CN108961203A - A kind of three-dimensional rebuilding method of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique - Google Patents
A kind of three-dimensional rebuilding method of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique Download PDFInfo
- Publication number
- CN108961203A CN108961203A CN201810152782.9A CN201810152782A CN108961203A CN 108961203 A CN108961203 A CN 108961203A CN 201810152782 A CN201810152782 A CN 201810152782A CN 108961203 A CN108961203 A CN 108961203A
- Authority
- CN
- China
- Prior art keywords
- data
- dimensional
- hollow plate
- type ceramic
- ceramic membrane
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 83
- 239000000919 ceramic Substances 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004927 fusion Effects 0.000 title claims abstract description 16
- 238000002604 ultrasonography Methods 0.000 title claims abstract 4
- 239000012528 membrane Substances 0.000 claims abstract description 63
- 238000005516 engineering process Methods 0.000 claims abstract description 55
- 238000001514 detection method Methods 0.000 claims description 27
- 238000005315 distribution function Methods 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 6
- 238000009877 rendering Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 2
- 239000013535 sea water Substances 0.000 description 5
- 238000010612 desalination reaction Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000003325 tomography Methods 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 239000011148 porous material Substances 0.000 description 2
- 229910010293 ceramic material Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000001223 reverse osmosis Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
- G06T2207/10136—3D ultrasound image
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
A kind of three-dimensional rebuilding method of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique.The present invention realizes the three-dimensional reconstruction of the complete defect of hollow plate type ceramic film by merging hollow plate type ceramic film internal flaw three-dimensional reconstruction data and hollow board-like ceramic membrane surface defect three-dimensional reconstruction data, the former is acquired by ultrasonic detecting technology, and the latter is acquired by machine vision technique；The weight of the hollow plate type ceramic film internal flaw three-dimensional data by ultrasonic technique acquisition and the hollow board-like ceramic membrane surface defect three-dimensional data based on machine vision acquisition is calculated separately using evidence theory, and value is closed to the weight setting of above-mentioned acquisition, with the final defect boundary of determination and obtain the three-dimensional data of the complete defect of hollow plate type ceramic film；Non-rigid alignment based on constraint is carried out to the three-dimensional data of the complete defect after redistributing, to realize three-dimensionalreconstruction.The method of the present invention can effectively solve the problems, such as that defect complexity is different, waste of material.
Description
Technical Field
The invention relates to a three-dimensional reconstruction method for defects of a hollow plate-type ceramic membrane by fusing ultrasonic and machine vision technologies, and belongs to the technical field of mechanical engineering and computer engineering.
Background
In the face of increasingly severe water shortage situation, the supply of water to the sea occupying 96.5 percent of the total water resource reserves of the ball is the necessary way to solve the problem of water shortage. Among the numerous methods of desalination of sea water, reverse osmosis desalination of sea water: () The technology has the characteristics of small occupied area, short construction period, simple operation, small specific investment, no phase change, low energy consumption, quick starting and running and the like, and is rapidly developed in the field of seawater desalination. At present, the methodThe pretreatment process can be divided into a conventional method and a membrane method, and the membrane method pretreatment process includes an organic membrane method and an inorganic membrane method. As one of the inorganic membranes, the hollow plate-type ceramic membrane has narrow pore size distribution and poresHigh efficiency, thin separation layer, small filtration resistance and the like, and has high unit membrane surface area treatment capacity, large water production capacity and stable chemical properties of the membrane, can stably run in seawater for a long time, and is more suitable for seawater desalination pretreatment. The hollow plate-type ceramic membrane is a brittle material, the Young's modulus is high, and even a tiny defect or slight strain can cause extremely large mechanical stress. Defects such as cracks, internal pores, interlayers and the like are non-perfect phenomena often occurring in ceramic materials. To accurately detect the shape, position, distribution