CN109932281B - Vision-based liquid viscosity on-line measuring method - Google Patents
Vision-based liquid viscosity on-line measuring method Download PDFInfo
- Publication number
- CN109932281B CN109932281B CN201711373218.1A CN201711373218A CN109932281B CN 109932281 B CN109932281 B CN 109932281B CN 201711373218 A CN201711373218 A CN 201711373218A CN 109932281 B CN109932281 B CN 109932281B
- Authority
- CN
- China
- Prior art keywords
- liquid
- viscosity
- calculating
- optical flow
- field
- 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
Images
Landscapes
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a liquid viscosity on-line measuring method based on vision, which mainly comprises the following steps: calculating a velocity field by an optical flow method and calculating the viscosity of the liquid according to the velocity field. The method comprises the steps of firstly, collecting a fluid picture sequence or video at fixed time intervals by using a camera, then calculating an optical flow field by using an optical flow technology, then calculating a liquid velocity field according to an object-image proportional relation, and finally calculating the liquid viscosity according to a Newtonian fluid formula or a table look-up method. The invention can measure the liquid viscosity on line in real time in a non-contact way, thereby monitoring the liquid viscosity information in the equipment in real time on the premise of not influencing the normal work of the equipment.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a method for measuring liquid viscosity.
Background
The measurement of the viscosity of a fluid is very important in the fields of industrial production and scientific research, and particularly, the viscosity needs to be accurately measured in the production processes of medicines, foods, chemical industry and the like so as to ensure the product quality. The measuring devices and methods used are also various, and a pipe flow method, a ball drop method, a rotation method, a drainage method and the like are common. The conventional rotary viscometer for measuring the fluid viscosity in a laboratory is not suitable for viscosity detection in a production field, and devices such as a portable funnel viscometer and the like adopted in the production field also have the problems of inaccurate measurement result, complex operation and the like. In addition, the methods are all offline measurement, production procedures are additionally added, and when the difference between production and measurement environments is large, such as a high-temperature production environment, the measurement result has a large error. In addition, the viscosity of the fluid in the production process cannot be monitored in real time, so that viscosity change caused by material preparation and environment change in the production process is difficult to find in time, and the quality of the product is influenced.
Disclosure of Invention
The invention provides an on-line viscosity detection method for monitoring the viscosity of liquid in real time. The method collects the liquid flow image in real time, and calculates the velocity field and viscosity information thereof, thereby realizing the online real-time measurement of the viscosity.
The technical scheme adopted by the invention for realizing the purpose is as follows: a method for measuring a speed field and viscosity on line comprises the following steps:
image acquisition: acquiring a flow image of the liquid;
calculating an optical flow field: calculating an optical flow field by an optical flow method;
calculating a speed field: calculating a velocity field according to the camera parameters and the optical flow field;
estimating the viscosity: and estimating the liquid viscosity according to the velocity field.
The image acquisition comprises the following steps:
the camera collects images at set time intervals on flowing liquid to obtain a picture pair consisting of pictures 1 and 2 which are shot adjacently.
The calculating the optical flow field comprises the following steps:
1) establishing a Gaussian image pyramid 1 and a Gaussian image pyramid 2 according to the picture 1 and the picture 2 respectively, wherein the Gaussian image pyramid 1 and the Gaussian image pyramid 2 are
The gray value of each layer of image is respectively as follows: i is1,I2；
2) The gradient of each layer of image in two gaussian image pyramids is calculated: i isx,Iy；
3) Forming pyramid layer pairs by each layer of pyramids from high to low for the image pyramids 1 and 2, and jointly completing the following operations to obtain an optical flow field u, v:
3.1) calculating the time gradient of the pyramid of the layer: i ist＝I2-I1；
3.2) clearing the increment of the optical flow field: du, dv;
3.3) calculating du, dv of each pixel point by using an ultra-relaxation iteration method;
3.4) updating the optical flow by using du, dv calculation result: u + du, v + v;
3.5) obtaining an image before liquid movement by using the image pyramid 2 of the layer and an optical flow result, and replacing the image pyramid 2 of the layer;
4) passing the optical flow results of each layer to the next layer in sequence from high to low: u-k, v-k, where k is the pyramid down-sampling scale.
