CN206019585U - Rail Abrasion Detection System system - Google Patents
Rail Abrasion Detection System system Download PDFInfo
- Publication number
- CN206019585U CN206019585U CN201620989467.8U CN201620989467U CN206019585U CN 206019585 U CN206019585 U CN 206019585U CN 201620989467 U CN201620989467 U CN 201620989467U CN 206019585 U CN206019585 U CN 206019585U
- Authority
- CN
- China
- Prior art keywords
- rail
- microprocessor
- image sensor
- image
- ccd image
- 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.)
- Expired - Fee Related
Links
Abstract
Rail Abrasion Detection System system, belongs to detection field, in order to obtain a kind of Rail Abrasion Detection System system for being easy to application, is characterized in that：Including a wordline laser device, ccd image sensor, microprocessor, LCD display, acoustooptic alarm system and interface unit, the wordline light beam place plane and tested Rail Surface that a wordline laser device sends is in 60 ° of angles, ccd image sensor is located at the surface of a wordline light beam place plane, the input of the microprocessor receives the rail image information of ccd image sensor collection, the outfan of microprocessor respectively with LCD display, acoustooptic alarm system, interface unit connects, the interface unit is connected to exchange the information between microprocessor and host computer with host computer again.
Description
Technical field
This utility model belongs to detection field, is related to a kind of rail wear automatic checkout system.
Background technology
Railway is the large artery trunks of transportation, compares other means of transportation, and heavy haul railway transport is big, low cost with freight volume
Feature is developed rapidly all over the world.In track equipment, rail is most important building block, directly bears train load
Lotus simultaneously guides wheel to run.Whether the state of the art of rail is intact, and can directly affect train safe, flat by the speed of regulation
Steady and continual operation.Railway locomotive is to transmit driving force and brake force by the frictional force between wheel track, and between wheel track
Friction can then cause the generation of rail wear.With the high speed of locomotive, heavy duty, high density operation, the abrasion of rail will be quick
The increase of degree, particularly sharp radius curve outer rail medial surface abrasion are particularly acute.
The detection technique of rail wear have passed through monocular of conforming to the principle of simplicity measure ruler class tool detection, digitized instrument detection waited
Journey.At present, China has the main methods such as contact fixture measurement, EDDY CURRENT, optical triangulation in terms of Rail Abrasion Detection System,
Testing result is often depending on the experience that the attitude of detection workman and instrument are used, these methods exist detection efficiency low, inspection
The not high problems of precision are surveyed, the development need of current high speed can not be met.Although occur in that now a kind of using sharp
The testing equipment of light detection rail surface abrasion, but can not realize that accurately step-by-step movement detection, other detection methods also simply stop
Stay in theoretical research aspect.
Utility model content
In order to obtain a kind of Rail Abrasion Detection System system for being easy to application, this utility model is adopted the following technical scheme that：Bag
Include a wordline laser device, ccd image sensor, microprocessor, LCD display, acoustooptic alarm system and interface unit, a wordline
The wordline light beam place plane and tested Rail Surface that laser instrument sends is in 60 ° of angles, and ccd image sensor is positioned at a wordline light
The surface of beam place plane, the input of the microprocessor receive the rail image information of ccd image sensor collection, micro-
The outfan of processor is connected with LCD display, acoustooptic alarm system, interface unit respectively, the interface unit again with upper
Machine connects to exchange the information between microprocessor and host computer.
Further, the detecting system also includes that performance element, performance element receive the control signal of microprocessor, hold
Row unit includes that the first servomotor and the second servomotor, microprocessor connect the first servomotor to control rail wear inspection
Examining system direct of travel and speed, microprocessor connect the second servomotor, and the second servomotor connects ccd image sensor,
Second servomotor is controlling the orientation of ccd image sensor.
Beneficial effect：This utility model gives a kind of Rail Abrasion Detection System system, and laser and guide rail surface are into certain
Angular illumination is two sections of laser images being formed on surface when ensureing that rail has abrasion perpendicular to the direction of guide rail not at one
On straight line；60 ° is to form the right angled triangle of a special triangle, i.e., 60 ° on abrasion section for two sections of images,
So convenient calculating wears away width and depth.And further technical scheme is limited, performance element, increased detecting system can
Operability and automaticity.
