CN116167983A - Rail web alignment method, system and terminal based on minimum DTW distance - Google Patents

Rail web alignment method, system and terminal based on minimum DTW distance Download PDF

Info

Publication number
CN116167983A
CN116167983A CN202310045121.7A CN202310045121A CN116167983A CN 116167983 A CN116167983 A CN 116167983A CN 202310045121 A CN202310045121 A CN 202310045121A CN 116167983 A CN116167983 A CN 116167983A
Authority
CN
China
Prior art keywords
rail
profile
data
point
straight line
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
Application number
CN202310045121.7A
Other languages
Chinese (zh)
Inventor
王云龙
周蕾
王克文
张金鑫
李想
曾杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Tangyuan Electric Co Ltd
Original Assignee
Chengdu Tangyuan Electric Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chengdu Tangyuan Electric Co Ltd filed Critical Chengdu Tangyuan Electric Co Ltd
Priority to CN202310045121.7A priority Critical patent/CN116167983A/en
Publication of CN116167983A publication Critical patent/CN116167983A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30236—Traffic on road, railway or crossing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The invention discloses a rail web alignment method, a rail web alignment system and a rail web alignment terminal based on minimum DTW distance, which relate to the technical field of rail detection and have the technical scheme that: acquiring rail profile point cloud data comprising rail web and rail head; determining two first characteristic points and a fourth characteristic point which are positioned at the middle point, and establishing a midpoint straight line to obtain the angle of the midpoint straight line; determining a rotation angle according to an angle difference value between the midpoint straight line and the standard straight line in the reference profile; carrying out integral rotation on the rail profile to be aligned according to the rotation angle, and calculating translation parameters in the rotated rail profile; and searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile which is searched and adjusted and the reference profile, and selecting an adjustment result with the minimum DTW distance as a profile alignment result. According to the invention, the rail web data are utilized for alignment, and fine adjustment is performed in a searching mode after primary alignment, so that the alignment effect is more stable and accurate.

Description

Rail web alignment method, system and terminal based on minimum DTW distance
Technical Field
The invention relates to the technical field of track detection, in particular to a rail web alignment method, a rail web alignment system and a rail web terminal based on minimum DTW distance.
Background
In rail traffic, the safe operation of an electrified railway is closely related to the performance optimization problem of a steel rail. In a working mode with long-lasting operation and no backup, rail wear cannot be avoided. The method is an effective method for timely detecting and measuring related parameters such as rail abrasion and the like so as to guide the formulation of rail polishing strategies or the formulation of other maintenance strategies.
At present, steel rail abrasion detection is generally carried out by imaging steel rails through structured light, extracting steel rail profile point cloud data through an image processing technology, and calculating relevant parameters after aligning acquired profile data with reference profile data. Alignment is a serious problem in the whole process, and most of the currently adopted alignment modes use rail head information, and the modes are relatively unstable and inaccurate, because rail head areas are usually worn or extruded, and deformation with different degrees is generated, so that alignment fluctuation is large.
Therefore, how to research and design a rail web alignment method, system and terminal based on minimum DTW distance, which can overcome the defects, is a problem which needs to be solved urgently at present.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a rail web alignment method, a rail web alignment system and a terminal based on minimum DTW distance, which are used for alignment by using rail web data and fine-tuning in a searching mode after primary alignment, so that the alignment effect is more stable and accurate.
The technical aim of the invention is realized by the following technical scheme:
in a first aspect, a rail web alignment method based on minimum DTW distance is provided, comprising the steps of:
acquiring rail profile point cloud data comprising rail web and rail head, and dividing the data into left side data after segmentation and right side data after segmentation;
determining two first characteristic points and four characteristic points which are positioned at middle points according to the segmented left-side data and the segmented right-side data, establishing a midpoint straight line according to the first characteristic points and the fourth characteristic points, and analyzing to obtain angles of the midpoint straight line;
determining a rotation angle according to an angle difference value between the midpoint straight line and a standard straight line corresponding to the reference profile;
carrying out integral rotation on the rail profile to be aligned according to the rotation angle, and calculating translation parameters in the rotated rail profile according to the first characteristic point or the fourth characteristic point;
and searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile which is searched and adjusted and the reference profile, and selecting the adjustment result with the minimum DTW distance as the profile alignment result.
Further, the left-side data after segmentation and the right-side data after segmentation are formed by cutting after removing rail top data in the rail profile point cloud data.
Further, the determining process of the first feature point specifically includes:
calculating the distance between any two points in the segmented left data and the segmented right data;
and taking the midpoint of the two feature points corresponding to the smallest distance as a first feature point.
Further, the determining process of the fourth feature point specifically includes:
acquiring the arc radius of the lower part of the rail web;
drawing a circle by taking each data point in the segmented left data and the segmented right data as a circle center and the radius of the circular arc as the radius;
respectively selecting intersection points with maximum distribution density of the inner circle intersection points of the left side rail waist and the right side rail waist in a preset radius range;
taking the average value of all the intersection points in the intersection point set of the left rail web as a second characteristic point and taking the average value of all the intersection points in the intersection point set of the right rail web as a third characteristic point;
and taking the midpoint between the second characteristic point and the third characteristic point as a fourth characteristic point.
Further, the process of obtaining the angle of the midpoint straight line specifically includes:
calculating a slope value of the midpoint straight line according to the first characteristic point and the fourth characteristic point;
and carrying out arctangent solving on the slope value to obtain the angle of the midpoint straight line.
Further, the translation parameters include a lateral translation amount and a longitudinal translation amount;
the transverse translation amount is a transverse coordinate difference value of a first characteristic point corresponding to the rail profile to be aligned and the reference profile;
the longitudinal translation amount is a longitudinal coordinate difference value of a first characteristic point corresponding to the rail profile to be aligned and the reference profile.
Further, the process of searching and adjusting the initially aligned steel rail profile by using the DTW method specifically comprises the following steps:
setting an angle searching range and a step length;
rotating the rail profile which is aligned for the first time again according to the angle searching range and the step length;
and after rotation, translating by calculating translation parameters to obtain the adjusted profile data.
Further, the calculation formula of the DTW distance specifically includes:
Figure BDA0004055044370000021
DTW k ＝γ(I,J)
wherein γ (i, j) represents the cumulative distance;
Figure BDA0004055044370000022
representation D k The ith point in (b) and the ith point in the reference profilej points Norm j Is a Euclidean distance of (2); DTW (draw bench) k Represents the DTW distance for the kth time; I. j respectively represents D k And the total number of points in Norm.
In a second aspect, there is provided a rail web alignment system based on minimum DTW distance comprising:
the data acquisition module is used for acquiring the profile point cloud data of the steel rail comprising the rail web and the rail head and dividing the profile point cloud data into left data after segmentation and right data after segmentation;
the midpoint analysis module is used for determining two first characteristic points and four characteristic points which are positioned at middle points according to the segmented left-side data and the segmented right-side data, establishing a midpoint straight line according to the first characteristic points and the fourth characteristic points, and analyzing to obtain angles of the midpoint straight line;
the angle analysis module is used for determining a rotation angle according to an angle difference value between the midpoint straight line and a standard straight line corresponding to the reference profile;
the translation analysis module is used for integrally rotating the steel rail profile to be aligned according to the rotation angle, and calculating translation parameters according to the first characteristic point or the fourth characteristic point in the rotated steel rail profile;
and the alignment analysis module is used for searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile after searching and adjusting and the reference profile, and selecting the adjustment result with the minimum DTW distance as the profile alignment result.
In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the DTW distance-based minimum rail web alignment method according to any one of the first aspects when the program is executed.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the rail web alignment method based on the DTW with the minimum distance, the rail head is usually deformed due to abrasion and other reasons, the collected profile data is more stable, and the rail web is aligned with the reference profile, so that compared with the alignment by using the rail head data, the alignment is more stable and accurate; fine adjustment is performed in a searching mode after primary alignment, so that the alignment effect is stable and accurate;
2. the method takes the midpoint of two characteristic points corresponding to the minimum distance in the segmented left-side data and the segmented right-side data as a first characteristic point, and the characteristic point is more stable and easier to detect relative to other characteristic points;
3. the invention extracts the second characteristic point and the third characteristic point in a mode of solving the intersection point of the concentric circles, so that the characteristic point is extracted more stably, rapidly and accurately.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:
FIG. 1 is a flow chart in an embodiment of the invention;
FIG. 2 is a schematic view of rail profile point cloud data in an embodiment of the present invention;
FIG. 3 is a schematic view of point cloud data of a profile of a rail after rail head removal in an embodiment of the present invention;
FIG. 4 is a schematic view of a first feature point in an embodiment of the invention;
FIG. 5 is a schematic representation of the features of the lower arc of the web in an embodiment of the invention;
fig. 6 is a schematic diagram of a second feature point and a third feature point in an embodiment of the present invention;
fig. 7 is a system block diagram in an embodiment of the invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Example 1: the rail web alignment method based on minimum DTW distance, as shown in figure 1, comprises the following steps:
s1: acquiring rail profile point cloud data comprising rail web and rail head, and dividing the data into left side data after segmentation and right side data after segmentation;
s2: determining two first characteristic points and four characteristic points which are positioned at middle points according to the segmented left-side data and the segmented right-side data, establishing a midpoint straight line according to the first characteristic points and the fourth characteristic points, and analyzing to obtain angles of the midpoint straight line;
s3: determining a rotation angle according to an angle difference value between the midpoint straight line and a standard straight line corresponding to the reference profile;
s4: carrying out integral rotation on the rail profile to be aligned according to the rotation angle, and calculating translation parameters in the rotated rail profile according to the first characteristic point or the fourth characteristic point;
s5: and searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile which is searched and adjusted and the reference profile, and selecting the adjustment result with the minimum DTW distance as the profile alignment result.
1. First feature point detection
As shown in fig. 2 and 3, after the collected rail profile point cloud data including the web and the head is collected, the rail top data is removed first for facilitating subsequent calculation.
The steel rail profile point cloud data is divided into two parts, and the data is divided equally according to the number in the normal case, namely:
D＝[d 0 d 1 …d n …d N-1 ]
D L ＝[d 0 …d N/2 ]
D R ＝[d N/2+1 …d N-1 ]
wherein D represents the profile point cloud data of the steel rail with the rail top removed, and D n ＝(x n ，y n ) Represents the nth point in the data, (x) n ，y n ) Represents the abscissa, D of the point L Represents left data after segmentation, D R Indicating right data after segmentation.
And then calculating the distance between each point in the left data and the right data, wherein the midpoint of the two points with the smallest distance is the first characteristic point, namely:
Figure BDA0004055044370000041
Figure BDA0004055044370000042
Figure BDA0004055044370000043
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure BDA0004055044370000044
representing the coordinates of the two nearest points in the two-sided data, respectively, < >>
Figure BDA0004055044370000045
The abscissa indicating the i-th point of the left data,/, is shown>
Figure BDA0004055044370000046
Ordinate indicating the i-th point of the left data,/, respectively>
Figure BDA0004055044370000047
The abscissa indicating the j-th point of the left data, is->
Figure BDA0004055044370000048
Ordinate indicating the j-th point of the left data,/>
Figure BDA0004055044370000051
Respectively representing the abscissa and the ordinate of the first feature point, which is shown in fig. 4.
2. Second feature point and third feature point detection
As shown in fig. 5, the rail web lower portion generally has an arc of radius r in the rail profile.
Then, taking the second feature point detection as an example, starting from the data point at the waist bottom of the left side rail, drawing a circle by taking each data point as a circle center and r as a radius, wherein two circles in succession inevitably have intersection points, and taking the mean coordinate of the intersection points nearby at the most dense position of the intersection points at the outer side of the rail waist as the second feature point, namely:
Figure BDA0004055044370000052
wherein u is i Represents the intersection of the outer sides of the rail web of the ith circle and the (i-1) th circle, U (■) represents an operator for obtaining the intersection of the two circles,
Figure BDA0004055044370000053
expressed in dots +.>
Figure BDA0004055044370000054
Is a circle with a radius r.
Order the
Figure BDA0004055044370000055
Wherein Cnt (u) i Z) represents the calculation at the intersection point u i Where v represents the set of all circle intersections where the number of circle intersections is greatest.
Finally, the second feature point can be obtained by calculating the average value of v, namely:
Figure BDA0004055044370000056
Figure BDA0004055044370000057
representing the second feature point coordinates, mean (■) represents the averaging operator.
Similarly, the third feature point can be obtained by drawing a circle from the right and obtaining the average value of the intersection points
Figure BDA0004055044370000058
As shown in fig. 6.
3. Calculating rotation translation parameters and performing primary rotation translation
First, calculating the midpoint between the second feature point and the third feature point, and recording the midpoint as a fourth feature point, namely:
Figure BDA0004055044370000059
Figure BDA00040550443700000510
determining a midpoint straight line through the first characteristic point and the fourth characteristic point, wherein the angle is as follows:
Figure BDA00040550443700000511
the angle of the corresponding midpoint line in the reference profile can be determined directly manually, noted as θ Norm Then, the rotation angle θ can be obtained by:
θ＝θ Norm -θ D 。
firstly, carrying out integral rotation on the steel rail profile to be aligned through a rotation angle theta, and solving translation parameters in the rotated profile by utilizing first characteristic points, namely:
Figure BDA0004055044370000061
Figure BDA0004055044370000062
wherein t is x ，t y Respectively representing the transverse translation amount and the longitudinal translation amount;
Figure BDA0004055044370000063
respectively in the reference profileAnd the abscissa and the ordinate of the first characteristic point.
4. Rotation translation fine tuning based on DTW
Since one translational rotation may not be aligned precisely, fine tuning is performed by searching for the minimum DTW distance, and each fine tuning is based on the initial alignment and not on the previous fine tuning. DTW is a dynamic time warping method.
The angle search range and step size are first set and can be expressed as
Figure BDA0004055044370000068
At the kth fine tuning, by
Figure BDA0004055044370000064
Rotating the initially aligned profile again, translating the initially aligned profile by calculating the translation amount after rotating, and recording the finely adjusted profile data as D k 。
And calculating the DTW distance between the profile after fine adjustment and the reference profile, namely:
Figure BDA0004055044370000065
DTW k ＝γ(I,J)
wherein gamma (i, j) represents the cumulative distance,
Figure BDA0004055044370000066
representation D k The ith point in (a) and the jth point in the reference profile, nor j Is the Euclidean distance, DTW k Represents the DTW distance of the kth time, I, J represent D respectively k And the total number of points in Norm.
For all of
Figure BDA0004055044370000067
After calculating the DTW distance, selecting a fine adjustment result corresponding to the minimum DTW as profile alignment output, namely:
D * ＝argmin k DTW k 。
example 2: the rail web alignment system based on minimum DTW distance is used for realizing the rail web alignment method described in the embodiment 1, and comprises a data acquisition module, a midpoint analysis module, an angle analysis module, a translation analysis module and an alignment analysis module as shown in fig. 7.
The data acquisition module is used for acquiring the data of the profile point cloud of the steel rail comprising the rail web and the rail head and dividing the data into left data after segmentation and right data after segmentation; the midpoint analysis module is used for determining two first characteristic points and four characteristic points which are positioned at middle points according to the segmented left-side data and the segmented right-side data, establishing a midpoint straight line according to the first characteristic points and the fourth characteristic points, and analyzing to obtain angles of the midpoint straight line; the angle analysis module is used for determining a rotation angle according to an angle difference value between the midpoint straight line and a standard straight line corresponding to the reference profile; the translation analysis module is used for integrally rotating the steel rail profile to be aligned according to the rotation angle, and calculating translation parameters according to the first characteristic point or the fourth characteristic point in the rotated steel rail profile; and the alignment analysis module is used for searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile after searching and adjusting and the reference profile, and selecting the adjustment result with the minimum DTW distance as the profile alignment result.
Working principle: the rail head is usually deformed due to abrasion and other reasons, the acquired profile data are more stable, and the rail web data are aligned with the reference profile by adopting the rail web of the steel rail, so that compared with the alignment by utilizing the rail head data, the alignment is more stable and accurate; fine adjustment is performed in a searching mode after primary alignment, so that the alignment effect is stable and accurate; in addition, the midpoint of two feature points corresponding to the minimum distance between the segmented left data and the segmented right data is used as a first feature point, and the feature point is more stable and easier to detect relative to other feature points; in addition, the second characteristic point and the third characteristic point are extracted in a mode of solving the intersection point by the concentric circles, so that the characteristic points are extracted more stably, rapidly and accurately.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the invention is not limited to the particular embodiments disclosed, but is intended to cover all modifications, equivalents, alternatives, and improvements within the spirit and principles of the invention.

Claims (10)

1. The rail web alignment method based on the minimum DTW distance is characterized by comprising the following steps of:
acquiring rail profile point cloud data comprising rail web and rail head, and dividing the data into left side data after segmentation and right side data after segmentation;
determining two first characteristic points and four characteristic points which are positioned at middle points according to the segmented left-side data and the segmented right-side data, establishing a midpoint straight line according to the first characteristic points and the fourth characteristic points, and analyzing to obtain angles of the midpoint straight line;
determining a rotation angle according to an angle difference value between the midpoint straight line and a standard straight line corresponding to the reference profile;
carrying out integral rotation on the rail profile to be aligned according to the rotation angle, and calculating translation parameters in the rotated rail profile according to the first characteristic point or the fourth characteristic point;
and searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile which is searched and adjusted and the reference profile, and selecting the adjustment result with the minimum DTW distance as the profile alignment result.
2. The DTW distance minimum-based rail web alignment method of claim 1, wherein the split left-side data and split right-side data are formed by removing rail top data from rail profile point cloud data and then splitting.
3. The method for aligning rail web of steel rail based on minimum DTW distance according to claim 1, wherein the determining process of the first feature point specifically comprises:
calculating the distance between any two points in the segmented left data and the segmented right data;
and taking the midpoint of the two feature points corresponding to the smallest distance as a first feature point.
4. The method for aligning rail web of steel rail based on minimum DTW distance according to claim 1, wherein the determining process of the fourth feature point specifically comprises:
acquiring the arc radius of the lower part of the rail web;
drawing a circle by taking each data point in the segmented left data and the segmented right data as a circle center and the radius of the circular arc as the radius;
respectively selecting intersection points with maximum distribution density of the inner circle intersection points of the left side rail waist and the right side rail waist in a preset radius range;
taking the average value of all the intersection points in the intersection point set of the left rail web as a second characteristic point and taking the average value of all the intersection points in the intersection point set of the right rail web as a third characteristic point;
and taking the midpoint between the second characteristic point and the third characteristic point as a fourth characteristic point.
5. The method for aligning rail web of steel rail based on minimum DTW distance according to claim 1, wherein the angle obtaining process of the midpoint straight line specifically comprises the following steps:
calculating a slope value of the midpoint straight line according to the first characteristic point and the fourth characteristic point;
and carrying out arctangent solving on the slope value to obtain the angle of the midpoint straight line.
6. The DTW distance minimum based rail web alignment method of claim 1, wherein the translation parameters include a lateral translation amount and a longitudinal translation amount;
the transverse translation amount is a transverse coordinate difference value of a first characteristic point corresponding to the rail profile to be aligned and the reference profile;
the longitudinal translation amount is a longitudinal coordinate difference value of a first characteristic point corresponding to the rail profile to be aligned and the reference profile.
7. The method for aligning rail web of steel rail based on minimum DTW distance according to claim 1, wherein the process of performing search adjustment on the profile of the steel rail which is initially aligned by using the DTW method specifically comprises the following steps:
setting an angle searching range and a step length;
rotating the rail profile which is aligned for the first time again according to the angle searching range and the step length;
and after rotation, translating by calculating translation parameters to obtain the adjusted profile data.
8. The rail web alignment method based on minimum DTW distance according to any one of claims 1 to 7, wherein the calculation formula of the DTW distance is specifically:
Figure FDA0004055044360000021
DTW k ＝γ(I,J)
wherein γ (i, j) represents the cumulative distance;
Figure FDA0004055044360000022
representation D k The ith point in (a) and the jth point in the reference profile, nor j Is a Euclidean distance of (2); DTW (draw bench) k Represents the DTW distance for the kth time; I. j respectively represents D k And the total number of points in Norm.
9. Rail web alignment system based on minimum DTW distance, characterized by including:
the data acquisition module is used for acquiring the profile point cloud data of the steel rail comprising the rail web and the rail head and dividing the profile point cloud data into left data after segmentation and right data after segmentation;
the midpoint analysis module is used for determining two first characteristic points and four characteristic points which are positioned at middle points according to the segmented left-side data and the segmented right-side data, establishing a midpoint straight line according to the first characteristic points and the fourth characteristic points, and analyzing to obtain angles of the midpoint straight line;
the angle analysis module is used for determining a rotation angle according to an angle difference value between the midpoint straight line and a standard straight line corresponding to the reference profile;
the translation analysis module is used for integrally rotating the steel rail profile to be aligned according to the rotation angle, and calculating translation parameters according to the first characteristic point or the fourth characteristic point in the rotated steel rail profile;
and the alignment analysis module is used for searching and adjusting the rail profile which is aligned for the first time by using a DTW method, analyzing the DTW distance between the rail profile after searching and adjusting and the reference profile, and selecting the adjustment result with the minimum DTW distance as the profile alignment result.
10. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the DTW distance based minimum rail web alignment method as claimed in any one of claims 1 to 8 when the program is executed by the processor.
CN202310045121.7A 2023-01-30 2023-01-30 Rail web alignment method, system and terminal based on minimum DTW distance Pending CN116167983A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310045121.7A CN116167983A (en) 2023-01-30 2023-01-30 Rail web alignment method, system and terminal based on minimum DTW distance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310045121.7A CN116167983A (en) 2023-01-30 2023-01-30 Rail web alignment method, system and terminal based on minimum DTW distance

Publications (1)

Publication Number Publication Date
CN116167983A true CN116167983A (en) 2023-05-26

Family

ID=86419436

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310045121.7A Pending CN116167983A (en) 2023-01-30 2023-01-30 Rail web alignment method, system and terminal based on minimum DTW distance

Country Status (1)

Country Link
CN (1) CN116167983A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117611752A (en) * 2024-01-22 2024-02-27 卓世未来(成都)科技有限公司 Method and system for generating 3D model of digital person

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117611752A (en) * 2024-01-22 2024-02-27 卓世未来(成都)科技有限公司 Method and system for generating 3D model of digital person
CN117611752B (en) * 2024-01-22 2024-04-02 卓世未来(成都)科技有限公司 Method and system for generating 3D model of digital person

Similar Documents

Publication Publication Date Title
US8078025B2 (en) Vehicle dynamic measurement device and method for comprehensive parameters of rail wear
CN104101600B (en) Cross Section of CC Billet testing of small cracks method
US20110138505A1 (en) Scanning probe microscopy employing correlation pattern recognition
WO2023045299A1 (en) Road surface technical condition detection method and device based on three-dimensional contour
CN102135417A (en) Full-automatic three-dimension characteristic extracting method
CN109059775B (en) Steel rail abrasion detection method with image edge extraction step
CN108177660B (en) Steel rail abrasion detection method with laser image processing step
CN116167983A (en) Rail web alignment method, system and terminal based on minimum DTW distance
CN113340909B (en) Glue line defect detection method based on machine vision
CN110211178B (en) Pointer instrument identification method using projection calculation
CN112991287B (en) Automatic indentation measurement method based on full convolution neural network
Qin et al. Research on automatic monitoring method of face milling cutter wear based on dynamic image sequence
US20230258445A1 (en) Three-dimensional (3d) structured light camera based method and system for measuring gap of vehicle body
CN107388991A (en) A kind of more fillet axial workpiece radius of corner measuring methods in end face
CN112395809A (en) Method for detecting surface vibration line defects of machined part
CN110189419B (en) Vehicle-mounted Lidar steel rail point cloud extraction method based on generalized neighborhood height difference
CN113947583A (en) Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image
Chen et al. Tool wear monitoring based on the combination of machine vision and acoustic emission
Póka et al. A robust digital image processing method for measuring the planar burr length at milling
CN112950562A (en) Fastener detection algorithm based on line structured light
CN116625270A (en) Machine vision-based full-automatic detection system and method for precisely turned workpiece
CN111415348A (en) Method for extracting characteristics of bubbles in automobile brake pipeline
CN113096090B (en) End face gap visual measurement method with chamfer, device, equipment and storage medium
CN113240629B (en) Edge-based image matching narrow-gap weld initial point positioning device and method
CN110021027B (en) Edge cutting point calculation method based on binocular vision

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