CN103400139A - Method for identifying concrete crack characteristic information - Google Patents
Method for identifying concrete crack characteristic information Download PDFInfo
- Publication number
- CN103400139A CN103400139A CN201310277205XA CN201310277205A CN103400139A CN 103400139 A CN103400139 A CN 103400139A CN 201310277205X A CN201310277205X A CN 201310277205XA CN 201310277205 A CN201310277205 A CN 201310277205A CN 103400139 A CN103400139 A CN 103400139A
- Authority
- CN
- China
- Prior art keywords
- crack
- image
- pixel
- fracture
- characteristic information
- 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.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a method for identifying concrete crack characteristic information. The method comprises the steps of acquiring an image of a crack, carrying out pretreatment on the crack image in sequence, wherein the pretreatment comprises image graying, smoothing and sharpening, identifying the crack image by adopting a two-dimensional OTSU method or a Markov segmentation algorithm, judging the type of the crack image by adopting a projection method, and finally analyzing the crack image by using a computer control system to extract the crack characteristic information. In the process of extracting the crack characteristic information, the computer control system can extract the crack characteristic information automatically and quickly in a mass mode, and structural state assessment is completed by combining with physical parameters, thereby accomplishing the whole process of identifying the concrete crack characteristic information. The method provided by the invention carries out long-distance, quick and accurate detection on surface cracks caused by cracking and damages of a concrete structure through the computer controls system, provides effective parameters for structural state assessment and the like, and greatly improves the rapidity, the accuracy and the scientificity of detection.
Description
Technical field
The present invention relates to distress in concrete recognition technology field, be specially a kind of recognition methods of distress in concrete characteristic information.
Background technology
The buildings of xoncrete structure such as bridge structure, industry all there will be and reach in various degree multi-form crack in construction and use procedure with covil construction etc., the destruction of fabric structure and to collapse be all also from the expansion in crack, so crack often becomes the qualitative and quantificational indices in the fabric structure destructive process, and crack also can affect the endurance quality of the attractive in appearance and structure of structure, therefore the member that produces crack is detected to maintenance termly, and be to be necessary very much according to the assessment that actual conditions are carried out dynamical state.Traditional Crack Detection means mainly, by instruments such as New Instrument for Crack Widths, ruler, manually operate, and not only speed is slow and waste time and energy.Development along with camera work and computer technology, adopt digital image processing techniques to provide new method for the identification of distress in concrete information, concrete structural surface Crack Detection research based on the image processing, because it detects for convenience of, data many-sided advantage such as Rapid Science comparatively accurately and comparatively, more and more be subject to scientific research personnel's attention; It is undesirable that yet traditional crack pattern looks like to cut apart the recognizer effect, therefore how more rapid, accuracy, scientific identify the distress in concrete characteristic information and become those skilled in the art's important topic urgently to be resolved hurrily.
Summary of the invention
Technical matters solved by the invention is to provide a kind of recognition methods of distress in concrete characteristic information, to solve the shortcoming in the above-mentioned background technology.
Technical matters solved by the invention realizes by the following technical solutions:
a kind of recognition methods of distress in concrete characteristic information, at first fracture carries out image acquisition, the fracture image carries out pre-service successively, pre-service comprises the crack image gray processing, the level and smooth sharpening that reaches, then by two dimension large Tianjin method or Markov partitioning algorithm fracture image, carry out identifying processing, and adopt sciagraphy to carry out crack pattern to judge as type, finally utilize computer control system fracture image to analyze and extract FRACTURE CHARACTERISTICS information, can robotization at characteristic information extraction process computer control system, mass, extract FRACTURE CHARACTERISTICS information rapidly, and complete structure condition assessment in conjunction with physical parameter, thereby complete the overall process of distress in concrete characteristic information identification.