The method for calculating du and dv of each pixel point by using the super-relaxation iteration method comprises the following steps:
(1) calculating the weight w of each pixel point in the pyramid of the current layerhAnd wsWherein
(2) Calculating the weight w of each pixel pointsThe product of the gradient is denoted by Ixx＝ws*Ix*Ix,Ixy＝ws*Ix*Iy,Iyy＝ws*Iy*Iy,Ixt＝ws*Ix*It,Iyt＝ws*Iy*It；
(3) Iteratively calculating du and dv of each pixel point by using an ultra-relaxation iterative method until the iteration times are met, wherein the calculation formula is
Wherein alpha and omega are constants; when the coordinate of the calculation point is (x, y), the corresponding parameter subscript is (x, y).
The calculating the velocity field comprises the steps of:
according to the formula
Obtaining an image distance; where o is the object distance, i is the image distance, f is the focal length;
according to the formula d ═ dplpObtaining the spatial displacement corresponding to the displacement of each pixel in the optical flow field, wherein d is the spatial displacement of the image, dpIs the pixel shift in the optical flow field,/pIs the physical size of the pixel;
according to the formula
Determining the liquid velocity field corresponding to the optical flow field, where voIs the liquid velocity and T is the sampling time interval.
The estimating the viscosity comprises the steps of:
firstly, taking the maximum speed in the liquid speed field as the surface flow speed of the liquid;
then, the liquid viscosity is estimated: measuring the thickness h of the flowing liquid; then by the formula
Calculating the viscosity of the liquid, wherein mu is the viscosity of the liquid, rho is the density of the liquid, g is the universal gravitation constant, vsIs the liquid surface flow velocity and theta is the angle between the liquid flow direction and the horizontal direction.
When the liquid flow is fixed, the liquid viscosity is estimated by a table look-up method:
estimating the viscosity requires fixing the flow of the liquid;
then respectively calculating the velocity fields of the liquid with different known viscosities and obtaining the corresponding relation between the liquid viscosity and the surface flow velocity by an interpolation method;
and obtaining the liquid viscosity corresponding to the current surface flow rate by searching the corresponding relation between the surface flow rate and the liquid viscosity.
The invention has the following beneficial effects and advantages:
1. the invention can carry out real-time on-line measurement, thereby being capable of monitoring the liquidity and the viscosity of the liquid in real time.
2. The invention adopts a non-contact detection mode, does not need to carry out additional operation on the liquid to be detected, and avoids additional working procedures and interference on the normal work of production equipment.
3. The invention carries out computer automatic detection, automatically returns speed field and viscosity information, and saves labor cost.
4. The invention is more sensitive to the variation of the result, and can find the change of the viscosity in time, thereby improving the sensitivity of measurement.
Drawings
FIG. 1 is a schematic view of an on-line measurement system of the present invention;
wherein 1 is a camera, 2 is a flowing liquid, and 3 is a liquid-bearing flat plate;
FIG. 2 is a basic process flow diagram of the present invention;
FIG. 3 is a flow chart of the method for determining optical flow field by dense optical flow method.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
An on-line speed field and viscosity measurement system comprising the steps of:
image acquisition: acquiring a flow image of the liquid;
calculating an optical flow field: calculating an optical flow field by an optical flow method;
calculating a speed field: calculating a velocity field according to the camera parameters and the optical flow field;
estimating the viscosity: and estimating the liquid viscosity according to the velocity field.
The camera acquires images, i.e. a sequence of pictures or video, at regular time intervals on the flowing liquid.
And calculating the optical flow field of adjacent pictures in the picture sequence or the video by a sparse or dense optical flow method. The sparse optical flow method firstly selects pixel points with obvious brightness change in the picture as key points, and then calculates the sparse optical flow field of the key point positions of the adjacent pictures. The method has the characteristics of high operation speed, good real-time performance and capability of generating the optical flow field with the same frame rate as the shot image.
The dense optical flow method first extracts a certain number of adjacent pairs of pictures at each calculation, and then calculates a dense optical flow for each pair of pictures. The method has the characteristic that the optical flow field is paved on the whole picture, and each pixel has the corresponding optical flow value.
And calculating a speed field, namely firstly obtaining a space displacement field of an image according to the pixel displacement and the physical size of the pixel in the optical flow field, and then obtaining an image distance and a speed field of liquid according to an object-image relational expression.
