CN116188459B - Line laser rapid identification method and system for belt tearing detection - Google Patents
Line laser rapid identification method and system for belt tearing detection Download PDFInfo
- Publication number
- CN116188459B CN116188459B CN202310437077.4A CN202310437077A CN116188459B CN 116188459 B CN116188459 B CN 116188459B CN 202310437077 A CN202310437077 A CN 202310437077A CN 116188459 B CN116188459 B CN 116188459B
- Authority
- CN
- China
- Prior art keywords
- image
- belt
- mask
- result
- laser
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000003628 erosive effect Effects 0.000 description 4
- 230000010339 dilation Effects 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000000109 continuous material Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000013598 vector 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of belt tearing detection, and particularly relates to a line laser rapid identification method and system for belt tearing detection. The method comprises the following steps: preprocessing an original image; carrying out background extraction on the preprocessed image to obtain a mask image; and carrying out laser stripe line recognition on the mask image. According to the method, the original image of the belt is preprocessed, then background extraction is carried out, so that a mask image of the belt is obtained, finally, laser stripe line recognition is carried out on the mask image of the belt, interference caused by sundries in the belt image can be effectively eliminated through the recognition method, so that the accuracy of recognition and analysis of the belt image is improved, and compared with the existing line scanning camera recognition and area array camera recognition mode, the time required for image result acquisition is shorter, and the situation that whether the belt is torn or not is more convenient for staff is recognized.
Description
Technical Field
The invention belongs to the technical field of belt tearing detection, and particularly relates to a line laser rapid identification method and system for belt tearing detection.
Background
The belt conveyor system has the advantages of simple structure, high conveying efficiency and the like in the aspect of long-distance continuous material conveying in the process industry, is important equipment for industrial coal, ore and the like transportation, and is the most critical fault type influencing the operation of the conveyor during the operation process of the conveyor. Because the conveyor runs at a fast speed and over a long distance, if the tearing accident is not detected timely, the belt can be damaged by tens of meters or even hundreds of meters. Repairing the belt is time-consuming and labor-consuming, and can affect normal production, thereby causing direct and indirect economic losses for enterprises. The detection method commonly adopted by the current belt conveying systems in various enterprises is a scheme of periodic manual inspection, has poor real-time performance and depends on responsibility of workers. In the aspect of the overall system, the problems of operation and maintenance prevention, numerous potential safety hazards and the like are lacked, and online monitoring and intelligent operation and maintenance are very necessary.
The current mainstream technical scheme mainly includes two technical routes, one is to carry out image acquisition and image analysis through a line scanning camera to determine the form and position of a fault, and the system can detect the fault to a certain extent by combining a plurality of line scanning cameras with image fusion and image detection technologies, but because the line scanning camera acquisition needs stable speed feedback to control shooting, the system is not suitable for a severe environment.
The other technical scheme is that fault detection is carried out by a line laser auxiliary line matched with an area array camera and a triangulation principle. It is worth mentioning that detection and measurement systems based on laser triangulation are a large class, e.g. line laser profile scanners, structured light flaw detectors, etc. are all done using this principle. In the principle of laser triangulation, when a laser irradiates vertically downwards and a camera shoots at a certain included angle, different longitudinal depths can enable laser points to be reflected on different positions imaged by the camera, and depth information of the laser point positions can be effectively obtained by analyzing light bars and light spots of the laser.
The two technical schemes can effectively detect faults, but because the bottom of the conveyor belt is more dirty, a plurality of false detection signals can appear in the system, and because the acquisition time is very short, the exposure of the camera is very low, and when the manual inspection, whether the fault is true tearing or not is difficult to distinguish by using manual assistance.
In order to solve the above problems, a line laser rapid identification method and system for belt tearing detection needs to be designed.
Disclosure of Invention
In view of the above problems, the present invention provides a line laser rapid identification method for belt tear detection, the method comprising:
preprocessing an original image;
carrying out background extraction on the preprocessed image to obtain a mask image;
and carrying out laser stripe line recognition on the mask image.
