CN111968086B - Chemical industry sight glass split-phase detection method based on machine vision - Google Patents
Chemical industry sight glass split-phase detection method based on machine vision Download PDFInfo
- Publication number
- CN111968086B CN111968086B CN202010811296.0A CN202010811296A CN111968086B CN 111968086 B CN111968086 B CN 111968086B CN 202010811296 A CN202010811296 A CN 202010811296A CN 111968086 B CN111968086 B CN 111968086B
- Authority
- CN
- China
- Prior art keywords
- sight glass
- value
- liquid phase
- image
- phase
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 55
- 239000000126 substance Substances 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 239000007791 liquid phase Substances 0.000 claims abstract description 70
- 230000000007 visual effect Effects 0.000 claims abstract description 36
- 239000012071 phase Substances 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000004438 eyesight Effects 0.000 claims abstract description 22
- 238000013507 mapping Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000005191 phase separation Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000004044 response Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 7
- 239000007788 liquid Substances 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000016776 visual perception Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000012824 chemical production Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 238000006243 chemical reaction Methods 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 description 10
- 239000000463 material Substances 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004382 visual function Effects 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- 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
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Abstract
The invention relates to a chemical industry sight glass split-phase detection method based on machine vision, which comprises the steps of firstly, obtaining a sight glass liquid-phase image by using a vision sensor, and transmitting the image to a vision data processing module; then, processing the visual data, including preprocessing, data space conversion and data feature extraction; and finally, mapping the visual data characteristic value with the liquid phase state, wherein the mapping comprises calibration and characteristic value region division. By the method, the liquid phase of the chemical industry sight glass can be accurately and rapidly identified, the accuracy of phase separation of the sight glass is improved, the stability of a chemical production process is ensured, and unmanned chemical production sites can be realized.
Description
Technical Field
The invention particularly relates to a chemical industry vision mirror split-phase detection method based on machine vision.
Background
In the liquid phase separation process of chemical production, chemical materials are continuously changed in production equipment. Each material state corresponds to a seed liquid phase, and the production operation steps are controlled by observing the liquid phase of the material in real time through a sight glass. Currently, chemical plants mainly obtain the state of a liquid phase through manual observation and take corresponding operations. The production process is brought with a plurality of uncertain factors by adopting a manual observation mode, such as misjudgment of liquid phase by personnel, failure to respond to the change of liquid phase in time, and the like. Some chemical plants have high production environment risks and are not suitable for personnel to observe on site.
At present, the chemical industry sight glass split phase generally adopts a manual observation operation method, and on-site personnel adjust a control valve to split materials by observing the liquid phase state in the sight glass. The personnel observe the information such as the liquid color, the liquid flowing state and the like in the sight glass, and judge the liquid phase in the sight glass according to the information, so as to operate and control the size of the valve to divide materials.
The manual observation operation has several drawbacks:
the manual observation and judgment has subjectivity, so that the judgment error on the liquid phase state of the sight glass is easy to occur, and the waste of production materials is caused.
Personnel have uncertainty in response time to liquid phase changes, and thus stability of the production process cannot be ensured. Many chemical industries are not suitable for personnel to observe in the field.
With the technology maturity and cost reduction of the vision sensor and the continuous enhancement of computing power of edge equipment, the machine vision technology is increasingly used in industrial production scenes. The machine vision technology simulates the visual function of human beings through a computer, extracts information from images, processes and understands the information, and is finally used for completing the actual detection function. The chemical industry sight glass liquid phase detection technology based on machine vision is first application of the machine vision technology in the chemical industry sight glass liquid phase splitting field, sight glass liquid phase pictures are collected through a vision sensor, vision feature extraction calculation is carried out at the edge end, and a liquid phase vision signal is converted into a liquid phase state signal and output in real time. The method has the characteristics of non-contact, unattended operation, high accuracy, low power consumption, low delay and the like.
Disclosure of Invention
The invention aims to provide a chemical industry vision mirror phase-splitting detection method based on machine vision, which aims to solve the existing technical problems.
In order to achieve the above purpose, the present invention provides the following technical solutions: a chemical industry sight glass split-phase detection method based on machine vision comprises three steps of liquid phase state vision perception, vision data processing and vision characteristic and liquid phase state mapping.
Preferably, the specific operation steps are as follows:
A. visual perception of liquid phase state
Firstly positioning data to be detected, selecting a detection area on a liquid phase image of a sight glass, wherein the area is a square area, and then performing median filtering on image data in the area;
B. visual data processing
(1) Data preprocessing
Firstly positioning data to be detected, selecting a detection area on a liquid phase image of a sight glass, wherein the area is a square area, and then performing median filtering on image data in the area;
(2) The value of each pixel point in the square area of the image is converted from a color space to a gray value space.
The calculation formula is s=k (a1×r+a2×g+a3×b)/3;
(3) Feature extraction
Convolving with a convolution kernel in a selected region:
V＝kernel*I,
kernel＝(a11,a12,a13,a21,a22,a23,a31,a32,a33)
converting the convolved two-dimensional image into a one-dimensional feature vector, extracting a certain proportion of numerical values from the feature vector, and calculating the average value of the numerical values:
C. visual features and liquid phase state mapping
(1) Calibrating
Respectively inputting pictures of each phase of the liquid phase of the sight glass, and calculating characteristic values according to a method in the visual data processing module, wherein the obtained characteristic values are used as response reference values; for n liquid phases, the reference value obtained is (F1, F2 … Fn);
(2) Eigenvalue interval partitioning
According to the principle that intersection does not exist in each phase characteristic value interval, the characteristic value interval of each phase is determined, and the formula is as follows:
(F l ,F r )＝(F i -α i ,F i +β i )；
(3) The characteristic value maps the liquidus state, and the characteristic value of each frame of sight glass liquidus image detected by the vision sensor is calculated by using a calculating method in the second step;
and (2) if the characteristic value falls in a characteristic value interval corresponding to a certain state in the step (2), the frame image corresponds to the state phase, so that liquid level phase separation is realized.
Preferably, in step B (2), S is a luminance value, R, G, B is three components of a color space value, a1, a2, a3 weighting coefficients, and k is a scaling coefficient; in the step B (3), V is a gray level image after convolution, kernel is a convolution kernel, parameters a11 and a12 … in the convolution kernel are set values, and I is an image of a detection area; n is the length of the feature vector, P is the proportion value of the selected feature value number to the total number, the value range of P (0.5, 1), and F is the feature response value of the visual data.
Preferably, F in step C (2) i Is the reference value of the i-th phase, alpha i For the left offset value of the reference feature, beta i For right offset value of reference feature, alpha i 、β i And (5) the set characteristic value interval offset parameter.
Compared with the prior art, the invention has the beneficial effects that:
(1) The chemical industry sight glass liquid phase can be accurately and rapidly identified, and each phase state of the sight glass liquid phase can be accurately detected;
(2) The low delay response mirror changes the liquid phase, so that the stability of the chemical production process is ensured;
(3) The production site does not need personnel to participate, and the production safety is improved.
Description of the drawings:
fig. 1: the step flow chart of the invention;
fig. 2: the device of the invention is schematically shown.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
The patent provides a chemical industry sight glass phase-splitting detection method based on machine vision, which realizes complete chemical industry sight glass liquid phase-splitting function on the basis of hardware such as a vision sensor, edge equipment and the like.
Example 1
A chemical industry sight glass split-phase detection method based on machine vision comprises three steps of liquid phase state vision perception, vision data processing and vision characteristic and liquid phase state mapping.
1. Visual perception of liquid phase state
The visual sensor arranged on the outer side of the sight glass is used for capturing the image of the liquid phase of the sight glass in real time and transmitting the captured image to the visual processing module of the edge equipment through the serial port.
2. Visual data processing
1. And (5) preprocessing data. The data to be detected are positioned first, and a detection area is selected from the liquid phase image of the sight glass, wherein the detection area is a square area. And then median filtering is carried out on the image data in the region.
