CN108022266B - Artificial intelligent image recognition method for photovoltaic cell on-line position detection - Google Patents
Artificial intelligent image recognition method for photovoltaic cell on-line position detection Download PDFInfo
- Publication number
- CN108022266B CN108022266B CN201711337777.7A CN201711337777A CN108022266B CN 108022266 B CN108022266 B CN 108022266B CN 201711337777 A CN201711337777 A CN 201711337777A CN 108022266 B CN108022266 B CN 108022266B
- Authority
- CN
- China
- Prior art keywords
- photovoltaic cell
- detection
- central axis
- image
- transmission belt
- 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 52
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000005540 biological transmission Effects 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 238000005516 engineering process Methods 0.000 claims description 17
- 238000003709 image segmentation Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 3
- 229910021421 monocrystalline silicon Inorganic materials 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 239000002210 silicon-based material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000003672 processing method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 239000012636 effector Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002699 waste material 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Abstract
The invention discloses an artificial intelligent image recognition method for photovoltaic cell on-line position detection. The invention comprises an industrial camera, an image data acquisition card, a photovoltaic cell position sensor, an image recognition module facing to the detection of the photovoltaic cell position and a detection transmission belt; when the photovoltaic cell position sensor senses that the photovoltaic cell is placed at a visual detection station of the detection conveyor belt, the industrial camera shoots an original image of the photovoltaic cell area, the original image is transmitted to the image data acquisition card through a signal wire and converted into a pixel image based on pixels, and then the pixel image is further transmitted to an image recognition module which operates in a micro-processing period and faces to the photovoltaic cell position detection, and feature extraction is carried out on coordinate errors and angle errors of the photovoltaic cell. The invention can measure the position deviation and the angle deviation of the photovoltaic cell relative to the transmission belt to obtain accurate measurement, and can greatly improve the precision and the efficiency of the on-line nondestructive detection of the position of the photovoltaic cell.
Description
Technical Field
The invention belongs to the field of industrial artificial intelligence, and particularly relates to an artificial intelligent image recognition method for photovoltaic cell online position detection, which can greatly improve the precision and efficiency of photovoltaic cell online nondestructive detection and can be widely applied to the industry.
Background
Solar renewable energy is gradually replacing conventional energy, and becomes one of clean energy for protecting the ecological environment of the earth. The solar cell is an important component of the photovoltaic power generation system, has close relation with the working efficiency and the power generation capacity of the system, and can increase the utilization rate of solar energy by improving the energy conversion efficiency of the solar cell. Because some factors in practical application can influence the characteristics of the solar cells, the characteristics or performances of the battery units are inconsistent or not similar, so that unnecessary energy waste can be caused, and even the phenomenon of reducing the service life of the battery can occur. Therefore, when the photovoltaic cell array is configured, the characteristics of the photovoltaic cell array need to be tested, and the cell array meeting the requirements is selected, so that the working efficiency of the photovoltaic power generation system is improved.
The photovoltaic characteristic testing system for the photovoltaic device of the solar cell belongs to a photoelectric testing device, and can solve the problems that the existing testing system must adopt a manual operation mode to set irradiance values, and irradiance value measurement and sample cell testing processes cannot be performed simultaneously.
Based on the research of the characteristic analysis and detection methods of the photovoltaic cells, the portable characteristic tester based on the low-power consumption singlechip is designed for the existing market products, and the characteristics of the photovoltaic cells are measured and analyzed, so that scientific data are provided for the assembly of various photovoltaic cells. However, such simple devices cannot be matched with the production of large-scale photovoltaic cells and are only suitable for sampling detection. Recently, we have disclosed a control system architecture and control flow of a full-automatic intelligent photovoltaic cell detection and sorting device, which are core architecture and technical foundation for realizing the intellectualization and automation of a photovoltaic detection and sorting system.
Currently, artificial intelligence 2.0 is rising in China, and image recognition is a typical artificial intelligence technology, which utilizes a computer to process, analyze and understand images so as to recognize targets and objects in various modes. In general industrial use, an industrial camera is adopted to shoot pictures, and then software is utilized to further identify and process according to the gray level difference of the pictures. If the position detection of the photovoltaic cell can be carried out by combining the image recognition technology, the method has a promotion effect on the upgrading of the photovoltaic cell industry.