and other characteristics of the defects, it is necessary to realize the rapid detection and three-dimensional reconstruction of the defects. For the internal defect detection of the hollow plate-type ceramic membrane, the conventional two-dimensional CT-based image detection means is easy to have misjudgment and missing judgment, and the ultrasonic technology for detecting, identifying and measuring the defects of the three-dimensional space is a development direction in the future. Aiming at the surface detection of the hollow plate-type ceramic membrane, in the traditional pipeline inner wall detection technology, a magnetic flux leakage method and an eddy current method cannot be used due to the limitation of detection materials, and the detection precision of an ultrasonic detection method is too low. The machine vision detection technology is used as a pipeline inner wall detection method with the best development prospect, and has the advantages of high measurement speed, high measurement precision, complete image contained information, easiness in automatic continuous detection, capability of meeting the speed requirement on a production line and the like. The three-dimensional detection of the deep-layer defects of the hollow plate-type ceramic membrane can be realized by an ultrasonic technology, the three-dimensional detection of the surface defects of the hollow plate-type ceramic membrane can be realized based on machine vision, the characteristics of the defects such as appearance, position, distribution, size and the like can be accurately detected based on the detection data of non-rigid alignment fusion of the two defects, and a corresponding three-dimensional reconstruction model can be constructed. And estimating the quality classification of the hollow plate type ceramic membrane according to the volume calculation of the defects, thereby effectively solving the problems of complicated and various defects and material waste.
In the prior art, Kumakiri et al in Norway propose a new thin film characterization technique in "Membrane characterization by a novel defect detection technique" (Micropole and mesopole Materials, Vol115, No1-2(October),2008: 33-39) for visualization and localization of nano-defects, which greatly simplifies the leak detection of the Membrane and makes it possible to accurately locate small leaks; france sco Lanza et al at California university establishes a finite element model of an Ultrasonic Tomography array on a defect track in the text of "Ultrasonic Tomography for Three-Dimensional Imaging of internal Rail motions of Proof-of-Positive Numerical Simulances" (TransportationResearch Record. Vol2374, 2013: 162-168), and proposes a Three-Dimensional in-orbit defect Tomography algorithm; in the research and implementation of a ceramic valve core surface defect detection system based on regional classification (combined machine tool and automatic processing technology, volume 10, pages 82-86 in 2017), the Tangliang of Hubei university of industry and the like, a ceramic valve core surface defect detection algorithm optimized in a regional and multistage way is provided according to the difference of the surface reflectivity of the ceramic valve core; "a phased array ultrasonic detection method based on improved dynamic depth focusing" (patent No. CN 102809610B) of Zhongzheng gan and Xuna of Beijing aerospace university obtains the patent of national invention. However, these studies only adopt a detection technology, and there is still a gap in the data obtained by fusing different detection technologies, and there is a considerable distance from practical production and application. A RANSAC thinning algorithm of three-point ICP is proposed in the '3D orientation of dynamic vertical using spark 3D-laser-scanner and 2Dimage fusion' by Dennis Christie et al from Gunadrma University, so as to carry out three-dimensional reconstruction of rigid moving objects; the application framework of the data fusion CT technology in the field of concrete structure detection is established in the 'application research of the data fusion technology in the concrete structure detection' of Wangting of the university of Tongji, and the infrared imaging and the ultrasonic technology are combined, so that the three-dimensional reconstruction of the defect size and the identification of the defect type are realized. However, the researches are in a theoretical exploration stage, and whether the three-dimensional data suitable for fusing the internal defects and the surface defects of the hollow plate-type ceramic membrane is still to be verified.
Disclosure of Invention
In order to overcome the defects and defects of the prior art, the invention provides a three-dimensional reconstruction method for the defects of the hollow plate-type ceramic membrane by adopting an advanced fusion technology and fusing ultrasonic and machine vision technologies, and the method can improve the accuracy of the three-dimensional reconstruction of the defects of the hollow plate-type ceramic membrane.
