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
- dimensional
- data
- defect
- plate type
- hollow plate
- 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
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 present invention relates to the three-dimensional reconstruction sides of a kind of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique
Method belongs to mechanical engineering and computer engineering design field.
Background technique
In face of increasingly serious water shortage situation, wanting water to the sea for accounting for earth water resource gross reserves 96. 5% is to solve to lack
The only way of water problems.In numerous method for desalting seawater, reverse osmosis seawater desalting () technology have land occupation
Less, construction period is short, easy to operate, specific investment is small, without phase-change, the features such as low energy consumption and starting operation is fast, led in sea water desalination
Domain is quickly grown.At presentPretreating process can be divided into conventional method and embrane method, and membrane pretreatment technique includes organic embrane method
With inorganic embrane method.As one kind of inoranic membrane, hollow plate type ceramic film have pore-size distribution is narrow, porosity is high, separating layer is thin,
The advantages that filtration resistance is small, and unit membrane area treating capacity is high, water-yielding capacity is big, and the chemical property of film is stablized, Ke Yi
Long-term stable operation, is more suitable for seawater desalinization pretreatment in seawater.Hollow plate type ceramic film is fragile material, Young's modulus compared with
Height, even if small defect or slight strain can all lead to great mechanical stress.Crackle class scarce, internal porosity, interlayer etc. lack
Falling into is the non-complete phenomenon often occurred in ceramic material.Accurately to find out the characters such as pattern, position, the distribution of defect spy
Sign, it is therefore desirable to realize quick detection and the three-dimensional reconstruction of drawbacks described above.For hollow plate type ceramic film Inner Defect Testing, pass
System is easy to appear erroneous judgement based on two-dimensional CT image detection means, fails to judge, and ultrasonic technique is used for the defects detection of three-dimensional space, knows
It is not developing direction from now on measurement.It is detected for hollow board-like ceramic membrane surface, in traditional inner wall of the pipe detection technique
In, leakage method and eddy-current method are limited and cannot be used by detection material, and ultrasonic Detection Method detection accuracy is too low.Machine view
Feel the detection technique inner wall of the pipe detection method best as development prospect, have measuring speed fast, measurement accuracy is high, image packet
It is complete containing information, automatic continuous detection easy to accomplish, many advantages, such as rate request on production line can be met.By ultrasonic technique
The three dimensional detection that can be realized hollow plate type ceramic film deep zone defect can be realized hollow plate type ceramic film table based on machine vision
The three dimensional detection of planar defect, based on it is non-rigid alignment fusion both detection data, come accurately find out various defects pattern,
The features such as position, distribution and size, and corresponding Three-dimension Reconstruction Model can be constructed.It is calculated, is estimated hollow according to the volume of defect
The classification of plate type ceramic film quality effectively solves the problems, such as that defect complexity is different, waste of material.
In prior art, Kumakiri of Norway etc. is in " Membrane characterisation by a novel defect
Detection technique " (Microporous and Mesoporous Materials, Vol115, No1-2
(October), 2008:33-39) a kind of new film characterization technology is proposed in a text, for nano-defects visualization and
Positioning, this new technology enormously simplify the leak detection of film, make it possible that Small leak is accurately positioned also;University of California
Francesco Lanza etc. is in " Ultrasonic Tomography for Three-Dimensional Imaging of
Internal Rail Flaws Proof-of-Principle Numerical Simulations " (Transportation
Research Record.Vol2374,2013:162-168) ultrasound tomography array on defect track is established in a text
Finite element model proposes a kind of three-dimensional internal rail defect tomography algorithm;Hubei University Of Technology's soup is bright equal " based on region point
Grade the system research of ceramic cartridge surface defects detection and realize " (building-block machine and automation processing technology, 2017 volume 10
The 82-86 pages) in a text, according to the difference of ceramic cartridge surface reflectivity, propose the ceramics of a kind of subregion, multilevel optimization
Spool face defects detection algorithm;Dry, Xu Na " one kind is poly- based on improved dynamic depth for Beijing Space aviation university straight
Burnt phased array ultrasonic detecting method " (patent authorization number: CN102809610B) obtains national inventing patent.But these researchs are equal
Only with a kind of detection technique means, there are still certain blank in terms of merging different detection technique data obtained, from
Also there are also quite long distances for production application.Dennis Christie from Gunadarma University etc. exists
“3D reconstruction of dynamic vehicles using sparse 3D-laser-scanner and 2D
The RANSAC thinning algorithm of one three point ICP is proposed in an image fusion " text, to carry out the three of rigid motion object
Dimension is rebuild;It is established in Wang Ting " Data fusion technique is in the application study in concrete structure detection " text of Tongji University
Data fusion CT technology combines infrared imaging with ultrasonic technique in the application framework of concrete structure detection field, realizes
Three-dimensionalreconstruction to defect size and the identification to defect type.But these researchs are in the theory study stage, are
There are also to be verified for the no three-dimensional data suitable for merging hollow plate type ceramic film internal flaw and surface defect.
