CN108725511A - The real time position modification method of rail corrugation string measuring point - Google Patents
The real time position modification method of rail corrugation string measuring point Download PDFInfo
- Publication number
- CN108725511A CN108725511A CN201810573690.8A CN201810573690A CN108725511A CN 108725511 A CN108725511 A CN 108725511A CN 201810573690 A CN201810573690 A CN 201810573690A CN 108725511 A CN108725511 A CN 108725511A
- Authority
- CN
- China
- Prior art keywords
- rail
- image
- real time
- boundary line
- measuring point
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of real time position modification methods of rail corrugation string measuring point, including obtain the image of rail to be detected；Carry out picture superposition；Extract the rail top margin boundary line of rail；Laser measurement point is positioned；Carry out the removal of perspective image distortion；The position of laser measurement point is corrected in real time.The real time position modification method of this rail corrugation string measuring point provided by the invention, by whether keeping making real-time and accurately monitoring and amendment in the middle part of in-orbit top in effective range to string measuring point during dynamic measurement wave mill, to be effectively guaranteed the accuracy that wave grinds measurement data, solid technical foundation has been established for the rail wear Dynamic High-accuracy detection based on laser displacement.
Description
Technical field
Present invention relates particularly to a kind of real time position modification methods of rail corrugation string measuring point.
Background technology
With the development and the improvement of people's living standards of economic technology, railway has come into the production and life of people
Among, endless facility is brought to the production and life of people.Rail is the important component in the railway system.Rail exists
After coming into operation, with the increase of service time, gradually certain positions at the top of rail, the longitudinal surface along rail can occur one
Regular, similar to wave-like irregularity phenomenon is planted, and this phenomenon is referred to as the corrugation of rail, abbreviation steel
Rail wave is ground.
Currently, there are mainly three types of the measurement methods of rail corrugation：Artificial slide calliper rule method, inertial reference method and chord measurement.
Height of the vernier caliper that artificial slide calliper rule method is contacted by one with raceway surface in 1m rulers band out of shape rises and falls
Variation, the wave as the fragment position grind curve.This method efficiency is too low, and the position of ruler and raceway surface contact point,
It is influenced by deformation of rail and surface hurt, usually not in same level, to affect measurement accuracy.
Inertial reference method is commonly used on high speed track checking car, it installs accelerometer on the car body, and light is installed on axle box
Dielectric displacement meter, the displacement for measuring axle box relative acceleration fixed point are used as the wave mill of the point.This method can accurately describe wave
The long rail corrugation from 100mm to 50m, but measurement accuracy is affected by running speed, wheel tread irregularity.
Chord measurement is led to using the intrinsic transmission function relationship between multiple displacement sensor configurations string measured value gone out and wave mill value
It crosses and corresponding inverse filter is designed to carry out after-treatment to string measured value so that output waveform approaches the true face of track wave mill
Looks.It is compared with inertial reference method, measured value is not influenced by the car body speed of service, has obtained answering extensively in railway maintenance
With.
Currently, common string survey model mainly has 3 kinds in railway line：2 strings, the strings such as 3 points and 3 points of inclined strings.Wherein three
The inclined string of point is most widely used.
According to the requirement of BS EN 15610-2009 and 13231-3-2012, the position of string measuring point should be located at away from rail
In the range of the center line ± 10mm of rail top.However, during dynamic detection, due to the influence of following two factor so that current three
The measurement error of the chord measurement of the inclined string of point is still larger：
(1) circuit bend
The least radius of track upper curve rail is about 150m, and the length of compartment is about 20m, is thus easy to derive
Maximum transversal deviation in the middle part of compartment is 340mm, effective range of this numerical value far beyond ± 10mm.At this point, 3 measurement points
It will be to rail top edge side synchronizing moving.
(2) car body serpentine locomotion
Because of reasons such as track irregularities, wheel shows to that can occur to deviate any to the left or to the right in rolls forward
As contact point of such left and right wheels on rail will change.Since wheel tread has certain gradient, left and right vehicle
The radius size for taking turns rolling circle will be inconsistent, and the big wheel velocity of rolling radius is fast, and the wheel of the other side moves forwards speed
It accordingly will be slow.In this way, the direction of axle will change, wheel just will appear a little while to the left, a little while to the right,
And moved forwards according to certain amplitude, it takes turns and is moved ahead to forward appearance just as a snake wriggles in orbit, here it is snakes
Movement.At this point, the line of 3 measurement points will favour rail top center line.