The method is suitable for the liquid with certain flowing texture or speed reference objects containing impurities, bubbles and the like, and the maximum speed in the speed field is used as the surface flow speed of the liquid. And (4) estimating the liquid viscosity by adopting a calculation method or a table look-up method according to the actual situation.
Selecting a method according to actual conditions: when the liquid thickness is easily measured, the viscosity can be estimated using a calculation method; when the liquid flow is fixed, the viscosity can be estimated using a look-up table;
the calculation method for estimating the liquid viscosity comprises the following steps:
step (1): measuring the thickness of the liquid;
step (2): and calculating the liquid viscosity through a viscosity formula of Newtonian fluid according to the liquid surface flow rate and the liquid thickness.
Estimating the liquid viscosity by a table look-up method: when the flow of the liquid is stable, the corresponding relation between the viscosity and the speed of the liquid with fixed flow is obtained through calibration, and the corresponding viscosity of the liquid with the same flow speed is obtained through a table look-up method in actual work.
The calibration comprises the following steps:
step (1): fixing the flow rate of the liquid;
step (2): respectively calculating stable speed fields of liquids with different known viscosities;
and (3): taking the maximum speed in the speed field as the surface flow speed of the liquid;
and (4): and obtaining a corresponding relation curve of the liquid viscosity and the surface flow rate by an interpolation method.
The hardware structure of the measurement system is shown in fig. 1. The production equipment works normally, a section of area where the liquid 2 flows at a constant speed is selected, and the camera 1 shoots and obtains an image of the liquid in the area, which slowly flows down from the liquid bearing flat plate 3.
The basic method flow diagram of the present invention is shown in fig. 2. Firstly, a camera shoots a picture sequence or a video of flowing liquid; secondly, calculating an optical flow field by using a sparse or dense optical flow method; then calculating a velocity field according to the optical flow field; and finally, estimating the viscosity of the liquid by a calculation method or a table look-up method according to the calculated speed field.
Considering that the liquid picture obtained by shooting has the characteristics of few characteristic points, low sharpness and non-rigidity, the invention adopts an optical flow method to calculate the velocity field. And calculating the optical flow field of adjacent pictures in the picture sequence or the video by a sparse or dense optical flow method. The sparse method firstly selects pixel points such as sift characteristic points, Harris corner points and the like which are greatly distinguished from the periphery in a picture as key points, and when impurities or bubbles are contained in liquid, edge points or center points of the impurities or the bubbles are usually selected as the key points. And then calculating the sparse optical flow field at the key point in the picture by using a Lucas Kanade method and the like. The method has the advantages of high operation speed, good real-time performance and capability of generating the optical flow field with the same frame rate as the shot image. The dense method firstly extracts a certain number of adjacent picture pairs in each calculation, and then calculates dense optical flows for each picture pair by using a dense optical flow algorithm. The method has the advantages that the optical flow field is paved on the whole image, and each pixel has the corresponding optical flow velocity.
As shown in fig. 3, the patent uses a suitable dense optical flow algorithm to complete the measurement of the liquid optical flow field u, v, and the specific implementation steps are as follows:
(1) generating a picture pair consisting of two adjacent shot pictures 1 and 2;
(2) carrying out image preprocessing such as denoising and image graying;
(3) respectively establishing a Gaussian image pyramid 1 and a Gaussian image pyramid 2 according to the picture 1 and the picture 2, wherein the gray value of each layer of image is as follows: i is1,I2；
(4) The gradient of each layer of image in two gaussian image pyramids is calculated: i isx,Iy；
(5) The following operations are performed on each pyramid layer from high to low:
(5.1) performing outer iteration until the iteration number is satisfied:
(5.1.1) calculating the time gradient of the pyramid of the layer: i ist＝I2-I1；
(5.1.2) clearing the optical flow field increment: du, dv;
(5.1.3) performing inner layer iteration until the iteration number is satisfied:
(5.1.3.1) calculating the weight w of each pixel point in the pyramid of the current layerhAnd wsWherein
(5.1.3.2) calculating the weight w of each pixel pointsThe product of the gradient is denoted by Ixx＝ws*Ix*Ix,Ixy＝ws*Ix*Iy,Iyy＝ws*Iy*Iy,Ixt＝ws*Ix*It,Iyt＝ws*Iy*It，
(5.1.3.3) iteratively calculating du, dv of each pixel point by using an over relaxation iterative method (SOR) until the iteration times are met, wherein the calculation formula is
Wherein α is 0.75 and ω is 1.8; when the coordinate of the calculation point is (x, y), the corresponding parameter subscript is (x, y), the parameter with the subscript of (x-1, y) belongs to the left point of the calculation point, and the default parameter subscript is (x, y);
(5.1.4) update the optical flow with du, dv calculation: u + du, v + v;
(5.1.5) utilizing the image pyramid 2 of the layer and the optical flow result to calculate an image before movement, and replacing the image pyramid 2 of the layer;
(5.2) transmitting the optical flow field result jointly calculated by the current layers of the pyramids 1 and 2 to the next layer: u-k, v-k, where k is the pyramid down-sampling scale, typically 2;
the basic method for calculating the velocity field through the optical flow field is: according to the formula
Finding an image distance, wherein o is the object distance, i is the image distance, and f is the focal length; according to the formula d ═ dplpObtaining the spatial displacement corresponding to the displacement of each pixel in the optical flow field, wherein d is the spatial displacement of the image, dpIs the pixel shift in the optical flow field,/pIs the physical size of the pixel; according to the formula
Determining the liquid velocity field corresponding to the optical flow field, where voIs the liquid velocity and T is the sampling time interval.
According to the speedThe liquid viscosity is estimated by the degree field, the maximum speed in the liquid speed field is taken as the surface flow rate of the liquid, and then the liquid viscosity is estimated by adopting a calculation method or a table look-up method. The calculation method estimates the viscosity and needs to measure the thickness h of the flowing liquid; then by the formula
Calculating the viscosity of the liquid, wherein mu is the viscosity of the liquid, rho is the density of the liquid, g is the universal gravitation constant, vsIs the liquid surface flow velocity, and theta is the angle between the liquid flow direction (flat plate) and the horizontal direction. Estimating the flow of the liquid with the viscosity needing to be fixed by a table look-up method; then respectively calculating stable speed fields of the liquid with different known viscosities and obtaining a corresponding relation between the liquid viscosity and the surface flow rate by an interpolation method; in practical application, the liquid viscosity corresponding to the current surface layer flow velocity is obtained by searching a flow velocity-viscosity correspondence table. The viscosity can be calculated using a calculation method when the thickness of the liquid is easily measured, and the viscosity of the liquid can be estimated using a lookup table method when the flow rate in actual operation is stable.
Claims (3)
1. A method for measuring a speed field and viscosity on line is characterized by comprising the following steps:
image acquisition: acquiring a flow image of the liquid;
calculating an optical flow field: calculating an optical flow field by an optical flow method;
the image acquisition comprises the following steps:
the camera collects images with set time intervals for flowing liquid to obtain a picture pair consisting of a picture 1 and a picture 2 which are shot adjacently;
the calculating the optical flow field comprises the following steps:
1) respectively establishing a Gaussian image pyramid 1 and a Gaussian image pyramid 2 according to the picture 1 and the picture 2, wherein the gray value of each layer of image is as follows: i is1，I2；
2) The gradient of each layer of image in two gaussian image pyramids is calculated: i isx，Iy；
3) Forming pyramid layer pairs by each layer of pyramids from high to low for the image pyramids 1 and 2, and jointly completing the following operations to obtain an optical flow field u, v:
3.1) calculating the time gradient of the pyramid of the layer: i ist＝I2-I1；
3.2) clearing the increment of the optical flow field: du, dv;
3.3) calculating du, dv of each pixel point by using an ultra-relaxation iteration method;
3.4) updating the optical flow by using du, dv calculation result: u + du, v + v;
3.5) obtaining an image before liquid movement by using the image pyramid 2 of the layer and an optical flow result, and replacing the image pyramid 2 of the layer;
4) passing the optical flow results of each layer to the next layer in sequence from high to low: u ═ u × k, v ═ v × k, where k is the pyramid downsampling scale;
calculating a speed field: calculating a velocity field according to the camera parameters and the optical flow field;
estimating the viscosity: estimating the liquid viscosity according to the velocity field;
the calculating the velocity field comprises the steps of:
according to the formula
Obtaining an image distance; where o is the object distance, i is the image distance, f is the focal length;
according to the formula d ═ dplpObtaining the spatial displacement corresponding to the displacement of each pixel in the optical flow field, wherein d is the spatial displacement of the image, dpIs the pixel shift in the optical flow field,/pIs the physical size of the pixel;
according to the formula
Determining the liquid velocity field corresponding to the optical flow field, where voIs the liquid velocity, T is the sampling time interval;
the estimating the viscosity comprises the steps of:
firstly, taking the maximum speed in the liquid speed field as the surface flow speed of the liquid;
then estimatingLiquid viscosity: measuring the thickness h of the flowing liquid; then by the formula
Calculating the viscosity of the liquid, wherein mu is the viscosity of the liquid, rho is the density of the liquid, g is the universal gravitation constant, vsIs the liquid surface flow velocity and theta is the angle between the liquid flow direction and the horizontal direction.
2. The on-line measuring method for velocity field and viscosity according to claim 1, wherein said calculating du, dv for each pixel point by using the super-relaxation iteration method comprises the following steps:
(1) calculating the weight w of each pixel point in the pyramid of the current layerhAnd wsWherein
(2) Calculating the weight w of each pixel pointsThe product of the gradient is denoted by Ixx＝ws*Ix*Ix，Ixy＝ws*Ix*Iy，Iyy＝ws*Iy*Iy，Ixt＝ws*Ix*It，Iyt＝ws*Iy*It；
(3) Iteratively calculating du and dv of each pixel point by using an ultra-relaxation iterative method until the iteration times are met, wherein the calculation formula is
Wherein alpha and omega are constants; when the coordinate of the calculation point is (x, y), the corresponding parameter subscript is (x, y).
3. The on-line measuring method for the velocity field and the viscosity according to claim 1, characterized in that: when the liquid flow is fixed, the liquid viscosity is estimated by a table look-up method:
estimating the viscosity requires fixing the flow of the liquid;
then respectively calculating the velocity fields of the liquid with different known viscosities and obtaining the corresponding relation between the liquid viscosity and the surface flow velocity by an interpolation method;
and obtaining the liquid viscosity corresponding to the current surface flow rate by searching the corresponding relation between the surface flow rate and the liquid viscosity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711373218.1A CN109932281B (en) | 2017-12-19 | 2017-12-19 | Vision-based liquid viscosity on-line measuring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711373218.1A CN109932281B (en) | 2017-12-19 | 2017-12-19 | Vision-based liquid viscosity on-line measuring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109932281A CN109932281A (en) | 2019-06-25 |
| CN109932281B true CN109932281B (en) | 2021-08-17 |
Family
ID=66983562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711373218.1A Active CN109932281B (en) | 2017-12-19 | 2017-12-19 | Vision-based liquid viscosity on-line measuring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109932281B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116205914B (en) * | 2023-04-28 | 2023-07-21 | 山东中胜涂料有限公司 | Waterproof coating production intelligent monitoring system |
| CN116612123B (en) * | 2023-07-21 | 2023-10-13 | 山东金胜粮油食品有限公司 | Visual detection method for peanut oil processing quality |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561383A (en) * | 2009-05-26 | 2009-10-21 | 上海大学 | Computer vision-based system and computer-vision based method for automatically measuring viscosity of colored liquid |
| CN101750515A (en) * | 2008-12-03 | 2010-06-23 | 中国科学院理化技术研究所 | Non-contact measurement method for measuring liquid parameter |
| CN104869387A (en) * | 2015-04-19 | 2015-08-26 | 中国传媒大学 | Method for acquiring binocular image maximum parallax based on optical flow method |
| CN106204640A (en) * | 2016-06-29 | 2016-12-07 | 长沙慧联智能科技有限公司 | A kind of moving object detection system and method |
| CN106780559A (en) * | 2016-12-28 | 2017-05-31 | 中国科学院长春光学精密机械与物理研究所 | A kind of moving target detecting method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8079250B2 (en) * | 2008-07-09 | 2011-12-20 | Lockheed Martin Corporation | Viscometer system utilizing an optical flow cell |
| US8509489B2 (en) * | 2009-10-05 | 2013-08-13 | The United States Of America, As Represented By The Secretary Of The Navy | System and method for estimating velocity from image sequence with first order continuity |
| CN103499514A (en) * | 2013-09-25 | 2014-01-08 | 北京化工大学 | Method and device for testing fluid viscosity on line |
| CN107102165B (en) * | 2017-04-14 | 2020-03-20 | 重庆大学 | Surface flow field measuring method based on particle image velocimetry |
-
2017
- 2017-12-19 CN CN201711373218.1A patent/CN109932281B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101750515A (en) * | 2008-12-03 | 2010-06-23 | 中国科学院理化技术研究所 | Non-contact measurement method for measuring liquid parameter |
| CN101561383A (en) * | 2009-05-26 | 2009-10-21 | 上海大学 | Computer vision-based system and computer-vision based method for automatically measuring viscosity of colored liquid |
| CN104869387A (en) * | 2015-04-19 | 2015-08-26 | 中国传媒大学 | Method for acquiring binocular image maximum parallax based on optical flow method |
| CN106204640A (en) * | 2016-06-29 | 2016-12-07 | 长沙慧联智能科技有限公司 | A kind of moving object detection system and method |
| CN106780559A (en) * | 2016-12-28 | 2017-05-31 | 中国科学院长春光学精密机械与物理研究所 | A kind of moving target detecting method and device |
Non-Patent Citations (5)
| Title |
|---|
| Use of an optical meter to measure the flow;J. Vorwerk et al;《 Flow Measurement and Instrumentation》;19940131;51-54 * |
| 图像处理技术在微流控芯片中流体运动检测的应用;蔡绍皙等;《重庆大学学报》;20131231;43-50 * |
| 基于光流方程和目标匹配的视频图像目标跟踪方法;丛杨等;《红外与激光工程》;20061031;312-315 * |
| 新型微试样黏度检测装置及其在细胞生物学中的应用;邹米莎;《中国博士学位论文全文数据库 医疗卫生科技辑》;20170915;E080-1 * |
| 背景差分法自动检测毛细管粘度计液位的方法;梁西银等;《计算机工程与应用》;20140915;245-249 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109932281A (en) | 2019-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105787901B (en) | A kind of multiple dimensioned velocity field measurement method for adjacent two interframe in sun full resolution pricture sequence | |
| CN111781113B (en) | Dust grid positioning method and dust grid monitoring method | |
| CN108615244A (en) | A kind of image depth estimation method and system based on CNN and depth filter | |
| WO2021036565A1 (en) | Space debris observation method based on alternation of different exposure times of ccd camera | |
| CN107102165B (en) | Surface flow field measuring method based on particle image velocimetry | |
| CN109932281B (en) | Vision-based liquid viscosity on-line measuring method | |
| CN109060290B (en) | Method for measuring wind tunnel density field based on video and sub-pixel technology | |
| CN109489566A (en) | Lithium battery diaphragm material cuts checking method for width, detection system and device | |
| CN108305277A (en) | A kind of heterologous image matching method based on straightway | |
| CN116563279B (en) | Measuring switch detection method based on computer vision | |
| CN114187330A (en) | Structural micro-amplitude vibration working mode analysis method based on optical flow method | |
| CN108399614B (en) | Fabric defect detection method based on non-sampling wavelet and Gumbel distribution | |
| Zhao | PIPE VIBRATION DETECTION ALGORITHM USING COMPUTER VISION TECHNOLOGY | |
| CN110348459A (en) | Based on multiple dimensioned quick covering blanket method sonar image fractal characteristic extracting method | |
| CN115752250A (en) | Bridge high-precision displacement monitoring method fusing computer vision and acceleration | |
| CN108205210B (en) | LCD defect detection system and method based on Fourier mellin and feature matching | |
| CN115717867A (en) | Bridge deformation measurement method based on airborne double cameras and target tracking | |
| CN108416091A (en) | A kind of measurement method of easy camera ground resolution and drone flying height relationship | |
| CN105608674B (en) | A kind of image enchancing method based on image registration, interpolation and denoising | |
| CN110969601B (en) | Structure rotation response non-contact identification method based on visual characteristic tracking algorithm | |
| CN107369163B (en) | Rapid SAR image target detection method based on optimal entropy dual-threshold segmentation | |
| CN112525326A (en) | Computer vision measurement method for three-dimensional vibration of unmarked structure | |
| CN109978982B (en) | Point cloud rapid coloring method based on oblique image | |
| Wang et al. | Vision technique for deflection measurements based on laser positioning | |
| CN110675393A (en) | Blank specification detection method 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 |