The image recognition artificial intelligence method for the photovoltaic cell on-line position detection is disclosed, based on geometric features of the photovoltaic cell and a transmission belt, an image segmentation technology, a region description technology, a central axis feature extraction technology and an image processing method of a pixel coordinate technology are adopted, the position deviation and the angle deviation of the photovoltaic cell relative to the transmission belt are accurately measured, the precision and the efficiency of the photovoltaic cell position on-line nondestructive detection can be greatly improved, and the method can be widely applied to the industry.
Disclosure of Invention
The invention aims at overcoming the defects of the prior art, and provides an artificial intelligent image recognition method for photovoltaic cell on-line position detection, which is based on geometric characteristics of a photovoltaic cell and a transmission belt, adopts an image processing method of an image segmentation technology, a region description technology, a central axis characteristic extraction technology and a pixel coordinate technology, accurately measures the position deviation and the angle deviation of the photovoltaic cell relative to the transmission belt, accurately measures the position deviation and the angle deviation of the photovoltaic cell, greatly improves the precision and the efficiency of the photovoltaic cell position on-line nondestructive detection, and can be widely applied to the industry.
The invention comprises an industrial camera, an image data acquisition card, a photovoltaic cell position sensor, an image recognition module facing to photovoltaic cell position detection and a detection transmission belt.
When the photovoltaic cell position sensor senses that the photovoltaic cell is placed at a visual detection station of the detection conveyor belt, the industrial camera shoots an original image of the photovoltaic cell area, the original image is transmitted to the image data acquisition card through the signal wire, the image data acquisition card converts digital signals into pixel images based on pixels, then the pixel images are further transmitted to the image recognition module which operates in a micro-processing period and faces to the photovoltaic cell position detection, and feature extraction is carried out on coordinate errors and angle errors of the photovoltaic cell.
Specifically, an image recognition intelligent algorithm for photovoltaic cell position detection is adopted, namely, a class of image recognition artificial intelligent method is adopted to extract characteristics of coordinate errors and angle errors of the photovoltaic cells.
The original image comprises image information of a photovoltaic cell and a transmission belt with scale features. Photovoltaic cells are typically blue single crystal silicon materials, and photovoltaic cells are typically regular squares or rectangles. The industrial detection conveyor belt is made of rubber materials and is green or black. Thus, the photovoltaic cell and the graduated transmission have a certain chromatic aberration and the optical characteristics are different.
The image recognition module facing the position detection of the photovoltaic cell is specifically realized as follows:
first, the method comprises the following steps: the method is performed on a pixel image based on an image segmentation technique and a region description technique. Extracting the region of the photovoltaic cell from the original image by adopting edge extraction and region segmentation as key features; simultaneously extracting edge characteristics of the belt and detecting scale characteristics of the transmission belt; from visual processing, it is recognized what pixels belong to the photovoltaic cell, what pixels belong to the belt edge, and what pixels belong to the scale information.
Secondly: based on a central axis feature extraction technology, four pieces of photovoltaic cells are identified by adopting edge extraction features, statistical median processing is carried out on corresponding edges, edge sharpening is carried out after the processing is finished, and two central axes of the photovoltaic cells are extracted; and identifying the central axis characteristic of the belt, and then retaining the characteristic pixels of the three lines.
Then: and carrying out coordinate processing on the central axis characteristic pixels of the transmission belt by utilizing the scale characteristics of the transmission belt through a pixel-based coordinate processing technology, so that the pixels have coordinate characteristics.
And then: determining a characteristic point on the central axis of the photovoltaic cell by utilizing the central axis pixel characteristic of the photovoltaic cell and the pixel characteristic of the detection transmission belt central axis, calculating the number n of pixels from the characteristic point to the central axis, and calculating the number m of pixels corresponding to the detection transmission belt central axis; and calculating the angle deviation delta theta of the central axis of the photovoltaic cell and the central axis of the transmission belt by using an inverse tangent function arctan (n/m).
Finally: extracting the intersection point of the characteristics of the two central axes of the photovoltaic cell as a new characteristic pixel, and calculating the number n of pixels from the characteristic point to the central axes and the number m of pixels of a half span scale value corresponding to the central axes of the transmission belt; and calculating the position deviation deltax from the central point of the photovoltaic cell to the central axis of the transmission belt by using a proportional relation, namely: Δθ= (n/m) 0.5 scale.
The image recognition technology meets the technical requirements of photovoltaic cell position sensing based on the image artificial intelligence technology required by the framework of the invention, and can be applied to detection equipment of various photovoltaic cells.
The beneficial effects of the invention are as follows:
(1) Image processing methods based on an image segmentation technology and a region description technology are provided for carrying out image recognition of the photovoltaic cell and image recognition of the transmission belt;
(2) The image processing method based on the central axis feature extraction technology is provided, so that the image features of the photovoltaic cell and the transmission belt are simplified;
(3) An image processing method based on a pixel coordinate technology is provided, and the coordinate system of the image processing method can measure the sitting quantity represented by pixels;
(4) The angular deviation feature extraction method and the translational deviation feature extraction method based on the image feature pixels are provided, so that the position deviation and the angular deviation of the photovoltaic cell relative to the transmission belt are accurately measured;
(5) The image recognition artificial intelligence integrated with the method can improve the precision and efficiency of the on-line nondestructive detection of the position of the photovoltaic cell, and can be widely applied to the industry.
Drawings
FIG. 1 is a schematic diagram of the architecture of the present invention.
FIG. 2 is a schematic diagram of a robot end effector layout of the present invention.
Fig. 3 is a schematic diagram of a process for correcting a photovoltaic cell by a robotic end effector of the present invention.
Fig. 4 is a schematic diagram of image processing based on a central axis feature extraction technique according to the present invention.
Fig. 5 is a schematic image diagram of the present invention based on pixel co-ordination techniques.
FIG. 6 is a schematic diagram of an angular feature extraction process based on image feature pixels according to the present invention.
FIG. 7 is a schematic diagram of a process for extracting position translation features based on image feature pixels according to the present invention.
Fig. 8 is a schematic diagram of the obtained translational and rotational deviations of the photovoltaic cell of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in FIG. 1, the artificial intelligent image recognition method for the photovoltaic cell on-line position detection comprises an industrial camera, an image data acquisition card, a photovoltaic cell position sensor, an image recognition module for the photovoltaic cell position detection and a detection transmission belt.
When the photovoltaic cell position sensor senses that the photovoltaic cell is placed at a visual detection station of the detection conveyor belt, the industrial camera shoots an original image of the photovoltaic cell area, the original image is transmitted to the image data acquisition card through the signal wire, the image data acquisition card converts digital signals into pixel images based on pixels, then the pixel images are further transmitted to the image recognition module which operates in a micro-processing period and faces to the photovoltaic cell position detection, and feature extraction is carried out on coordinate errors and angle errors of the photovoltaic cell.
Image features after raw data acquisition are described in connection with fig. 2. The original image comprises image information of a photovoltaic cell and a transmission belt with scale features. Photovoltaic cells are typically blue single crystal silicon materials, and photovoltaic cells are typically regular squares or rectangles. Industrial conveyor belts are often made of rubber materials in colors such as green or black. Thus, the photovoltaic cell and the graduated transmission have a certain chromatic aberration and the optical characteristics are different.
An image processing method based on the image segmentation technique and the region description technique is described with reference to fig. 3. Extracting the region of the photovoltaic cell from the original image by adopting image segmentation processing methods such as edge extraction, region segmentation and the like as key features; simultaneously extracting edge characteristics of the belt and scale characteristics of the transmission belt; from visual processing, it is recognized what pixels belong to the photovoltaic cell, what pixels belong to the belt edge, and what pixels belong to the scale information.
An image processing method based on the center axis feature extraction technique is described with reference to fig. 4. Identifying four pieces of the photovoltaic cell by adopting edge extraction characteristics, carrying out statistical median processing on corresponding edges, carrying out edge sharpening after the processing is finished, and extracting two central axes of the photovoltaic cell; the central axis characteristic of the belt is identified in a similar manner. The feature pixels of the three lines are retained.
An image processing method based on the pixel-wise coordinated technique is described with reference to fig. 5. And carrying out coordinate processing on the central axis characteristic pixels of the transmission belt by utilizing the scale characteristics of the transmission belt. So that the pixel has a certain coordinate characteristic.
Referring to fig. 6, an angular feature extraction method based on image feature pixels is described. Determining a characteristic point on the central axis of the photovoltaic cell by utilizing the central axis pixel characteristic of the photovoltaic cell and the pixel characteristic of the central axis of the transmission belt, and calculating the number n of pixels from the characteristic point to the central axis and the number m of pixels corresponding to the central axis of the transmission belt; then, the angular deviation delta theta of the central axis of the photovoltaic cell and the central axis of the transmission belt is calculated by using an inverse tangent function arctan (n/m).
A method of extracting a position-translation feature based on image feature pixels is described with reference to fig. 7. Extracting the intersection point of the characteristics of the two central axes of the photovoltaic cell as a new characteristic pixel, and calculating the number n of pixels from the characteristic point to the central axes and the number m of pixels of a half span scale value corresponding to the central axes of the transmission belt; then, calculating the position deviation deltax from the center point of the photovoltaic cell to the central axis of the transmission belt by using a proportional relation, namely: (n/m) 0.5 scale.
With reference to fig. 8, accurate detection of translational and rotational misalignment amounts of a photovoltaic cell obtained after image recognition is described.
In summary, the image recognition technology meets the technical requirements of photovoltaic cell position sensing based on the image artificial intelligence technology required by the framework of the invention, and can be applied to detection equipment of various photovoltaic cells.
Claims (1)
1. The artificial intelligent image recognition method for the photovoltaic cell on-line position detection is characterized by comprising an industrial camera, an image data acquisition card, a photovoltaic cell position sensor, an image recognition module for the photovoltaic cell position detection and a detection transmission belt;
when the photovoltaic cell position sensor senses that the photovoltaic cell is placed at a visual detection station of a detection conveyor belt, an industrial camera shoots an original image of a photovoltaic cell area, the original image is transmitted to an image data acquisition card through a signal wire, the image data acquisition card converts digital signals into pixel images based on pixels, then the pixel images are further transmitted to an image recognition module which operates in a microprocessor and faces to the position detection of the photovoltaic cell, and feature extraction is carried out on the pixel images to obtain coordinate errors and angle errors of the photovoltaic cell;
the original image comprises image information of a photovoltaic cell and a transmission belt with scale features;
the photovoltaic cell is made of blue monocrystalline silicon material; the photovoltaic cell is regular square or rectangle; the industrial detection transmission belt is green or black and is made of rubber materials;
the image recognition module facing the position detection of the photovoltaic cell is specifically realized as follows:
first,: performing a method on the pixel image based on an image segmentation technique and a region description technique; extracting the region of the photovoltaic cell from the original image by adopting edge extraction and region segmentation as key features; simultaneously extracting edge characteristics of the belt and detecting scale characteristics of the transmission belt;
secondly: based on a central axis feature extraction technology, four sides of the photovoltaic cell are identified by utilizing edge extraction features, statistical median processing is carried out on the corresponding sides, edge sharpening is carried out after the processing is finished, and two central axes of the photovoltaic cell are extracted; identifying the central axis characteristics of the belt, and then reserving the characteristic pixels of the three lines;
then: the scale features of the transmission belt are utilized, and the pixels with the central axis features of the transmission belt are subjected to coordinate processing based on a pixel coordinate technology, so that the pixels have coordinate features;
and then: determining a characteristic point on the central axis of the photovoltaic cell by utilizing the central axis pixel characteristic of the photovoltaic cell and the pixel characteristic of the central axis of the detection conveyor belt, calculating the number n of pixels from the characteristic point to the central axis of the detection conveyor belt, and calculating the number m of pixels corresponding to the length from the central axis of the detection conveyor belt to the intersection point of the central axis of the photovoltaic cell and the central axis of the detection conveyor belt; then calculating the angle deviation delta theta between the central axis of the photovoltaic cell and the central axis of the transmission belt by using an inverse tangent function arctan (n/m);
finally: extracting the intersection point of the characteristics of the two central axes of the photovoltaic cell as a new characteristic pixel, and calculating the number n of pixels from the characteristic point to the central axes and the number m of pixels of a half span scale value corresponding to the central axes of the transmission belt; and calculating the position deviation deltax from the central point of the photovoltaic cell to the central axis of the transmission belt by using a proportional relation, namely: Δx= (n/m) 0.5 scale.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711337777.7A CN108022266B (en) | 2017-12-14 | 2017-12-14 | Artificial intelligent image recognition method for photovoltaic cell on-line position detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711337777.7A CN108022266B (en) | 2017-12-14 | 2017-12-14 | Artificial intelligent image recognition method for photovoltaic cell on-line position detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108022266A CN108022266A (en) | 2018-05-11 |
CN108022266B true CN108022266B (en) | 2024-02-02 |
Family
ID=62073545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711337777.7A Active CN108022266B (en) | 2017-12-14 | 2017-12-14 | Artificial intelligent image recognition method for photovoltaic cell on-line position detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108022266B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1332840A (en) * | 1998-12-03 | 2002-01-23 | 株式会社科浪 | Information reader |
CN1745385A (en) * | 2003-02-03 | 2006-03-08 | 光子动力学公司 | Method and apparatus for optical inspection of a display |
JP2009128383A (en) * | 2007-11-19 | 2009-06-11 | Ricoh Co Ltd | Relative position detection device, optical linear encoder, rotary encoder, rotating driving apparatus, belt conveying device, image forming apparatus |
CN101872423A (en) * | 2010-05-27 | 2010-10-27 | 天津大学 | Method for tracking moving object on production line |
EP2284520A1 (en) * | 2009-07-28 | 2011-02-16 | David Marcos Muntal | Assembly for the inspection in a continuous manner of cells, strings and photovoltaic modules and inspection method thereof |
CN102602681A (en) * | 2012-01-13 | 2012-07-25 | 天津工业大学 | Machine vision based online deviation fault detecting method for conveying belts |
CN202366890U (en) * | 2011-12-20 | 2012-08-08 | 浚鑫科技股份有限公司 | Solar cell sheet sorting device |
CN102673106A (en) * | 2012-05-09 | 2012-09-19 | 华中科技大学 | Silk screen print positioning equipment and method for photovoltaic solar silicon chip |
CN103344281A (en) * | 2013-07-04 | 2013-10-09 | 中国水产科学研究院黄海水产研究所 | Fish body growth character fast measuring device and measuring method |
CN103837097A (en) * | 2012-11-23 | 2014-06-04 | 上海久点触控计算机系统股份有限公司 | Workpiece angle automatic measurement device based on image processing and measurement method thereof |
CN104089575A (en) * | 2014-07-02 | 2014-10-08 | 北京东方迈视测控技术有限公司 | Intelligent plane detector and detecting method |
CN104573698A (en) * | 2014-12-31 | 2015-04-29 | 河海大学 | Image texture main direction recognition method oriented to imaging measurement |
WO2015154487A1 (en) * | 2014-04-09 | 2015-10-15 | 华南理工大学 | Grouped holes verticality detection system and method based on visual measurement |
CN106651828A (en) * | 2016-09-21 | 2017-05-10 | 哈尔滨工业大学 | Product dimension sub-pixel measurement method under industrial microscale motion blurred imaging condition |
CN106709529A (en) * | 2017-01-18 | 2017-05-24 | 河北工业大学 | Visual detection method for color difference classification of photovoltaic cells |
CN107306242A (en) * | 2016-04-20 | 2017-10-31 | 中兴通讯股份有限公司 | Carrier phase recovery method and device |
-
2017
- 2017-12-14 CN CN201711337777.7A patent/CN108022266B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1332840A (en) * | 1998-12-03 | 2002-01-23 | 株式会社科浪 | Information reader |
CN1745385A (en) * | 2003-02-03 | 2006-03-08 | 光子动力学公司 | Method and apparatus for optical inspection of a display |
JP2009128383A (en) * | 2007-11-19 | 2009-06-11 | Ricoh Co Ltd | Relative position detection device, optical linear encoder, rotary encoder, rotating driving apparatus, belt conveying device, image forming apparatus |
EP2284520A1 (en) * | 2009-07-28 | 2011-02-16 | David Marcos Muntal | Assembly for the inspection in a continuous manner of cells, strings and photovoltaic modules and inspection method thereof |
CN101872423A (en) * | 2010-05-27 | 2010-10-27 | 天津大学 | Method for tracking moving object on production line |
CN202366890U (en) * | 2011-12-20 | 2012-08-08 | 浚鑫科技股份有限公司 | Solar cell sheet sorting device |
CN102602681A (en) * | 2012-01-13 | 2012-07-25 | 天津工业大学 | Machine vision based online deviation fault detecting method for conveying belts |
CN102673106A (en) * | 2012-05-09 | 2012-09-19 | 华中科技大学 | Silk screen print positioning equipment and method for photovoltaic solar silicon chip |
CN103837097A (en) * | 2012-11-23 | 2014-06-04 | 上海久点触控计算机系统股份有限公司 | Workpiece angle automatic measurement device based on image processing and measurement method thereof |
CN103344281A (en) * | 2013-07-04 | 2013-10-09 | 中国水产科学研究院黄海水产研究所 | Fish body growth character fast measuring device and measuring method |
WO2015154487A1 (en) * | 2014-04-09 | 2015-10-15 | 华南理工大学 | Grouped holes verticality detection system and method based on visual measurement |
CN104089575A (en) * | 2014-07-02 | 2014-10-08 | 北京东方迈视测控技术有限公司 | Intelligent plane detector and detecting method |
CN104573698A (en) * | 2014-12-31 | 2015-04-29 | 河海大学 | Image texture main direction recognition method oriented to imaging measurement |
CN107306242A (en) * | 2016-04-20 | 2017-10-31 | 中兴通讯股份有限公司 | Carrier phase recovery method and device |
CN106651828A (en) * | 2016-09-21 | 2017-05-10 | 哈尔滨工业大学 | Product dimension sub-pixel measurement method under industrial microscale motion blurred imaging condition |
CN106709529A (en) * | 2017-01-18 | 2017-05-24 | 河北工业大学 | Visual detection method for color difference classification of photovoltaic cells |
Non-Patent Citations (4)
Title |
---|
DELTA机器人传送带与视觉的综合标定方法;杨强, 刘冠峰;机电工程技术;第44卷(第1期);第5-10页 * |
Research on Geometric Positioning Algorithm of Vision System in High Speed and High Precision Chip Mounter;Huang Y H , Li D B;.Applied Mechanics and Materials;第519-520页 * |
杨应平等.《光电技术实验》.北京邮电大学出版社,2012,第162-163页. * |
王伟 ; 郑永果 ; 卫文学 ; .基于机器视觉的在线电池检测系统研究.系统仿真学报.2006,第18卷第425-429页. * |
Also Published As
Publication number | Publication date |
---|---|
CN108022266A (en) | 2018-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106238350B (en) | A kind of solar battery sheet method for separating and system based on machine vision | |
CN106935683B (en) | A kind of positioning of solar battery sheet SPEED VISION and correction system and its method | |
Zhang et al. | Solar cell surface defect detection based on improved YOLO v5 | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN105303168A (en) | Multi-view pointer type instrument identification method and device | |
CN102393181B (en) | Automatic online detection method and device of angle steel geometric parameters | |
CN104063873A (en) | Shaft sleeve part surface defect on-line detection method based on compressed sensing | |
CN104964886A (en) | Welded member fatigue stress and strain real-time non-contact type monitoring method | |
CN106643965B (en) | Method for accurately identifying liquid level by utilizing template matching | |
CN107133962A (en) | A kind of diamond saw blade extracting thermal crack method based on rim detection | |
CN105718964A (en) | Transmission line vibration damper visual detection method | |
CN113989241A (en) | Photovoltaic module EL defect detection method based on image processing and deep learning fusion | |
CN206056509U (en) | Axial workpiece machine vision size detecting device | |
CN104807397A (en) | Product detection system and product detection method | |
CN115375636A (en) | Full-size detection method and equipment for power battery module | |
CN108022266B (en) | Artificial intelligent image recognition method for photovoltaic cell on-line position detection | |
CN208314857U (en) | Artificial intelligence pattern recognition device towards the online position detection of photovoltaic cell | |
CN102980536B (en) | Brake block steel back flatness detection system and method | |
CN201903330U (en) | Transparent detection tool | |
Li et al. | Insulator infrared image segmentation algorithm based on dynamic mask and box annotation | |
CN102789998B (en) | Inspecting method and inspecting equipment | |
CN104165696A (en) | Material surface color feature on-line automatic detection method | |
Chang et al. | Fast and high-resolution optical inspection system for in-line detection and labeling of surface defects | |
Xu et al. | A Segmentation Method for PV Modules in Infrared Thermography Images | |
Jie et al. | Method for measuring rotation angle of faucet handle based on machine vision |
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 |