Invention content
Monitoring in real time and amendment can be carried out to the position of string measuring point the purpose of the present invention is to provide a kind of, to ensure
The real time position modification method of the reliable rail corrugation string measuring point accurately run of chord measurement.
The real time position modification method of this rail corrugation string measuring point provided by the invention, includes the following steps：
S1. the image of rail to be detected is obtained；
S2. to the image of the obtained rail to be detected of step S1, picture superposition is carried out；
S3. the image obtained according to step S2 extracts the rail top margin boundary line of rail；
S4. the laser measurement point in chord measurement is positioned；
S5. to the image for including laser measurement point after the positioning that is obtained in step S4, the shifting of perspective image distortion is carried out
It removes；
S6. the image obtained according to step S5 corrects the position of the laser measurement point in chord measurement in real time.
Picture superposition is carried out to image described in step S2, specially uses homomorphism to increase clear algorithm and image is carried out
Contrast enhances.
The rail top margin boundary line of extraction rail described in step S3, is specially extracted using following steps：
A. borderline region is positioned；
B. boundary line fitting is carried out to the borderline region of step A positioning；
C. conditional test is carried out to the image after progress boundary line fitting.
Being positioned to borderline region described in step A is specially positioned using following formula：
R in formulawidthIndicate the width of rectangle, RheightIndicate the height of rectangle, IwidthIndicate the width of entire image, α
For the proportionality coefficient being previously set, NpixelIndicate the number of pixels of 8 connected regions.
Boundary line fitting described in step B, specially uses Hough transform to carry out boundary line to the borderline region in image
Fitting.
Conditional test is carried out to image described in step C, specially first according to the high-low-position of the obtained boundary lines step B
It sets relationship and confirms upper border line and following boundary line；Then should be shadow region with the lower section of upper border line, following boundary line it is upper
It is condition that side, which should be shadow region, conditional test is carried out to the boundary line that step B is obtained, to obtain true rail top boundary
Line.
Being positioned to the laser measurement point in chord measurement described in step S4, is specially determined using following steps
Position：
A. image is obtained using colored area array cameras, while is measured a little using the laser displacement sensor of red laser
Instruction；
B. RGB threshold methods is used to realize the positioning of laser measurement point.
The positioning that laser measurement point is realized using RGB threshold methods described in step b, is specially determined using following steps
Position：
(1) one and original color rail image R are givencAn equal amount of bianry image Rbw, and enable Rbw=0；
(2) according to the threshold range T being previously setrSearch original color rail image R by columncIf image RcIn i-th
The i-th of rowsA pixel is to i-theThe rgb value of a pixel is in the red threshold range T being previously setrIt is interior, then by bianry image
RbwIn i-thsTo i-theThe i-th capable row pixel value is all assigned a value of 1；
(3) the bianry image R that operation obtains step (2) is opened by morphology areabwIt is handled, to remove noise
Point；
(4) the bianry image R for being obtained step (3) by morphological dilationsbwOn pixel region connection be an entirety；
(5) threshold range is re-set as Tw, to bianry image RbwIt is middle that the region for being is marked to measure a little secondary
Verification, meet range is considered final laser measurement point, to complete the positioning of laser measurement point.
The removal of progress perspective image distortion described in step S5, specially uses 4 vertex of boundary line as feature
Point removes perspective image distortion using following formula：
(u, v) is the pixel of original image in formula, and (x', y') is transformed image slices vegetarian refreshments, k11、k12、k13、k21、
k22、k23、k31And k32It is transformation coefficient.
The position to the laser measurement point in chord measurement described in step S6 is corrected in real time, specially using following step
Suddenly it is corrected in real time：
1) using the lateral position deviation w of following formula calculation and measurement pointdev：
D in formulapFor the distance between measurement point on image and rail top inner boundary, DbBetween the inner and outer boundary of image upper rail top
Distance, wrailFor the width between the inner and outer boundary of true rail top；
If 2) w that step 1) obtainsdevAbsolute value be more than the threshold value that is previously set, then adjustment laser measurement point in real time
Position is until wdevAbsolute value be less than or equal to the threshold value that is previously set.