In the present invention, a kind of recognition methods concrete steps of distress in concrete characteristic information are as follows:
1), crack image acquisition and crack pattern are as pre-service
Adopt the image collecting device fracture to carry out image acquisition, then the fracture image carries out pre-service, and pre-service comprises the crack image gray processing, smoothly reaches sharpening;
2), crack image recognition processing
By the large Tianjin of two dimension method and or the Markov partitioning algorithm to step 1) the gained crack pattern looks like to carry out identifying processing, in the method for the large Tianjin of two dimension, establishes the crack pattern picture
For M gray level, crack pattern picture
In zone arbitrary pixel and its neighborhood territory pixel point interval be (0～M-1), establish arbitrary pixel and its neighborhood territory pixel point set is combined into the binary array
,
Represent this grey scale pixel value,
Certain grey scale pixel value in expression pixel interval,
Expression binary array
The frequency that occurs in the pixel interval range,
The total number of pixels of expression crack pattern picture, so joint probability density
For
Wherein
,
,
If the segmentation threshold of crack area is two-dimensional vector
, according to the distribution of crack area two-dimensional histogram projection plane, crack area is divided into to 4 different zones (0,1,2,3), wherein, 0 and 1 region represents the set of target crack and background pixel point, and this its gray-scale value of class pixel and neighborhood territory pixel point grey value difference are little usually; 2 and 3 regions represent edge and the set of noise pixel point, and this class pixel and neighborhood territory pixel point grey value difference are larger;
With
Represent respectively crack and background area in two-dimensional histogram, probability of cracks in two-dimensional histogram
With the background area probability
Be expressed as respectively:
Separately expectation value two-dimensional vector in two zones
For
Two-dimensional histogram total expected value vector
Be expressed as
Introduce simultaneously the scatter matrix between crack target and its background area
, it is expressed as:
Scatter matrix
Mark weigh the inter-class variance size between its background and target area, crack:
The processing of the large Tianjin of two dimension method fracture image, according to above-mentioned formula (1)～(6), at first travel through whole crack image-region, calculates each two-dimensional vector
Corresponding inter-class variance size, determine corresponding two-dimensional vector this moment when this value is maximum
For the optimal threshold of crack area, markov random file partitioning algorithm and two large rule classes of algorithms are seemingly;
3), the types of fractures of judgement crack pattern picture
Through step 2) after fracture image recognition and discrimination, from the crack characteristics, by sciagraphy, judge types of fractures, the distress in concrete that relates in patent of the present invention is divided into transverse crack, longitudinal crack, oblique crack and the large class of chicken-wire cracking four; The pixel of crack area
All value is 1, and the pixel of background area equal value is 0, utilizes these characteristics by sciagraphy, all kinds of crack patterns to be looked like to analyze, and concrete grammar is as follows:
(1) the crack pattern picture adopts matrix representation, at first determines the rectangular coordinate system take quadrature pixel position, image upper left as initial point;
(2) in the target area, crack, projection is carried out along X-axis and Y-axis respectively in each pixel position, take the x of each pixel position or y as horizontal ordinate, with each pixel in the target area, crack, to the pixel that X-direction or Y direction carry out being superposeed after projection, add up to ordinate respectively
Or
, graphing then, it is shown as curve shape;
(3) finally the perspective view by the crack pattern picture can judge above-mentioned all kinds types of fractures;
4), utilize computer control system to extract FRACTURE CHARACTERISTICS information
Computer control system adopts the method for VC++ and matlab hybrid programming, and add that the large Tianjin of two dimension, Markov are cut apart, automatic classification, system calibrating algorithm, be compiled into C++ or matlab program, call successively and respectively process function, form automatic processing capacity, the composition dialog frame, add in-service xoncrete structure evaluation module, can realize robotization, mass, rapid extract FRACTURE CHARACTERISTICS information, specifically comprise the steps:
(1) in VC++, utilize guide Appwzard to form software frame;
(2) VC++, Matlab hybrid programming environment are set;
(3) set up message maps, add conventional fracture image processing and identification, information extraction algorithm;
(4) establishment C++ or matlab program, add that the large Tianjin of two dimension, Markov are cut apart, automatic classification and system calibrating algorithm;
(5) establishment C++ or matlab program, call successively and respectively process function, forms automatic processing capacity;
(6) be similar to automatic processing, establishment batch processing program, and set in advance automatic processing template;
(7) write the word write-in program, pre-designed analysis report output template;
(8) composition dialog frame, add in-service xoncrete structure evaluation module;
(9) the various program functions of operation debugging;
(10) generate FRACTURE CHARACTERISTICS information automatic control system.