Description of the drawings
Fig. 1 is the structured flowchart of the Rail Abrasion Detection System system；
Fig. 2 is without abrasion laser image schematic diagram；
Fig. 3 wears away laser image schematic diagram for having；
Fig. 4 is brightness curve and disk diameter schematic diagram；
Fig. 5 is the labelling schematic diagram of data point and characteristic quantity.
Specific embodiment
Embodiment 1：A kind of Rail Abrasion Detection System system, including a wordline laser device, ccd image sensor, microprocessor,
LCD display, acoustooptic alarm system and interface unit, a wordline light beam place plane and tested steel that a wordline laser device sends
Track surface is in 60 ° of angles, and ccd image sensor is positioned at the surface of a wordline light beam place plane, the input of the microprocessor
End receives the rail image information of ccd image sensor collection, the outfan of microprocessor respectively with LCD display, acousto-optic report
Alarm system, interface unit connection, the interface unit are connected to exchange the information between microprocessor and host computer with host computer again.
Further, the detecting system also includes that performance element, performance element receive the control signal of microprocessor, hold
Row unit includes that the first servomotor and the second servomotor, microprocessor connect the first servomotor to control rail wear inspection
Examining system direct of travel and speed, microprocessor connect the second servomotor, and the second servomotor connects ccd image sensor,
Second servomotor sends control signal by microprocessor to control the orientation of ccd image sensor, controls performance element
Servomotor was determined next test point, and is finely tuned ccd image by servomotor by fixed velocity form, set time
The angle of sensor, it is ensured that laser beam is with Rail Surface into 60 ° of angles.
Embodiment 2：Detecting system shown in embodiment 1, its can be executed to detection method in the present embodiment, to obtain one
The detection for kind more optimizing, a kind of rail wear automatic testing method gather the laser image of rail, and with complete rail laser
Light belt image carries out image comparison, to judge to detect whether rail has abrasion, judges that rail has abrasion, to the laser figure for gathering
As carrying out laser image process, the laser image is processed includes Image semantic classification and Edge extraction, laser image process
Afterwards, the laser image characteristic quantity related to rail wear amount is selected and extracts, to be calculated rail wear depth and width.Its
In：The extraction laser image characteristic quantity related to rail wear amount is one or more of following characteristics amount：
1) length l of two sections of straight line portioies of laser imageAAnd lB；
2) the stand out e of two sections of linear laser images；
3) the lengthwise position difference z of two sections of linear laser images；
4) between two sections of linear laser images changeover portion length lC；
5) between two sections of linear laser images changeover portion inclination angle theta；
Abrasion width and abrasion depth are referred to as the characteristic quantity of rail wear, one or more laser images during selection is above-mentioned
Characteristic quantity, for calculating the depth and width of rail wear；
And when the depth and width of rail wear are calculated, and non-selection whole above-mentioned laser image characteristic quantity is counted
Calculate, in order to optimize calculating process, the combination of laser image characteristic quantity is selected as the base of the depth and width for calculating rail wear
Plinth calculates data, selects the method during combination to be：Determine related to the wear characteristics laser image characteristic quantity first, and from
Preferred features amount is selected in laser image characteristic quantity, the degree of association system of remaining each laser image characteristic quantity and preferred features amount is calculated
Number, and its meansigma methods is sought, the meansigma methodss are the threshold value beta that characteristic quantity is selected, if wherein between certain two laser image feature
Absolute value | rTij | >=β of correlation coefficient, two laser images are characterized in that relevant redundancy feature, only select one of conduct
The laser image characteristic quantity that rail wear judges.I.e. when the combination for the laser image characteristic quantity for judging is selected, it is assumed that M is
The feature samples set for collecting is pinpointed on the rail with abrasion, and what reaction of the set comprising N number of fixing point wore away swashs
Light image characteristic quantity, select correlation coefficient as metric parameter, the parameter be characterized by between similarity, two laser figures
As being characterized in that relevant redundancy feature, one of them is only selected as the laser image characteristic quantity of rail wear judgement, for finding
The combination of the minimum laser image characteristic quantity of rail wear width and depth can effectively be judged.