The real time position modification method of this rail corrugation string measuring point provided by the invention, it is honed by measuring wave to dynamic
Whether string measuring point keeps making real-time and accurately monitoring in the middle part of in-orbit top in effective range and correct in journey, to effectively ensure
The accuracy of wave mill measurement data has established solid technology for the rail wear Dynamic High-accuracy detection based on laser displacement
Basis.
Description of the drawings
Fig. 1 is the hardware realization schematic diagram of the method for the present invention.
Fig. 2 is the method flow diagram of the method for the present invention.
Fig. 3 is the effect diagram before and after the picture superposition of the method for the present invention.
Fig. 4 is the borderline region locating effect schematic diagram of the method for the present invention.
Fig. 5 is the boundary line fitting effect schematic diagram of the method for the present invention.
Fig. 6 is the rail top margin boundary line final effect schematic diagram of the rail of the method for the present invention.
Fig. 7 is the locating effect schematic diagram of the laser measurement point of the method for the present invention.
Fig. 8 is the typical rail schematic diagram in the embodiment of the method for the present invention.
Fig. 9 is 4 kinds of different string point position distribution schematic diagrams in the embodiment of the method for the present invention.
Figure 10 is the correction effect schematic diagram in the embodiment of the method for the present invention.
Figure 11 is the 60kg/m rail top of steel rail boundary geometrical position views in the embodiment of the method for the present invention.
Specific implementation mode
It is the hardware realization schematic diagram of the method for the present invention as shown in Figure 1：This rail corrugation string measuring point provided by the invention
Real time position modification method, realized using hardware as shown in Figure 1：It will be noted from fig. 1 that being passed using laser displacement
Sensor carries out the instruction and measurement of string measuring point, is illuminated using LED light source, is carried out to rail chord measuring point using area array cameras
It takes pictures, and the image taken pictures is uploaded to computer by interchanger and is handled；In addition, computer is calculated by correction algorithm
After correction amount, the position of laser displacement sensor is moved by stepper motor, to be corrected in real time to string measuring point.
The correction algorithm of the present invention, specifically comprises the following steps：
S1. the image of rail to be detected is obtained；
S2. to the image of the obtained rail to be detected of step S1, picture superposition is carried out；
In order to help to extract rail top margin boundary line, picture superposition algorithm is considered as following problem：
First：The difference of Rail Surface illumination and reflectivity can interfere the positioning in rail top margin boundary line：For example, natural light, especially
Its sunlight can obscure rail image, reduce the difference of rail top boundary and other positions.On the other hand, due to bright rail top
Band out of shape can reflect more light than other rough regions, and the boundary in the region may also be erroneously interpreted as rail top boundary；
Second：Vertical linear feature contained by rail top margin boundary line：Essentially, rail top margin boundary line is exactly two along track
Longitudinal straight line, light intensity and Rail Surface reflectivity are almost stablized constant on this straight line.Rail top margin boundary line positioned
Cheng Zhong, we can make full use of this feature；
Third：The synchronization existence of shadow region near boundary line：Observation chart 11, due to rail head 1:The inclination angle of 20 straight lines
Close to 90 °, width only has 1.1mm, which reflects almost without light.The end in the regions R13, drastically due to circular arc inclination angle
Increase, light reflectance be far below other positions of rail head, just the inside close to rail top margin boundary line synchronize to be formed one it is long and narrow
Shadow band, therefore us can be helped to verify the accuracy of extracted boundary line；
Therefore, clear algorithm is increased using homomorphism and contrast enhancing is carried out to image；Homomorphism increases clear also known as homomorphic filtering, is a kind of
Dynamic range of images is subjected to the method compressed and enhance picture contrast in a frequency domain.Its illumination-based on image
Reflectivity Model, by every piece image f (x, y) with the product of its luminance component i (x, y) and reflecting component r (x, y) come table
Show；
By taking Fig. 3 as an example, Fig. 3 (a) be original rail image for, before homomorphic filtering, due to the influence of sunlight, original steel
Rail image is fuzzy, and the shadow region of rail top margin boundary line both sides cannot clearly be found in corresponding Fig. 3 (b) binary map；Together
After state filtering, the influence of luminance component is weakened, and the picture contrast in Fig. 3 (c) is enhanced considerably, and the shadow region of both sides is being schemed
It is clearly displayed in 3 (d), this point is very useful in subsequent marginal check；
S3. the image obtained according to step S2 extracts the rail top margin boundary line of rail；Specially carried using following steps
It takes：
A. borderline region is positioned；
By taking the enhanced rail gray level image of Fig. 3 (c) contrasts as an example, the direct two-value arrived using canny operator extractions
Edge image is shown in Fig. 4 (a), and in image in addition to rail top margin boundary line, there is also other a large amount of unrelated lines.In order to remove these nothings
Lines are closed, the vertical linear feature contained by boundary line is fully utilized at this.