Preferably, the pretreatment comprises the steps of:
extracting a belt area image from the original image, and eliminating the interference of a complex change background;
and extracting laser line stripes from the belt region image.
Preferably, the extracting the background from the preprocessed image includes:
extracting the belt profile in the image;
dividing the image to obtain a division mask result;
and carrying out all-weather identification on the segmentation mask result to obtain a mask image.
Preferably, the step of extracting the belt profile in the image includes the steps of:
establishing a window based on a morphological processing core according to the preprocessed image, wherein the window comprises a gray scale domain and a brightness domain;
performing open operation on the gray scale domain of the window;
and performing a closing operation on the result of the opening operation.
Preferably, the segmenting the image includes:
segmenting a bright part and a dark part in an image, and extracting the dark part in the image;
and eliminating holes and small-area interference in the image.
Preferably, the all-weather identification of the segmentation mask result includes:
storing one image every hour, and calculating the average brightness of each image;
sorting the images according to brightness, and selecting sample images;
carrying out belt segmentation mask calculation on the sample image;
selecting the median value of the pixels at the same position in the sample image as an effective result, and performing median filtering on the effective result;
and performing open operation on the median filtering result, deleting arc points generated by the open operation, and obtaining a mask image.
Preferably, the identifying the laser stripe line on the mask image includes:
performing laser stripe candidate region segmentation on the mask image;
and carrying out gradient identification on the laser stripe candidate region.
Preferably, the performing laser stripe candidate region segmentation on the mask image includes:
deleting the result of the open operation by using the preprocessed image and superposing the mask image;
and carrying out threshold segmentation and morphological processing on the superposition result to distinguish laser stripe candidate regions.
Preferably, the gradient identifying of the laser stripe candidate region includes:
establishing and analyzing a hessian matrix of the laser stripe candidate region;
and performing scale screening on the laser stripe candidate region.
The invention also provides a line laser rapid identification system for belt tearing detection, which comprises:
the preprocessing module is used for preprocessing the original image;
the extraction module is used for extracting the background of the preprocessed image to obtain a mask image;
and the identification module is used for carrying out laser stripe line identification on the mask image.
Preferably, the preprocessing module is configured to preprocess an original image, and includes:
the preprocessing module is used for extracting a belt area image from the original image and eliminating the interference of a complex change background;
and extracting laser line stripes from the belt region image.
Preferably, the extracting module is configured to perform background extraction on the preprocessed image to obtain a mask image, and includes:
the extraction module is used for extracting the belt outline in the image;
dividing the image to obtain a division mask result;
and carrying out all-weather identification on the segmentation mask result to obtain a mask image.
Preferentially, the identifying module is used for identifying laser stripe lines of the mask image, and comprises:
the identification module is used for carrying out laser stripe candidate region segmentation on the mask image;
and carrying out gradient identification on the laser stripe candidate region.
The invention has the following beneficial effects:
according to the method, the original image of the belt is preprocessed, then background extraction is carried out, so that a mask image of the belt is obtained, finally, laser stripe line recognition is carried out on the mask image of the belt, interference caused by sundries in the belt image can be effectively eliminated through the recognition method, so that the accuracy of recognition and analysis of the belt image is improved, and compared with the existing line scanning camera recognition and area array camera recognition mode, the time required for image result acquisition is shorter, and the situation that whether the belt is torn or not is more convenient for staff is recognized.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a line laser rapid identification method for belt tear detection in an embodiment of the invention;
FIG. 2 illustrates a morphological processing kernel H-style diagram in an embodiment of the present invention;
FIG. 3 shows a schematic representation of gray domain expansion in an embodiment of the invention;
FIG. 4 shows a schematic representation of gray domain erosion in an embodiment of the invention;
FIG. 5 is a diagram showing an all-weather recognition process of a division mask result in an embodiment of the present invention;
FIG. 6 shows a laser line brightness profile in an embodiment of the invention;
FIG. 7 shows a tangential and normal schematic of the current gradient in an embodiment of the invention;
fig. 8 shows a schematic diagram of a line laser rapid identification system for belt tear detection in an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention provides a line laser rapid identification method for belt tearing detection, which comprises the following steps:
(1) Preprocessing an original image
The pretreatment comprises the following steps: extracting a belt area image from the original image, and eliminating the interference of a complex change background; and extracting laser line stripes from the belt region image.
(2) Extracting background of the preprocessed image to obtain a mask image
The background extraction of the preprocessed image comprises the following steps: extracting the belt profile in the image; dividing the image to obtain a division mask result; and carrying out all-weather identification on the segmentation mask result to obtain a mask image.
The belt profile in the extracted image comprises the following steps: establishing a window based on a morphological processing core according to the preprocessed image, wherein the window comprises a gray scale domain and a brightness domain; performing open operation on the gray scale domain of the window; and performing a closing operation on the result of the opening operation. In this embodiment, a cross-shaped morphology processing kernel H is used, as shown in fig. 2, and corrosion (erode) and expansion (dilate) are morphology changing operations in image processing, which are defined as that a morphology processing kernel is used as a window to scratch through the whole image, wherein, the shape of the morphology processing kernel can be customized by controlling the position of a non-zero part in the window in the interior of the window, and for a point I (I, j) on the image I, the formula of performing gray domain corrosion operation using the morphology processing kernel H with a window size of m×n is as follows:
；
the gray domain expansion operation formula is as follows:
；
wherein,,is the value of the corresponding point position of the processed image.
Gray domain erosion and dilation operations as shown in fig. 3 and 4, in digital image processing, a combination of operations of first erosion and then dilation on an image is called an open operation, and an operation of first dilation and then erosion is called a close operation.
The segmenting the image includes: segmenting a bright part and a dark part in an image, and extracting the dark part in the image; and eliminating holes and small-area interference in the image.
As shown in fig. 5, the all-weather identification of the segmentation mask result includes: storing one image every hour, and calculating the average brightness of each image; sorting the images according to brightness, and selecting sample images; carrying out belt segmentation mask calculation on the sample image; selecting the median value of the pixels at the same position in the sample image as an effective result, and carrying out median filtering on the effective result according to the pixel in a time sequence; and performing open operation on the median filtering result, deleting arc points generated by filtering, and obtaining a mask image.
(3) Laser stripe line identification for mask image
The identifying the laser stripe lines of the mask image comprises the following steps: performing laser stripe candidate region segmentation on the mask image; and carrying out gradient identification on the laser stripe candidate region.
The performing laser stripe candidate region segmentation on the mask image comprises the following steps: deleting the result of the open operation by using the preprocessed image and superposing the mask image; and carrying out threshold segmentation and morphological processing on the superposition result to distinguish laser stripe candidate regions.
The gradient identification of the laser stripe candidate region comprises the following steps: establishing and analyzing a hessian matrix of the laser stripe candidate region; and (3) the size of sigma of the hessian matrix is calibrated and adjusted in advance, gradient information with proper thickness is screened, and the scale screening of the laser stripe candidate region is realized.
The image of the laser line falling on the belt is shown in fig. 6, the X-axis and the Y-axis represent the positions of the image, the Z-axis represents the brightness value of the gray scale image, and the overall brightness characteristic can be found to be the characteristic of a convex ridge line. In the middle area, although the laser lines have the problems of halation, the laser lines are characterized by a ridge line shape, and the characteristic fine positioning can be performed by analyzing the characteristic values and the characteristic vectors of the hessian matrix.
For image I, the image-corresponding Hessian matrix is defined as a matrix of its second partial derivatives in x and y directions,。
when the I is a discrete image, derivative filtering is realized by a convolution mode,is the convolution kernel of (2)，/>Is +.>，/>Is +.>Before convolution, according to the image pyramid principle, the derivative scale setting can be realized by carrying out Gaussian blur filtering with different sigma degrees on the original image.
As shown in fig. 7, each point on the input image has a corresponding second-order hessian matrix, and the two eigenvectors are the tangential direction and the normal direction of the current gradient.
Based on the image pyramid principle, the scale of the image can be selected by a method of Gaussian filtering and downsampling the original image. According to the pixel width of the laser line in the image, a proper Gaussian kernel is selected for scale screening, so that the quality of the extracted image can be effectively improved.
Through the screening of the candidate areas in the last step, only the calculation results of the candidate areas can be analyzed, and the calculation speed is greatly reduced. In this embodiment, through testing, when the image size is 1920×1080 pixels, the single frame segmentation speed can reach within 25 ms.
As shown in fig. 8, the present invention further proposes a line laser rapid identification system for belt tear detection, the system comprising:
the preprocessing module is used for preprocessing the original image and comprises the following steps: the preprocessing module is used for extracting a belt area image from the original image and eliminating the interference of a complex change background; and extracting laser line stripes from the belt region image.
The extraction module is used for extracting the background of the preprocessed image to obtain a mask image, and comprises the following steps: the extraction module is used for extracting the belt outline in the image; dividing the image to obtain a division mask result; and carrying out all-weather identification on the segmentation mask result to obtain a mask image.
The identification module is used for carrying out laser stripe line identification on the mask image and comprises the following steps: the identification module is used for carrying out laser stripe candidate region segmentation on the mask image; and carrying out gradient identification on the laser stripe candidate region.
Those of ordinary skill in the art will appreciate that: although the invention has been described in detail with reference to the foregoing embodiments, it is to be understood that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. A line laser rapid identification method for belt tear detection, the method comprising:
preprocessing an original image; the pretreatment comprises the following steps: extracting a belt area image from the original image, and eliminating the interference of a complex change background; extracting laser line stripes from the belt area image;
carrying out background extraction on the preprocessed image to obtain a mask image; the background extraction of the preprocessed image comprises the following steps: extracting the belt profile in the image; dividing the image to obtain a division mask result; all-weather identification is carried out on the segmentation mask result to obtain a mask image, wherein the segmentation of the image comprises the following steps: segmenting a bright part and a dark part in an image, and extracting the dark part in the image; eliminating holes and small-area interference in the image; wherein, the all-weather identification of the segmentation mask result comprises: storing one image every hour, and calculating the average brightness of each image; sorting the images according to brightness, and selecting sample images; carrying out belt segmentation mask calculation on the sample image; selecting the median value of the pixels at the same position in the sample image as an effective result, and performing median filtering on the effective result; performing open operation on the median filtering result, deleting arc points generated by the open operation, and obtaining a mask image;
carrying out laser stripe line identification on the mask image; comprising the following steps: performing laser stripe candidate region segmentation on the mask image; and carrying out gradient identification on the laser stripe candidate region.
2. A line laser rapid identification method for belt tear detection as defined in claim 1, wherein,
the belt profile in the extracted image comprises the following steps:
establishing a window based on a morphological processing core according to the preprocessed image, wherein the window comprises a gray scale domain and a brightness domain;
performing open operation on the gray scale domain of the window;
and performing a closing operation on the result of the opening operation.
3. A line laser rapid identification method for belt tear detection as defined in claim 1, wherein,
the performing laser stripe candidate region segmentation on the mask image comprises the following steps:
deleting the result of the open operation by using the preprocessed image and superposing the mask image;
and carrying out threshold segmentation and morphological processing on the superposition result to distinguish laser stripe candidate regions.
4. A line laser rapid identification method for belt tear detection as defined in claim 1, wherein,
the gradient identification of the laser stripe candidate region comprises the following steps:
establishing and analyzing a hessian matrix of the laser stripe candidate region;
and performing scale screening on the laser stripe candidate region.