Summary of the invention
For overcome the deficiencies in the prior art and defect, the present invention use advanced integration technology, and it is super to provide a kind of fusion
The three-dimensional rebuilding method of the hollow plate type ceramic film defect of sound and machine vision technique, this method can be improved hollow plate type ceramic
The accuracy of film defect three-dimensional reconstruction.
The purpose of the present invention is what is be achieved through the following technical solutions, the hollow plate type ceramic of fusion ultrasound and machine vision technique
The three-dimensional rebuilding method of film defect, comprising the following steps:
1) region growth technique based on ultrasound data realizes hollow plate type ceramic film internal flaw three-dimensional reconstruction;
2) three-dimensional reconstruction of hollow board-like ceramic membrane surface defect is realized based on machine vision technique;
3) fusion ultrasound and machine vision technique realize the three-dimensional reconstruction of the complete defect of hollow plate type ceramic film.
Preferably, the ultrasound data in the step (1) is answered after referring to the data progress volume drawing by ultrasonic detecting technology acquisition
Three-dimensionalreconstruction is realized based on the blend rendering method of region growth technique with a kind of new;
Wherein the principle of the region growth technique be by choosing a sub-pixel as growing point, then with peripheral region
The similitude (generally average gray value) of pixel compares within the scope of threshold value in domain, and structure is connected if with uniformity
At region, the growth of plane is extended in three-dimensional space bay, visualization segmentation can be thus achieved, with threshold value selecting technology, if
A threshold range is set, to obtain the most clearly in the form of two-dimensional defect;
The three-dimensional reconstruction is that entire scanning zone is placed in cartesian coordinate system, and the value of each position corresponds to current location
Volumetric pixel, with 3D region increase technology, that is, choose an individual pixel as seed point and then look for adjacent position threshold
The image adjacent pixel connection that threshold value is chosen is reassembled into solid threedimensional image by the calculation point being worth in range.
Preferably, the machine vision technique in the step (2) refers to hollow board-like using double monocular three-dimension measuring systems acquisitions
The point cloud data of ceramic membrane surface defect.
The method of the three-dimensional reconstruction of the hollow board-like ceramic membrane surface defect are as follows:
(1) point cloud data of acquisition is pre-processed: including carrying out median filtering to data to improve the antinoise energy of data
Power, resampling, Unitary coordinate;
(2) by Laplace operator and point cloud data convolution, useless point cloud data is removed, split point cloud data forms hollow plate
The three-dimensional data of formula ceramic membrane surface defect, and carry out three-dimensional reconstruction.
Preferably, data fusion obtains after referring to the data three-dimensional reconstruction that fusion acquire by ultrasonic technique in the step (3)
DataThe data obtained after being rebuild with the data three-dimensional acquired by machine vision, two class data are calculated using evidence theory and are existed
Weight respectively shared, then carries out the non-rigid alignment based on constraint after fusion, lacks to obtain hollow plate type ceramic film three-dimensional
It falls into partial data and carries out three-dimensional reconstruction.The process for calculating weight is as follows:
(1) the hollow plate type ceramic film internal flaw three-dimensional data acquired by ultrasonic technique is determined respectively and is adopted based on machine vision
The weight of the hollow board-like ceramic membrane surface defect three-dimensional data of collection, that is, the probability assignments value before merging;
(2) the probability distribution function value that the two after fusion is calculated using evidence theory, that is, determine different three dimensional data collection modes
Confidence level;
(3) value is closed to the fused probability distribution function value setting of above-mentioned acquisition, with the defect boundary that determination is final;
(4) three-dimensional data of the hollow complete defect of plate type ceramic film is obtained;
The evidence theory refers toTheoretical or belief function is theoretical, often referred to simply asTheory,
Rule of combination is as follows
IfWithIt is same identification frameworkOn two probability distribution functions, then its it is orthogonal andFor
WhenWhen,(1)
WhenWhen,(2)
Wherein,(3)
If, then it is orthogonal andIt is also a probability distribution function;If, then there is no orthogonal and, claimWith
It contradicts.
Compared with prior art, the medicine have the advantages that due to carrying out fusion ultrasound and machine vision skill using New Algorithm
The three-dimensional rebuilding method of the hollow plate type ceramic film defect of art reduces data and calculates, stores, simplifies imaging algorithm, improve
Ceramic membrane detection efficiency.
Detailed description of the invention
The stream of the three-dimensional rebuilding method of a kind of fusion ultrasound of Fig. 1 and the hollow plate type ceramic film defect of machine vision technique
Cheng Tu.
Specific embodiment
The ultrasonic Three-dimensional Gravity with the hollow plate type ceramic film defect of machine vision technique is merged with a kind of with reference to the accompanying drawing
Construction method is further described specific implementation of the invention.
As shown in Figure 1, the present invention merges ultrasound and machine vision technique realizes the three-dimensional reconstruction side of hollow plate type ceramic film defect
Method includes the following steps:
1) region growth technique based on ultrasound data realizes hollow plate type ceramic film internal flaw three-dimensional reconstruction
The data of ultrasound detection acquisition apply a kind of new blend rendering method based on region growth technique after carrying out volume drawing
To realize three-dimensionalreconstruction.Region increase principle be by choose a sub-pixel as growing point, then with peripheral region
The similitude (generally average gray value) of interior pixel compares within the scope of threshold value, and composition is connected if with uniformity
The growth of plane is extended in three-dimensional space bay and visualization segmentation can be thus achieved by region.With threshold value selecting technology, setting
One threshold range, to obtain the most clearly in the form of two-dimensional defect.Entire scanning zone is placed in cartesian coordinate system, each
The value of position corresponds to the volumetric pixel of current location.Increase technology with 3D region, that is, chooses an individual pixel as seed point
The calculation point in adjacent position threshold range is then looked for, the image adjacent pixel connection that threshold value is chosen is reassembled into entity three
Tie up image.
2) three-dimensional reconstruction based on the hollow board-like ceramic membrane surface defect of realizing of Robot Vision
Refer to the point that hollow board-like ceramic membrane surface defect is obtained using double monocular three-dimension measuring systems based on machine vision technique
Cloud data.The point cloud data of acquisition is pre-processed first: including carrying out median filtering to data to improve the anti-noise of data
Sound ability, resampling and Unitary coordinate etc. determine Defect Edge and remove then by Laplace operator and point cloud data convolution
Useless point cloud data is removed, then split point cloud data forms the three-dimensional data of hollow board-like ceramic membrane surface defect, most laggard
Row three-dimensional reconstruction.
3) fusion ultrasound and machine vision technique realize the three-dimensional reconstruction of the complete defect of hollow plate type ceramic film
If obtaining data after being rebuild by the data three-dimensional of ultrasonic technique acquisition, after being rebuild by the data three-dimensional of machine vision acquisition
Obtain data, two class data weight respectively shared after fusion is calculated using evidence theory, is then carried out based on constraint
Non-rigid alignment, to obtain hollow plate type ceramic film 3 D defects partial data.The process for calculating weight is as follows:
(1) the hollow plate type ceramic film internal flaw three-dimensional data acquired by ultrasonic technique is determined respectively and is adopted based on machine vision
The weight of the hollow board-like ceramic membrane surface defect three-dimensional data of collection, that is, the probability assignments value before merging;
(2) the probability distribution function value that the two after fusion is calculated using evidence theory, that is, determine different three dimensional data collection modes
Confidence level;
(3) value is closed to the fused probability distribution function value setting of above-mentioned acquisition, with the defect boundary that determination is final;
(4) three-dimensional data of the hollow complete defect of plate type ceramic film is obtained;
The evidence theory refers toTheoretical or belief function is theoretical, often referred to simply asTheory,
Rule of combination is as follows
IfWithIt is same identification frameworkOn two probability distribution functions, then its it is orthogonal andFor
WhenWhen,(4)
WhenWhen,(5)
Wherein,(6)
If, then it is orthogonal andIt is also a probability distribution function;If, then there is no orthogonal and, claimWith
It contradicts.
Non-rigid alignment based on constraint is carried out to the three-dimensional data of the complete defect after redistributing, to realize hollow board-like
The three-dimensional reconstruction of the complete defect of ceramic membrane.It is non-rigid be aligned selection be thin-plate spline interpolation algorithm (), define corresponding miss
Difference function, including
Range error;(7)
Smoothing error;(8)
Optimization formula is defined as follows:;(9)
UsingAlgorithm is solved.
Wherein in formula (7)Represent data,Represent data,For transformation matrix.Using(one kind is quasi- for algorithm
The method of newton) it solves, numerical experimentation showsAlgorithm is to solve for the effective ways of extensive border issue
One of.
Claims (4)
1. the three-dimensional rebuilding method of a kind of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique, feature exist
In the described method comprises the following steps:
1) region growth technique based on ultrasound data realizes hollow plate type ceramic film internal flaw three-dimensional reconstruction;
2) three-dimensional reconstruction of hollow board-like ceramic membrane surface defect is realized based on machine vision technique;
3) fusion ultrasound and machine vision technique realize the three-dimensional reconstruction of the complete defect of hollow plate type ceramic film.
2. the three-dimensional of a kind of fusion ultrasound according to claim 1 and the hollow plate type ceramic film defect of machine vision technique
Method for reconstructing, characterized in that the ultrasound data in the step (1) refers to and carries out body by the data of ultrasonic detecting technology acquisition
Three-dimensionalreconstruction is realized based on the blend rendering method of region growth technique using a kind of new after drafting;
Wherein the principle of the region growth technique be by choose a sub-pixel as growing point, then with peripheral region
The similitude (generally average gray value) of interior pixel compares within the scope of threshold value, and composition is connected if with uniformity
The growth of plane is extended in three-dimensional space bay and visualization segmentation can be thus achieved by region, with threshold value selecting technology, setting
One threshold range, to obtain the most clearly in the form of two-dimensional defect;
The three-dimensional reconstruction is that entire scanning zone is placed in cartesian coordinate system, and the value of each position corresponds to current location
Volumetric pixel increases technology with 3D region, that is, chooses an individual pixel as seed point and then look for adjacent position threshold value
The image adjacent pixel connection that threshold value is chosen is reassembled into solid threedimensional image by the calculation point in range.
3. the three-dimensional of a kind of fusion ultrasound according to claim 1 and the hollow plate type ceramic film defect of machine vision technique
Method for reconstructing, characterized in that the machine vision technique in the step (2) refers to using in double monocular three-dimension measuring systems acquisitions
The point cloud data of hollow plate formula ceramic membrane surface defect;
The method of the three-dimensional reconstruction of the hollow board-like ceramic membrane surface defect are as follows:
(1) point cloud data of acquisition is pre-processed: including carrying out median filtering to data to improve the antinoise energy of data
Power, resampling, Unitary coordinate;
(2) by Laplace operator and point cloud data convolution, useless point cloud data is removed, split point cloud data forms hollow plate
The three-dimensional data of formula ceramic membrane surface defect, and carry out three-dimensional reconstruction.
4. the three-dimensional of a kind of fusion ultrasound according to claim 1 and the hollow plate type ceramic film defect of machine vision technique
Method for reconstructing, characterized in that after data fusion refers to that fusion is rebuild by the data three-dimensional that ultrasonic technique acquires in the step (3)
Obtain dataData are obtained after rebuilding with the data three-dimensional acquired by machine vision, two class numbers are calculated using evidence theory
According to weight respectively shared after fusion, the non-rigid alignment based on constraint is carried out, then to obtain hollow plate type ceramic film three
Dimension defect partial data simultaneously carries out three-dimensional reconstruction;
The process for calculating weight is as follows:
(1) the hollow plate type ceramic film internal flaw three-dimensional data acquired by ultrasonic technique is determined respectively and is adopted based on machine vision
The weight of the hollow board-like ceramic membrane surface defect three-dimensional data of collection, that is, the probability assignments value before merging;
(2) the probability distribution function value that the two after fusion is calculated using evidence theory, that is, determine different three dimensional data collection modes
Confidence level;
(3) value is closed to the fused probability distribution function value setting of above-mentioned acquisition, with the defect boundary that determination is final;
(4) three-dimensional data of the hollow complete defect of plate type ceramic film is obtained;
The evidence theory refers toTheoretical or belief function is theoretical, often referred to simply asTheory,
Rule of combination is as follows
IfWithIt is same identification frameworkOn two probability distribution functions, then its it is orthogonal andFor
WhenWhen,(1)
WhenWhen,(2)
Wherein,(3)
If, then it is orthogonal andIt is also a probability distribution function;If, then there is no orthogonal and, claimWithIt contradicts.
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 (3)
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 |
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 (5)
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 |
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 |
---|---|---|
CN105193445B (en) | A kind of ultrasonic probe nominal volume mould, ultrasonic probe calibration system and its scaling method | |
CN108763711B (en) | Permeability prediction method based on rock core scanning image block numerical simulation | |
CN108961203A (en) | A kind of three-dimensional rebuilding method of fusion ultrasound and the hollow plate type ceramic film defect of machine vision technique | |
CN103871064B (en) | Preprocessing and segmentation threshold value determining method of volcanic CT images | |
CN103971406B (en) | Submarine target three-dimensional rebuilding method based on line-structured light | |
CN105303616B (en) | Embossment modeling method based on single photo | |
WO2015003496A1 (en) | Method for constructing submarine topography and geomorphology based on fusion of bathymetric data from multiple sources | |
CN104331579A (en) | Simulation method of low-permeability reservoir crude oil boundary layer | |
CN103292697A (en) | Three-dimensional scanning system | |
CN105551004A (en) | Core CT image processing-based remaining oil micro-occurrence representing method | |
CN102928844A (en) | Underwater sub-wavelength resolution ratio three-dimensional imaging method | |
CN107728150A (en) | The method for investigating lake submerged plant through water | |
CN108846860A (en) | A kind of damaged cylindrical drainage pipeline inner wall three-dimensional rebuilding method | |
CN106383133A (en) | Method for measuring capillary pressure of CO2-saline-core system based on X-ray computed tomography (CT) technology | |
CN107766818A (en) | A kind of didactic submerged structure environment line feature extraction method | |
CN105445694A (en) | Equal-gradient sound ray tracking acoustic velocity profile adaptive layering method | |
CN107103610A (en) | Stereo mapping satellite image matches suspicious region automatic testing method | |
CN1301494C (en) | Three-dimensional dividing method for medical images | |
CN110599477B (en) | Method and system for detecting effective porosity of grass planting concrete | |
CN101996415A (en) | Three-dimensional modeling method for eyeball | |
CN113567968B (en) | Underwater target real-time segmentation method based on shallow water multi-beam water depth data and application thereof | |
CN115204456A (en) | Oil displacement rate prediction method based on oil reservoir displacement etching image | |
Wang et al. | Study on edge detection of LIDAR point cloud | |
CN108763731B (en) | Overlapped type duo body delta training image establishing method | |
CN110189403A (en) | A kind of submarine target three-dimensional rebuilding method based on simple beam Forward-looking Sonar |
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 |