CN104034733A - Service life prediction method based on binocular vision monitoring and surface crack image recognition - Google Patents
Service life prediction method based on binocular vision monitoring and surface crack image recognition Download PDFInfo
- Publication number
- CN104034733A CN104034733A CN201410312059.4A CN201410312059A CN104034733A CN 104034733 A CN104034733 A CN 104034733A CN 201410312059 A CN201410312059 A CN 201410312059A CN 104034733 A CN104034733 A CN 104034733A
- Authority
- CN
- China
- Prior art keywords
- crackle
- crack
- image
- identification
- binocular vision
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a service life prediction method based on binocular vision monitoring and surface crack image recognition. The service life prediction method is used for solving the problem that an existing monocular vision method for monitoring fatigue cracks is low in operability and complex in implementation process, improving measurement accuracy and efficiency, and finally predicting the service life of a monitored target. According to the principle of the service life prediction method, a binocular vision system is used for continuously shooting the monitored target, and surface crack images, changing according to time, of the monitored object are collected; an image technology is used for preprocessing the crack images; a design algorithm is used for recognizing crack characteristic values; obtained crack data are analyzed, a degeneration track is fitted, and thus the service life of the monitored target can be predicted. The service life prediction method based on binocular vision monitoring and surface crack image recognition is wide in application range, and high in operability and reliability, and can provide guidance for production practice.
Description
Technical field
The present invention relates to a kind of life-span prediction method that fully utilizes binocular vision technology monitoring and image technique identified surface crack value, specifically a kind of life-span prediction method based on binocular vision monitoring and surface crack image recognition.
Background technology
Job facilities, due to the effect of the various loads in design, construction and use procedure, all can produce surface crack gradually.Surface crack is defect common in engineering structure, and a lot of penetrated cracks can be reviewed as being formed by surface crack growth.Therefore, in order to ensure the material or the member that germinate surface crack, in use can there is not security incident, need carry out continuous monitoring to its surface crack, accurately measure the characteristic value information such as length, width of crackle, thereby Obtaining Accurate surface crack growth speed, and then realize the residual life of monitoring target is estimated.
Traditional crack detecting method is the shortcoming such as precision is not high, complex operation, cost height owing to existing, and more and more can not adapt to the requirement that new period job facilities detect development.Along with the development of computer technology, there is in recent years scholar to start digital image processing techniques to apply to body surface crack detection.But the crack image acquisition mode that they propose is too simple, only limit to monocular monitoring, only use a camera acquisition crack image.Because pixel and video camera self parameter, shooting distance, the shooting angle of camera acquisition image all exists relation, only with a video camera shooting, can cause the problem that the relative position of monitored object and camera must be fixing.Mobile camera position, just needs the physical size of uncalibrated image pixel again.Meanwhile, a video camera cannot obtain angle parameter, and shooting angle can only be in the direction vertical with surface crack, otherwise cannot Accurate Calibration pixel size.Strict restrictive condition has caused monocular monitoring crack technology can only rest on laboratory stage above, can not apply in Practical Project widely.
Binocular vision technology monitoring crack has had conspicuousness raising compared to monocular monitoring.Binocular monitoring, uses two video cameras to take from different perspectives crack image, can overcome the scope of application that monocular monitoring exists little, require harsh problem.Complete after the demarcation of binocular camera, can use binocular shooting and monitoring target in the locus of conversion, establishing shot angle or distance again, adaptability is greatly improved.
By utilizing binocular vision system to take continuously destination object, can collect the surface crack image of a series of monitoring targets, these images have all recorded the extend information of crackle.By these crack images are identified, can extract continually varying crack Value Data.The crackle data that identify are carried out to statistical study, can simulate crackle Degradation path, and then realize the residual life of monitoring target is estimated.
Use binocular vision monitoring to be combined with image recognition technology, for realizing life prediction, provide a new way.
Summary of the invention
The present invention is directed to monocular vision monitoring objective surface fatigue state practicality low, implement the problems such as loaded down with trivial details, propose a kind of based on binocular vision monitoring the life-span prediction method with surface crack image recognition.Applicant found through experiments, and utilizes binocular vision system to gather the image of monitoring target surface fatigue crackle, and identifies crack value by image technique, can help preferably to carry out the prediction to monitoring objective residual life.
A life-span prediction method based on binocular vision monitoring with surface crack image recognition, its feature mainly comprises the following steps:
Step 1, completes the inside and outside portion parameter calibration to binocular vision system.
Fixedly the relative position of biocular systems middle left and right video camera is taken 2D checkerboard type target with different angles simultaneously, by demarcating tool box in MATLAB, completes the demarcation to left and right camera inner parameter; With left and right camera, to being fixed on the target of same position, respectively take a photo, complete the demarcation to left and right camera external parameter.
Step 2, carries out torture test to sample, gathers time dependent crack image.
Determine target to be predicted, choose test specimen, the pre-service of complete paired samples; With reference to the crack image monitoring system of the present invention's design, utilize binocular vision system to monitor continuously sample, select suitable sample interval; By sample acquisitions to image transmitting in image identification system.
Step 3, completes the image recognition to crackle, obtains crack Value Data.
(1) by left and right Image Mosaics, gray processing, spatial domain filtering, binaryzation and dilation and corrosion, operate, complete gathering the pre-service work of crack image, extract crackle skeleton and crackle profile.
(2) realize the identification to crack length, be specifically divided into again:
Short type Identification of Cracks, mainly completes by computed image coordinate.First crackle skeleton is abstracted into tree structure model; Then the tree structure model of skeleton is pruned, reject tiny branch, retain crackle skeleton trunk; By the tree structure of skeleton trunk is traveled through, draw trunk pixel length; Finally the length in pixels of crackle trunk and biocular systems are demarcated to the imaging multiplication obtaining, calculate physical length.
Elongated Identification of Cracks, mainly completes by calculating world coordinates.First mark the initial end points of crackle skeleton, and utilize polar curve restrict detect to go out on the way each unique point; Then the volume coordinate of above each point is resolved, obtained its world coordinates; Finally by Pythagorean theorem, calculate every segment length, the cumulative physical length that draws elongated crackle.
Medium-sized Identification of Cracks.First utilize the short type crackle method of identification to calculate crackle physical length; Then by identification elongated crackle method, calculate crackle physical length; Finally get the mean value of twice computational length value, be designated as medium-sized crackle physical length.
(3) realize the identification to crack width, first find two end points of crackle trunk, take crackle trunk as center line, crackle profile is divided into P
1and P
2both sides; Then by P
1on point be set to impact point, all the other points are all set to background dot, and the image after upgrading is carried out to Euclidean distance variation; Finally extract the rear image P of conversion
2the value at place, is the pixel wide of each point on crackle trunk, gets its average and is designated as crackle mean pixel width, is multiplied by imaging coefficient and obtains crackle actual average width.
Step 4: matching crackle degraded data, target of prediction residual life.
First, the length of selection fatigue crack and width, as the degeneration index of target to be predicted, draw the Degradation path of each test sample according to the degraded data identifying; Then according to the Degradation path variation tendency of each sample, adequacy of fit degradation model; Follow the pseudo-burn-out life data by extrapolated each test sample of model, the pseudo-Failure life distribution of matching, and it is carried out to test of hypothesis; Finally pseudo-burn-out life data are carried out to reliability assessment, prediction unit residual life.
Beneficial effect of the present invention:
1. binocular vision monitoring system has applied widely, workable, reliability high, can be convenient, fast, the image that effectively gathers target.
2. utilize image processing techniques automatically to identify crack value, improved measuring accuracy and efficiency, reduced labour demand.
3. the present invention can be widely used in the surface fatigue crack detection that workpiece material is carried out, and for obtaining in time the information such as its duty and fatigue strength, offers help.
4. the present invention is combined binocular vision monitoring with image recognition technology, for realizing, to the life prediction of mechanical workpieces, provides a new way.
5. the hardware system the present invention relates to and software algorithm are easy to realize.
Accompanying drawing explanation
Fig. 1 is the life-span prediction method operational flowchart with surface crack image recognition based on binocular vision monitoring
Fig. 2 crack image monitoring system schematic diagram
Fig. 3 crack image pretreatment process figure
Fig. 4 crack length identification process figure
Fig. 5 crack width identification process figure
Fig. 6 processes the fiduciary level change curve of the test parts drawing by the inventive method
Embodiment
Life-span prediction method operating process based on binocular vision monitoring and surface crack image recognition as shown in Figure 1, is described in detail the inventive method below in conjunction with embodiment.
Step 1, completes the inside and outside portion parameter calibration to binocular vision system.
(1) fix the relative position of left and right cameras in biocular systems, binocular camera to be calibrated is placed in to diverse location, with different angles, 2D checkerboard type target is taken simultaneously, take 30 pictures, use the TOOLBOX_calib calibration tool case in MATLAB to complete the demarcation to left and right camera inner parameter.
(2) use the left and right camera in biocular systems respectively to take a photo to being fixed on the target of same position, complete the demarcation to left and right camera external parameter.
Step 2, carries out tired rotation test to sample, gathers time dependent crack image.
(1) determine certain job facilities parts target to be predicted, never in the homotype parts that crack, sample, choose 21 test samples, use wire cutting machine on each instance element, to cut an otch root radius-of-curvature and equal 0.08mm, the serrate otch that length is 0.9mm.
(2) designed, designed crack image monitoring system as shown in Figure 2, image monitoring system is comprised of image capturing system and image identification system.Utilize binocular camera to carry out and monitor being continuously rotated the parts of torture test, sample interval selects every 10000 to turn.The image transmitting collecting during by sampling is in image identification system.
Step 3, completes the image recognition to crackle, obtains crack Value Data.
(1) by left and right Image Mosaics, gray processing, spatial domain filtering, binaryzation and dilation and corrosion, operate, complete gathering the pre-service work of crack image, extract crackle skeleton and crackle profile, detailed process as shown in Figure 3.
(2) utilize flow process shown in Fig. 4 to realize the identification to crack length, be specifically divided into:
Identify short type crackle, mainly by computed image coordinate, complete, (a) the crackle skeleton extracting is abstracted into tree structure model, by model ergod being obtained to the information of each pixel on crackle skeleton, (b) the tree structure model of skeleton is pruned, repair except the tiny branch on crackle trunk, retain crackle skeleton trunk, (c) by the tree structure of skeleton trunk is traveled through, draw trunk pixel length; (d) length in pixels of crackle trunk and biocular systems are demarcated to the imaging multiplication obtaining, calculate physical length.
Identification elongated crackle, mainly by calculating world coordinates, complete, (a) the initial end points of mark crackle skeleton, and utilize polar curve restrict detect to go out on the way each unique point, (b) adopt general measure model, utilize least square method to resolve the volume coordinate of each angle point, (c) obtain the world coordinates of the initial end points of crackle skeleton and each unique point, by Pythagorean theorem, calculate every segment length, the cumulative physical length that draws elongated crackle.
Identify medium-sized crackle, (a) utilize the short type crackle method of identification to calculate crackle physical length, (b) by identification elongated crackle method, calculate crackle physical length, (c) get the mean value of twice computational length value, be medium-sized crackle physical length.
(3) utilize flow process shown in Fig. 5 to realize the identification to crack width, first find two end points of crackle trunk, take crackle trunk as center line, crackle profile is divided into P
1and P
2both sides; Then by P
1on point be set to impact point, all the other points are all set to background dot, and the image after upgrading is carried out to Euclidean distance variation; Finally extract the rear image P of conversion
2the value at place, is the pixel wide of each point on crackle trunk, gets its average and is designated as crackle mean pixel width, is multiplied by imaging coefficient and obtains crackle actual average width.
Step 4: matching crackle degraded data, target of prediction residual life.
(1) select the length of fatigue crack and width as the degeneration index of target to be predicted, by the degraded data of each test sample of first three collection step length and width in observation time, and draw the Degradation path of each test sample.
(2), with reference to the Degradation path variation tendency of each sample, select suitable Degradation path models fitting, and use cftool tool box in MATLAB to estimate the model parameter of each sample.
(3) according to the failure threshold of Degradation path model and regulation, the pseudo-burn-out life data of extrapolated each test sample, the pseudo-Failure life distribution of matching, and it is carried out to test of hypothesis.
(4) pseudo-burn-out life data are carried out to reliability assessment, prediction unit residual life.
The reliablity estimation that can draw this test parts by above step is:
In formula, t is time variable.Fig. 6 is the fiduciary level change curve of test parts.
Claims (1)
1. the life-span prediction method with surface crack image recognition based on binocular vision monitoring, its feature mainly comprises the following steps:
Step 1, complete the inside and outside portion parameter calibration to binocular vision system;
Fixedly the relative position of biocular systems middle left and right video camera, demarcates target to 2D checkerboard type with different angles simultaneously and takes, and by demarcating tool box in MATLAB, completes the demarcation to left and right camera inner parameter; With left and right camera, to being fixed on the target of same position, respectively take a photo, complete the demarcation to left and right camera external parameter;
Step 2, sample is carried out to torture test, gather time dependent crack image;
Determine target to be predicted, choose test specimen, the pre-service of complete paired samples; Utilize binocular vision system to monitor continuously sample, select suitable sample interval; By sample acquisitions to image transmitting in image identification system;
Step 3, complete the image recognition to crackle, obtain crack Value Data;
(1) by left and right Image Mosaics, gray processing, spatial domain filtering, binaryzation and dilation and corrosion, operate, complete the pre-service work of the crack image to collecting, extract crackle skeleton and crackle profile;
(2) realize the identification to crack length, be specifically divided into again:
Short type Identification of Cracks, mainly completes by computed image coordinate, first crackle skeleton is abstracted into tree structure model; Then the tree structure model of skeleton is pruned, reject tiny branch, retain crackle skeleton trunk; By the tree structure of skeleton trunk is traveled through, draw trunk pixel length; Finally the length in pixels of crackle trunk and binocular vision system are demarcated to the imaging multiplication obtaining, calculate physical length;
Elongated Identification of Cracks, mainly completes by calculating world coordinates, first marks the initial end points of crackle skeleton, and utilizes polar curve restrict detect to go out on the way each unique point; Then the volume coordinate of above each point is resolved, obtained world coordinates; Finally by Pythagorean theorem, calculate every segment length, the cumulative physical length that draws elongated crackle;
Medium-sized Identification of Cracks, first utilizes the short type crackle method of identification to calculate crackle physical length; Then by identification elongated crackle method, calculate crackle physical length; Finally get the mean value of twice computational length value, be designated as medium-sized crackle physical length;
(3) realize the identification to crack width, first find two end points of crackle trunk, take crackle trunk as center line, crackle profile is divided into P
1and P
2both sides; Then by P
1on point be set to impact point, all the other points are all set to background dot, and the image after upgrading is carried out to Euclidean distance variation; Finally extract the rear image P of conversion
2the value at place, is the pixel wide of each point on crackle trunk, gets its average and is designated as crackle mean pixel width, is multiplied by imaging coefficient and obtains crackle actual average width;
Step 4, matching crackle degraded data, target of prediction residual life;
The length of selection fatigue crack and width, as the degeneration index of object to be predicted, draw the Degradation path of each test sample, matching degradation model according to the degraded data identifying; Follow the pseudo-burn-out life data by extrapolated each test sample of model, the pseudo-Failure life distribution of matching, and it is carried out to test of hypothesis; Finally pseudo-burn-out life data are carried out to reliability assessment, the residual life of prediction monitoring component.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410312059.4A CN104034733A (en) | 2014-07-02 | 2014-07-02 | Service life prediction method based on binocular vision monitoring and surface crack image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410312059.4A CN104034733A (en) | 2014-07-02 | 2014-07-02 | Service life prediction method based on binocular vision monitoring and surface crack image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104034733A true CN104034733A (en) | 2014-09-10 |
Family
ID=51465582
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410312059.4A Pending CN104034733A (en) | 2014-07-02 | 2014-07-02 | Service life prediction method based on binocular vision monitoring and surface crack image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104034733A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104463888A (en) * | 2014-12-19 | 2015-03-25 | 中国科学院武汉岩土力学研究所 | Crack width change monitoring device and method |
CN104535589A (en) * | 2015-01-20 | 2015-04-22 | 广东电网有限责任公司电力科学研究院 | Online detection method and device for low-voltage current mutual inductor |
CN104655642A (en) * | 2015-02-06 | 2015-05-27 | 江苏大学 | Automatic measurement, characterization and classification method for steel cracking defects and system of method |
CN104777174A (en) * | 2015-03-27 | 2015-07-15 | 中国人民解放军装甲兵工程学院 | Shaft type part section abrupt change position surface fatigue crack detection system and method thereof |
CN107677682A (en) * | 2017-11-07 | 2018-02-09 | 泉州创力模具有限公司 | A kind of footwear mould surface damage detection device and detection method |
CN108337900A (en) * | 2015-06-30 | 2018-07-27 | 倍耐力轮胎股份公司 | The method and apparatus of the defect on surface for detecting tire |
CN108394426A (en) * | 2017-02-02 | 2018-08-14 | 淡水河谷公司 | Railway wheel monitors system and method |
CN109444150A (en) * | 2018-11-06 | 2019-03-08 | 西北工业大学 | Contactless crackle measurement method and its device |
CN109716108A (en) * | 2016-12-30 | 2019-05-03 | 同济大学 | A kind of Asphalt Pavement Damage detection system based on binocular image analysis |
CN110155369A (en) * | 2019-05-29 | 2019-08-23 | 中国民航大学 | A kind of aircraft skin face crack inspection method |
CN110501344A (en) * | 2019-08-30 | 2019-11-26 | 无锡先导智能装备股份有限公司 | Battery material online test method |
CN111008956A (en) * | 2019-11-13 | 2020-04-14 | 武汉工程大学 | Beam bottom crack detection method, system, device and medium based on image processing |
CN111155659A (en) * | 2020-01-22 | 2020-05-15 | 哈尔滨工业大学 | Connection node and crack identification method |
CN111256594A (en) * | 2020-01-18 | 2020-06-09 | 中国人民解放军国防科技大学 | Method for measuring physical characteristics of surface state of aircraft skin |
CN111815694A (en) * | 2020-09-14 | 2020-10-23 | 湖南大学 | Fatigue crack propagation life prediction method, device, equipment and storage medium |
CN112782181A (en) * | 2020-12-28 | 2021-05-11 | 吉林大学 | Binocular vision-based axle scratch detection and measurement system and method |
CN112950603A (en) * | 2021-03-11 | 2021-06-11 | 温州大学激光与光电智能制造研究院 | Sleeper tiny crack detection method based on graph structure abnormity evaluation |
CN113052089A (en) * | 2021-03-29 | 2021-06-29 | 广东电网有限责任公司 | System, method, device, equipment and storage medium for identifying surface cracks |
CN113188975A (en) * | 2021-05-07 | 2021-07-30 | 中南大学 | Rock mass fracture and flying rock motion analysis system and method based on image processing technology |
CN115830118A (en) * | 2022-12-08 | 2023-03-21 | 重庆市信息通信咨询设计院有限公司 | Crack detection method and system for cement electric pole based on binocular camera |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS62265558A (en) * | 1986-05-12 | 1987-11-18 | Kawasaki Heavy Ind Ltd | Measuring method for degree of damage and crack measuring element |
JPH08122221A (en) * | 1994-10-24 | 1996-05-17 | Osaka Gas Co Ltd | Integrity evaluating method and device for underground buried pipe |
CN103335604A (en) * | 2013-07-05 | 2013-10-02 | 温州大学 | On-line monitoring method of overall three-dimensional deformation of wind wheel blades in working states |
-
2014
- 2014-07-02 CN CN201410312059.4A patent/CN104034733A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS62265558A (en) * | 1986-05-12 | 1987-11-18 | Kawasaki Heavy Ind Ltd | Measuring method for degree of damage and crack measuring element |
JPH08122221A (en) * | 1994-10-24 | 1996-05-17 | Osaka Gas Co Ltd | Integrity evaluating method and device for underground buried pipe |
CN103335604A (en) * | 2013-07-05 | 2013-10-02 | 温州大学 | On-line monitoring method of overall three-dimensional deformation of wind wheel blades in working states |
Non-Patent Citations (4)
Title |
---|
冯毅: "焊缝成形的双目视觉评判方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 10, 15 October 2012 (2012-10-15) * |
申宇: "基于双目立体视觉的结构变形监测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 5, 15 May 2012 (2012-05-15) * |
董聪 等: "疲劳裂纹扩展寿命预测概率模型", 《强度与环境》, no. 4, 31 August 1994 (1994-08-31), pages 13 - 18 * |
郑立春 等: "疲劳裂纹形成寿命预测方法综述", 《力学与实践》, vol. 18, no. 4, 10 August 1996 (1996-08-10), pages 9 - 14 * |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104463888A (en) * | 2014-12-19 | 2015-03-25 | 中国科学院武汉岩土力学研究所 | Crack width change monitoring device and method |
CN104535589A (en) * | 2015-01-20 | 2015-04-22 | 广东电网有限责任公司电力科学研究院 | Online detection method and device for low-voltage current mutual inductor |
CN104655642A (en) * | 2015-02-06 | 2015-05-27 | 江苏大学 | Automatic measurement, characterization and classification method for steel cracking defects and system of method |
CN104655642B (en) * | 2015-02-06 | 2017-07-18 | 江苏大学 | A kind of automatic measurement of steel cracking type defect, sign sorting technique and its system |
CN104777174A (en) * | 2015-03-27 | 2015-07-15 | 中国人民解放军装甲兵工程学院 | Shaft type part section abrupt change position surface fatigue crack detection system and method thereof |
CN104777174B (en) * | 2015-03-27 | 2017-11-28 | 中国人民解放军装甲兵工程学院 | Axial workpiece abrupt change of cross-section portion faces fatigue crack detecting system and method |
CN108337900B (en) * | 2015-06-30 | 2020-04-07 | 倍耐力轮胎股份公司 | Method and apparatus for detecting defects on the surface of a tyre |
CN108337900A (en) * | 2015-06-30 | 2018-07-27 | 倍耐力轮胎股份公司 | The method and apparatus of the defect on surface for detecting tire |
CN109716108B (en) * | 2016-12-30 | 2021-07-13 | 同济大学 | Bituminous paving disease detecting system based on two mesh image analysis |
CN109716108A (en) * | 2016-12-30 | 2019-05-03 | 同济大学 | A kind of Asphalt Pavement Damage detection system based on binocular image analysis |
CN108394426A (en) * | 2017-02-02 | 2018-08-14 | 淡水河谷公司 | Railway wheel monitors system and method |
CN107677682A (en) * | 2017-11-07 | 2018-02-09 | 泉州创力模具有限公司 | A kind of footwear mould surface damage detection device and detection method |
CN107677682B (en) * | 2017-11-07 | 2024-03-08 | 泉州创力模具有限公司 | Shoe mold surface damage detection device and detection method |
CN109444150A (en) * | 2018-11-06 | 2019-03-08 | 西北工业大学 | Contactless crackle measurement method and its device |
CN110155369A (en) * | 2019-05-29 | 2019-08-23 | 中国民航大学 | A kind of aircraft skin face crack inspection method |
CN110155369B (en) * | 2019-05-29 | 2022-05-17 | 中国民航大学 | Method for checking surface cracks of aircraft skin |
CN110501344A (en) * | 2019-08-30 | 2019-11-26 | 无锡先导智能装备股份有限公司 | Battery material online test method |
CN111008956A (en) * | 2019-11-13 | 2020-04-14 | 武汉工程大学 | Beam bottom crack detection method, system, device and medium based on image processing |
CN111256594A (en) * | 2020-01-18 | 2020-06-09 | 中国人民解放军国防科技大学 | Method for measuring physical characteristics of surface state of aircraft skin |
CN111256594B (en) * | 2020-01-18 | 2022-01-14 | 中国人民解放军国防科技大学 | Method for measuring physical characteristics of surface state of aircraft skin |
CN111155659B (en) * | 2020-01-22 | 2022-02-18 | 哈尔滨工业大学 | Connection node and crack identification method |
CN111155659A (en) * | 2020-01-22 | 2020-05-15 | 哈尔滨工业大学 | Connection node and crack identification method |
CN111815694A (en) * | 2020-09-14 | 2020-10-23 | 湖南大学 | Fatigue crack propagation life prediction method, device, equipment and storage medium |
CN112782181A (en) * | 2020-12-28 | 2021-05-11 | 吉林大学 | Binocular vision-based axle scratch detection and measurement system and method |
CN112950603A (en) * | 2021-03-11 | 2021-06-11 | 温州大学激光与光电智能制造研究院 | Sleeper tiny crack detection method based on graph structure abnormity evaluation |
CN113052089A (en) * | 2021-03-29 | 2021-06-29 | 广东电网有限责任公司 | System, method, device, equipment and storage medium for identifying surface cracks |
CN113188975A (en) * | 2021-05-07 | 2021-07-30 | 中南大学 | Rock mass fracture and flying rock motion analysis system and method based on image processing technology |
CN113188975B (en) * | 2021-05-07 | 2022-07-15 | 中南大学 | Rock mass fracture and flying rock motion analysis system and method based on image processing technology |
CN115830118A (en) * | 2022-12-08 | 2023-03-21 | 重庆市信息通信咨询设计院有限公司 | Crack detection method and system for cement electric pole based on binocular camera |
CN115830118B (en) * | 2022-12-08 | 2024-03-19 | 重庆市信息通信咨询设计院有限公司 | Crack detection method and system for cement electric pole based on binocular camera |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104034733A (en) | Service life prediction method based on binocular vision monitoring and surface crack image recognition | |
CN108196260B (en) | Method and device for testing multi-sensor fusion system of unmanned vehicle | |
Li et al. | Long-distance precision inspection method for bridge cracks with image processing | |
CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
CN111856448A (en) | Marine obstacle identification method and system based on binocular vision and radar | |
CN105784710B (en) | A kind of glue into concrete beam cracks detection device based on Digital Image Processing | |
CN110986778B (en) | System and method for detecting size of rivet hole of carbon fiber composite material | |
CN111210477B (en) | Method and system for positioning moving object | |
CN105865344A (en) | Workpiece dimension measuring method and device based on machine vision | |
CN102346013A (en) | Tunnel lining crack width measuring method and device | |
CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
CN101512551A (en) | A method and a system for measuring an animal's height | |
CN102692188A (en) | Dynamic crack length measurement method for machine vision fatigue crack propagation test | |
CN106996748A (en) | A kind of wheel footpath measuring method based on binocular vision | |
CN103617611A (en) | Automatic threshold segmentation detection method for center and size of light spot | |
CN105405126A (en) | Multi-scale air-ground parameter automatic calibration method based on monocular vision system | |
CN105307115A (en) | Distributed vision positioning system and method based on action robot | |
JP2017083245A (en) | Clearance limit determination device | |
CN110136186A (en) | A kind of detection target matching method for mobile robot object ranging | |
CN108582075A (en) | A kind of intelligent robot vision automation grasping system | |
CN114663672B (en) | Method and system for detecting corrosion of steel member of power transmission line tower | |
Liu et al. | An approach for auto bridge inspection based on climbing robot | |
CN108180871B (en) | method for quantitatively evaluating composite insulator surface pulverization roughness | |
CN102830391B (en) | Accuracy index calculating method of infrared search and track system | |
CN107767366B (en) | A kind of transmission line of electricity approximating method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140910 |
|
WD01 | Invention patent application deemed withdrawn after publication |