2. The value of each pixel point in the square area of the image is converted from a color space to a gray value space, and the calculation formula is S=k (a1×R+a2×G+a3×B)/3.
Where S is the luminance value, R, G, B is the three components of the color space value, a1, a2, a3 weighting coefficients, and k is the scaling coefficient.
3. Feature extraction, performing convolution calculation in a selected area by using a 3-dimensional convolution kernel:
V＝kernel*I,
kernel＝(a11,a12,a13,a21,a22,a23,a31,a32,a33)
wherein: v is a gray level image after convolution, kernel is a convolution kernel, parameters a11 and a12 … in the convolution kernel are set values, and I is an image of a detection area.
And converting the convolved two-dimensional image into a one-dimensional feature vector. Extracting a certain proportion of numerical values from the characteristic vector, and calculating the average value of the numerical values:
wherein N is the length of the feature vector, P is the proportion value of the selected feature value number to the total number, the value range (0.5, 1) of P is the feature response value of the visual data.
3. Visual eigenvalue and liquidus state mapping
1. And calibrating, namely respectively inputting pictures of each phase of the liquid phase of the sight glass, and calculating a characteristic value according to a method in the visual data processing module, wherein the obtained characteristic value is used as a response reference value. For the n liquid phases, the reference value obtained is (F1, F2 … Fn).
2. Dividing the eigenvalue intervals, and determining the eigenvalue interval of each phase according to the principle that the eigenvalue interval of each phase does not have intersection, wherein the formula is as follows: (F) l ,F r )＝(F i -α i ,F i +β i )。
Wherein F is i Is the reference value of the i-th phase, alpha i For the left offset value of the reference feature, beta i For right offset value of reference feature, alpha i 、β i And (5) the set characteristic value interval offset parameter.
3. The characteristic value maps the liquidus state, and the characteristic value of each frame of sight glass liquidus image detected by the vision sensor is calculated by using the calculating method in the second step. And (2) if the characteristic value falls in a characteristic value interval corresponding to a certain state in the step (2), the frame image corresponds to the state phase, so that liquid level phase separation is realized.
4. Liquid phase state output
The visual data of the liquid phase of the sight glass is transmitted into the visual data processing module (II), the visual data processing module outputs the characteristic value of the data, and then the characteristic value is transmitted into the characteristic value mapping part (3) of the visual characteristic value and liquid phase state mapping module (III). Outputting the liquid phase state.
Example two
A chemical industry sight glass split-phase detection method based on machine vision comprises three steps of liquid phase state vision perception, vision data processing and vision characteristic and liquid phase state mapping.
1. Visual perception of liquid phase state
The visual sensor arranged on the outer side of the sight glass is used for capturing the image of the liquid phase of the sight glass in real time and transmitting the captured image to the visual processing module of the edge equipment through the serial port.
2. Visual data processing
1. And (5) preprocessing data. The data to be detected are positioned first, and a detection area is selected from the liquid phase image of the sight glass, wherein the detection area is a square area. And then carrying out Gaussian filtering and mean filtering on the image data in the region.
2. The value of each pixel point in the square area of the image is converted from a color space to a gray value space, and the calculation formula is S=k (a1×R+a2×G+a3×B)/3.
Where S is the luminance value, R, G, B is the three components of the color space value, a1, a2, a3 weighting coefficients, and k is the scaling coefficient.
3. Feature extraction, and convolution computation is performed in the selected area by using other multidimensional convolution kernels (such as 5-dimensional, 7-dimensional and the like):
V＝kernel*I,
kernel＝(a11,a12,a13,a21,a22,a23,a31,a32,a33)
wherein: v is a gray level image after convolution, kernel is a convolution kernel, parameters a11 and a12 … in the convolution kernel are set values, and I is an image of a detection area.
And converting the convolved two-dimensional image into a one-dimensional feature vector. Extracting a certain proportion of numerical values from the characteristic vector, and calculating the average value of the numerical values:
wherein N is the length of the feature vector, P is the proportion value of the selected feature value number to the total number, the value range (0.5, 1) of P is the feature response value of the visual data.
3. Visual eigenvalue and liquidus state mapping
1. And calibrating, namely respectively inputting pictures of each phase of the liquid phase of the sight glass, and calculating a characteristic value according to a method in the visual data processing module, wherein the obtained characteristic value is used as a response reference value. For the n liquid phases, the reference value obtained is (F1, F2 … Fn).
2. Dividing the eigenvalue intervals, and determining the eigenvalue interval of each phase according to the principle that the eigenvalue interval of each phase does not have intersection, wherein the formula is as follows: (F) l ,F r )＝(F i -α i ,F i +β i )。
Wherein F is i Is the reference value of the i-th phase, alpha i For the left offset value of the reference feature, beta i For right offset value of reference feature, alpha i 、β i And (5) the set characteristic value interval offset parameter.
3. The characteristic value maps the liquidus state, and the characteristic value of each frame of sight glass liquidus image detected by the vision sensor is calculated by using the calculating method in the second step. And (2) if the characteristic value falls in a characteristic value interval corresponding to a certain state in the step (2), the frame image corresponds to the state phase, so that liquid level phase separation is realized.
4. Liquid phase state output
And (3) the visual data of the liquid phase of the sight glass is transmitted into the (second) visual data processing module, the visual data processing module outputs the characteristic value of the data, and then the characteristic value is transmitted into the characteristic value mapping part of the (third) visual characteristic value and the (3) characteristic value of the liquid phase state mapping module, so as to output the liquid phase state.
In the above embodiment, the image of the liquid phase of the sight glass is transmitted to the edge device in real time, including the data transmission method described in the embodiment; the visual data processing module of the liquid phase of the sight glass comprises data preprocessing, a data characteristic extraction mode and the like in the embodiment; mapping the characteristic value of the data of the liquid phase of the sight glass with the state of the liquid phase, wherein the mapping comprises a calibration method, characteristic value interval division, characteristic value mapping and the like.
According to the embodiment, the chemical industry sight glass liquid phase can be accurately and rapidly identified, the accuracy of sight glass phase separation is improved, the stability of a chemical industry production process is ensured, and unmanned chemical industry production site can be realized.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (1)
1. A chemical industry sight glass split-phase detection method based on machine vision is characterized in that: the method comprises three steps of liquid phase state visual perception, visual data processing and visual characteristic and liquid phase state mapping;
a chemical industry sight glass phase separation method based on machine vision; the method comprises the following steps: 1) The visual sensor is arranged on the outer side of the chemical industry sight glass, and liquid phase images of the chemical industry sight glass are acquired in real time; 2) Transmitting the liquid phase image of the sight glass to edge equipment in real time, wherein the method comprises a data transmission method; 3) The visual data of the liquid phase of the sight glass is processed in real time at the edge end; 4) The visual data processing module of the liquid phase of the sight glass comprises a specific data preprocessing and a data characteristic extraction mode; 5) Mapping the data characteristic value of the liquid phase of the sight glass with the liquid phase state; the method comprises the steps of demarcating a characteristic value interval and mapping the characteristic value;
the specific operation steps are as follows:
A. visual perception of liquid phase state
Firstly positioning data to be detected, selecting a detection area on a liquid phase image of a sight glass, wherein the area is a square area, and then performing median filtering on image data in the area;
B. visual data processing
(1) Data preprocessing
Firstly positioning data to be detected, selecting a detection area on a liquid phase image of a sight glass, wherein the area is a square area, and then performing median filtering on image data in the area;
(2) Converting the value of each pixel point in the square area of the image from a color space to a gray value space;
the calculation formula is s=k (a1×r+a2×g+a3×b)/3;
(3) Feature extraction
Convolving with a convolution kernel in a selected region:
V＝kernel*I,kernel＝(a11,a12,a13,a21,a22,a23,a31,a32,a33)
converting the convolved two-dimensional image into a one-dimensional feature vector, extracting a certain proportion of numerical values from the feature vector, and calculating the average value of the numerical values:
C. visual features and liquid phase state mapping
(1) Calibrating
Respectively inputting pictures of each phase of the liquid phase of the sight glass, and calculating characteristic values according to a method in the visual data processing module, wherein the obtained characteristic values are used as response reference values; for n liquid phases, the reference value obtained is (F1, F2...fn);
(2) Eigenvalue interval partitioning
According to the principle that intersection does not exist in each phase characteristic value interval, the characteristic value interval of each phase is determined, and the formula is as follows: (Fl, fr) = (Fi- αi, fi+βi);
(3) The characteristic value maps the liquidus state, and the characteristic value of each frame of sight glass liquidus image detected by the vision sensor is calculated by using a calculating method in the second step;
the characteristic value falls in a characteristic value interval corresponding to a certain state in the step 2, and the frame image corresponds to the state phase, so that liquid level phase separation is realized;
in the step B (2), S is a brightness value, R, G, B is three components of a color space value, a1, a2 and a3 weighting coefficients and k is a scaling coefficient; in the step B (3), V is a gray level image after convolution, kernel is a convolution kernel, parameters a11 and a12 … in the convolution kernel are set values, and I is an image of a detection area; n is the length of the feature vector, P is the proportion value of the selected feature value number to the total number, the value range of P (0.5, 1), F is the feature response value of the visual data;
f in step C (2) i Is the reference value of the i-th phase, alpha i For the left offset value of the reference feature, beta i For right offset value of reference feature, alpha i 、β i And (5) the set characteristic value interval offset parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010811296.0A CN111968086B (en) | 2020-08-13 | 2020-08-13 | Chemical industry sight glass split-phase detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010811296.0A CN111968086B (en) | 2020-08-13 | 2020-08-13 | Chemical industry sight glass split-phase detection method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111968086A CN111968086A (en) | 2020-11-20 |
| CN111968086B true CN111968086B (en) | 2024-04-16 |
Family
ID=73365399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010811296.0A Active CN111968086B (en) | 2020-08-13 | 2020-08-13 | Chemical industry sight glass split-phase detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111968086B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114677371B (en) * | 2022-05-06 | 2022-09-02 | 南通市海视光电有限公司 | Chemical interface detection method based on machine vision |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1645139A (en) * | 2004-12-27 | 2005-07-27 | 长春迪瑞实业有限公司 | Method for analysing non-centrifugal urine by image identifying system |
| JP2006138814A (en) * | 2004-11-15 | 2006-06-01 | Matsushita Electric Works Ltd | Liquid level detection method |
| WO2011062352A1 (en) * | 2009-11-19 | 2011-05-26 | 한국건설기술연구원 | Method for recognizing a liquid level using temporal variation in the distribution of the pixel concentration in images, and apparatus for recognizing a liquid level using same |
| CN104501737A (en) * | 2014-12-19 | 2015-04-08 | 中国人民解放军国防科学技术大学 | Device and method for positioning boundary of liquid jet spray |
| CN107784644A (en) * | 2016-08-25 | 2018-03-09 | 台州道致科技有限公司 | A kind of determination method and device of immiscible liquid interface |
| CN108562586A (en) * | 2017-12-25 | 2018-09-21 | 西南石油大学 | A kind of pipeline oil-water two-phase flow distributed mutually recognition methods |
| CN108830824A (en) * | 2018-04-16 | 2018-11-16 | 中北大学 | Transfusion liquid facial vision detects alarm system and its detection method |
| CN110782436A (en) * | 2019-10-18 | 2020-02-11 | 宁波大学 | Conveyor belt material state detection method based on computer vision |
| CN111389323A (en) * | 2020-04-17 | 2020-07-10 | 中国计量大学上虞高等研究院有限公司 | Machine vision sight glass liquid separation identification control device and method for partition confirmation |