The invention aims to realize the three-dimensional reconstruction method of the defects of the hollow plate-type ceramic membrane by fusing ultrasonic and machine vision technologies, which comprises the following steps:
1) three-dimensional reconstruction of internal defects of the hollow plate-type ceramic membrane is realized based on a region growing technology of ultrasonic data;
2) realizing three-dimensional reconstruction of surface defects of the hollow plate-type ceramic membrane based on a machine vision technology;
3) and the three-dimensional reconstruction of the complete defects of the hollow plate-type ceramic membrane is realized by combining ultrasonic and machine vision technologies.
Preferably, the ultrasonic data in step (1) is obtained by performing volume rendering on data acquired by an ultrasonic detection technology and then implementing three-dimensional reconstruction by applying a new mixed rendering method based on a region growing technology;
the principle of the region growing technology is that a seed pixel is selected as a growing point, then the similarity (generally, average gray value) of the seed pixel and pixels in surrounding regions is compared in a threshold value range, if the similarity exists, the seed pixel and the pixels are connected to form a region, the growth of a plane is extended into a three-dimensional space field, visual segmentation can be achieved, and a threshold value range is set by using a threshold value selecting technology to obtain the clearest two-dimensional defect form;
the three-dimensional reconstruction is to place the whole scanned area in a Cartesian coordinate system, the value of each position corresponds to the volume pixel of the current position, a three-dimensional area growing technology is applied, namely, one volume pixel is selected as a seed point, then calculation points in the threshold range of adjacent positions are searched, and the adjacent pixels of the image selected by the threshold are connected and reconstructed into an entity three-dimensional image.
Preferably, the machine vision technology in the step (2) is to adopt a double monocular three-dimensional measurement system to obtain point cloud data of the surface defects of the hollow plate-type ceramic membrane.
The three-dimensional reconstruction method of the surface defects of the hollow plate-type ceramic membrane comprises the following steps:
(1) preprocessing the acquired point cloud data: performing median filtering on the data to improve the anti-noise capability, resampling and coordinate normalization of the data;
(2) and (3) performing convolution on the Laplace operator and the point cloud data, removing useless point cloud data, splicing the point cloud data to form three-dimensional data of the surface defects of the hollow plate-type ceramic membrane, and performing three-dimensional reconstruction.
Preferably, the data fusion in the step (3) is to fuse data acquired by the ultrasonic technology after three-dimensional reconstructionAnd data obtained by three-dimensional reconstruction of data acquired by machine visionAnd respectively calculating weights of the two types of data after fusion by adopting an evidence theory, and then carrying out constraint-based non-rigid alignment to obtain complete three-dimensional defect data of the hollow plate-type ceramic membrane and carrying out three-dimensional reconstruction. The process of calculating the weight is as follows:
(1) respectively determining the weight of the three-dimensional data of the internal defects of the hollow plate-type ceramic membrane acquired by the ultrasonic technology and the weight of the three-dimensional data of the surface defects of the hollow plate-type ceramic membrane acquired based on machine vision, namely the probability distribution value before fusion;
(2) calculating probability distribution function values of the two fused data by adopting an evidence theory, namely determining the credibility of different three-dimensional data acquisition modes;
(3) setting a closed value for the obtained fused probability distribution function value to determine a final defect boundary;
(4) acquiring three-dimensional data of the complete defects of the hollow plate-type ceramic membrane;
the evidence theory refers toTheory or belief function theory, often referred to simply asTheory, the combination rule is as follows
Is provided withAndis the same identification frameTwo probability distribution functions of (1), then orthogonal sum thereofIs composed of
When in useWhen the temperature of the water is higher than the set temperature,（1）
when in useWhen the temperature of the water is higher than the set temperature,（2）
wherein,（3）
if it is notThen are orthogonal toIs also a probability distribution function; if it is notThen there is no orthogonal sumBalance ofAndare in contradiction.
Compared with the prior art, the method has the advantages that the novel algorithm is adopted to carry out the three-dimensional reconstruction method for the defects of the hollow plate-type ceramic membrane by fusing the ultrasonic and machine vision technologies, so that data calculation and storage are reduced, the imaging algorithm is simplified, and the detection efficiency of the ceramic membrane is improved.