In the present invention, in step 4), FRACTURE CHARACTERISTICS information comprises fracture length, fracture width, crack angle and fracture interval.
in the present invention, by computer control system, realize the concrete structural surface crack that forms because of the breakage of ftractureing is carried out at a distance, detect fast and accurately, for structure condition assessment etc. provides actual parameter, the physics assessment models set up of binding and work out the in-service xoncrete structure evaluation module of design simultaneously, analyze comparatively exactly its service state, its overall process has realized whole xoncrete structure collection crack image acquisition, process, identification, the operation of feature extraction and structural appraisal is integrated, greatly improve the rapidity that detects, accuracy and science.
Beneficial effect
(1) simple operation of the present invention; The method can " be processed " and " batch processing " automatically, the convenient plenty of time of using and saving the testing personnel, also be convenient to the processing of crack pattern picture on same time point, same detection architecture, different parts, also facilitated the unified management of a large amount of deal with data simultaneously;
(2) perfect in shape and function of the present invention; " classification of rifts " function can go out types of fractures by automatic identification, user friendly detection analysis; " FRACTURE CHARACTERISTICS information examining report " function is reflected in all crack information result of calculation and structure condition assessment result in a examining report, facilitates user data management etc.;
(3) the present invention calculates accurately; " the large Tianjin method of two dimension or Markov partitioning algorithm " improved the identification segmentation effect of crack pattern picture; Improvement fracture width, length scheduling algorithm have improved the accuracy of result of calculation; " system calibrating " provides comparatively accurate, full and accurate data for state estimation;
(4) applicability of the present invention is strong; ，Yi crack information characteristics is as the state estimation major parameter aspect evaluation module, and the important test item of FRACTURE CHARACTERISTICS while being structure detection, system has applicability; Input by parameter in software is the internal force status of exportable beam, for the assessment of structure service state provides foundation, has convenience; By as can be known to system evaluation result and experimental result comparative analysis, the system evaluation result can truly reflect the internal force status of member, so assessment result has reliability.
The accompanying drawing explanation
In Fig. 1 the present invention, crack pattern is as processing flow chart.
In Fig. 2 the present invention crack pattern as pre-service after schematic diagram.
Schematic diagram after the image recognition processing of crack in Fig. 3 the present invention.
Fig. 4 computer control system development process of the present invention figure.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.
Referring to the recognition methods of a kind of distress in concrete characteristic information of Fig. 1, Fig. 2, Fig. 3, Fig. 4, concrete steps are as follows:
1, crack image acquisition and crack pattern are as pre-service
Adopt the image collecting device fracture to carry out image acquisition, then the fracture image carries out pre-service, and pre-service comprises the crack image gray processing, smoothly reaches sharpening;
2, crack image recognition processing
By the large Tianjin of two dimension method and or the Markov partitioning algorithm to step 1 gained crack pattern, look like to carry out identifying processing, in the method for the large Tianjin of two dimension, establish the crack pattern picture
For M gray level, crack pattern picture
In zone arbitrary pixel and its neighborhood territory pixel point interval be (0～M-1), establish arbitrary pixel and its neighborhood territory pixel point set is combined into the binary array
,
Represent this grey scale pixel value,
Certain grey scale pixel value in expression pixel interval,
Expression binary array
The frequency that occurs in the pixel interval range,
The total number of pixels of expression crack pattern picture, so joint probability density
For
Wherein
,
,
If the segmentation threshold of crack area is two-dimensional vector
, according to the distribution of crack area two-dimensional histogram projection plane, crack area is divided into to 4 different zones (0,1,2,3), wherein, 0 and 1 region represents the set of target crack and background pixel point, and this its gray-scale value of class pixel and neighborhood territory pixel point grey value difference are little usually; 2 and 3 regions represent edge and the set of noise pixel point, and this class pixel and neighborhood territory pixel point grey value difference are larger;
With
Represent respectively crack and background area in two-dimensional histogram, probability of cracks in two-dimensional histogram
With the background area probability
Be expressed as respectively:
Separately expectation value two-dimensional vector in two zones
For
Two-dimensional histogram total expected value vector
Be expressed as
Introduce simultaneously the scatter matrix between crack target and its background area
, it is expressed as:
Scatter matrix
Mark weigh the inter-class variance size between its background and target area, crack:
(6)
The processing of the large Tianjin of two dimension method fracture image, according to above-mentioned formula (1)～(6), at first travel through whole crack image-region, calculates each two-dimensional vector
Corresponding inter-class variance size, determine corresponding two-dimensional vector this moment when this value is maximum
Optimal threshold for crack area;
3, the types of fractures of judgement crack pattern picture
After the image recognition of step 2 fracture and discrimination, from the crack characteristics, by sciagraphy, judge types of fractures, the distress in concrete that relates in patent of the present invention is divided into transverse crack, longitudinal crack, oblique crack and the large class of chicken-wire cracking four; The pixel of crack area
All value is 1, and the pixel of background area equal value is 0, utilizes these characteristics by sciagraphy, all kinds of crack patterns to be looked like to analyze, and concrete grammar is as follows:
(1) the crack pattern picture adopts matrix representation, at first determines the rectangular coordinate system take quadrature pixel position, image upper left as initial point;
(2) in the target area, crack, projection is carried out along X-axis and Y-axis respectively in each pixel position, take the x of each pixel position or y as horizontal ordinate, with each pixel in the target area, crack, to the pixel that X-direction or Y direction carry out being superposeed after projection, add up to ordinate respectively
Or
, graphing then, it is shown as curve shape;
(3) finally the perspective view by the crack pattern picture can judge the crack image type, and in the present embodiment, the analysis result of faulted joint image is oblique crack;
4, utilize computer control system to extract FRACTURE CHARACTERISTICS information
Computer control system adopts the method for VC++ and matlab hybrid programming, and add that the large Tianjin of two dimension, Markov are cut apart, automatic classification, system calibrating algorithm, be compiled into C++ or matlab program, call successively and respectively process function, form automatic processing capacity, the composition dialog frame, add in-service xoncrete structure evaluation module, can realize robotization, mass, rapid extract FRACTURE CHARACTERISTICS information, specifically comprise the steps:
(1) in VC++, utilize guide Appwzard to form software frame;
(2) VC++, Matlab hybrid programming environment are set;
(3) set up message maps, add conventional fracture image processing and identification, information extraction algorithm;
(4) establishment C++ or matlab program, add that the large Tianjin of two dimension, Markov are cut apart, automatic classification and system calibrating algorithm;
(5) establishment C++ or matlab program, call successively and respectively process function, forms automatic processing capacity;
(6) be similar to automatic processing, establishment batch processing program, and set in advance automatic processing template;
(7) write the word write-in program, pre-designed analysis report output template;
(8) composition dialog frame, add in-service xoncrete structure evaluation module;
(9) the various program functions of operation debugging;
(10) generate FRACTURE CHARACTERISTICS information automatic control system.
In the present embodiment, in step 1), image collecting device comprises CCD camera/digital camera, 1394/USB image pick-up card and data connecting line.
In the present embodiment, in step 4) in FRACTURE CHARACTERISTICS information the crack mean breadth be 0.5200mm.
In the present embodiment, with actual fracture width contrast of measuring, its precision, in 8%, improves rapidity, accuracy and the science that detects greatly after above-mentioned processing.
Above demonstration and described ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; that in above-described embodiment and instructions, describes just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.The claimed scope of the present invention is defined by appending claims and equivalent thereof.
Claims (4)
1. the recognition methods of a distress in concrete characteristic information, it is characterized in that, at first fracture carries out image acquisition, the fracture image carries out pre-service successively, pre-service comprises the crack image gray processing, the level and smooth sharpening that reaches, then by two dimension large Tianjin method or Markov partitioning algorithm fracture image, carry out identifying processing, and adopt sciagraphy to carry out crack pattern to judge as type, finally utilize computer control system fracture image to analyze and extract FRACTURE CHARACTERISTICS information, can robotization at characteristic information extraction process computer control system, mass, extract FRACTURE CHARACTERISTICS information rapidly, and complete structure condition assessment in conjunction with physical parameter, thereby complete the overall process of distress in concrete characteristic information identification.
2. the recognition methods of a kind of distress in concrete characteristic information according to claim 1, is characterized in that, concrete steps are as follows:
1), crack image acquisition and crack pattern are as pre-service
Adopt the image collecting device fracture to carry out image acquisition, then the fracture image carries out pre-service, and pre-service comprises the crack image gray processing, smoothly reaches sharpening;
2), crack image recognition processing
By the large Tianjin of two dimension method and or the Markov partitioning algorithm to step 1) gained crack pattern, look like to carry out identifying processing, in the method for the large Tianjin of two dimension, establish the crack pattern picture
For M gray level, crack pattern picture
In zone arbitrary pixel and its neighborhood territory pixel point interval be (0～M-1), establish arbitrary pixel and its neighborhood territory pixel point set is combined into the binary array
,
Represent this grey scale pixel value,
Certain grey scale pixel value in expression pixel interval,
Expression binary array
The frequency that occurs in the pixel interval range,
The total number of pixels of expression crack pattern picture, so joint probability density
For
Wherein
,
,
If the segmentation threshold of crack area is two-dimensional vector
, according to the distribution of crack area two-dimensional histogram projection plane, crack area is divided into to 4 different zones (0,1,2,3), wherein, 0 and 1 region represents the set of target crack and background pixel point, and this its gray-scale value of class pixel and neighborhood territory pixel point grey value difference are little usually; 2 and 3 regions represent edge and the set of noise pixel point, and this class pixel and neighborhood territory pixel point grey value difference are larger;
With
Represent respectively crack and background area in two-dimensional histogram, probability of cracks in two-dimensional histogram
With the background area probability
Be expressed as respectively:
Separately expectation value two-dimensional vector in two zones
For
Two-dimensional histogram total expected value vector
Be expressed as
(4)
Introduce simultaneously the scatter matrix between crack target and its background area
, it is expressed as:
Scatter matrix
Mark weigh the inter-class variance size between its background and target area, crack:
The processing of the large Tianjin of two dimension method fracture image, according to above-mentioned formula (1)～(6), at first travel through whole crack image-region, calculates each two-dimensional vector
Corresponding inter-class variance size, determine corresponding two-dimensional vector this moment when this value is maximum
Optimal threshold for crack area;
3) types of fractures of judgement crack pattern picture
Through step 2) after fracture image recognition and discrimination, from the crack characteristics, by sciagraphy, judge types of fractures, the distress in concrete that relates in patent of the present invention is divided into transverse crack, longitudinal crack, oblique crack and the large class of chicken-wire cracking four; The pixel of crack area
All value is 1, and the pixel of background area equal value is 0, utilizes these characteristics by sciagraphy, all kinds of crack patterns to be looked like to analyze, and concrete grammar is as follows:
(1) the crack pattern picture adopts matrix representation, at first determines the rectangular coordinate system take quadrature pixel position, image upper left as initial point;
(2) in the target area, crack, projection is carried out along X-axis and Y-axis respectively in each pixel position, take the x of each pixel position or y as horizontal ordinate, with each pixel in the target area, crack, to the pixel that X-direction or Y direction carry out being superposeed after projection, add up to ordinate respectively
Or
, graphing then, it is shown as curve shape;
(3) finally the perspective view by the crack pattern picture can judge above-mentioned all kinds types of fractures;
4), utilize computer control system to extract FRACTURE CHARACTERISTICS information
Computer control system adopts the method for VC++ and matlab hybrid programming, and add that the large Tianjin of two dimension, Markov are cut apart, automatic classification, system calibrating algorithm, be compiled into C++ or matlab program, call successively and respectively process function, form automatic processing capacity, the composition dialog frame, add in-service xoncrete structure evaluation module, can realize robotization, mass, rapid extract FRACTURE CHARACTERISTICS information, specifically comprise the steps:
(1) in VC++, utilize guide Appwzard to form software frame;
(2) VC++, Matlab hybrid programming environment are set;
(3) set up message maps, add conventional fracture image processing and identification, information extraction algorithm;
(4) establishment C++ or matlab program, add that the large Tianjin of two dimension, Markov are cut apart, automatic classification and system calibrating algorithm;
(5) establishment C++ or matlab program, call successively and respectively process function, forms automatic processing capacity;
(6) be similar to automatic processing, establishment batch processing program, and set in advance automatic processing template;
(7) write the word write-in program, pre-designed analysis report output template;
(8) composition dialog frame, add in-service xoncrete structure evaluation module;
(9) the various program functions of operation debugging;
(10) generate FRACTURE CHARACTERISTICS information automatic control system.
3. the recognition methods of a kind of distress in concrete characteristic information according to claim 2, is characterized in that, in step 1), image collecting device comprises CCD camera/digital camera, 1394/USB image pick-up card and data connecting line.
4. the recognition methods of a kind of distress in concrete characteristic information according to claim 2, is characterized in that, in step 4), FRACTURE CHARACTERISTICS information comprises fracture length, fracture width, crack angle and fracture interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310277205XA CN103400139A (en) | 2013-07-04 | 2013-07-04 | Method for identifying concrete crack characteristic information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310277205XA CN103400139A (en) | 2013-07-04 | 2013-07-04 | Method for identifying concrete crack characteristic information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103400139A true CN103400139A (en) | 2013-11-20 |
Family
ID=49563757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310277205XA Pending CN103400139A (en) | 2013-07-04 | 2013-07-04 | Method for identifying concrete crack characteristic information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103400139A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127777A (en) * | 2016-06-27 | 2016-11-16 | 中山大学 | A kind of three dimensions crack separation identification and characterizing method |
| CN104008553B (en) * | 2014-06-17 | 2017-03-22 | 武汉武大卓越科技有限责任公司 | Crack detection method with image gradient information and watershed method conflated |
| CN107403427A (en) * | 2017-07-20 | 2017-11-28 | 重庆邮电大学 | A kind of concrete surface crack detection method based on genetic planning and flow model in porous media |
| CN107506787A (en) * | 2017-07-27 | 2017-12-22 | 陕西师范大学 | A kind of glue into concrete beam cracks sorting technique based on migration self study |
| CN109685759A (en) * | 2018-11-05 | 2019-04-26 | 北京中企卓创科技发展有限公司 | A kind of acceleration concrete cracking equipment and its test method |
| JP2019200213A (en) * | 2015-12-25 | 2019-11-21 | 富士フイルム株式会社 | Damage information processing apparatus and damage information processing method |
| CN112785594A (en) * | 2021-03-16 | 2021-05-11 | 合肥工业大学 | Automatic bridge structure crack identification method based on image two-dimensional amplitude estimation |
| CN113240635A (en) * | 2021-05-08 | 2021-08-10 | 中南大学 | Structural object detection image quality testing method with crack resolution as reference |
| CN114839192A (en) * | 2022-04-26 | 2022-08-02 | 哈尔滨理工大学 | Concrete bridge crack detection system |
| CN117115135A (en) * | 2023-09-15 | 2023-11-24 | 延安大学 | Concrete crack detection system and method based on machine vision |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7965908B2 (en) * | 2005-08-18 | 2011-06-21 | Fujifilm Corporation | Image searching apparatus, image printing apparatus, print ordering system, over-the-counter printing terminal apparatus, image capturing apparatus, image searching program and method |
| CN102680480A (en) * | 2012-05-03 | 2012-09-19 | 中南大学 | Intelligent detecting method for cracks of concrete structures |
-
2013
- 2013-07-04 CN CN201310277205XA patent/CN103400139A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7965908B2 (en) * | 2005-08-18 | 2011-06-21 | Fujifilm Corporation | Image searching apparatus, image printing apparatus, print ordering system, over-the-counter printing terminal apparatus, image capturing apparatus, image searching program and method |
| CN102680480A (en) * | 2012-05-03 | 2012-09-19 | 中南大学 | Intelligent detecting method for cracks of concrete structures |
Non-Patent Citations (4)
| Title |
|---|
| PHILIPPE DELAGNES ET AL.: "A MARKOV RANDOM FIELD FOR RECTILINEAR STRUCTURE EXTRACTION IN PAVEMENT DISTRESS IMAGE ANALYSIS", 《IEEE IINTERNATIONAL CONFERENCE ON IMAGE PROCESSING》 * |
| 张国旗: "基于图像处理的混凝土桥梁底面裂缝检测方法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 景晓军 等: "一种基于二维最大类间方差的图像分割算法", 《通信学报》 * |
| 曾艳霞: "混凝土裂缝特征信息识别研究", 《中国优秀硕士学位全文数据库信息科技辑》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008553B (en) * | 2014-06-17 | 2017-03-22 | 武汉武大卓越科技有限责任公司 | Crack detection method with image gradient information and watershed method conflated |
| JP2019200213A (en) * | 2015-12-25 | 2019-11-21 | 富士フイルム株式会社 | Damage information processing apparatus and damage information processing method |
| CN106127777A (en) * | 2016-06-27 | 2016-11-16 | 中山大学 | A kind of three dimensions crack separation identification and characterizing method |
| CN107403427A (en) * | 2017-07-20 | 2017-11-28 | 重庆邮电大学 | A kind of concrete surface crack detection method based on genetic planning and flow model in porous media |
| CN107506787A (en) * | 2017-07-27 | 2017-12-22 | 陕西师范大学 | A kind of glue into concrete beam cracks sorting technique based on migration self study |
| CN107506787B (en) * | 2017-07-27 | 2019-09-10 | 陕西师范大学 | A kind of glue into concrete beam cracks classification method based on migration self study |
| CN109685759A (en) * | 2018-11-05 | 2019-04-26 | 北京中企卓创科技发展有限公司 | A kind of acceleration concrete cracking equipment and its test method |
| CN109685759B (en) * | 2018-11-05 | 2022-05-10 | 北京中企卓创科技发展有限公司 | Concrete cracking acceleration equipment and test method thereof |
| CN112785594A (en) * | 2021-03-16 | 2021-05-11 | 合肥工业大学 | Automatic bridge structure crack identification method based on image two-dimensional amplitude estimation |
| CN112785594B (en) * | 2021-03-16 | 2022-08-30 | 合肥工业大学 | Automatic bridge structure crack identification method based on image two-dimensional amplitude estimation |
| CN113240635A (en) * | 2021-05-08 | 2021-08-10 | 中南大学 | Structural object detection image quality testing method with crack resolution as reference |
| CN113240635B (en) * | 2021-05-08 | 2022-05-03 | 中南大学 | Structural object detection image quality testing method with crack resolution as reference |
| CN114839192A (en) * | 2022-04-26 | 2022-08-02 | 哈尔滨理工大学 | Concrete bridge crack detection system |
| CN117115135A (en) * | 2023-09-15 | 2023-11-24 | 延安大学 | Concrete crack detection system and method based on machine vision |
| CN117115135B (en) * | 2023-09-15 | 2024-04-30 | 延安大学 | Concrete crack detection system and method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103400139A (en) | Method for identifying concrete crack characteristic information | |
| US20220309640A1 (en) | Product defect detection method, device and system | |
| Arena et al. | A new computational approach to cracks quantification from 2D image analysis: Application to micro-cracks description in rocks | |
| WO2019134252A1 (en) | Method and device for automated portrayal and accurate measurement of width of structural crack | |
| CN103065134B (en) | A kind of fingerprint identification device and method with information | |
| CN111553303B (en) | Remote sensing orthographic image dense building extraction method based on convolutional neural network | |
| Liu et al. | Automated crack pattern recognition from images for condition assessment of concrete structures | |
| RU2015134095A (en) | METHOD AND DEVICE FOR DETECTING A DIRECT LINE | |
| JP2011158373A (en) | Method for creation of teacher data for use in automatic defect classification, and method and apparatus for automatic defect classification | |
| CN107832838A (en) | The method and apparatus for evaluating cell smear sample satisfaction | |
| CN101533466B (en) | Image processing method for positioning eyes | |
| US11657644B2 (en) | Automatic ruler detection | |
| JP6733983B2 (en) | Image analysis device | |
| CN110969610A (en) | Power equipment infrared chart identification method and system based on deep learning | |
| CN113096121A (en) | Pavement crack detection method and system based on cross fracture mechanics and image processing | |
| CN108335310B (en) | Portable grain shape and granularity detection method and system | |
| Lang et al. | Pavement cracking detection and classification based on 3d image using multiscale clustering model | |
| CN111553345A (en) | Method for realizing meter pointer reading identification processing based on Mask RCNN and orthogonal linear regression | |
| CN103268494B (en) | Parasite egg recognition methods based on rarefaction representation | |
| CN113393430B (en) | Thermal imaging image enhancement training method and device for fan blade defect detection | |
| CN109596639A (en) | Defect detecting system and defect inspection method | |
| CN106203351A (en) | The method of crack Intelligent Recognition classification | |
| Yan et al. | Quality analysis on ransac-based roof facets extraction from airborne lidar data | |
| CN111008635A (en) | OCR-based multi-bill automatic identification method and system | |
| CN106548474A (en) | A kind of micro-structure surface detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131120 |