CN108961203B - Three-dimensional reconstruction method for defects of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies - Google Patents
Three-dimensional reconstruction method for defects of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies Download PDFInfo
- Publication number
- CN108961203B CN108961203B CN201810152782.9A CN201810152782A CN108961203B CN 108961203 B CN108961203 B CN 108961203B CN 201810152782 A CN201810152782 A CN 201810152782A CN 108961203 B CN108961203 B CN 108961203B
- Authority
- CN
- China
- Prior art keywords
- data
- dimensional
- ceramic membrane
- hollow plate
- type ceramic
- 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
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 three-dimensional reconstruction method for defects of a hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies. According to the invention, three-dimensional reconstruction of the complete defect of the hollow plate type ceramic membrane is realized by fusing three-dimensional reconstruction data of the internal defect of the hollow plate type ceramic membrane and three-dimensional reconstruction data of the surface defect of the hollow plate type ceramic membrane, wherein the three-dimensional reconstruction data are acquired by an ultrasonic detection technology, and the three-dimensional reconstruction data are acquired by a machine vision technology; respectively calculating the weight of the three-dimensional data of the internal defect of the hollow plate type ceramic membrane acquired by an ultrasonic technology and the three-dimensional data of the surface defect of the hollow plate type ceramic membrane acquired based on machine vision by adopting an evidence theory, and setting a closed value for the obtained weight to determine a final defect boundary and acquire the three-dimensional data of the complete defect of the hollow plate type ceramic membrane; and carrying out constraint-based non-rigid alignment on the three-dimensional data of the complete defect after the redistribution, thereby realizing three-dimensional reconstruction. The method can effectively solve the problems of complex defects and waste of materials.
Description
Technical Field
The invention relates to a three-dimensional reconstruction method of a hollow plate type ceramic membrane defect by combining ultrasonic and machine vision technologies, and belongs to the technical fields of mechanical engineering and computer engineering.
Background
In the face of increasingly severe water shortage situation, the problem of water shortage is solved by leading sea water accounting for 96.5% of the total reserve of the earth water resource. In many seawater desalination methods, reverse osmosis seawater desalination is performed) 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 operation and the like, and can be developed rapidly in the field of sea water desalination. At present->Pretreatment processes can be classified into conventional methods and membrane methods, and membrane pretreatment processes include organic and inorganic membrane methods. As one of inorganic membranes, the hollow plate type ceramic membrane has the advantages of narrow pore size distribution, high porosity, thin separation layer, small filtration resistance and the like, and the unit membrane has high surface area treatment amount, large water production capacity and stable chemical property, can stably operate in seawater for a long time, and is more suitable for seawater desalination pretreatment. Hollow-panel ceramic membranes are brittle materials with a high young's modulus, and even minor imperfections or mild strains can result in significant mechanical stresses. The defects of cracks, internal pores, interlayers and the like are frequently incomplete phenomena in ceramic materials. To accurately ascertain the shape, position, distribution and other characteristics of the defects, it is necessary to realize rapid detection and three-dimensional reconstruction of the defects. Aiming at the detection of the internal defects of the hollow plate type ceramic membrane, the traditional detection means based on the two-dimensional CT image is easy to have misjudgment and missed judgment, and the ultrasonic technology is used for three-dimensional detectionSpatial defect detection, identification and measurement are the direction of future development. For the surface detection of the hollow plate type ceramic membrane, in the traditional pipeline inner wall detection technology, a magnetic 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. As a pipeline inner wall detection method with the best development prospect, the machine vision detection technology has the advantages of high measurement speed, high measurement precision, complete image containing information, easy realization of automatic continuous detection, capability of meeting the speed requirement on a production line and the like. The ultrasonic technology can realize the three-dimensional detection of the deep defects of the hollow plate type ceramic membrane, the three-dimensional detection of the surface defects of the hollow plate type ceramic membrane can be realized based on machine vision, the features such as the appearance, the position, the distribution, the size and the like of various defects can be accurately ascertained based on the detection data of the non-rigid alignment fusion, and a corresponding three-dimensional reconstruction model can be constructed. And according to the volume calculation of the defects, the classification of the quality of the hollow plate type ceramic membrane is estimated, and the problems of complex and different defects and material waste are effectively solved.
In the prior art, kumakiri et al, norway, in "Membrane characterisation by a novel defect detection technique" (Microporous and Mesoporous Materials, vol115, no. 1-2 (October), 2008:33-39) propose a new thin film characterization technique for visualization and localization of nano-defects, which greatly simplifies the leak detection of the film, making it possible to localize small leaks accurately; francisco Lanza et al, university of California, in section "Ultrasonic Tomography for Three-Dimensional Imaging of Internal Rail Flaws Proof-of-Principle Numerical Simulations" (Transportation Research record. Vol2374, 2013:162-168) built a finite element model of an on-defect-orbit ultrasonic tomography array, and proposed a three-dimensional in-orbit defect tomography algorithm; 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) of Hubei university of industry Shang Liang and the like is disclosed, and a ceramic valve core surface defect detection algorithm with regional and multistage optimization is provided according to the difference of the reflectivity of the ceramic valve core surface; the invention discloses a phased array ultrasonic detection method based on improved dynamic depth focusing (patent grant number: CN 102809610B) of Zhenggan, xu Na of Beijing aerospace university. However, all the researches only adopt one detection technical means, a certain blank still exists in the aspect of fusing the data obtained by different detection technologies, and the research is quite long away from the actual production application. The RANSAC refinement algorithm of three-point ICP was proposed by Dennis Christie et al from Gunadarma University in "3D reconstruction of dynamic vehicles using sparse 3D-laser-scanner and 2D image fusion" to perform three-dimensional reconstruction of rigid moving objects; wang Ting of the university of the same university establishes an application framework of the data fusion CT technology in the field of concrete structure detection in the application study of the data fusion technology in the concrete structure detection, combines infrared imaging and ultrasonic technology, and realizes three-dimensional reconstruction of defect size and identification of defect types. However, all the researches are in a theoretical exploration stage, and whether the three-dimensional data of the internal defects and the surface defects of the hollow plate type ceramic membrane are suitable for fusion is yet to be verified.
Disclosure of Invention
In order to overcome the defects and the defects of the prior art, the invention adopts an advanced fusion technology, and provides a three-dimensional reconstruction method for the defects of the hollow plate type ceramic membrane by fusing ultrasonic and machine vision technologies.
The invention aims at realizing the three-dimensional reconstruction method of the defects of the hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies by the following technical scheme, which comprises the following steps:
1) Realizing three-dimensional reconstruction of internal defects of the hollow plate type ceramic membrane by using an ultrasonic data-based region growing technology;
2) Realizing three-dimensional reconstruction of the surface defects of the hollow plate type ceramic membrane based on a machine vision technology;
3) And the three-dimensional reconstruction of the complete defect of the hollow plate type ceramic membrane is realized by combining ultrasonic and machine vision technologies.
Preferably, the ultrasonic data in the step (1) means that after volume rendering is performed on the data acquired by the ultrasonic detection technology, a new hybrid rendering method based on the region growing technology is applied 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 seed pixel is compared with the similarity (average gray value in general) of pixels in surrounding regions within a threshold value range, if the seed pixel is consistent with the threshold value range, the seed pixel is connected to form a region, the planar growth is extended into a three-dimensional space field to realize visual segmentation, and a threshold value range is set by applying a threshold value selecting technology so as to obtain the most clear two-dimensional defect form;
the three-dimensional reconstruction is to place the whole scanning area in a Cartesian coordinate system, the value of each position corresponds to the volume pixel of the current position, and the three-dimensional area growth technology is applied, namely, one volume pixel is selected as a seed point, then calculation points in the threshold range of the adjacent position are searched, and the adjacent pixels of the image selected by the threshold value are connected and reconstructed into the solid three-dimensional image.
Preferably, the machine vision technology in the step (2) refers to acquiring point cloud data of the surface defect of the hollow plate type ceramic membrane by adopting a double-monocular three-dimensional measurement system.
The three-dimensional reconstruction method of the surface defect of the hollow plate type ceramic membrane comprises the following steps:
(1) Preprocessing the acquired point cloud data: the method comprises the steps of performing median filtering on data to improve noise immunity, resampling and coordinate normalization of the data;
(2) And convolving the Laplacian operator with the point cloud data, removing useless point cloud data, splicing the point cloud data to form three-dimensional data of the surface defect of the hollow plate-type ceramic membrane, and carrying out three-dimensional reconstruction.
Preferably, the data fusion in the step (3) refers to fusion of data obtained after three-dimensional reconstruction of data acquired by an ultrasonic technologyAnd data obtained after three-dimensional reconstruction of the data acquired by machine vision +.>And calculating the weight of each 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 complete data of the three-dimensional defect 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 an ultrasonic technology and 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) Three-dimensional data of the complete defect of the hollow plate type ceramic membrane are obtained;
the evidence theory refers toTheory or trust function theory, commonly abbreviated as +.>Theoretically, the combination rule is as follows
Is provided withAnd->Is the same identification frame->Two probability distribution functions of the two, then they are orthogonal and +>Is that
When (when)When (I)> （1）
When (when)When (I)> （2）
Wherein, the liquid crystal display device comprises a liquid crystal display device, （3）
if it isThen orthogonalize and->Is also a probability distribution function; if->There is no orthogonal sum->Let the name->And->Contradiction.