Drawings
FIG. 1 is a flow chart of a three-dimensional reconstruction method for defects of a hollow plate-type ceramic membrane by fusing ultrasonic and machine vision technologies.
Detailed Description
The following will further describe the specific implementation of the present invention with reference to the accompanying drawings and a three-dimensional reconstruction method for defects of a hollow plate-type ceramic membrane by combining ultrasonic and machine vision techniques.
As shown in FIG. 1, the method for realizing the three-dimensional reconstruction of the hollow plate-type ceramic membrane defect by fusing the ultrasonic technology and the machine vision technology comprises the following steps:
1) three-dimensional reconstruction of internal defects of hollow plate-type ceramic membrane based on ultrasonic data region growing technology
After volume rendering is carried out on data acquired by ultrasonic detection, a novel mixed rendering method based on a region growing technology is applied to realize three-dimensional reconstruction. The principle of region growth is that a seed pixel is selected as a growth point, then the similarity (generally, average gray value) of the seed pixel and pixels in surrounding regions is compared in a threshold range, if the similarity exists, the seed pixel and the pixels are connected to form a region, and the growth of a plane is extended into a three-dimensional space field, so that visual segmentation can be realized. A threshold value range is set by using a threshold value selection technology so as to obtain the clearest two-dimensional defect form. And (3) placing the whole scanned area in a Cartesian coordinate system, wherein the value of each position corresponds to the voxel of the current position. And (3) applying a three-dimensional region growing technology, namely selecting a voxel as a seed point, searching for an arithmetic point in a threshold range at an adjacent position, and connecting adjacent pixels of an image selected by a threshold to form a solid three-dimensional image.
2) Three-dimensional reconstruction of surface defects of hollow plate-type ceramic membrane based on machine vision
The machine vision technology is used for acquiring point cloud data of the surface defects of the hollow plate-type ceramic membrane by adopting a double-monocular three-dimensional measurement system. Firstly, preprocessing acquired point cloud data: the method comprises the steps of carrying out median filtering on data to improve the noise resistance, resampling, coordinate normalization and the like of the data, then convolving a Laplacian operator with point cloud data, determining the defect edge and removing useless point cloud data, then splicing the point cloud data to form three-dimensional data of the surface defect of the hollow plate-type ceramic membrane, and finally carrying out three-dimensional reconstruction.
3) Three-dimensional reconstruction for realizing complete defects of hollow plate-type ceramic membrane by fusing ultrasonic and machine vision technologies
Data acquired by ultrasonic technology are three-dimensionally reconstructed to obtain dataObtaining data after three-dimensional reconstruction of data acquired by machine visionAnd respectively calculating weights of the two types of data after fusion by adopting an evidence theory, and then carrying out constraint-based non-rigid alignment to obtain the three-dimensional defect complete data of the hollow plate-type ceramic membrane. The process of calculating the weight is as follows:
(1) respectively determining the weight of the three-dimensional data of the internal defects of the hollow plate-type ceramic membrane acquired by the ultrasonic technology and the weight of the three-dimensional data of the surface defects of the hollow plate-type ceramic membrane acquired based on machine vision, namely the probability distribution value before fusion;
(2) calculating probability distribution function values of the two fused data by adopting an evidence theory, namely determining the credibility of different three-dimensional data acquisition modes;
(3) setting a closed value for the obtained fused probability distribution function value to determine a final defect boundary;
(4) acquiring three-dimensional data of the complete defects of the hollow plate-type ceramic membrane;
the evidence theory refers toTheory or belief function theory, often referred to simply asTheory, the combination rule is as follows
Is provided withAndis the same identification frameTwo probability distribution functions of (1), then orthogonal sum thereofIs composed of
When in useWhen the temperature of the water is higher than the set temperature,（4）
when in useWhen the temperature of the water is higher than the set temperature,（5）
wherein,（6）
if it is notThen are orthogonal toIs also a probability distribution function; if it is notThen there is no orthogonal sumBalance ofAndare in contradiction.
And performing constraint-based non-rigid alignment on the redistributed three-dimensional data of the complete defects, thereby realizing the three-dimensional reconstruction of the complete defects of the hollow plate-type ceramic membrane. Non-rigid alignment selection is a thin-plate spline interpolation algorithm (b)) Defining a corresponding error function, comprising
Error in distance； （7）
Smoothing errors； （8）
The optimization formula is defined as follows:； （9）
by usingAnd solving the algorithm.
Wherein in formula (7)Representative data，Representative data，Is a transformation matrix. By usingThe algorithm (a quasi-Newton method) is solved, and numerical tests show thatThe algorithm is one of the effective methods for solving the large-scale boundary problem.
Claims (4)
1. A three-dimensional reconstruction method for hollow plate-type ceramic membrane defects by combining ultrasonic and machine vision technologies, which is characterized by comprising the following steps:
1) three-dimensional reconstruction of internal defects of the hollow plate-type ceramic membrane is realized based on a region growing technology of ultrasonic data;
2) realizing three-dimensional reconstruction of surface defects of the hollow plate-type ceramic membrane based on a machine vision technology;
3) and the three-dimensional reconstruction of the complete defects of the hollow plate-type ceramic membrane is realized by combining ultrasonic and machine vision technologies.
2. The method for reconstructing the defect of the hollow plate-type ceramic membrane by fusing the ultrasonic and machine vision technologies as claimed in claim 1, wherein the ultrasonic data in the step (1) is obtained by performing volume rendering on data acquired by an ultrasonic detection technology and then applying a new mixed rendering method based on a region growing technology to realize three-dimensional reconstruction;
the principle of the region growing technology is that a seed pixel is selected as a growing point, then the similarity (generally, average gray value) of the seed pixel and pixels in surrounding regions is compared in a threshold value range, if the similarity exists, the seed pixel and the pixels are connected to form a region, the growth of a plane is extended into a three-dimensional space field, visual segmentation can be achieved, and a threshold value selecting technology is used for setting a threshold value range to obtain the clearest two-dimensional defect form;
the three-dimensional reconstruction is to place the whole scanned area in a Cartesian coordinate system, the value of each position corresponds to the volume pixel of the current position, a three-dimensional area growing technology is applied, namely, one volume pixel is selected as a seed point, then calculation points in the threshold range of adjacent positions are searched, and the adjacent pixels of the image selected by the threshold are connected and reconstructed into an entity three-dimensional image.
3. The method for three-dimensional reconstruction of the hollow plate-type ceramic membrane defects by fusing the ultrasonic and machine vision technologies as claimed in claim 1, wherein the machine vision technology in the step (2) is to use a binomial three-dimensional measurement system to obtain point cloud data of the hollow plate-type ceramic membrane surface defects;
the three-dimensional reconstruction method of the surface defects of the hollow plate-type ceramic membrane comprises the following steps:
(1) preprocessing the acquired point cloud data: performing median filtering on the data to improve the anti-noise capability, resampling and coordinate normalization of the data;
(2) and (3) performing convolution on the Laplace operator and the point cloud data, removing useless point cloud data, splicing the point cloud data to form three-dimensional data of the surface defects of the hollow plate-type ceramic membrane, and performing three-dimensional reconstruction.
4. The method for three-dimensional reconstruction of hollow plate-type ceramic membrane defects by fusion of ultrasound and machine vision technologies as claimed in claim 1, wherein the data fusion in step (3) is to fuse the data acquired by the ultrasound technology and three-dimensional reconstruction to obtain dataAnd three-dimensionally reconstructing the data acquired by the machine vision to obtain the dataCalculating respective weight values of the two types of data after fusion by adopting an evidence theory, and then carrying out constraint-based non-rigid alignment to obtain complete three-dimensional defect data of the hollow plate-type ceramic membrane and carrying out three-dimensional reconstruction;
the process of calculating the weight is as follows:
(1) respectively determining the weight of the three-dimensional data of the internal defects of the hollow plate-type ceramic membrane acquired by the ultrasonic technology and the weight of the three-dimensional data of the surface defects of the hollow plate-type ceramic membrane acquired based on machine vision, namely the probability distribution value before fusion;
(2) calculating probability distribution function values of the two fused data by adopting an evidence theory, namely determining the credibility of different three-dimensional data acquisition modes;
(3) setting a closed value for the obtained fused probability distribution function value to determine a final defect boundary;
(4) acquiring three-dimensional data of the complete defects of the hollow plate-type ceramic membrane;
the evidence theory refers toTheory or belief function theory, often referred to simply asTheory, the combination rule is as follows
Is provided withAndis the same identification frameTwo probability distribution functions of (1), then orthogonal sum thereofIs composed of
When in useWhen the temperature of the water is higher than the set temperature,（1）
when in useWhen the temperature of the water is higher than the set temperature,（2）
wherein,（3）
if it is notThen are orthogonal toIs also a probability distribution function; if it is notThen there is no orthogonal sumBalance ofAndare in contradiction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810152782.9A CN108961203B (en) | 2018-02-19 | 2018-02-19 | Three-dimensional reconstruction method for defects of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810152782.9A CN108961203B (en) | 2018-02-19 | 2018-02-19 | Three-dimensional reconstruction method for defects of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108961203A true CN108961203A (en) | 2018-12-07 |
| CN108961203B CN108961203B (en) | 2023-07-18 |
Family
ID=64495099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810152782.9A Active CN108961203B (en) | 2018-02-19 | 2018-02-19 | Three-dimensional reconstruction method for defects of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108961203B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110231343A (en) * | 2019-06-25 | 2019-09-13 | 明阳科技（苏州）股份有限公司 | A kind of composite material on-line measuring device and its detection method |
| CN114088817A (en) * | 2021-10-28 | 2022-02-25 | 扬州大学 | Deep learning flat ceramic membrane ultrasonic defect detection method based on deep features |
| CN114820368A (en) * | 2022-04-27 | 2022-07-29 | 广东职业技术学院 | Damaged ceramic image restoration method and system based on 3D scanning |
| CN116630328A (en) * | 2023-07-25 | 2023-08-22 | 深圳市鑫冠亚科技有限公司 | Online detection method and system for heat dissipation bottom plate |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697006A (en) * | 2009-09-18 | 2010-04-21 | 北京航空航天大学 | Target identification method based on data fusion of airborne radar and infrared imaging sensor |
| CN102486462A (en) * | 2010-12-03 | 2012-06-06 | 中国科学院沈阳自动化研究所 | Three-dimensional reconstruction method for internal defect of alloy firmware |
| CN107256575A (en) * | 2017-04-07 | 2017-10-17 | 天津市天中依脉科技开发有限公司 | A kind of three-dimensional tongue based on binocular stereo vision is as method for reconstructing |
| CN107271867A (en) * | 2017-06-27 | 2017-10-20 | 国网河南省电力公司检修公司 | GIS partial discharge fault type recognition method based on D S evidence theories |
| US20180042176A1 (en) * | 2016-08-15 | 2018-02-15 | Raptor Maps, Inc. | Systems, devices, and methods for monitoring and assessing characteristics of harvested specialty crops |
-
2018
- 2018-02-19 CN CN201810152782.9A patent/CN108961203B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697006A (en) * | 2009-09-18 | 2010-04-21 | 北京航空航天大学 | Target identification method based on data fusion of airborne radar and infrared imaging sensor |
| CN102486462A (en) * | 2010-12-03 | 2012-06-06 | 中国科学院沈阳自动化研究所 | Three-dimensional reconstruction method for internal defect of alloy firmware |
| US20180042176A1 (en) * | 2016-08-15 | 2018-02-15 | Raptor Maps, Inc. | Systems, devices, and methods for monitoring and assessing characteristics of harvested specialty crops |
| CN107256575A (en) * | 2017-04-07 | 2017-10-17 | 天津市天中依脉科技开发有限公司 | A kind of three-dimensional tongue based on binocular stereo vision is as method for reconstructing |
| CN107271867A (en) * | 2017-06-27 | 2017-10-20 | 国网河南省电力公司检修公司 | GIS partial discharge fault type recognition method based on D S evidence theories |
Non-Patent Citations (1)
| Title |
|---|
| 刘自德等: "基于区域生长法的超声图像分割", 《医学影像》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110231343A (en) * | 2019-06-25 | 2019-09-13 | 明阳科技（苏州）股份有限公司 | A kind of composite material on-line measuring device and its detection method |
| CN114088817A (en) * | 2021-10-28 | 2022-02-25 | 扬州大学 | Deep learning flat ceramic membrane ultrasonic defect detection method based on deep features |
| CN114088817B (en) * | 2021-10-28 | 2023-10-24 | 扬州大学 | Deep learning flat ceramic membrane ultrasonic defect detection method based on deep features |
| CN114820368A (en) * | 2022-04-27 | 2022-07-29 | 广东职业技术学院 | Damaged ceramic image restoration method and system based on 3D scanning |
| CN116630328A (en) * | 2023-07-25 | 2023-08-22 | 深圳市鑫冠亚科技有限公司 | Online detection method and system for heat dissipation bottom plate |
| CN116630328B (en) * | 2023-07-25 | 2023-09-29 | 深圳市鑫冠亚科技有限公司 | Online detection method and system for heat dissipation bottom plate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108961203B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108961203A (en) | A kind of three-dimensional rebuilding method of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique | |
| CN112581457B (en) | Pipeline inner surface detection method and device based on three-dimensional point cloud | |
| Wang | 3D building modeling using images and LiDAR: A review | |
| CN109035224B (en) | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud | |
| CN109816664B (en) | Three-dimensional point cloud segmentation method and device | |
| CN102032875B (en) | Image-processing-based cable sheath thickness measuring method | |
| Ghahremani et al. | Damage detection and finite-element model updating of structural components through point cloud analysis | |
| CN101788666B (en) | Underwater three dimensional terrain reconstruction method based on multi-beam sonar data | |
| CN109615654B (en) | Method for measuring corrosion depth and area of inner surface of drainage pipeline based on binocular vision | |
| CN103226828B (en) | The method for registering images of a kind of underwater voice 3 D visual imaging | |
| Gui et al. | Automated defect detection and visualization for the robotic airport runway inspection | |
| CN108305278B (en) | Image matching correlation improvement method in ORB-SLAM algorithm | |
| CN107103610A (en) | Stereo mapping satellite image matches suspicious region automatic testing method | |
| O’Byrne et al. | Image-based damage assessment for underwater inspections | |
| CN104392428A (en) | Splicing system for side-scan sonar images | |
| Paetsch et al. | Automated 3D crack detection for analyzing damage processes in concrete with computed tomography | |
| Guo et al. | Detection and classification of pipe defects based on pipe-extended feature pyramid network | |
| Azouz et al. | Evolution of Crack Analysis in Structures Using Image Processing Technique: A Review | |
| Altingövde et al. | 3D reconstruction of curvilinear structures with stereo matching deep convolutional neural networks | |
| Li et al. | Spatial-temporal measurement of waves in laboratory based on binocular stereo vision and image processing | |
| Guldur et al. | Damage detection on structures using texture mapped laser point clouds | |
| Brahim et al. | 3D reconstruction of underwater scenes using image sequences from acoustic camera | |
| Bouchahma et al. | Optical-flow-based approach for the detection of shoreline changes using remote sensing data | |
| CN113806892A (en) | Reverse engineering-based propeller digital design and processing method | |
| Wang et al. | Crack Detection and Feature Extraction of Heritage Architecture Via Point Clouds |
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 |