As a kind of embodiment, above-mentioned middle correlation coefficient as metric parameter, to be characterized by the concrete of a dependency
Method is：It is respectively using two groups of different laser image features are set：Ti={ tik, k=1,2 ..., n } and Tj={ tjk, k=1,
2 ..., n }, wherein k represents k-th test point, has n test point, then the correlation coefficient of two groups of laser image features is defined such as
Under：
In formula,WithRespectively two stack features TiAnd TjMeansigma methodss：With
Correlation coefficient r TijReflect two stack features TiAnd TjDegree of correlation, rTijValue for negative when, represent two features
Negatively correlated；rTijValue be timing, represent two feature positive correlations；Work as rTijWhen=0, between two wear characteristics be incoherent,
Work as rTijAbsolute value when being closer to 1, the degree of correlation of two laser image features is higher, and the redundancy of generation is bigger, in reaction
In the laser image characteristic set of rail wear, using the correlation coefficient between each laser image characteristic quantity, threshold value beta is set, if
The absolute value of the correlation coefficient wherein between certain two laser image feature | rTij| >=β, two laser images are characterized in that correlation
Redundancy feature, the laser image characteristic quantity for only selecting one of them to judge as rail wear.
In another embodiment, for the determination method of threshold value beta described above is：For certain single laser image spy
The amount of levying, chooses which as preferred features, judges that remaining laser image characteristic quantity for the method for the probability of redundancy feature is：Determine
After preferred features, by calculate obtain in rail wear width and depth associated laser characteristics of image set with preferred features amount it
Between correlation coefficient, the average of this group of correlation coefficient data is set to threshold value beta, the determination method of threshold value beta is：
Wherein：The quantity of the c amounts of being characterized in formula, l are the sequence number of first-selected characteristic quantity, and j is the sequence number of alternative features amount.
Thus, above-described embodiment, tries to achieve the correlation coefficient between feature to obtain the probability size of redundancy between feature, should
The average of group correlation coefficient data is set to threshold value beta, using this threshold value as the judging characteristic whether foundation of redundancy, so as to sentence
During disconnected two feature redundancy, a laser image feature as the depth and width for calculating abrasion between redundancy feature is only selected,
To optimize calculating process, minimal features combination is obtained with this.
As a kind of embodiment, the computational methods of concrete open abrasion depth and width：Two sections of line parts of laser image
Length l that dividesAUsed as the preferred features of abrasion width detection, the lengthwise position difference z of two sections of linear laser images is deep as abrasion
The preferred features of degree detection；Two straight line portioies of laser image are calculated by the correlation coefficient of two groups of laser image features
Length lAAnd lBUsed as the characteristic quantity of abrasion width detection, the lengthwise position difference z of two sections of linear laser images is used as abrasion depth inspection
The characteristic quantity of survey, wearing away width calculation formula is：
Wherein, l is the width for not wearing away rail；
Wearing away depth calculation formula is：
60 ° of V=z tan
Used as a kind of embodiment, described image pretreatment comprises the steps：
The rectangular histogram of gray level image first by image gray processing, is drawn, gray scale is found out and is concentrated scope；
Then using following formula, grey level enhancement is carried out to gray level image, becomes apparent from image；
Wherein：A, b are respectively the left and right boundary point of gray value integrated distribution in gray level image rectangular histogram, and x, y are represented respectively
Gray value before and after grey level enhancement.
As a kind of embodiment, the method for described image edge extracting, comprise the steps：
Appoint and take a medium filtering brightness curve for being distributed pixel in the horizontal direction, in the curve peak-peak both sides point
Not Qu Chu the maximum continuity point of brightness step change, take between the midpoint p of two groups of continuity points and q, p and q distance as detection
Template diameter；
If the brightness of image is f (i, j), a round s (c, r) is taken in picture field as detection template, wherein c is circle
The heart, its coordinate are (ic,jc), r is radius；
Define the set of s (c, r) interior pixel, and remember in round s the brightness of pixel and be：
The a small range movement in the horizontal direction of the detection template center of circle is made, each pixel in the detection template of each position is calculated bright
Degree and, should in the range of brightness and maximum template home position, be a Pixel-level roof edge point of the bright wisp, using most
Little square law fitting a straight line, the straight line are a wordline laser picture centre line, and the small range is to put a left side centered on the center of circle
The image of right each 2 times of radiuses is interval, to obtain length l of two sections of straight line portioies of laser imageAAnd lB, two sections of linear laser figures
Length l of changeover portion as betweenC.