Shown in the minimum rectangle such as Fig. 4 (b) for surrounding each 8 connected pixel area.Longitudinally width direction, rail are indicated with track
Short transverse is indicated away from direction, and according to vertical linear feature, belonging in the minimum rectangle geometric dimension in rail top boundary region should expire
The following empirical condition of foot：
R in formulawidthIndicate the width of rectangle, RheightIndicate the height of rectangle, IwidthIndicate the width of whole sub-picture, α
For the proportionality coefficient being previously set, NpixelIndicate the number of pixels of 8 connected regions；
Using above formula, treated that result is shown in Fig. 4 (c).Obviously, outside the pixel for removing borderline region, remaining irrelevant is equal
It is effectively removed, potential boundary line clearly displays, and is convenient for the fitting a straight line of next step；
B. boundary line fitting is carried out to the borderline region of step A positioning；Specially use Hough transform to the side in image
Battery limit (BL) domain carries out boundary line fitting；By taking Fig. 5 as an example, since straight line may be divided on a plurality of adjacent pixel fragment, two
The thresholding interval that the adjacent straight line of item is merged is set as 300, and the retained threshold length of the straight line after merging is set as 30, extracts
Describe in Figure 5 in potential rail top margin boundary line (shown in green solid lines).Obviously, the number of potential boundary line is more than 2 on figure, meaning
Some distracters to still remain；
C. conditional test is carried out to the image after progress boundary line fitting；The boundary specially obtained first according to step B
The high and low position relationship of line confirms upper border line and following boundary line；Then should be shadow region with the lower section of upper border line, under
The top of boundary line should be that shadow region is condition, and conditional test is carried out to the boundary line that step B is obtained, true to obtain
Rail top margin boundary line；It is final, and the results are shown in Figure 6；
S4. the laser measurement point in chord measurement is positioned；Specially positioned using following steps：
A. image is obtained using colored area array cameras, while is measured a little using the laser displacement sensor of red laser
Instruction；
Since camera use herein is colored area array cameras, the color and image of sensor red laser measurement point
The color in other upper regions is dramatically different, so the application directly can realize determining for laser measurement point using RGB threshold methods
Position；
However it was found that some rust stainings of Rail Surface may also be erroneously interpreted as laser measurement point in actual test,
One example is shown in Fig. 7 (a).The enlarged view of laser measurement point is shown in Fig. 7 (b).The two is compared, and the latter removes the red area of outer ring
Outside, dazzling white is presented in internal optical center.In conjunction with the two features, laser measurement point can realize more accurate positioning；
B. RGB threshold methods is used to realize the positioning of laser measurement point；Specially positioned using following steps：
(1) one and original color rail image R are givencAn equal amount of bianry image Rbw, and enable Rbw=0；
(2) according to the threshold range T being previously setr(threshold range TrIt could be provided as Tr={ R > 215, G < 185, B <
200 } original color rail image R) is searched for by columncIf image RcIn i-th row i-thsA pixel is to i-theA pixel
Rgb value in the red threshold range T being previously setrIt is interior, then by bianry image RbwIn i-thsTo i-theThe i-th capable row pixel
Value is all assigned a value of 1；
(3) the bianry image R that operation obtains step (2) is opened by morphology areabwIt is handled, to remove noise
Point；
(4) the bianry image R for being obtained step (3) by morphological dilationsbwOn pixel region connection be an entirety；
(5) the bianry image R to being obtained in step (4)bwIn measurement point counted；Shown in Fig. 7, in figure (c)
The measurement point arrived is more than 3, hence it is evident that noise spot occurs；Therefore, algorithm also needs to carry out following step；
(6) threshold range is re-set as Tw(threshold range TwIt could be provided as Tw={ R > 250, G > 240, B >
240 }), to bianry image RbwThe region that middle label is measures secondary verification a little, and meet range is considered final
Laser measurement point (shown in such as Fig. 7 (d)), to complete the positioning of laser measurement point；
S5. to the image for including laser measurement point after the positioning that is obtained in step S4, the shifting of perspective image distortion is carried out
It removes；It specially uses 4 vertex of boundary line as characteristic point, perspective image distortion is removed using following formula：
(u, v) is the pixel of original image in formula, and (x', y') is transformed image slices vegetarian refreshments, k11、k12、k13、k21、
k22、k23、k31And k32It is transformation coefficient；
S6. the image obtained according to step S5 is corrected the position of the laser measurement point in chord measurement, specifically in real time
To be corrected in real time using following steps：
1) using the lateral position deviation w of following formula calculation and measurement pointdev：
D in formulapFor the distance between measurement point on image and rail top inner boundary, DbBetween the inner and outer boundary of image upper rail top
Distance, wrailFor the width between the inner and outer boundary of true rail top；If wdev> 0 then shows that the position of measurement point need to be to track inside
It is adjusted, otherwise the position of measurement point needs to be adjusted on the outside of track；
If 2) w that step 1) obtainsdevAbsolute value be more than the threshold value that is previously set (threshold value can be wanted according to string measuring point
Ask and the specific size of rail determine), then the position of laser measurement point is adjusted in real time until wdevAbsolute value be less than or wait
In the threshold value being previously set.In specific adjust, using simple closed-loop control.
The method of the present invention is further described below in conjunction with one embodiment：
Static experiment：
Static validity test is mainly used for the performance of check position watchdog subsystem.We are respectively in new rail, active service steel
600 width rail images are collected into the typical rail form of 3 kinds of rail after rail and milling turnning and milling etc., each form respectively accounts for 200 width.
These three forms almost cover all possible Rail Surface reflection characteristic, and example is successively as shown in Fig. 8 (a)~(c).Image
Size 1280*1024, resolution ratio 1mm*1mm；
In addition, being directed to each type, string measuring point is also distributed the 4 different lateral positions in in-orbit top and is tested,
Specific location distribution is as shown in Figure 9；
The string measuring point position error statistics of 4 different location distributions see the table below 1 in 3 kinds of rail forms：
Lateral deviation under the different string point position distributions of 13 kinds of table rail 4 calculates error
In table, MAE indicates that root-mean-square error, RSME indicate mean absolute error；
N represents the number of test sample, x in formulaiWithRespectively i-th exact value and estimated value.
Dynamic experiment：
In order to verify performance, dynamic is simulated by two moveable 60kg/m rail in laboratory environments and surveyed
Examination；
First, two one steel rails are normally placed by standard gauge, obtaining track wave mill value by cart type detection platform makees
For actual value；
Then, the front and back gauge of two tracks is artificially adjusted, and without using such as Fig. 1 institutes during experiment porch advances
The system shown corrects the position of string measuring point, and the wave mill value of acquisition is as the result before adding system as shown in Figure 1；
Finally, it still on the track of gauge confusion, is supervised using system as shown in Figure 1 during experiment porch advances
Depending on and correct the position of string measuring point, the wave mill value of acquisition is as the result after adding system as shown in Figure 1.
The long 6m of track, speed about 4km/h.Wave that off/on system as shown in Figure 1 is obtained mill measured value with it is true
The qualitative and quantitative comparison of value, difference Figure 10 and table 2.
The application condition of wave mill measured value and actual value that 2 off/on of the table auxiliary system is obtained
| Closing system | Open system | |
| MAE(mm) | 0.1216 | 0.0374 |
| RMSE(mm) | 0.1489 | 0.0475 |
In table, MAE indicates that root-mean-square error, RSME indicate mean absolute error；
N represents the number of test sample, x in formulaiWithRespectively i-th exact value and estimated value.
The chaotic introduced wave of gauge is can be seen that by table 2 and Figure 10 and grinds measurement error, is by as shown in Figure 1
System can be corrected effectively, and two indexs are respectively reduced from 0.1216 and 0.1489mm before amendment to 0.0374 He
0.0475mm, wave mill measurement result more approach the true rolling shape of track.
Claims (10)
1. a kind of real time position modification method of rail corrugation string measuring point, includes the following steps：
S1. the image of rail to be detected is obtained；
S2. to the image of the obtained rail to be detected of step S1, picture superposition is carried out；
S3. the image obtained according to step S2 extracts the rail top margin boundary line of rail；
S4. the laser measurement point in chord measurement is positioned；
S5. to the image for including laser measurement point after the positioning that is obtained in step S4, the removal of perspective image distortion is carried out；
S6. the image obtained according to step S5 corrects the position of the laser measurement point in chord measurement in real time.
2. the real time position modification method of rail corrugation string measuring point according to claim 1, it is characterised in that step S2 institutes
That states carries out picture superposition to image, specially uses homomorphism to increase clear algorithm and carries out contrast enhancing to image.
3. the real time position modification method of rail corrugation string measuring point according to claim 1, it is characterised in that step S3 institutes
The rail top margin boundary line for the extraction rail stated, is specially extracted using following steps：
A. borderline region is positioned；
B. boundary line fitting is carried out to the borderline region of step A positioning；
C. conditional test is carried out to the image after progress boundary line fitting.
4. the real time position modification method of rail corrugation string measuring point according to claim 3, it is characterised in that described in step A
Borderline region is positioned, specially positioned using following formula：
R in formulawidthIndicate the width of rectangle, RheightIndicate the height of rectangle, IwidthIndicate that the width of whole sub-picture, α are prior
The proportionality coefficient of setting, NpixelIndicate the number of pixels of 8 connected regions.
5. the real time position modification method of rail corrugation string measuring point according to claim 3, it is characterised in that described in step B
Boundary line fitting, specially use Hough transform in image borderline region carry out boundary line fitting.
6. the real time position modification method of rail corrugation string measuring point according to claim 3, it is characterised in that described in step C
To image carry out conditional test, specially first according to the high and low position relationship of the obtained boundary lines step B confirm coboundary
Line and following boundary line；Then should be shadow region with the lower section of upper border line, the top in following boundary line should be shadow region
For condition, conditional test is carried out to the boundary line that step B is obtained, to obtain true rail top margin boundary line.
7. the real time position modification method of the rail corrugation string measuring point according to one of claim 1~6, it is characterised in that step
Being positioned to the laser measurement point in chord measurement described in rapid S4, is specially positioned using following steps：
A. image is obtained using colored area array cameras, while finger a little is measured using the laser displacement sensor of red laser
Show；
B. RGB threshold methods is used to realize the positioning of laser measurement point.
8. the real time position modification method of rail corrugation string measuring point according to claim 7, it is characterised in that described in step b
Using RGB threshold methods realize laser measurement point positioning, specially positioned using following steps：
(1) one and original color rail image R are givencAn equal amount of bianry image Rbw, and enable Rbw=0；
(2) according to the threshold range T being previously setrSearch original color rail image R by columncIf image RcIn i-th row
I-thsA pixel is to i-theThe rgb value of a pixel is in the red threshold range T being previously setrIt is interior, then by bianry image RbwIn
I-thsTo i-theThe i-th capable row pixel value is all assigned a value of 1；
(3) the bianry image R that operation obtains step (2) is opened by morphology areabwIt is handled, to remove noise spot；
(4) the bianry image R for being obtained step (3) by morphological dilationsbwOn pixel region connection be an entirety；
(5) threshold range is re-set as Tw, to bianry image RbwIt is middle mark that the region for being measures a little secondary test
Card, meet range is considered final laser measurement point, to complete the coarse positioning of laser measurement point.
9. the real time position modification method of the rail corrugation string measuring point according to one of claim 1~6, it is characterised in that step
The removal of progress perspective image distortion described in rapid S5, specially uses 4 vertex of boundary line as characteristic point, using as follows
Formula removes perspective image distortion：
(u, v) is the pixel of original image in formula, and (x', y') is transformed image slices vegetarian refreshments, k11、k12、k13、k21、k22、
k23、k31And k32It is transformation coefficient.
10. the real time position modification method of the rail corrugation string measuring point according to one of claim 1~6, it is characterised in that
The position to the laser measurement point in chord measurement described in step S6 is corrected in real time, specially uses following steps to carry out real
Shi Xiuzheng：
1) using the lateral position deviation w of following formula calculation and measurement pointdev：
D in formulapFor the distance between measurement point on image and rail top inner boundary, DbFor the distance between the inner and outer boundary of image upper rail top,
wrailFor the width between the inner and outer boundary of true rail top；
If 2) w that step 1) obtainsdevAbsolute value be more than the threshold value that is previously set, then the position of adjustment laser measurement point in real time
Until wdevAbsolute value be less than or equal to the threshold value that is previously set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810573690.8A CN108725511B (en) | 2018-06-06 | 2018-06-06 | Real-time position correction method for rail corrugation measuring point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810573690.8A CN108725511B (en) | 2018-06-06 | 2018-06-06 | Real-time position correction method for rail corrugation measuring point |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108725511A true CN108725511A (en) | 2018-11-02 |
| CN108725511B CN108725511B (en) | 2019-12-20 |
Family
ID=63932148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810573690.8A Active CN108725511B (en) | 2018-06-06 | 2018-06-06 | Real-time position correction method for rail corrugation measuring point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108725511B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109855562A (en) * | 2019-01-28 | 2019-06-07 | 武汉武大卓越科技有限责任公司 | Measurement of rail wear method and device |
| CN112033316A (en) * | 2020-07-20 | 2020-12-04 | 深圳市埃伯瑞科技有限公司 | Track waveform determining method and device, electronic equipment and storage medium |
| CN113011283A (en) * | 2021-03-01 | 2021-06-22 | 浙江大学 | Non-contact type rail sleeper relative displacement real-time measurement method based on video |
| CN114384078A (en) * | 2021-12-31 | 2022-04-22 | 武汉大学 | Rail corrugation damage positioning detection method and device |
| CN115307599A (en) * | 2022-08-11 | 2022-11-08 | 济南致通华铁测量技术有限公司 | Railway track smoothness adjusting method |
| CN115523869A (en) * | 2022-11-02 | 2022-12-27 | 湖南科天健光电技术有限公司 | Laser measurement system, corrugation measurement vehicle and operation train |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2165915A2 (en) * | 2008-09-23 | 2010-03-24 | VolkerRail Nederland BV | Monitoring a turnout of a railway or tramway line |
| CN103171589A (en) * | 2011-12-26 | 2013-06-26 | 同济大学 | Rail outline detection method based on abrasion value |
| CN206019585U (en) * | 2016-08-30 | 2017-03-15 | 大连民族大学 | Rail Abrasion Detection System system |
| US20170166226A1 (en) * | 2014-01-31 | 2017-06-15 | Siemens Aktiengesellschaft | Rail Vehicle |
| FR3057380A1 (en) * | 2016-10-10 | 2018-04-13 | Sncf Reseau | METHOD AND SYSTEM FOR DETECTING REDUCED RAIL-WHEEL ADHERENCE, AND VEHICLE EQUIPPED WITH SUCH A SYSTEM |
-
2018
- 2018-06-06 CN CN201810573690.8A patent/CN108725511B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2165915A2 (en) * | 2008-09-23 | 2010-03-24 | VolkerRail Nederland BV | Monitoring a turnout of a railway or tramway line |
| CN103171589A (en) * | 2011-12-26 | 2013-06-26 | 同济大学 | Rail outline detection method based on abrasion value |
| US20170166226A1 (en) * | 2014-01-31 | 2017-06-15 | Siemens Aktiengesellschaft | Rail Vehicle |
| CN206019585U (en) * | 2016-08-30 | 2017-03-15 | 大连民族大学 | Rail Abrasion Detection System system |
| FR3057380A1 (en) * | 2016-10-10 | 2018-04-13 | Sncf Reseau | METHOD AND SYSTEM FOR DETECTING REDUCED RAIL-WHEEL ADHERENCE, AND VEHICLE EQUIPPED WITH SUCH A SYSTEM |
Non-Patent Citations (1)
| Title |
|---|
| 李宏锋: "地铁轨道波浪形磨耗检测系统研究", 《中国优秀硕士论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109855562A (en) * | 2019-01-28 | 2019-06-07 | 武汉武大卓越科技有限责任公司 | Measurement of rail wear method and device |
| CN112033316A (en) * | 2020-07-20 | 2020-12-04 | 深圳市埃伯瑞科技有限公司 | Track waveform determining method and device, electronic equipment and storage medium |
| CN113011283A (en) * | 2021-03-01 | 2021-06-22 | 浙江大学 | Non-contact type rail sleeper relative displacement real-time measurement method based on video |
| CN113011283B (en) * | 2021-03-01 | 2022-04-29 | 浙江大学 | Non-contact type rail sleeper relative displacement real-time measurement method based on video |
| CN114384078A (en) * | 2021-12-31 | 2022-04-22 | 武汉大学 | Rail corrugation damage positioning detection method and device |
| CN114384078B (en) * | 2021-12-31 | 2023-11-24 | 武汉大学 | Method and equipment for detecting wave abrasion damage of steel rail in positioning mode |
| CN115307599A (en) * | 2022-08-11 | 2022-11-08 | 济南致通华铁测量技术有限公司 | Railway track smoothness adjusting method |
| CN115307599B (en) * | 2022-08-11 | 2023-09-22 | 济南致通华铁测量技术有限公司 | Railway track smoothness adjusting method |
| CN115523869A (en) * | 2022-11-02 | 2022-12-27 | 湖南科天健光电技术有限公司 | Laser measurement system, corrugation measurement vehicle and operation train |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108725511B (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108725511A (en) | The real time position modification method of rail corrugation string measuring point | |
| CA3023641C (en) | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud | |
| US11551341B2 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| CN104236498B (en) | Method for measuring end size of switch rail | |
| CN105809668B (en) | The body surface deformation behaviour extracting method of three-dimensional point cloud is scanned based on line | |
| US8078025B2 (en) | Vehicle dynamic measurement device and method for comprehensive parameters of rail wear | |
| CN107180416B (en) | Train wheel tread image deformity correction method and system | |
| CN109060821A (en) | Tunnel defect detection method and tunnel defect detection device based on laser detection | |
| CN103886594B (en) | Road surface line laser rut detection and recognition methods and disposal system | |
| CN104990926A (en) | TR element locating and defect detecting method based on vision | |
| CN106091951A (en) | A kind of municipal rail train wheel rim parameter on-line detecting system and method | |
| CN112767359B (en) | Method and system for detecting corner points of steel plate under complex background | |
| CN109269403A (en) | A kind of contact line conducting wire measurement of wear method and device based on machine vision | |
| CN107341781A (en) | Based on the SAR image correcting methods for improving the matching of phase equalization characteristic vector base map | |
| CN110674732B (en) | Asphalt pavement rut three-dimensional size automatic detection and positioning method integrating multivariate data | |
| CN108596968B (en) | Sleeper counting method based on track 3D depth image | |
| CN112964195B (en) | Power supply rail geometric parameter comprehensive detection method and system based on laser triangulation method | |
| CN114119957A (en) | Method and device for detecting high-speed railway steel rail profile | |
| CN116433527A (en) | Road surface laser line extraction device and method | |
| CN111583241B (en) | Mobile detection method and device for regularity of ultra-large area honeycomb products | |
| Ziqiang et al. | Research of the algorithm calculating the length of bridge crack based on stereo vision | |
| CN111583235B (en) | Branch point identification vertex extraction method and system for detecting cellular regularity | |
| CN117495759A (en) | Sleeper crack detection method | |
| CN114913131A (en) | Vertical absolute and relative vertical deformation detection method for ballastless track structure | |
| CN109064417B (en) | Subway tunnel image processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liu Hongli Inventor after: Zheng Qian Inventor after: Li Yanfu Inventor after: Chen Liang Inventor after: Ma Ziji Inventor before: Liu Hongli Inventor before: Li Yanfu Inventor before: Chen Liang Inventor before: Ma Ziji |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |