CN106290379A - Rail surface defects based on Surface scan camera detection device and method - Google Patents
Rail surface defects based on Surface scan camera detection device and method Download PDFInfo
- Publication number
- CN106290379A CN106290379A CN201610769651.6A CN201610769651A CN106290379A CN 106290379 A CN106290379 A CN 106290379A CN 201610769651 A CN201610769651 A CN 201610769651A CN 106290379 A CN106290379 A CN 106290379A
- Authority
- CN
- China
- Prior art keywords
- image
- rail
- defect
- camera
- processing module
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
The present invention discloses a kind of rail surface defects based on Surface scan camera detection device and method, it is possible to increase the efficiency of detection and accuracy, and greatly reduces the workload of workman.Described device includes: Surface scan camera, data collecting card and processing module；Wherein, described Surface scan camera, for gathering the surface image of rail to be detected；Described data collecting card, is used for obtaining described image, and described image is sent to described processing module；Described processing module, for processing described image, obtains defect characteristic value, and by grader good for described defect characteristic value input training in advance, obtains the classification belonging to defect of described rail to be detected.
Description
Technical field
The present invention relates to rail surface defects detection field, be specifically related to a kind of Rail Surface based on Surface scan camera and lack
Fall into detection device and method.
Background technology
Along with the development of railway cause, high ferro rail has indispensable status in terms of transportation.But, railway
Can there is certain defect in the rail in running or after processing, the service life of material, mechanical property etc. can be produced by defect
Directly affect, and can gradually develop, deteriorate, cause material failure the most at last and rupture, it is also possible to cause life or property
Massive losses.Now with the introduction of advanced production technology, such as high-carbon steel and iron and steel process for cleanly preparing, rail is internal to be lacked
The existing probability that traps out is said the fewest, and the situation that rail surface defects causes rail fracture is increasingly common；Rail surface defects
Also resulting in wheel wear aggravation, form flake-off block, make derailing be more easy to occur, therefore the detection of rail surface defects just seems
Particularly important.
It is ultrasound examination, impulse eddy current in steel rail defect context of detection, current comparative maturity and the more technology of application
Automatization, the semi-automatic techniques such as detection.But these methods on the one hand testing cost is high, and equipment is complicated, is on the other hand difficult to
Distinguish internal flaw and the surface defect of rail, need manually to utilize miniature instrument to check.
Summary of the invention
The deficiency existed for prior art and defect, the present invention provides a kind of Rail Surface based on Surface scan camera to lack
Fall into detection device and method.
On the one hand, the embodiment of the present invention proposes a kind of rail surface defects based on Surface scan camera detection device, including:
Surface scan camera, data collecting card and processing module；Wherein,
Described Surface scan camera, for gathering the surface image of rail to be detected；
Described data collecting card, is used for obtaining described image, and described image is sent to described processing module；
Described processing module, for processing described image, obtains defect characteristic value, and by described defect characteristic value
The grader that input training in advance is good, obtains the classification belonging to defect of described rail to be detected.
On the other hand, the embodiment of the present invention proposes a kind of detection method of surface flaw of steel rail, including:
Utilize the surface image of described Surface scan collected by camera rail to be detected；
Utilize described data collecting card to obtain described image, and described image is sent to described processing module；
Utilize described processing module that described image is processed, obtain defect characteristic value, and by described defect characteristic value
The grader that input training in advance is good, obtains the classification belonging to defect of described rail to be detected.
Rail surface defects based on the Surface scan camera detection device and method that the embodiment of the present invention provides, utilization processes
Module is detected by the classification belonging to the defect of the surface image of the rail to be detected of grader opposite scanning camera collection,
Identification and the classification of steel rail defect can be realized well, improve efficiency and the accuracy of detection, and greatly reduce the work of workman
Amount, meanwhile, instant invention overcomes the automatizatioies such as existing ultrasound examination, Pulsed eddy current testing, semi-automatic technique cost height,
The shortcomings such as equipment is complicated, on the premise of ensureing detection efficiency and accuracy, it is achieved that the identification of rail surface defects and classification.
Accompanying drawing explanation
Fig. 1 is the structural representation of present invention rail surface defects based on Surface scan camera detection device one embodiment；
Fig. 2 is the concrete stream involved by present invention rail surface defects based on Surface scan camera detection device one embodiment
Journey schematic diagram；
Fig. 3 is the structural representation of camera mobile platform of the present invention；
Fig. 4 is the detail view of the camera mobile platform rail sections described in Fig. 3；
Fig. 5 is the overall flow schematic diagram of detection method of surface flaw of steel rail one embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of embodiment rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
Make the every other embodiment obtained under creative work premise, broadly fall into the scope of protection of the invention.
Referring to Fig. 1, the present embodiment discloses a kind of rail surface defects based on Surface scan camera detection device, including:
Surface scan camera 11, data collecting card 12 and processing module 13；Wherein,
Described Surface scan camera 11, for gathering the surface image of rail to be detected；
In actual applications, can there is distortion in camera lens, and this is due to the zones of different amplification to image on focal plane
The phenomenon of the picture torsional deformation that rate is different and is formed.The accuracy of defects detection can be impacted by distortion, and enters camera
Rower can reach to eliminate the effect of distortion surely, therefore before using the surface image of collected by camera rail to be detected, first
Need it to be demarcated, as shown in Figure 2.
Process to camera calibration actually solves the process of 12 inside and outside parameter of camera.Demarcate the instrument needed
Being scaling board, conventional scaling board has two kinds with chess array pattern of filled circles array pattern, and size can be according to regarding
Field range size selects.
After camera position and attitude are fixed, gather some width scaling board images.These images need to make the mark of diverse location
Determining plate and be paved with whole viewing field of camera, meanwhile, scaling board to have as far as possible many attitudes.By soft for scaling board image input machine vision
In the software program that part HALCON writes in advance, run the inside and outside parameter obtaining camera, utilize the inside and outside parameter of camera to phase
Machine is demarcated.
In the present embodiment, camera can use face battle array CMOS camera ARTCAM-300MI-WOM, can shoot maximum 2048
The image of × 1536 pixels, such high-resolution can ensure that collecting steel rail defect image can preserve actual as much as possible
Detailed information, thus ensure to omit the fewest defect.Can reach about 6000 due to every row pixel maximum again, therefore, make
Obtaining image with this camera, every millimeter of pixel that can include about 20, in conjunction with the algorithm of image procossing below, it is possible to protect
The result of card defective locations detection reaches required precision.Owing to, in experimentation, viewing field of camera size is about 15cm × 10cm, because of
This, use this camera the testing result of surface defect can be accurate to 0.1mm.
Described data collecting card 12, is used for obtaining described image, and described image is sent to described processing module 13；
Described processing module 13, for processing described image, obtains defect characteristic value, and by described defect characteristic
The grader (can be Gaussian classifier) that value input training in advance is good, obtains the class belonging to defect of described rail to be detected
Not.
Processing module 13 can be arranged in PC.As in figure 2 it is shown, processing module 13 is at the exterior view to rail to be detected
Before processing, needing to be trained grader, detailed process is as follows:
The surface image of the rail sample of the classification belonging to known defect is carried out pretreatment, feature extraction successively, obtains
The defect characteristic value of described rail sample, and utilize the classification belonging to defect of described rail sample and lacking of described rail sample
Fall into eigenvalue described grader is trained.
As in figure 2 it is shown, after complete to classifier training, the pretreatment submodule of processing module 13 can be to rail to be detected
Surface image carries out pretreatment, and calculating sub module can carry out feature extraction (i.e. obtaining defect information) to pretreated image,
Obtain defect characteristic value.Wherein, pretreatment includes: described image is filtered device filtering, image enhaucament and rail district successively
Territory localization process.It should be noted that filter filtering, mainly utilize Gaussian function (mean_image function) that image is carried out
Denoising smooth processes, the most effective to the noise removing Normal Distribution.
Feature extraction includes: the steel rail area obtaining described steel rail area localization process carries out image gray processing；To institute
The result stating image gray processing carries out image segmentation；The result splitting described image carries out Morphological scale-space；To described form
The result that process carries out defect demarcation；The eigenvalue of calculated defect, obtains defect characteristic value.Image gray processing, main
If the feature of prominent image, specifically can utilize decompose3 operator that coloured image is converted into black white image, it is simple to after
Continue and effectively process work.Image is split, and mainly extracts defect according to the difference of gray value, the most convenient and swift effectively
Extract defect information, have that realization is simple, amount of calculation is little, the feature that performance is more stable, it is particularly well-suited to target and background and occupies
The image of different grey-scale scope.Morphological scale-space includes that corrosion and expansive working, corrosion expansion are the bases of Morphological scale-space.
Undesired details can be ignored by corrosion expansive working, strengthen the feature of defect, reach to strengthen the effect of picture, filter out
Come region interested.Defect demarcation specifically can carry out edge with canny operator to defect picture and choose and position.Feature extraction
The eigenvalue extracted can include length and the positional information of defect.
It should be noted that the pretreatment that the surface image of the rail sample of the classification belonging to known defect is carried out, spy
Levying and extract the alignment processing process with the surface image to rail to be detected, here is omitted.
The defect classification utilizing the embodiment of the present invention to identify can include peeling off block, fish scale peels off, crackle and
Corrosion, naturally it is also possible to add other type of defect information and carry out defect recognition to grader.
Rail surface defects based on the Surface scan camera detection device that the embodiment of the present invention provides, utilizes processing module to lead to
The classification belonging to defect of the surface image crossing the rail to be detected of grader opposite scanning camera collection detects, can be very well
Realize identification and the classification of steel rail defect, improve efficiency and the accuracy of detection, meanwhile, instant invention overcomes existing ultrasonic
The automatizatioies such as ripple detection, Pulsed eddy current testing, semi-automatic technique cost height, the shortcomings such as equipment is complicated, ensureing detection efficiency
On the premise of accuracy, it is achieved that the identification of rail surface defects and classification.
On the basis of aforementioned means embodiment, described device can also include:
Motor and camera mobile platform；Wherein,
Described Surface scan camera is arranged on described camera mobile platform,
Described motor connects described camera mobile platform, for receiving the control instruction coming from described processing module, root
Drive described camera mobile platform to move according to described control instruction by drive mechanism, thus drive described Surface scan camera three
Dimension space moves.
Being illustrated in figure 3 the structural representation of camera mobile platform of the present invention, camera mobile platform is mainly used in controlling phase
The motion of machine, platform is respectively equipped with movable sliding block along tri-directions of XYZ, is used for driving camera in three-dimensional fortune
Dynamic.In Fig. 3,1,3 and 4 is slide block, and 2 is rail to be detected, and 5 is Surface scan camera.Before and after slide block at 1 is used for controlling camera
Motion, the slide block at 3,4 is respectively used to control the upper and lower of camera and side-to-side movement, and then realizes camera in three-dimensional fortune
Dynamic, the detail view of rail sections is as shown in Figure 4.By camera mobile platform chain of command scanning camera at three-dimensional space motion, with
Scanning obtains the surface image of rail to be detected.
As it is shown on figure 3, it is all double that the information between processing module and data collecting card and data collecting card and camera transmits
To.Processing module sends control signal and is adopted card realized the motor control of camera, the image information of collected by camera defect by number
Adopt card by number and send processing module to.
It should be noted that the camera mobile platform overall architecture shown in Fig. 3 and Fig. 4 uses rectangular structure, but this ties
Structure does not limits the invention, and is only used as one embodiment of the present of invention, and one of skill in the art can build the most controlled
The platform that camera processed moves at three dimensions.
The software translating environment of device mainly uses interactively programmatic interface HDevelop in HALCON to carry out whole
The software design of individual device.Software program can be directly embedded into inside device hardware, directly carry out defect recognition and classification, side
Just efficient, low cost.
Referring to Fig. 5, the present embodiment discloses a kind of detection method of surface flaw of steel rail based on Surface scan camera, including:
S1, utilize the surface image of described Surface scan collected by camera rail to be detected；
S2, utilize described data collecting card to obtain described image, and described image is sent to described processing module；
S3, utilize described processing module that described image is processed, obtain defect characteristic value, and by described defect characteristic
The grader that value input training in advance is good, obtains the classification belonging to defect of described rail to be detected.
The detection method of surface flaw of steel rail based on Surface scan camera that the embodiment of the present invention provides, utilizes processing module to lead to
The classification belonging to defect of the surface image crossing the rail to be detected of grader opposite scanning camera collection detects, can be very well
Realize identification and the classification of steel rail defect, improve efficiency and the accuracy of detection, meanwhile, instant invention overcomes existing ultrasonic
The automatizatioies such as ripple detection, Pulsed eddy current testing, semi-automatic technique cost height, the shortcomings such as equipment is complicated, ensureing detection efficiency
On the premise of accuracy, it is achieved that the identification of rail surface defects and classification.
Although being described in conjunction with the accompanying embodiments of the present invention, but those skilled in the art can be without departing from this
Making various modifications and variations in the case of bright spirit and scope, such amendment and modification each fall within by claims
Within limited range.
Claims (9)
1. rail surface defects based on a Surface scan camera detection device, it is characterised in that including:
Surface scan camera, data collecting card and processing module；Wherein,
Described Surface scan camera, for gathering the surface image of rail to be detected；
Described data collecting card, is used for obtaining described image, and described image is sent to described processing module；
Described processing module, for processing described image, obtains defect characteristic value, and described defect characteristic value is inputted
The grader that training in advance is good, obtains the classification belonging to defect of described rail to be detected.
Device the most according to claim 1, it is characterised in that described processing module, including:
Pretreatment submodule, for carrying out pretreatment to described image；
Calculating sub module, carries out defect extraction for described pretreatment submodule processes the image that obtains, and calculates and extract
The eigenvalue of the defect arrived, obtains defect characteristic value.
Device the most according to claim 2, it is characterised in that described pretreatment submodule, specifically for:
Described image is filtered successively device filtering, image enhaucament and rail localization process.
Device the most according to claim 3, it is characterised in that described calculating sub module, specifically for:
The steel rail area obtaining described rail localization process carries out image gray processing；
The result of described image gray processing is carried out image segmentation；
The result splitting described image carries out Morphological scale-space；
The result of described Morphological scale-space is carried out defect demarcation；
The eigenvalue of calculated defect, obtains defect characteristic value.
Device the most according to claim 1, it is characterised in that described processing module, is additionally operable to carrying out described image
Process, before obtaining defect characteristic value, the surface image of the rail sample of the classification belonging to known defect is processed, obtains
The defect characteristic value of described rail sample, and utilize the classification belonging to defect of described rail sample and lacking of described rail sample
Fall into eigenvalue described grader is trained.
Device the most according to claim 1, it is characterised in that also include:
Motor and camera mobile platform；Wherein,
Described Surface scan camera is arranged on described camera mobile platform,
Described motor connects described camera mobile platform, for receiving the control instruction coming from described processing module, according to institute
Stating control instruction drives described camera mobile platform to move by drive mechanism, thus drives described Surface scan camera at three-dimensional space
Between move.
Device the most according to claim 1, it is characterised in that
Described Surface scan camera, is additionally operable to, before gathering the surface image of rail to be detected, gather and be paved with viewing field of camera not
Image with the scaling board of attitude；
Described processing module, for obtaining the image of described scaling board, calculates described Surface scan according to the image of described scaling board
The inside and outside parameter of camera, and utilize described inside and outside parameter that described Surface scan camera is demarcated.
Device the most according to claim 1, it is characterised in that described Surface scan camera is face battle array CMOS camera ARTCAM-
300MI-WOM。
9. a detection method of surface flaw of steel rail based on the device described in claim 1, it is characterised in that including:
Utilize the surface image of described Surface scan collected by camera rail to be detected；
Utilize described data collecting card to obtain described image, and described image is sent to described processing module；
Utilize described processing module that described image is processed, obtain defect characteristic value, and described defect characteristic value is inputted
The grader that training in advance is good, obtains the classification belonging to defect of described rail to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610769651.6A CN106290379A (en) | 2016-08-30 | 2016-08-30 | Rail surface defects based on Surface scan camera detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610769651.6A CN106290379A (en) | 2016-08-30 | 2016-08-30 | Rail surface defects based on Surface scan camera detection device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106290379A true CN106290379A (en) | 2017-01-04 |
Family
ID=57675942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610769651.6A Pending CN106290379A (en) | 2016-08-30 | 2016-08-30 | Rail surface defects based on Surface scan camera detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106290379A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944505A (en) * | 2017-12-19 | 2018-04-20 | 青岛科技大学 | A kind of metal failure type automatization judgement method |
| CN110254468A (en) * | 2019-06-20 | 2019-09-20 | 吉林大学 | A kind of raceway surface defect intelligent online detection device and detection method |
| CN113034341A (en) * | 2021-05-25 | 2021-06-25 | 浙江双元科技股份有限公司 | Data acquisition processing circuit for Cameralink high-speed industrial camera |
| CN114235838A (en) * | 2021-12-20 | 2022-03-25 | 苏州金万轮精密机械有限公司 | A wearing and tearing check out test set for line guide rail processing |
| CN116152237A (en) * | 2023-04-18 | 2023-05-23 | 中铁四局集团有限公司 | Method and system for detecting flaking and falling blocks of steel rail |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699273A (en) * | 2009-10-29 | 2010-04-28 | 北京交通大学 | Auxiliary detection device and method of image processing for on-line flaw detection of rails |
| CN104132943A (en) * | 2013-05-02 | 2014-11-05 | 上海工程技术大学 | Method and device of vehicle-mounted high-speed dynamic railway surface defect video detection |
| CN104751169A (en) * | 2015-01-10 | 2015-07-01 | 哈尔滨工业大学（威海） | Method for classifying rail failures of high-speed rail |
| CN105092705A (en) * | 2015-08-28 | 2015-11-25 | 哈尔滨工业大学（威海） | Multi-mode signal detection method and multi-mode signal detection system for rail defects |
| CN205426067U (en) * | 2016-02-22 | 2016-08-03 | 东莞市邓工精密仪器设备有限公司 | Tower crane balanced type image measuring instrument ware |
-
2016
- 2016-08-30 CN CN201610769651.6A patent/CN106290379A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699273A (en) * | 2009-10-29 | 2010-04-28 | 北京交通大学 | Auxiliary detection device and method of image processing for on-line flaw detection of rails |
| CN104132943A (en) * | 2013-05-02 | 2014-11-05 | 上海工程技术大学 | Method and device of vehicle-mounted high-speed dynamic railway surface defect video detection |
| CN104751169A (en) * | 2015-01-10 | 2015-07-01 | 哈尔滨工业大学（威海） | Method for classifying rail failures of high-speed rail |
| CN105092705A (en) * | 2015-08-28 | 2015-11-25 | 哈尔滨工业大学（威海） | Multi-mode signal detection method and multi-mode signal detection system for rail defects |
| CN205426067U (en) * | 2016-02-22 | 2016-08-03 | 东莞市邓工精密仪器设备有限公司 | Tower crane balanced type image measuring instrument ware |
Non-Patent Citations (5)
| Title |
|---|
| MINGJIAN SUN ET AL.: ""Feature Selection and Classification Algorithm for Non-destructive Detecting of High-speed Rail Defects Based on Vibration Signals"", 《INSTRUMENT AND MEASUREMENT TECHNOLOGY CONFERENCE(12MTC) PROCEEDINGS,2014 IEEE INTERNATIOLAL》 * |
| 方玉红: ""基于机器视觉的轨道缺陷图像检测系统设计"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 王时丽、刘桂华: ""基于机器视觉的钢轨表面缺陷三维检测方法"", 《微机与应用》 * |
| 薛兴昌 等编著: "《钢铁工业自动化 轧钢卷》", 31 January 2010, 冶金工业出版社 * |
| 许文达: ""基于机器视觉的钢轨表面缺陷识别研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944505A (en) * | 2017-12-19 | 2018-04-20 | 青岛科技大学 | A kind of metal failure type automatization judgement method |
| CN110254468A (en) * | 2019-06-20 | 2019-09-20 | 吉林大学 | A kind of raceway surface defect intelligent online detection device and detection method |
| CN113034341A (en) * | 2021-05-25 | 2021-06-25 | 浙江双元科技股份有限公司 | Data acquisition processing circuit for Cameralink high-speed industrial camera |
| CN113034341B (en) * | 2021-05-25 | 2021-08-03 | 浙江双元科技股份有限公司 | Data acquisition processing circuit for Cameralink high-speed industrial camera |
| CN114235838A (en) * | 2021-12-20 | 2022-03-25 | 苏州金万轮精密机械有限公司 | A wearing and tearing check out test set for line guide rail processing |
| CN116152237A (en) * | 2023-04-18 | 2023-05-23 | 中铁四局集团有限公司 | Method and system for detecting flaking and falling blocks of steel rail |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106290379A (en) | Rail surface defects based on Surface scan camera detection device and method | |
| CN111062915B (en) | Real-time steel pipe defect detection method based on improved YOLOv3 model | |
| CN111044522A (en) | Defect detection method and device and terminal equipment | |
| CN101387493B (en) | Shape and position dimension non-contact photoelectric detection method for pylon component hole | |
| CN113465511B (en) | Steel coil size online measurement and omnibearing end surface defect online detection method | |
| CN107478657A (en) | Stainless steel surfaces defect inspection method based on machine vision | |
| CN105205821A (en) | Weld image segmentation method | |
| CN104259670A (en) | Turbine blade laser cutting system based on machine vision and industrial robot | |
| CN104700395A (en) | Method and system for detecting appearance crack of structure | |
| CN110400296A (en) | The scanning of continuous casting blank surface defects binocular and deep learning fusion identification method and system | |
| CN110288623B (en) | Data compression method for unmanned aerial vehicle maritime net cage culture inspection image | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN109166125A (en) | A kind of three dimensional depth image partitioning algorithm based on multiple edge syncretizing mechanism | |
| CN112061171B (en) | Embedded GPU-based track defect online inspection method and inspection device | |
| CN106841214A (en) | A kind of non-contact wind power blade dust storm erosion degree detection method | |
| CN101510295B (en) | Design method for machine vision system based on PCIe and Vision Assistan | |
| CN112833784B (en) | Steel rail positioning method combining monocular camera with laser scanning | |
| CN111524154B (en) | Image-based tunnel segment automatic segmentation method | |
| CN105242568A (en) | Tobacco leaf accurate rejecting control method based on digital image processing | |
| CN105023018A (en) | Jet code detection method and system | |
| CN104200215A (en) | Method for identifying dust and pocking marks on surface of big-caliber optical element | |
| CN102663781A (en) | Sub-pixel level welding center extraction method based on visual sense | |
| CN114004814A (en) | Coal gangue identification method and system based on deep learning and gray scale third moment analysis | |
| CN103149087A (en) | Follow-up window and digital image-based non-contact real-time strain measurement method | |
| CN113705564B (en) | Pointer type instrument identification reading 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 |
Application publication date: 20170104 |
|
| RJ01 | Rejection of invention patent application after publication |