The rail laser image of the present embodiment collection is compared with complete image, to judge whether to gather the steel in image
There is abrasion in rail, and when being judged as wearing and tearing, further select characteristic quantity to qualitatively judge abrasion to be calculated abrasion, first, then
Quantitative Analysis wear away the thinking of depth and width, and in calculating process, characteristic quantity are selected, to optimize abrasion depth
Calculating process with width.
Embodiment 3：As the supplement of 1 technical scheme of embodiment, or as a kind of single embodiment：Abrasion mainly go out
The head of rail, wearing away including top surface and side wear for abrasion, must detect the two numerical value simultaneously during detection, come comprehensive now
Close the wear intensity for judging rail.The present embodiment utilizes one word laser beam of high intensity narrow beam, laser instrument and a wordline light beam institute
In plane and tested Rail Surface in 60 ° of angles, high-resolution Array CCD sensor is located at the surface of laser image and shoots
Laser image.Bending is occurred in that in the Rail Surface light beam image for there are abrasion, the position occurred by bending point and degree of crook
Determine width and the depth of rail wear.
Rail wear automatic detection device includes：A wordline laser device, ccd image sensor, microprocessor, execute list
Unit, display and acousto-optic warning unit and interface unit.Ccd image sensor gathers laser image, the image information for being obtained
It is transferred to microprocessor and is analyzed process, extract image border and center fitting a straight line, forms complete rail laser
Light belt image outline, converts image information into rail profile parameter, stores the characteristic quantity of rail profile, and joins with complete rail
Number is compared, and judges rail with the presence or absence of abrasion.Proceed subsequent point detection without abrasion；There are abrasion, further determine that
Abrasion loss, including the depth and width for wearing away.Performance element receives the control signal of microprocessor, controls the traveling of detection means
Direction and speed, adjust the orientation of ccd image sensor, the outfan of microprocessor respectively with LCD display and sound and light alarm
System connects, and LCD display is used for current location and the wear intensity for showing rail, and acoustooptic alarm system is used for pointing out rail to work as
There are abrasion in front position, need to repair.Interface unit is used for exchanging information with host computer, and host computer can further to wearing away position
The further fine processing of the image put, determines accurately abrasion loss.
Processing stage Image semantic classification is the early stage of laser image edge extracting, first by image gray processing, gray scale is drawn
The rectangular histogram of image, finds out gray scale and concentrates scope, and using formula (1), (wherein a, b are respectively gray value in gray level image rectangular histogram
The left and right boundary point of integrated distribution, x, y represent the gray value before and after grey level enhancement respectively) grey level enhancement is carried out to gray level image,
Become apparent from image.
The rim detection of a wordline laser image adopts " ridge-shaped " edge detection method.Based on single pixel brightness
Edge detection method noise resisting ability is poor, in order to reduce the interference of picture noise, each pixel brightness in a certain region and
As " ridge-shaped " edge distinguishing rule.As circle is not affected by ridge-shaped edge direction to same tropism with each, therefore,
This utility model adopts plate way " ridge-shaped " edge detection method.By disk detection template appropriate for size in a wordline laser
Move in the certain limit of image both sides, when the graded of the brightness sum of each pixel in template meets certain requirements, mould
The central point of plate is ridge-shaped marginal point.
Appoint and take a medium filtering brightness curve for being distributed pixel in the horizontal direction, in the curve peak-peak both sides point
Not Qu Chu the maximum continuity point of brightness step change, take between the midpoint p of two groups of continuity points and q, p and q distance as detection
Template diameter, as shown in Figure 3.
If the brightness of image is f (i, j), a round s (c, r) is taken in picture field as detection template, wherein c is circle
The heart, its coordinate are (ic,jc), r is radius.Define the set of the interior pixels of s (c, r)：
And remember in round s the brightness of pixel and be：
The a small range movement in the horizontal direction of the detection template center of circle is made, each pixel in the detection template of each position is calculated bright
Degree and, should in the range of brightness and maximum template home position, be a Pixel-level roof edge point of the bright wisp.Using most
Little square law fitting a straight line, the straight line are a wordline laser picture centre line.The marginal point for detecting and the straight line of fitting are such as
Shown in Fig. 4.
Further extract and rail wear amount associated laser image feature amount, the system of selection and threshold value including characteristic quantity
Determine.
