CN107085854A - A kind of creation method of the railroad track two-dimensional map based on image processing techniques - Google Patents
A kind of creation method of the railroad track two-dimensional map based on image processing techniques Download PDFInfo
- Publication number
- CN107085854A CN107085854A CN201611156162.XA CN201611156162A CN107085854A CN 107085854 A CN107085854 A CN 107085854A CN 201611156162 A CN201611156162 A CN 201611156162A CN 107085854 A CN107085854 A CN 107085854A
- Authority
- CN
- China
- Prior art keywords
- msub
- mrow
- mtd
- mtr
- track
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 title claims abstract description 21
- 238000012937 correction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 5
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 4
- 238000000205 computational method Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 8
- 230000004927 fusion Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/004—Map manufacture or repair; Tear or ink or water resistant maps; Long-life maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/005—Map projections or methods associated specifically therewith
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of creation method of the railroad track two-dimensional map based on image processing techniques.Track is continuously shot first, the orbital image of one group of successive frame is obtained;Then it is corrected by geometrical model, the track of trapezoidal distortion is reduced;Image after reduction is matched;Splicing fusion is carried out to the image for having matched completion, the complete image of a width target track is obtained;Marginalisation processing is carried out to it again, inward flange line is taken, intactly rail profiles curve is obtained;Coordinate system is set up, is moved to after rail profiles curve is zoomed in and out in coordinate system, the two-dimensional map of rail profiles curve is created, and calculates corresponding map scale;Engineer's scale, can accurately measure the gauge of picture scope inner orbit and the rail of any chord length to parameter according to the map.Measurement of the present invention to gauge belongs to non-cpntact measurement, can also solve tolerance stack-up issue of the current long-chord rail into measurement, improve measurement accuracy, and cost is relatively low.
Description
Technical field
The present invention relates to a kind of creation method of the railroad track two-dimensional map based on image processing techniques.
Background technology
With the development of high-speed railway, the security and stability of train operation also requires that higher, and occurring in that can be accurately effective
The equipment of the every static geometric parameter of measure track --- rail inspection instrument;On the other hand, the image processing techniques based on machine vision
It is more ripe.The present invention combines this existing technological achievement of two aspects, it is proposed that a kind of rail based on image processing techniques
The creation method of road two-dimensional map, the geometric parameter for obtaining track, it is possible to increase the precision of measurement.
The content of the invention
Technical problem solved by the invention is, for currently available technology, proposes a kind of based on image processing techniques
The creation method of railroad track two-dimensional map, for the gauge of measure track and the rail of any chord length to parameter.
In order to realize above-mentioned technical purpose, the technical scheme is that:
A kind of creation method of the railroad track two-dimensional map based on image processing techniques, comprises the following steps:
Step 1:Track is continuously shot, the orbital image of one group of successive frame is obtained;
Step 2:The picture of shooting is corrected by geometrical model, the track of trapezoidal distortion is reduced into parallel rail
Road;
Step 3:Characteristic matching is carried out to the orbital image after reduction, the target track for needing to measure is found;
Step 4:By splicing to the picture for having matched completion, the complete image of target track is obtained;
Step 5:Marginalisation processing is carried out to this width complete track image, the inward flange curve of track is obtained;
Step 6:Coordinate system is set up, the two-dimensional map of rail profiles curve is created.
In described method, described step 1, track is continuously shot, is that camera is installed on instrument by in-orbit examine,
Track is shot simultaneously in in-orbit inspection instrument traveling process.
In described method, described step 2, the geometrical model being corrected is:
Wherein, f is the focal length of camera used, and the vertical range of camera shooting point S to two pictures is all f in a model,
ai、bi、ci(i=1,2,3) is constant, and by azimuth, element is determined, x, and y is the A points on the inclination picture of shooting in coordinate system 0
Coordinate in~xy, x0,y0,z0For the conformation A of A points on the horizontal picture after correction0Point is in coordinate system S~x0y0z0In seat
Mark.The process of progress characteristic matching is in described method, described step 3:
The characteristic point including marginal point, angle point, crosspoint is extracted first from adjacent two pictures, is recycled similar
Property carry out registration, obtain the joining relation of two width pictures;
If the content on first track picture around A points is similar to the content on the second pictures around B points, root
This two pictures is matched according to A, B point;Judge that the similar method of content is by two rows of predetermined interval in the first pictures
The difference of pixel finds the pole with first template sum of squares of deviations as feature templates, the second pictures same intervals calculating difference
Similitude is used as at small value, minimum;
Wherein the extracting method of characteristic point carries out feature extraction using Forstner operators, calculates around pixel (i, j)
The absolute value of gray scale difference is:
To given threshold value, if the value in above formula is both greater than threshold value, pixel is used as characteristic point.
In described method, described step 4, when being spliced, overlaying graphics degree is 0.4-0.7, that is, needs to be spelled
The accounting of the two pictures lap areas connect is 40%-70%.
In described method, described step 5, the step of carrying out marginalisation processing, the inward flange curve for obtaining track is:
1) spliced track picture is subjected to gaussian filtering, obtains the smoothed image after a vice processing.Wherein two dimension is high
Any first derivative of this function is noise filter;
2) amplitude and the direction of image gradient are calculated, the edge of image is detected;
Computational methods are as follows:
Amplitude
Direction
Wherein M (i, j) is the gray value of image, Mx(i, j) and My(i, j) is that the neighborhood of its transverse and longitudinal axle is poor.
3) range value of gradient is compared with default threshold value, excludes maximum point, make edge thinning.
In described method, described step 6, the step of setting up coordinate system is:
Choose some particular point in picture and be set to the origin of coordinates, the x for determining coordinate, y-axis are oriented by map sheet so that two dimension
Map has geodetic coordinates scalability;Wherein particular point is the known coordinate information determined by track CPIII points and control net
Point.
Wherein map sheet orientation realizes particular by four interior Marginal points of complete track picture, four interior Marginal points
Image coordinate is obtained from image, i.e. the four of entire image boundary point, is obtained after the theoretical geodetic coordinates of four Marginal points, is used
The parsing relational model that affine Transform Model is set up between geodetic coordinates and image coordinate;
Wherein affine Transform Model is:
Wherein, (x 'i,y′j) it is Marginal point geodetic coordinates, (xi,yj) it is Marginal point image coordinate, parameter k, θ, x0,y0For
Registration parameter, k is zoom factor, and θ is the anglec of rotation, x0,y0For translational movement.
A kind of gauge and rail based on track two-dimensional map are to measuring method:Image procossing skill is based on using described one kind
The creation method of the railroad track two-dimensional map of art, the gauge and any chord length of measure track in the track two-dimensional map of generation
Rail to the measuring method comprises the following steps:
Step 1:The gauge of some specified point of map middle orbit is calculated, is compared with measured data, obtains this width map
Engineer's scale, be set to 1:k;
Step 2:Calculated on map track it is any on any point gauge and any two points between rail to parameter, respectively
It is set to a, b;
Step 3:Passing ratio chi converts, that is, is capable of rail between the gauge of accurately measuring track and any two points to actual ginseng
Number, is ka, kb.
Brief description of the drawings
, below will be to embodiment or existing skill in order to become apparent from clearly stating the technical scheme in the embodiment of the present invention
The accompanying drawing used required in art description is simply introduced, it should be apparent that, drawings in the following description are only this hair
Some bright embodiments, on the premise of not paying creative work, can be with for one of ordinary skill in the art
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the implementation process figure that railroad track two-dimensional map is created based on image processing techniques that the present invention is provided;
Fig. 2 is the orbital image keystone model that the present invention is provided and correction result schematic diagram;
Fig. 3 is the orbital image splicing schematic diagram that the present invention is provided;
Fig. 4 is the gauge that provides of the present invention and rail to instrumentation plan.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
Do not limit the present invention.
Fig. 1 shows the creation method of heretofore described two-dimensional map, and step is as follows:
Step 1:Continuously track is taken pictures in in-orbit inspection instrument traveling process, the trajectory diagram of one group of successive frame is gathered
Picture;
Step 2:Orbital image is corrected, the trapezoidal track at side view visual angle is reduced into the parallel rail for overlooking visual angle
Road;
Step 3:The characteristic matching of orbital image is carried out, turnout, guard rail is excluded, finds target track;
Step 4:The picture that matching is completed is spliced, the complete image of target track is obtained;
Step 5:Marginalisation processing is carried out to complete orbital image, takes inward flange to obtain the appearance curve of track;
Step 6:Coordinate system is set up, will be moved to after the appearance curve scaling of track in coordinate system, create rail profiles bent
The two-dimensional map of line.
Fig. 2 shows heretofore described orbital image keystone model and correction result schematic diagram.In IMAQ
During, camera can produce trapezoidal distortion, it is necessary to carry out geometry to it using the visual angle laterally taken pictures, resulting orbital image
Correction, horizontal image is become by inclined image.According to described image geometric transformation model, if the A points on oblique photography 1 exist
Conformation on horizontal photo 2 is A0, coordinate of the A points in 0~xy of coordinate system is (x, y);A0Point is in coordinate system S~x0y0z0In
Coordinate is (x0,y0,z0).Then according to conformation equation, coordinate relation that can be between lead-out level photograph picture point corresponding with oblique aerial photograph
For:
Wherein ai、bi、ci(i=1,2,3) is constant, and by azimuth, element is determined, is calculated using the method for undetermined coefficients
Come.
According to the calibration model, the orbital image of distortion can be corrected to horizontal rail image, as shown in FIG..
Fig. 3 shows heretofore described orbital image splicing schematic diagram.Should have between the adjacent picture that camera is collected
There is lap, image can be spliced using lap, obtain a secondary complete image.In splicing, it is necessary to
The influence to image mosaic of turnout, guard rail is excluded according to characteristic matching, then by the trajectory diagram including straight rail, warp rail
As being spliced.According to industrial implementation case, overlaying graphics degree can be arranged between 0.4-0.7 so that splicing global error
Reduction.
Fig. 4 shows heretofore described two-dimensional map establishment and rail to instrumentation plan.Coordinate system is set up, by marginalisation
Rail profiles curve after processing is moved in coordinate system after zooming in and out, and obtains the two-dimensional map of track.This map needs meter
Calculate corresponding engineer's scale, it is assumed that the gauge at actually measured A points is a, keeps two-dimensional map scaling constant, calculates map
Gauge at middle A points
Then the engineer's scale of this width two-dimensional map isIn the rail of measure track any two points (2 points of A, B in such as figure)
Xiang Shi, calculates the chord length of AB points on map
Further according to map scale, the actual chord length for obtaining AB points isTherefore measurable any chord length
Rail to.Methods described measure long-chord rail to when, will not produce as traditional chord measurement measure rail to middle error be superimposed the problem of, carry
High measurement accuracy.
Similarly, the gauge of the outer arbitrfary point of A points on engineer's scale according to the map, measurable track, its measuring method belongs to non-and connect
Measurement is touched, precision increases.
With reference to Fig. 1 to Fig. 4 narration, below step shows to create rail profiles two-dimensional map simultaneously using image processing method
For measure rail to embodiment, it is as follows the step of the embodiment:
Step 1:Track is taken pictures, the orbital image of one group of successive frame is gathered;
Step 2:Using geometric correction model to being corrected to orbital image;
Step 3:Characteristic matching is carried out, turnout, guard rail is excluded, finds target track, overlaying graphics degree is arranged on 0.4-
Between 0.7, target track is spliced, the complete image of target track is obtained;
Step 4:Complete orbital image is subjected to marginalisation processing, the appearance curve of inner edges formation track is taken;
Step 5:Coordinate system is set up, rail profiles curve is implanted into coordinate system, rail profiles curve is created two-dimensionally
Figure;
Step 6:The gauge in somewhere on track is calculated in map, is contrasted with measured data, obtains map scale,
Engineer's scale, calculates the gauge of picture scope inner orbit and the rail of any chord length to parameter according to the map.
Claims (8)
1. a kind of creation method of the railroad track two-dimensional map based on image processing techniques, it is characterised in that including following step
Suddenly:
Step 1:Track is continuously shot, the orbital image of one group of successive frame is obtained;
Step 2:The picture of shooting is corrected by geometrical model, the track of trapezoidal distortion is reduced into parallel orbit;
Step 3:Characteristic matching is carried out to the orbital image after reduction, the target track for needing to measure is found;
Step 4:By splicing to the picture for having matched completion, the complete image of target track is obtained;
Step 5:Marginalisation processing is carried out to this width complete track image, the inward flange curve of track is obtained;
Step 6:Coordinate system is set up, the two-dimensional map of rail profiles curve is created.
2. according to the method described in claim 1, it is characterised in that in described step 1, being continuously shot to track, it is
By being installed on in-orbit inspection instrument in camera, in-orbit inspection instrument traveling process while being shot to track.
3. the geometrical model according to the method described in claim 1, it is characterised in that in described step 2, being corrected is:
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<msub>
<mi>x</mi>
<mn>0</mn>
</msub>
<mo>=</mo>
<mo>-</mo>
<mi>f</mi>
<mfrac>
<mrow>
<msub>
<mi>a</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>2</mn>
</msub>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>a</mi>
<mn>3</mn>
</msub>
<mi>f</mi>
</mrow>
<mrow>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>c</mi>
<mn>3</mn>
</msub>
<mi>f</mi>
</mrow>
</mfrac>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
<mo>=</mo>
<mo>-</mo>
<mi>f</mi>
<mfrac>
<mrow>
<msub>
<mi>b</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<msub>
<mi>b</mi>
<mn>2</mn>
</msub>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>b</mi>
<mn>3</mn>
</msub>
<mi>f</mi>
</mrow>
<mrow>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mi>x</mi>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>c</mi>
<mn>3</mn>
</msub>
<mi>f</mi>
</mrow>
</mfrac>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>z</mi>
<mn>0</mn>
</msub>
<mo>=</mo>
<mo>-</mo>
<mi>f</mi>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein, f is the focal length of camera used, and the vertical range of camera shooting point S to two pictures is all f, a in a modeli、bi、
ci(i=1,2,3) is constant, and by azimuth, element is determined, x, and y is the A points on the inclination picture of shooting in 0~xy of coordinate system
Coordinate, x0,y0,z0For the conformation A of A points on the horizontal picture after correction0Point is in coordinate system S~x0y0z0In coordinate.
4. according to the method described in claim 1, it is characterised in that the process of progress characteristic matching is in described step 3:
The characteristic point including marginal point, angle point, crosspoint is extracted first from adjacent two pictures, recycles similitude to enter
Row registration, obtains the joining relation of two width pictures;
If the content on first track picture around A points is similar to the content on the second pictures around B points, according to A,
B points are matched this two pictures;Judge that the similar method of content is by two row pixels of predetermined interval in the first pictures
Difference as feature templates, the second pictures same intervals calculating difference finds the minimum with first template sum of squares of deviations,
Similitude is used as at minimum;
Wherein the extracting method of characteristic point carries out feature extraction using Forstner operators, calculates pixel (i, j) surrounding gray scale
Difference absolute value be:
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<msub>
<mi>d</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mo>|</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>|</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>d</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mo>|</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>|</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>d</mi>
<mn>3</mn>
</msub>
<mo>=</mo>
<mo>|</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>-</mo>
<mn>1</mn>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>|</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>d</mi>
<mn>4</mn>
</msub>
<mo>=</mo>
<mo>|</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>|</mo>
</mtd>
</mtr>
</mtable>
</mfenced>
To given threshold value, if the value in above formula is both greater than threshold value, pixel is used as characteristic point.
5. according to the method described in claim 1, it is characterised in that in described step 4, when being spliced, overlaying graphics degree
For 0.4-0.7, that is, the accounting for needing the two pictures lap areas spliced is 40%-70%.
6. according to the method described in claim 1, it is characterised in that in described step 5, carrying out marginalisation processing, rail is obtained
The step of inward flange curve in road is:
1) spliced track picture is subjected to gaussian filtering, obtains the smoothed image after a vice processing.Wherein dimensional Gaussian letter
Several any first derivatives is noise filter;
2) amplitude and the direction of image gradient are calculated, the edge of image is detected;
Computational methods are as follows:
Amplitude
Direction
Wherein M (i, j) is the gray value of image, Mx(i, j) and My(i, j) is that the neighborhood of its transverse and longitudinal axle is poor.
3) range value of gradient is compared with default threshold value, excludes maximum point, make edge thinning.
7. according to the method described in claim 1, it is characterised in that in described step 6, the step of setting up coordinate system is:
Choose some particular point in picture and be set to the origin of coordinates, the x for determining coordinate, y-axis are oriented by map sheet so that two-dimensional map
With geodetic coordinates scalability;Wherein particular point is the point of the known coordinate information determined by track CPIII points and control net.
Wherein map sheet orientation is realized particular by four interior Marginal points of complete track picture, the image of four interior Marginal points
Coordinate is obtained from image, i.e. the four of entire image boundary point, is obtained after the theoretical geodetic coordinates of four Marginal points, using affine
The parsing relational model that transformation model is set up between geodetic coordinates and image coordinate;
Wherein affine Transform Model is:
<mrow>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msubsup>
<mi>x</mi>
<mi>i</mi>
<mo>&prime;</mo>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>y</mi>
<mi>i</mi>
<mo>&prime;</mo>
</msubsup>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>=</mo>
<mi>k</mi>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mi>&theta;</mi>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>s</mi>
<mi>i</mi>
<mi>n</mi>
<mi>&theta;</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mi>s</mi>
<mi>i</mi>
<mi>n</mi>
<mi>&theta;</mi>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mi>&theta;</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>y</mi>
<mi>j</mi>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>+</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>x</mi>
<mn>0</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, (x 'i,y'j) it is Marginal point geodetic coordinates, (xi,yj) it is Marginal point image coordinate, parameter k, θ, x0,y0For registration
Parameter, k is zoom factor, and θ is the anglec of rotation, x0,y0For translational movement.
8. a kind of gauge and rail based on track two-dimensional map are to measuring method, it is characterised in that:Appoint using in claim 1-5
The creation method of the railroad track two-dimensional map based on image processing techniques described in one, is surveyed in the track two-dimensional map of generation
The gauge of track and the rail of any chord length are measured to the measuring method comprises the following steps:
Step 1:The gauge of some specified point of map middle orbit is calculated, is compared with measured data, obtains the ratio of this width map
Example chi, is set to 1:k;
Step 2:On map calculate track it is any on any point gauge and any two points between rail to parameter, be set to
A, b;
Step 3:Passing ratio chi converts, that is, is capable of the rail between the gauge of accurately measuring track and any two points to actual parameter,
For ka, kb.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611156162.XA CN107085854A (en) | 2016-12-14 | 2016-12-14 | A kind of creation method of the railroad track two-dimensional map based on image processing techniques |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611156162.XA CN107085854A (en) | 2016-12-14 | 2016-12-14 | A kind of creation method of the railroad track two-dimensional map based on image processing techniques |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107085854A true CN107085854A (en) | 2017-08-22 |
Family
ID=59614087
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611156162.XA Pending CN107085854A (en) | 2016-12-14 | 2016-12-14 | A kind of creation method of the railroad track two-dimensional map based on image processing techniques |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107085854A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740609A (en) * | 2019-01-09 | 2019-05-10 | 银河水滴科技(北京)有限公司 | A kind of gauge detection method and device |
CN112017114A (en) * | 2020-06-08 | 2020-12-01 | 武汉精视遥测科技有限公司 | Method and system for splicing full image by using half image in tunnel detection |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104363822A (en) * | 2012-04-15 | 2015-02-18 | 天宝导航有限公司 | Image display improvements |
CN205327082U (en) * | 2015-12-01 | 2016-06-22 | 深圳大学 | Urban railway detection device based on integrated synchro control of multisensor |
CN205607332U (en) * | 2016-04-20 | 2016-09-28 | 武汉理工大学 | Measuring device is striden to bridge crane crane span structure based on machine vision |
-
2016
- 2016-12-14 CN CN201611156162.XA patent/CN107085854A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104363822A (en) * | 2012-04-15 | 2015-02-18 | 天宝导航有限公司 | Image display improvements |
CN205327082U (en) * | 2015-12-01 | 2016-06-22 | 深圳大学 | Urban railway detection device based on integrated synchro control of multisensor |
CN205607332U (en) * | 2016-04-20 | 2016-09-28 | 武汉理工大学 | Measuring device is striden to bridge crane crane span structure based on machine vision |
Non-Patent Citations (1)
Title |
---|
訾安琪: "基于SLAM的车辆运行轨迹算法研究", 《中国优秀硕士论文全文数据库 工程科技II辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740609A (en) * | 2019-01-09 | 2019-05-10 | 银河水滴科技(北京)有限公司 | A kind of gauge detection method and device |
CN112017114A (en) * | 2020-06-08 | 2020-12-01 | 武汉精视遥测科技有限公司 | Method and system for splicing full image by using half image in tunnel detection |
CN112017114B (en) * | 2020-06-08 | 2023-08-04 | 武汉精视遥测科技有限公司 | Method and system for splicing full images of half images in tunnel detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105699399B (en) | A kind of detection device and method of SMT masterplates quality | |
CN103761737B (en) | Robot motion's method of estimation based on dense optical flow | |
CN103593663B (en) | A kind of image position method of money forme | |
CN103729841B (en) | A kind of based on side's target model and the camera distortion bearing calibration of perspective projection | |
CN104575003B (en) | A kind of vehicle speed detection method based on traffic surveillance videos | |
CN106204544A (en) | A kind of automatically extract index point position and the method and system of profile in image | |
CN104156536A (en) | Visual quantitative calibration and analysis method for cutter abrasion of shield tunneling machine | |
CN102749047B (en) | Measuring method for size of roll bearing block | |
CN109685858A (en) | A kind of monocular cam online calibration method | |
CN104732482A (en) | Multi-resolution image stitching method based on control points | |
CN106996748A (en) | A kind of wheel footpath measuring method based on binocular vision | |
CN103366555B (en) | Aerial image-based traffic accident scene image rapid generation method and system | |
CN102609918A (en) | Image characteristic registration based geometrical fine correction method for aviation multispectral remote sensing image | |
CN106600592A (en) | Track long chord measurement method based on the splicing of continuous frame images | |
CN105118086A (en) | 3D point cloud data registering method and system in 3D-AOI device | |
CN105091748B (en) | Rail vehicle tolerance dimension measuring system | |
CN108833912A (en) | A kind of measurement method and system of video camera machine core optical axis center and field angle | |
CN106709944A (en) | Satellite remote sensing image registration method | |
CN103020967A (en) | Unmanned aerial vehicle aerial image accurate matching method based on island edge characteristics | |
CN104123725B (en) | A kind of computational methods of single line array camera homography matrix H | |
CN105387801A (en) | Subway tunnel segment dislocation quantity detection method | |
CN105550994A (en) | Satellite image based unmanned aerial vehicle image rapid and approximate splicing method | |
CN102141376A (en) | Auxiliary reference-based machine vision detection system and method | |
CN104180794B (en) | The disposal route in digital orthoimage garland region | |
CN109064448A (en) | Medium-and low-speed maglev F rail rail gap detection method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170822 |
|
RJ01 | Rejection of invention patent application after publication |