Compared with the prior art, the method has the beneficial effects that as the novel algorithm is adopted to carry out the three-dimensional reconstruction method of the defects of the hollow plate type ceramic membrane fusing the ultrasonic and machine vision technologies, the data calculation and storage are reduced, the imaging algorithm is simplified, and the ceramic membrane detection efficiency is improved.
Drawings
FIG. 1 is a flow chart of a three-dimensional reconstruction method of defects of a hollow plate type ceramic membrane fusing ultrasonic and machine vision technologies
Detailed Description
The following describes the implementation of the present invention further with reference to the accompanying drawings and a method for three-dimensional reconstruction of defects in hollow plate-type ceramic membranes by combining ultrasonic and machine vision techniques.
As shown in fig. 1, the three-dimensional reconstruction method for the defects of the hollow plate type ceramic membrane by fusing ultrasonic and machine vision technologies comprises the following steps:
1) Region growing technology based on ultrasonic data for realizing three-dimensional reconstruction of internal defects of hollow plate type ceramic membrane
After volume rendering is performed on data acquired by ultrasonic detection, a novel hybrid rendering method based on a region growing technology is applied to realize three-dimensional reconstruction. The principle of region growing is that a seed pixel is selected as a growing point, then the seed pixel is compared with the similarity (average gray value in general) of pixels in the surrounding region within a threshold value range, if the seed pixel has consistency, the seed pixel is connected to form a region, and the planar growth is extended into a three-dimensional space field, so that the visual segmentation can be realized. And setting a threshold range by using a threshold selection technology to obtain the most clear two-dimensional defect form. The entire scan area is placed in a Cartesian coordinate system with the value of each location corresponding to the voxel at the current location. And (3) applying a three-dimensional region growing technology, namely selecting a body pixel as a seed point, then searching algorithm points in a threshold range at adjacent positions, and connecting adjacent pixels of the image selected by the threshold to reconstruct a solid three-dimensional image.
2) Machine vision-based three-dimensional reconstruction of surface defects of hollow plate type ceramic membrane
The machine vision technology is adopted to acquire 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 the acquired point cloud data: the method comprises the steps of performing median filtering on data to improve noise resistance, resampling, coordinate normalization and the like of the data, then convoluting a Laplacian operator with point cloud data, determining defect edges, 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 finally performing three-dimensional reconstruction.
3) Realizing three-dimensional reconstruction of complete defect of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies
Data obtained after three-dimensional reconstruction of data acquired by ultrasonic technologyThree-dimensional reconstruction of data acquired by machine vision to obtain data +.>And calculating the weight of each 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 complete data of the three-dimensional defect 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 an ultrasonic technology and 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) Three-dimensional data of the complete defect of the hollow plate type ceramic membrane are obtained;
the evidence theory refers toTheory or trust function theory, commonly abbreviated as +.>Theoretically, the combination rule is as follows
Is provided withAnd->Is the same identification frame->Two probability distribution functions of the two, then they are orthogonal and +>Is that
When (when)When (I)> （4）
When (when)When (I)> （5）
Wherein, the liquid crystal display device comprises a liquid crystal display device, （6）
if it isThen orthogonalize and->Is also a probability distribution function; if->There is no orthogonal sum->Let the name->And->Contradiction.
And carrying out constraint-based non-rigid alignment on the three-dimensional data of the completely-distributed defects after the redistribution, thereby realizing the three-dimensional reconstruction of the completely-distributed defects of the hollow plate type ceramic membrane. The non-rigid alignment is selected by a thin plate spline interpolation algorithm) Defining a corresponding error function comprising
Distance error ； （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. Adopts->The algorithm (a quasi-Newton method) is solved, and numerical experiments show that +.>Algorithms are one of the effective methods for solving large-scale boundary problems.
Claims (1)
1. The three-dimensional reconstruction method of the hollow plate type ceramic membrane defect by combining ultrasonic and machine vision technologies is characterized by comprising the following steps of:
1) Realizing three-dimensional reconstruction of internal defects of the hollow plate type ceramic membrane by using an ultrasonic data-based region growing technology;
2) Realizing three-dimensional reconstruction of the surface defects of the hollow plate type ceramic membrane based on a machine vision technology;
3) Realizing three-dimensional reconstruction of the complete defect of the hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies;
the ultrasonic data in the step (1) refers to that after volume rendering is carried out on the data acquired by an ultrasonic detection technology, a new hybrid rendering method based on a region growing technology is applied 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 of the seed pixel and pixels in surrounding regions is compared within a threshold value range, if the seed pixel and the pixels in surrounding regions are consistent, 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, the visual segmentation can be realized, and a threshold value range is set by applying a threshold value selection technology so as to obtain the most clear two-dimensional defect form;
the three-dimensional reconstruction is to place the whole scanning area in a Cartesian coordinate system, the value of each position corresponds to the volume pixel of the current position, and a three-dimensional area growing technology is applied, namely, one volume pixel is selected as a seed point, then calculation points in a threshold range of adjacent positions are searched, and adjacent pixels of the image selected by the threshold are connected and reconstructed into a solid three-dimensional image;
the machine vision technology in the step (2) refers to the acquisition of point cloud data of the surface defects of the hollow plate type ceramic membrane by adopting a double-monocular three-dimensional measurement system;
the three-dimensional reconstruction method of the surface defect of the hollow plate type ceramic membrane comprises the following steps:
(1) Preprocessing the acquired point cloud data: the method comprises the steps of performing median filtering on data to improve noise immunity, resampling and coordinate normalization of the data;
(2) Convolving the Laplace operator with the point cloud data, removing useless point cloud data, splicing the point cloud data to form three-dimensional data of the surface defect of the hollow plate type ceramic membrane, and carrying out three-dimensional reconstruction;
the data fusion in the step (3) refers to the steps of fusing data acquired by an ultrasonic technology to obtain data A after three-dimensional reconstruction and data B after three-dimensional reconstruction of data acquired by machine vision, calculating the weight occupied by each of the two types of data after fusion by adopting an evidence theory, and then carrying out constraint-based non-rigid alignment to acquire complete data of three-dimensional defects 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 an ultrasonic technology and 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) Three-dimensional data of the complete defect of the hollow plate type ceramic membrane are obtained;
。
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 CN108961203A (en) | 2018-12-07 |
| CN108961203B true 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) |
Families Citing this family (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 |
| 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 |
| 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 |
Citations (4)
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018035082A1 (en) * | 2016-08-15 | 2018-02-22 | 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 (4)
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 基于区域生长法的超声图像分割;刘自德等;《医学影像》;20070716;第1-3页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108961203A (en) | 2018-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108961203B (en) | Three-dimensional reconstruction method for defects of hollow plate type ceramic membrane by combining ultrasonic and machine vision technologies | |
| CN112581457B (en) | Pipeline inner surface detection method and device based on three-dimensional point cloud | |
| CN106546521B (en) | A method of soil macropore spacial framework is quantified based on CT scan technology | |
| CN109035224B (en) | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud | |
| CN101788666B (en) | Underwater three dimensional terrain reconstruction method based on multi-beam sonar data | |
| CN102298779B (en) | Image registering method for panoramic assisted parking system | |
| CN101271582B (en) | Three-dimensional reconstruction method based on multi-vision angle two-dimension image combined with SIFT algorithm | |
| CN109242954B (en) | Multi-view three-dimensional human body reconstruction method based on template deformation | |
| CN103871064A (en) | Preprocessing and segmentation threshold value determining method of volcanic CT images | |
| CN105157609A (en) | Two-sets-of-camera-based global morphology measurement method of large parts | |
| CN107301648A (en) | Redundant points cloud minimizing technology based on overlapping region boundary angles | |
| CN108846860A (en) | A kind of damaged cylindrical drainage pipeline inner wall three-dimensional rebuilding method | |
| CN110766785A (en) | Real-time positioning and three-dimensional reconstruction device and method for underground pipeline | |
| CN111797836A (en) | Extraterrestrial celestial body patrolling device obstacle segmentation method based on deep learning | |
| CN107103610A (en) | Stereo mapping satellite image matches suspicious region automatic testing method | |
| CN112258521A (en) | Three-dimensional reconstruction method for pipeline weld joint based on single elliptical imaging radiograph | |
| Khaloo et al. | Extracting structural models through computer vision | |
| Ulaş et al. | A fast and robust scan matching algorithm based on ML-NDT and feature extraction | |
| CN113567968B (en) | Underwater target real-time segmentation method based on shallow water multi-beam water depth data and application thereof | |
| Bouchahma et al. | Optical-flow-based approach for the detection of shoreline changes using remote sensing data | |
| Ozog et al. | Identifying structural anomalies in image reconstructions of underwater ship hulls | |
| Kong | 3D image reconstruction of marine plankton based on virtual reality | |
| Yang et al. | Study on 3D printing based on UAV oblique photogrammetry | |
| CN1687968A (en) | Multi-resolution quaternary wavelet phase matching 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 |