The width of the rail wear that this utility model is related generally to and depth, can be true by the degree of crook of laser image
Determine width and the depth of rail wear, have following characteristic quantity to can be used to select：
1) length l of two sections of straight line portioies of laser imageAAnd lB；
2) the stand out e of two sections of linear laser images；
3) the lengthwise position difference z of two sections of linear laser images；
4) between two sections of linear laser images changeover portion length lC；
5) between two sections of linear laser images changeover portion inclination angle theta.
One or more characteristic quantities can be selected for judging the depth and width of rail wear, selected for judgement
During the combination of characteristic quantity, it is desirable to which different category features have marked difference, it is to avoid redundancy feature interference judges.Assume that M is that have
The feature samples set for collecting, wear characteristics of the set comprising n fixing point are pinpointed on the rail of abrasion.Select degree of association
Coefficient as metric parameter, the parameter can be characterized by between similarity, for find can effectively judge rail wear width
The combination of the minimal features amount of degree and depth.If two groups of different wear characteristics are respectively：Ti={ tik, k=1,2 ..., n } and
Tj={ tjk, k=1,2 ..., n }, wherein k represents k-th test point, has n test point, then the correlation coefficient of two stack features
It is defined as follows：
In formula,WithRespectively two stack features TiAnd TjMeansigma methodss：With
Correlation coefficient r TijReflect two stack features TiAnd TjDegree of correlation, rTijValue for negative when, represent two features
Negatively correlated；Value is timing, represents two feature positive correlations.Work as rTijWhen=0, it is incoherent between two features.Then work as rTij
Absolute value when being closer to 1, represent that the degree of correlation of two features is higher, now issuable redundancy is bigger.
In the characteristic set of rail wear, using the correlation coefficient between each characteristic quantity, threshold value beta is set, if wherein certain
The absolute value of the correlation coefficient between two features | rTij| >=β, illustrate that the two are characterized in that relevant redundancy feature, can only select
One of them characteristic quantity judged as rail wear.
For certain single features, its, determination methods bigger with the direct relation of rail wear depth and width is simpler, uses
Higher in the feasibility for judging abrasion loss, selected probability is bigger, and selected feature is used as preferred features.Judge a certain
The probability of redundancy feature is characterized as, according to its dependency with preferred features, dependency is higher, then become relevant redundancy feature
Probability bigger.After preferred features are determined, by calculate obtain in rail wear width and depth correlated characteristic set with
The average of this group of data is set to threshold value beta by the correlation coefficient between preferred features amount, as shown in formula (4):
The rail wear amount of test position after determining characteristic quantity, is calculated, is stored and is shown, had when transfiniting abrasion and start
Acoustic-optic alarm.
Interface unit is used for exchanging information with host computer in off-line case, and host computer can further to wearing away position
The further fine processing of image, determines accurately abrasion loss.Due to adopting above-mentioned technical proposal, a kind of steel that the present embodiment is provided
Rail abrasion automatic detection device has such beneficial effect, due to the method using image procossing, in the control of microprocessor
Under, depart from PC control, device can under the setting of operator automatic running.Equipment has certain integrity and actual effect
Property, it is easy to the use of testing staff, not only simple to operate, testing result is accurate, and manufacturing cost is low.
The above, only the invention preferably specific embodiment, but the protection domain of the invention is not
Be confined to this, any those familiar with the art in the technical scope that the invention is disclosed, according to the present invention
The technical scheme of creation and its inventive concept equivalent or change in addition, should all cover the invention protection domain it
Interior.
Claims (2)
1. a kind of Rail Abrasion Detection System system, it is characterised in that including a wordline laser device, ccd image sensor, microprocessor
Device, LCD display, acoustooptic alarm system and interface unit, a wordline light beam place plane and quilt that a wordline laser device sends
Rail Surface is surveyed in 60 ° of angles, ccd image sensor is located at the surface of a wordline light beam place plane, the microprocessor
Input receives the rail image information of ccd image sensor collection, the outfan of microprocessor respectively with LCD display, sound
Light alarm system, interface unit connection, the interface unit are connected to exchange between microprocessor and host computer with host computer again
Information.
2. Rail Abrasion Detection System system as claimed in claim 1, it is characterised in that the detecting system also includes executing list
Unit, performance element receive the control signal of microprocessor, and performance element includes the first servomotor and the second servomotor, micro- place
Reason device connects the first servomotor to control Rail Abrasion Detection System system direct of travel and speed, and microprocessor connects the second servo
Motor, the second servomotor connect ccd image sensor, and the second servomotor is controlling the orientation of ccd image sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620989467.8U CN206019585U (en) | 2016-08-30 | 2016-08-30 | Rail Abrasion Detection System system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620989467.8U CN206019585U (en) | 2016-08-30 | 2016-08-30 | Rail Abrasion Detection System system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206019585U true CN206019585U (en) | 2017-03-15 |
Family
ID=58254767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620989467.8U Expired - Fee Related CN206019585U (en) | 2016-08-30 | 2016-08-30 | Rail Abrasion Detection System system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206019585U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108725511A (en) * | 2018-06-06 | 2018-11-02 | 湖南大学 | The real time position modification method of rail corrugation string measuring point |
| CN110779450A (en) * | 2019-11-12 | 2020-02-11 | 中科(徐州)人工智能研究院有限公司 | Abrasion detection method and device for power supply three-rail |
| CN113514003A (en) * | 2021-03-16 | 2021-10-19 | 西安理工大学 | 5G-based laser scanning steel rail abrasion detection system and method |
-
2016
- 2016-08-30 CN CN201620989467.8U patent/CN206019585U/en not_active Expired - Fee Related
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108725511A (en) * | 2018-06-06 | 2018-11-02 | 湖南大学 | The real time position modification method of rail corrugation string measuring point |
| CN108725511B (en) * | 2018-06-06 | 2019-12-20 | 湖南大学 | Real-time position correction method for rail corrugation measuring point |
| CN110779450A (en) * | 2019-11-12 | 2020-02-11 | 中科(徐州)人工智能研究院有限公司 | Abrasion detection method and device for power supply three-rail |
| CN110779450B (en) * | 2019-11-12 | 2021-07-30 | 中科(徐州)人工智能研究院有限公司 | Abrasion detection method and device for power supply three-rail |
| CN113514003A (en) * | 2021-03-16 | 2021-10-19 | 西安理工大学 | 5G-based laser scanning steel rail abrasion detection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106274979B (en) | Rail wear automatic detection device | |
| CN106441107B (en) | Rail wear automatic testing method | |
| Zhang et al. | Automatic pavement defect detection using 3D laser profiling technology | |
| Luo et al. | Edge‐enhanced matching for gradient‐based computer vision displacement measurement | |
| González et al. | Automatic traffic signs and panels inspection system using computer vision | |
| CN109969736A (en) | A kind of large size carrier strip deviation fault intelligent detecting method | |
| CN105787486B (en) | A kind of girder steel crack detecting method based on image procossing | |
| CN206019585U (en) | Rail Abrasion Detection System system | |
| CN103837087B (en) | Pantograph automatic testing method based on active shape model | |
| CN103745238B (en) | Pantograph identification method based on AdaBoost and active shape model | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| JP6283534B2 (en) | Tire deterioration evaluation apparatus and system, method and program thereof | |
| CN102567744A (en) | Method for determining quality of iris image based on machine learning | |
| CN110288032A (en) | A kind of vehicle driving trace type detection method and device | |
| CN101995412A (en) | Robust glass scratch defect detection method and device thereof | |
| CN113689392A (en) | Railway fastener defect detection method and device | |
| CN105404866B (en) | A kind of implementation method of multi-mode automatic implementation body state perception | |
| Yang et al. | A study on the roughness detection for machined surface covered with chips based on deep learning | |
| CN102298780B (en) | Method for detecting shadow of color image | |
| CN114092411A (en) | Efficient and rapid binocular 3D point cloud welding spot defect detection method | |
| Liu et al. | A binocular reconstruction method fused with Laplacian image information for pavement texture evaluation | |
| Li et al. | Road Damage Evaluation via Stereo Camera and Deep Learning Neural Network | |
| CN106157316A (en) | A kind of rail fastener location algorithm based on geometric match and device | |
| Yu et al. | Surface defect detection of hight-speed railway hub based on improved YOLOv3 algorithm | |
| CN106502246A (en) | A kind of intelligent vehicle automated induction systems based on grader |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170315 Termination date: 20170830 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |