detecting method according to claim 3, wherein the step S405 includes:
presetting two hysteresis thresholds which are respectively a high threshold and a low threshold;
if the amplitude of a certain pixel is larger than the high threshold value, the pixel is reserved as an edge pixel;
if the amplitude of a pixel is less than the low threshold, the pixel is excluded;
if a pixel has an amplitude between the high and low thresholds, the pixel is retained only when connected to a pixel having an amplitude greater than the high threshold.
7. The belt deviation detecting method as claimed in claim 6, wherein the ratio of the high threshold to the low threshold is between 2:1 and 3: 1.
8. The belt off-tracking detecting method according to any one of claims 1 to 7, wherein the step S5 includes:
respectively calculating the distances between the four end points of the extracted two side edges and the corresponding electronic boundary;
the maximum value among the four distances is selected as a deviation value for judgment.
9. The belt off-tracking detecting method according to any one of claims 1 to 7, further comprising, after the step S6:
when the belt deviation is judged, an alarm is given to a worker, and the alarm mode comprises an acousto-optic alarm, a monitoring screen display alarm and a mobile terminal information pushing alarm.
10. The belt off-tracking detecting method according to any one of claims 1 to 7, further comprising, after the step S6:
when the belt deviation is judged, an instruction is sent to a belt motor controller to control the belt motor to stop or adjust the operation parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911262037.0A CN111003446A (en) | 2019-12-10 | 2019-12-10 | Belt deviation detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911262037.0A CN111003446A (en) | 2019-12-10 | 2019-12-10 | Belt deviation detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111003446A true CN111003446A (en) | 2020-04-14 |
Family
ID=70115020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911262037.0A Pending CN111003446A (en) | 2019-12-10 | 2019-12-10 | Belt deviation detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111003446A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432179A (en) * | 2020-04-26 | 2020-07-17 | 上海发电设备成套设计研究院有限责任公司 | Intelligent coal conveying belt inspection system and method based on computer vision |
| CN111908060A (en) * | 2020-08-31 | 2020-11-10 | 国电浙能宁东发电有限公司 | Power plant coal conveying belt deviation monitoring and early warning device and method |
| CN112124900A (en) * | 2020-08-28 | 2020-12-25 | 西安科技大学 | Visual detection method for underground belt deviation |
| CN113112485A (en) * | 2021-04-20 | 2021-07-13 | 中冶赛迪重庆信息技术有限公司 | Belt conveyor deviation detection method, system, equipment and medium based on image processing |
| CN113686269A (en) * | 2021-08-24 | 2021-11-23 | 浙江西大门新材料股份有限公司 | Method for testing and evaluating flatness of roller shutter fabric |
| CN113928824A (en) * | 2021-10-25 | 2022-01-14 | 三一汽车制造有限公司 | Belt deviation detection method and device and mixing station |
| CN115116010A (en) * | 2022-08-29 | 2022-09-27 | 山东千颐科技有限公司 | Belt deviation-preventing visual identification system based on image processing |
| CN115200857A (en) * | 2022-07-11 | 2022-10-18 | 李华涛 | Transmission belt fatigue detection method, device and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105083912A (en) * | 2015-07-07 | 2015-11-25 | 青岛科技大学 | Conveyer belt deviation detecting method based on image identification |
-
2019
- 2019-12-10 CN CN201911262037.0A patent/CN111003446A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105083912A (en) * | 2015-07-07 | 2015-11-25 | 青岛科技大学 | Conveyer belt deviation detecting method based on image identification |
Non-Patent Citations (1)
| Title |
|---|
| 王志喜: "《计算机图形图像技术》", 31 January 2018, 中国矿业大学出版社 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432179A (en) * | 2020-04-26 | 2020-07-17 | 上海发电设备成套设计研究院有限责任公司 | Intelligent coal conveying belt inspection system and method based on computer vision |
| CN112124900A (en) * | 2020-08-28 | 2020-12-25 | 西安科技大学 | Visual detection method for underground belt deviation |
| CN112124900B (en) * | 2020-08-28 | 2022-05-20 | 西安科技大学 | Visual detection method for underground belt deviation |
| CN111908060A (en) * | 2020-08-31 | 2020-11-10 | 国电浙能宁东发电有限公司 | Power plant coal conveying belt deviation monitoring and early warning device and method |
| CN113112485A (en) * | 2021-04-20 | 2021-07-13 | 中冶赛迪重庆信息技术有限公司 | Belt conveyor deviation detection method, system, equipment and medium based on image processing |
| CN113686269A (en) * | 2021-08-24 | 2021-11-23 | 浙江西大门新材料股份有限公司 | Method for testing and evaluating flatness of roller shutter fabric |
| CN113686269B (en) * | 2021-08-24 | 2024-01-16 | 浙江西大门新材料股份有限公司 | Rolling screen fabric flatness testing and evaluating method |
| CN113928824A (en) * | 2021-10-25 | 2022-01-14 | 三一汽车制造有限公司 | Belt deviation detection method and device and mixing station |
| CN115200857A (en) * | 2022-07-11 | 2022-10-18 | 李华涛 | Transmission belt fatigue detection method, device and system |
| CN115116010A (en) * | 2022-08-29 | 2022-09-27 | 山东千颐科技有限公司 | Belt deviation-preventing visual identification system based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111003446A (en) | Belt deviation detection method | |
| US20200228720A1 (en) | Target Object Capturing Method and Device, and Video Monitoring Device | |
| CN108107051B (en) | Lithium battery defect detection system and method based on machine vision | |
| NZ711997A (en) | Weld seam defect detection method | |
| CN107154034B (en) | State detection method and system for stay wire positioning hook of high-speed rail contact network | |
| CN111325787A (en) | Mobile belt deviation and transportation amount detection method based on image processing | |
| CN111815578A (en) | Image stripe detection method, video monitoring system and related device | |
| CN105205803A (en) | Display panel defect detection method | |
| CN116519707A (en) | Lithium battery defect detection method and device based on machine vision and electronic equipment | |
| CN112215825A (en) | Quality analysis method and system based on machine vision in new energy battery manufacturing | |
| CN115018869A (en) | Belt deviation detection method | |
| CN117475381B (en) | Real-time monitoring system for operation state of aerial working platform | |
| CN111275756B (en) | Spool positioning method and device | |
| CN112351247A (en) | Electro-optical flash detection method in hydraulic power plant based on image processing | |
| CN115880365A (en) | Double-station automatic screw screwing detection method, system and device | |
| CN110962611B (en) | Charging bow and pantograph connecting method and device and electronic equipment | |
| JP2013210798A (en) | Abnormality detecting method and abnormality detecting device | |
| CN114757905A (en) | Vision-based rope winding abnormity detection device and method | |
| CN113762276A (en) | Method for detecting angle of ladder in electric power operation | |
| CN114549406A (en) | Hot rolling line management method, device and system, computing equipment and storage medium | |
| CN113203843A (en) | Water quality monitoring method | |
| CN102724542B (en) | Method of detecting cloud deck camera working position by using motion vector method | |
| CN112837285A (en) | Edge detection method and device for panel image | |
| CN111811437A (en) | Band saw blade welding quality detection method and device | |
| CN113989666B (en) | High-speed rail pantograph abnormity detection method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200414 |