-
2020
- 2020-08-13 CN CN202010811296.0A patent/CN111968086B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006138814A (en) * | 2004-11-15 | 2006-06-01 | Matsushita Electric Works Ltd | Liquid level detection method |
| CN1645139A (en) * | 2004-12-27 | 2005-07-27 | 长春迪瑞实业有限公司 | Method for analysing non-centrifugal urine by image identifying system |
| WO2011062352A1 (en) * | 2009-11-19 | 2011-05-26 | 한국건설기술연구원 | Method for recognizing a liquid level using temporal variation in the distribution of the pixel concentration in images, and apparatus for recognizing a liquid level using same |
| CN104501737A (en) * | 2014-12-19 | 2015-04-08 | 中国人民解放军国防科学技术大学 | Device and method for positioning boundary of liquid jet spray |
| CN107784644A (en) * | 2016-08-25 | 2018-03-09 | 台州道致科技有限公司 | A kind of determination method and device of immiscible liquid interface |
| CN108562586A (en) * | 2017-12-25 | 2018-09-21 | 西南石油大学 | A kind of pipeline oil-water two-phase flow distributed mutually recognition methods |
| CN108830824A (en) * | 2018-04-16 | 2018-11-16 | 中北大学 | Transfusion liquid facial vision detects alarm system and its detection method |
| CN110782436A (en) * | 2019-10-18 | 2020-02-11 | 宁波大学 | Conveyor belt material state detection method based on computer vision |
| CN111389323A (en) * | 2020-04-17 | 2020-07-10 | 中国计量大学上虞高等研究院有限公司 | Machine vision sight glass liquid separation identification control device and method for partition confirmation |
Non-Patent Citations (2)
| Title |
|---|
| 化工搅拌釜内流动测量技术的应用进展;杨斌;《化工进展》;第31卷(第11期);1-10 * |
| 水平管气水两相流分相界面识别;许燕斌;《天津大学学报》;第43卷(第8期);1-6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111968086A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734694A (en) | Water quality monitoring method based on big data | |
| CN116167668B (en) | BIM-based green energy-saving building construction quality evaluation method and system | |
| CN111968086B (en) | Chemical industry sight glass split-phase detection method based on machine vision | |
| CN109215025A (en) | A kind of method for detecting infrared puniness target approaching minimization based on non-convex order | |
| CN115131561A (en) | Potassium salt flotation froth image segmentation method based on multi-scale feature extraction and fusion | |
| CN114241386A (en) | Method for detecting and identifying hidden danger of power transmission line based on real-time video stream | |
| CN117274756A (en) | Fusion method and device of two-dimensional image and point cloud based on multi-dimensional feature registration | |
| CN115775236A (en) | Surface tiny defect visual detection method and system based on multi-scale feature fusion | |
| Mateus et al. | Assessment of two techniques to merge ground-based and TRMM rainfall measurements: a case study about Brazilian Amazon Rainforest | |
| Lyu et al. | Automated visual inspection expert system for multivariate statistical process control chart | |
| Zhang et al. | Automatic non-destructive multiple lettuce traits prediction based on DeepLabV3+ | |
| CN112417980A (en) | Single-stage underwater biological target detection method based on feature enhancement and refinement | |
| CN111951163B (en) | Visual conversion system and method for real-time data image | |
| CN109932281B (en) | Vision-based liquid viscosity on-line measuring method | |
| CN116071437A (en) | Hydraulic tunnel apparent defect space calibration method | |
| CN112927139B (en) | Binocular thermal imaging system and super-resolution image acquisition method | |
| CN114910478A (en) | Visual interface instrument for chemical interface detection and detection method thereof | |
| CN115700760A (en) | Multi-mode data-based total-space laser radar scattering cross section calculation method | |
| CN112116561B (en) | Power grid transmission line detection method and device based on image processing fusion network weight | |
| CN114005064A (en) | Biological water body pollution early warning method and device based on machine vision technology | |
| CN114677371B (en) | Chemical interface detection method based on machine vision | |
| CN112085779A (en) | Wave parameter estimation method and device | |
| CN116399871B (en) | Automobile part assembly detection system and method based on machine vision | |
| Yang et al. | Star Photometry for DECam Legacy Survey and Sloan Digital Sky Survey Images Based on Convolutional Neural Networks | |
| CN115452823B (en) | Protection material quality detection method and device based on hybrid perception |
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 |