5. A line laser quick identification system for belt tear detection, the system comprising:
the preprocessing module is used for preprocessing the original image; comprising the following steps: the preprocessing module is used for extracting a belt area image from the original image and eliminating the interference of a complex change background; extracting laser line stripes from the belt area image;
the extraction module is used for extracting the background of the preprocessed image to obtain a mask image; comprising the following steps: the extraction module is used for extracting the belt outline in the image; dividing the image to obtain a division mask result; all-weather identification is carried out on the segmentation mask result, and a mask image is obtained; wherein the segmenting the image comprises: segmenting a bright part and a dark part in an image, and extracting the dark part in the image; eliminating holes and small-area interference in the image; wherein, the all-weather identification of the segmentation mask result comprises: storing one image every hour, and calculating the average brightness of each image; sorting the images according to brightness, and selecting sample images; carrying out belt segmentation mask calculation on the sample image; selecting the median value of the pixels at the same position in the sample image as an effective result, and performing median filtering on the effective result; performing open operation on the median filtering result, deleting arc points generated by the open operation, and obtaining a mask image;
the identification module is used for carrying out laser stripe line identification on the mask image; comprising the following steps: the identification module is used for carrying out laser stripe candidate region segmentation on the mask image; and carrying out gradient identification on the laser stripe candidate region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310437077.4A CN116188459B (en) | 2023-04-23 | 2023-04-23 | Line laser rapid identification method and system for belt tearing detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310437077.4A CN116188459B (en) | 2023-04-23 | 2023-04-23 | Line laser rapid identification method and system for belt tearing detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116188459A CN116188459A (en) | 2023-05-30 |
| CN116188459B true CN116188459B (en) | 2023-09-15 |
Family
ID=86444585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310437077.4A Active CN116188459B (en) | 2023-04-23 | 2023-04-23 | Line laser rapid identification method and system for belt tearing detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116188459B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117495858B (en) * | 2023-12-29 | 2024-06-11 | 合肥金星智控科技股份有限公司 | Belt offset detection method, system, equipment and medium |
| CN117495857B (en) * | 2023-12-29 | 2024-04-02 | 合肥金星智控科技股份有限公司 | Belt tearing edge detection method, system, equipment and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234475A (en) * | 2012-11-27 | 2013-08-07 | 深圳华用科技有限公司 | Sub-pixel surface morphology detecting method based on laser triangular measuring method |
| WO2015055060A1 (en) * | 2013-10-16 | 2015-04-23 | 湖南镭目科技有限公司 | Online detecting method for continuous casting slab surface quality |
| CN106023293A (en) * | 2016-05-26 | 2016-10-12 | 北京爱科声科技有限公司 | Three-dimensional reconstruction method based on C-scan ultrasonic image |
| CN106276132A (en) * | 2016-07-28 | 2017-01-04 | 天津工业大学 | A kind of conveyer belt longitudinal tear online test method based on line laser image |
| CN109596618A (en) * | 2018-12-26 | 2019-04-09 | 太原理工大学 | A kind of microcosmic heterogeneous structure three-dimensional modeling measurement method based on profiled outline sequence |
| WO2019188718A1 (en) * | 2018-03-28 | 2019-10-03 | バンドー化学株式会社 | Surface shape monitoring device, abrasion loss measuring system, and surface shape monitoring system |
| CN111563574A (en) * | 2020-05-14 | 2020-08-21 | 河北省机电一体化中试基地 | Machine vision-based white granulated sugar bag automatic counting device and method |
| CN113548419A (en) * | 2021-07-20 | 2021-10-26 | 湖北能源集团鄂州发电有限公司 | Belt tearing detection method, device and system based on machine vision image recognition |
| CN115947066A (en) * | 2023-03-14 | 2023-04-11 | 合肥金星智控科技股份有限公司 | Belt tearing detection method, device and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150022634A1 (en) * | 2013-07-16 | 2015-01-22 | The Steelastic Co., Llc | Object inspection system |
-
2023
- 2023-04-23 CN CN202310437077.4A patent/CN116188459B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234475A (en) * | 2012-11-27 | 2013-08-07 | 深圳华用科技有限公司 | Sub-pixel surface morphology detecting method based on laser triangular measuring method |
| WO2015055060A1 (en) * | 2013-10-16 | 2015-04-23 | 湖南镭目科技有限公司 | Online detecting method for continuous casting slab surface quality |
| CN106023293A (en) * | 2016-05-26 | 2016-10-12 | 北京爱科声科技有限公司 | Three-dimensional reconstruction method based on C-scan ultrasonic image |
| CN106276132A (en) * | 2016-07-28 | 2017-01-04 | 天津工业大学 | A kind of conveyer belt longitudinal tear online test method based on line laser image |
| WO2019188718A1 (en) * | 2018-03-28 | 2019-10-03 | バンドー化学株式会社 | Surface shape monitoring device, abrasion loss measuring system, and surface shape monitoring system |
| CN109596618A (en) * | 2018-12-26 | 2019-04-09 | 太原理工大学 | A kind of microcosmic heterogeneous structure three-dimensional modeling measurement method based on profiled outline sequence |
| CN111563574A (en) * | 2020-05-14 | 2020-08-21 | 河北省机电一体化中试基地 | Machine vision-based white granulated sugar bag automatic counting device and method |
| CN113548419A (en) * | 2021-07-20 | 2021-10-26 | 湖北能源集团鄂州发电有限公司 | Belt tearing detection method, device and system based on machine vision image recognition |
| CN115947066A (en) * | 2023-03-14 | 2023-04-11 | 合肥金星智控科技股份有限公司 | Belt tearing detection method, device and system |
Non-Patent Citations (1)
| Title |
|---|
| 李海滨 ; 张春明 ; 张元正 ; 徐刚 ; .线激光辅助的皮带撕裂视觉检测方法.光学技术.2011,(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116188459A (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116188459B (en) | Line laser rapid identification method and system for belt tearing detection | |
| CN113469177B (en) | Deep learning-based drainage pipeline defect detection method and system | |
| CN109886298A (en) | A kind of detection method for quality of welding line based on convolutional neural networks | |
| Schmugge et al. | Detection of cracks in nuclear power plant using spatial-temporal grouping of local patches | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN111179250B (en) | Industrial product defect detection system based on multitask learning | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN113436157B (en) | Vehicle-mounted image identification method for pantograph fault | |
| CN110161035A (en) | Body structure surface crack detection method based on characteristics of image and bayesian data fusion | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN111591715A (en) | Belt longitudinal tearing detection method and device | |
| Rathod et al. | A comparative study of different segmentation techniques for detection of flaws in NDE weld images | |
| CN115601355A (en) | Method and device for detecting and classifying product surface defects and storage medium | |
| KR100687811B1 (en) | Method and apparatus for detecting defects of the welded part | |
| CN112801962A (en) | Semi-supervised industrial product flaw detection method and system based on positive sample learning | |
| CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
| CN116309277A (en) | Steel detection method and system based on deep learning | |
| Hashmi et al. | Computer-vision based visual inspection and crack detection of railroad tracks | |
| CN109767426B (en) | Shield tunnel water leakage detection method based on image feature recognition | |
| Ibragimov et al. | Automated Pavement Condition Index Assessment with Deep Learning and Image Analysis: An End-to-End Approach | |
| Yang et al. | Weld defect cascaded detection model based on bidirectional multi-scale feature fusion and shape pre-classification | |
| Thiruganam et al. | Automatic defect detection and counting in radiographic weldment images | |
| CN112150453B (en) | Automatic detection method for breakage fault of bolster spring of railway wagon | |
| Wang et al. | Visual defect detection for substation equipment based on joint inspection data of camera and robot | |
| Zhai et al. | Defect detection in aluminum foil by measurement-residual-based chi-square detector |
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 |