CN114693619A - Rigid contact net abrasion detection method, equipment and storage medium - Google Patents
Rigid contact net abrasion detection method, equipment and storage medium Download PDFInfo
- Publication number
- CN114693619A CN114693619A CN202210273351.4A CN202210273351A CN114693619A CN 114693619 A CN114693619 A CN 114693619A CN 202210273351 A CN202210273351 A CN 202210273351A CN 114693619 A CN114693619 A CN 114693619A
- Authority
- CN
- China
- Prior art keywords
- contact line
- point
- point cloud
- cloud data
- busbar
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application belongs to the technical field of image processing, and particularly relates to a rigid contact net abrasion detection method, equipment and a storage medium, wherein the method comprises the following steps: acquiring a depth image to be detected; converting each line of depth image data into two-dimensional point cloud data; screening contact line point cloud data and bus bar groove point cloud data from the two-dimensional point cloud data based on a preset threshold; based on contact line point cloud data, obtaining a left end point and a right end point of a contact line surface through a k-mean clustering algorithm; matching the busbar groove point cloud data with corresponding template point cloud data in a busbar template and a contact line to determine a matching transformation relation; obtaining contact line matching points matched with the left end point and the right end point of the surface of the contact line based on the matching transformation relation; and obtaining the detection result of the wear of the contact line system based on the contact line matching point and the intersection point of the contact line and the busbar in the contact line and busbar template. The method can accurately and comprehensively detect the abrasion of the contact line.
Description
Technical Field
The application belongs to the technical field of image processing, and particularly relates to a rigid contact net abrasion detection method.
Background
The rigid overhead contact system is used as an important component of the urban rail transit traction power supply system and is directly related to whether the subway can run safely and reliably. At present, contact wires of part of special sections (an electric bus outbound accelerating section, an anchor section joint, a section insulator and the like) of an existing running line in China have serious abrasion problems, and the probability of accidents in the driving process is increased, so that the abrasion degree of a contact net needs to be detected so as to replace the contact wires in time.
The existing wear detection scheme for the contact line utilizes the characteristics that the reflectivity of the section to light is stronger than that of the rest arc-shaped parts of the contact line and the wear edge of the contact line generates obvious gradient change, a monocular camera is adopted to shoot an image of the contact line from bottom to top, and the outline information of the wear edge at the bottom of the contact line is extracted based on methods such as image enhancement, image analysis, edge detection, morphological processing and the like, so that the wear condition of the contact line is analyzed. Besides the common monocular camera scheme, a part of research adopts a binocular vision scheme, and the bottom abrasion information is further analyzed by acquiring the coordinate information of two points on the edge of the bottom based on a binocular ranging technology and a triangular imaging principle.
However, both the current monocular and binocular camera solutions only utilize information about the contact line wear face, and assume that the wear face is smooth and uniform, approaching a plane, which ignores the characteristic information about the middle area of the wear face. Meanwhile, conductive grease, carbon dust, dust and the like in a real environment are adsorbed on the side surface of the contact line, so that the intersection point of the contact line and the busbar cannot be shot directly, and the abrasion allowance cannot be measured.
Therefore, how to accurately and comprehensively detect the abrasion of the contact line becomes a problem to be solved urgently.
Disclosure of Invention
Technical problem to be solved
In view of the above-mentioned shortcomings and drawbacks of the prior art, the present application provides a rigid catenary wear detection method, apparatus, and readable storage medium.
(II) technical scheme
In order to achieve the purpose, the technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a method for detecting abrasion of a rigid catenary, where the method includes:
s10, acquiring depth images of the contact line and the busbar to be detected, and taking the acquired depth images as depth images to be detected;
s20, converting each line of depth image data in the depth image to be detected into two-dimensional point cloud data; screening the two-dimensional point cloud data based on a preset threshold value to obtain contact line point cloud data and bus bar groove point cloud data;
s30, based on the contact line point cloud data, obtaining a left end point and a right end point of the contact line surface through a k-mean clustering algorithm;
s40, matching the busbar groove point cloud data with pre-established contact line and corresponding template point cloud data in a busbar template to determine a matching transformation relation;
s50, obtaining contact line matching points, matched with the left end point and the right end point of the contact line surface, in the contact line and busbar template based on the matching transformation relation;
and S60, obtaining a contact net abrasion detection result based on the contact line matching point and the intersection point of the contact line and the busbar in the busbar template.
Optionally, S10 includes:
s11, acquiring initial depth images of the contact line and the bus bar acquired by the line structured light camera;
s12, carrying out median filtering on the initial depth image to obtain a depth image to be detected, wherein the median filtering method comprises the following steps:
setting a window with the size of (2k +1) multiplied by 1, and performing sliding window operation with the step length of 1 on the window along the X direction and the Y direction of the initial depth image respectively;
and taking the median of the gray values of all pixels in the current window as the gray value of the center point of the current window.
Optionally, S20 further includes removing outliers in the two-dimensional point cloud data by statistical filtering, where the statistical filtering method includes:
traversing all the point cloud data, and calculating the average distance between each point and the nearest point with the preset number n;
calculating the mean value and standard deviation of all average distances and setting a distance threshold value Dmax
Dmax＝μ+α×δ；
Where μ is the mean of all mean distances, δ is the standard deviation of all mean distances, and α is the distance threshold parameter
Traversing all point clouds, and eliminating n adjacent points with average distance larger than DmaxPoint (2) of (c).
Optionally, screening the two-dimensional point cloud data based on a preset threshold to obtain contact line point cloud data, including:
determining the maximum value Y of the two-dimensional point cloud data in the Y directionmax；
Contact line point cloud data for screening out contact line surfaces based on preset depth threshold T
As shown in the formula:
wherein C is all two-dimensional point cloud data, and p is in the point cloud dataA point, pyThe coordinate value of the point cloud data in the y direction is shown.
Optionally, S30 includes:
s31, respectively carrying out first-order difference and second-order difference operation on the contact line point cloud data along the X direction, and calculating the curvature of the contact line point cloud data in the X direction through the following formula:
wherein f isx' is the result of a first order difference operation, fx"is the second order difference operation result;
and S32, selecting the point cloud data with the maximum preset number in the curvature values, clustering by applying a k-mean clustering algorithm, and taking the two obtained clustering centers as the left end point and the right end point of the contact line surface.
Optionally, S40 includes:
s41, taking the busbar groove point cloud as a point cloud to be matched, calculating the closest points of each point in the contact line and the busbar template in the point cloud to be matched, and forming a point pair;
s42, calculating a rotation matrix and a translation matrix;
s43, converting the contact line and the point cloud in the busbar template through a rotation matrix and a translation matrix to obtain a converted template point cloud;
s44, calculating an error function by:
wherein n is the number of nearest neighbor point pairs, piFor the point to be matched in the ith pair of nearest neighbors, qiTemplate points in the ith pair of nearest neighbor points;
s45, repeating S42-S44 until the error function is smaller than the set error threshold or the set iteration number is reached;
and S46, taking the rotation matrix and the translation matrix obtained in the last iteration as matching matrices.
Optionally, S60 includes:
s61, respectively calculating a contact surface width, a wear allowance and an eccentric wear angle based on the contact line matching point and the intersection point of the contact line and the busbar in the busbar template, wherein the contact surface width is equal to the Euclidean distance between two points of the contact line matching point, the wear allowance is equal to the y-direction distance from the intersection point of the contact line and the busbar to the farthest point of the contact line matching point, and the eccentric wear angle is equal to the included angle between the horizontal line and the connecting line between the two points of the contact line matching point;
and S62, taking the contact surface width, the abrasion allowance and the eccentric wear angle as the detection result of the contact net abrasion.
In a second aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the rigid catenary wear detection method of any of the first aspects above.
In a third aspect, the present embodiments provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the rigid catenary wear detection method according to any one of the above first aspects.
(III) advantageous effects
The beneficial effect of this application is: the application provides a rigid contact net abrasion detection method, equipment and a readable storage medium, wherein the method comprises the following steps: acquiring a depth image to be detected; converting each line of depth image data into two-dimensional point cloud data; screening contact line point cloud data and bus bar groove point cloud data from the two-dimensional point cloud data based on a preset threshold; based on contact line point cloud data, obtaining a left end point and a right end point of a contact line surface through a k-mean clustering algorithm; matching the busbar groove point cloud data with corresponding template point cloud data in a busbar template and a contact line to determine a matching transformation relation; obtaining contact line matching points matched with the left end point and the right end point of the surface of the contact line based on the matching transformation relation; and obtaining the detection result of the wear of the contact line system based on the contact line matching point and the intersection point of the contact line and the busbar in the contact line and busbar template. The method can accurately and comprehensively detect the abrasion of the contact line, effectively adapt to the real field environment, and improve the low measurement precision.
Drawings
The application is described with the aid of the following figures:
fig. 1 is a schematic flow chart of a method for detecting wear of a rigid catenary in an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for detecting wear in a rigid catenary in another embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a line structured light camera shooting the bottom of a bus carrying a contact line according to another embodiment of the present disclosure;
FIG. 4 is an exemplary illustration of a depth image in another embodiment of the present application;
FIG. 5 is a diagram illustrating an example median filtering process in another embodiment of the present application;
FIG. 6 is an exemplary illustration of positions of feature points in another embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Description of reference numerals:
1-bus, 2-contact line, 3-line structured light camera.
Detailed Description
For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings. It is to be understood that the following specific examples are illustrative of the invention only and are not to be construed as limiting the invention. In addition, it should be noted that, in the case of no conflict, the embodiments and features in the embodiments in the present application may be combined with each other; for convenience of description, only portions related to the invention are shown in the drawings.
Example one
Fig. 1 is a schematic flow chart of a method for detecting wear of a rigid catenary in an embodiment of the present application, and as shown in fig. 1, the method for detecting wear of a rigid catenary in the embodiment includes:
s10, acquiring depth images of the contact line and the busbar to be detected, and taking the acquired depth images as depth images to be detected;
s20, converting depth image data of each line in the depth image to be detected into two-dimensional point cloud data; screening contact line point cloud data and bus bar groove point cloud data from the two-dimensional point cloud data based on a preset threshold;
s30, based on the contact line point cloud data, obtaining the left end point and the right end point of the contact line surface through a k-mean clustering algorithm;
s40, matching the busbar groove point cloud data with pre-established contact line and corresponding template point cloud data in a busbar template to determine a matching transformation relation;
s50, obtaining contact line matching points of the contact line and the busbar template, which are matched with the left end point and the right end point of the surface of the contact line, based on the matching transformation relation;
and S60, obtaining the detection result of the wear of the contact net based on the contact line matching point and the intersection point of the contact line and the busbar in the busbar template.
The rigid contact net abrasion detection method is suitable for real site environments, can effectively cope with complex scenes of real rigid contact nets, effectively solves the problem that direct measurement of a camera is easily influenced by oil stains, dust and the like, accurately and comprehensively detects abrasion of contact lines, and has the advantages of higher measurement precision, higher speed and better robustness.
In order to better understand the present invention, the steps in the present embodiment are explained below.
In this embodiment, S10 may include:
and S11, acquiring initial depth images of the contact wire and the bus bar acquired by the line structured light camera.
The depth image may also be acquired by a binocular camera, and the specific acquisition mode is not specifically limited in the present invention.
S12, carrying out median filtering on the initial depth image to obtain a depth image to be detected, wherein the median filtering method comprises the following steps:
setting a window with the size of (2k +1) multiplied by 1, and performing sliding window operation with the step length of 1 on the window along the X direction and the Y direction of the initial depth image respectively;
taking the median of the gray values of all pixels in the current window as the gray value of the center point of the current window, namely
v(x,y)＝mid{u(x,y-k),u(x,y-k+1),u(x,y-k+2),...,u(x,y+k)},u(x,y)∈I
Wherein, I is the initial depth image, and u is any point on the image I.
In the present embodiment, the axial direction of the contact line is defined as the Y direction, and the radial direction of the contact line parallel to the horizontal plane is defined as the X direction.
In this embodiment, S20 may further include removing outliers in the two-dimensional point cloud data by statistical filtering, where the statistical filtering method includes:
traversing all the point cloud data, and calculating the average distance between each point and the nearest point with the preset number n;
calculating the mean value and standard deviation of all average distances and setting a distance threshold value Dmax
Dmax＝μ+α×δ；
Wherein mu is the mean value of all average distances, delta is the standard deviation of all average distances, and alpha is a distance threshold parameter;
traversing all point clouds, and eliminating n adjacent points with average distance larger than DmaxPoint (2) of (c).
In this embodiment, screening contact line point cloud data from two-dimensional point cloud data based on a preset threshold includes:
determining the maximum value Y of the two-dimensional point cloud data in the Y directionmax；
Contact line point cloud data for screening out contact line surfaces based on preset depth threshold T
As shown in the formula:
wherein C is all two-dimensional point cloud data, p is one point in the point cloud data, and p isyThe coordinate value of the point cloud data in the y direction is shown.
In this embodiment, S30 includes:
s31, respectively carrying out first-order difference and second-order difference operation on the contact line point cloud data along the X direction, and calculating the curvature of the contact line point cloud data in the X direction through the following formula:
wherein f isx' is the result of a first order difference operation, fx"is the second order difference operation result;
and S32, selecting the point cloud data with the maximum preset number in the curvature values, clustering by applying a k-mean clustering algorithm, and taking the two obtained clustering centers as the left end point and the right end point of the contact line surface.
Specifically, the k-mean clustering algorithm comprises the following steps:
a1, selecting initialized k points as initial clustering centers ai,i∈[1,k]；
A2, calculating the distance from each point to k cluster centers, and assigning it to the class c corresponding to the cluster center with the smallest distancei,i∈[1,k]；
A3, recalculating the cluster center for each class:
wherein, aiAs cluster center of class i, ciAll points belonging to class i.
A4, repeating the above operations A2 and A3 until the error value calculated according to the following error function is less than the set error threshold value, or the set iteration number is reached,
wherein N represents ciThe number of points in the class.
In this embodiment, in S40, an Iterative closest Point (Iterative closest Point) algorithm is used for two-dimensional Point cloud template matching, and the basic principle is to find the closest Point of each Point in the template Point cloud in the Point cloud data to be matched, and calculate optimal matching parameters R and t to minimize an error function. The specific process comprises the following steps:
s41, taking the busbar groove point cloud as the point cloud to be matched, calculating the nearest points of each point in the contact line and the busbar template in the point cloud to be matched, and forming a point pair;
s42, calculating a rotation matrix and a translation matrix;
s43, converting the point cloud in the contact line and the busbar template through the rotation matrix and the translation matrix to obtain converted template point cloud;
s44, calculating an error function by:
wherein n is the number of nearest neighbor point pairs, piFor the point to be matched in the ith pair of nearest neighbors, qiTemplate points in the ith pair of nearest neighbor points;
s45, repeating S42-S44 until the error function is smaller than the set error threshold or the set iteration number is reached;
and S46, taking the rotation matrix and the translation matrix obtained in the last iteration as matching matrices.
In this embodiment, S60 includes:
s61, respectively calculating a contact surface width, a wear allowance and an eccentric wear angle based on a contact line matching point, a contact line and a junction point of the contact line and a busbar in a busbar template, wherein the contact surface width is equal to the Euclidean distance between two points of the contact line matching point, the wear allowance is equal to the y-direction distance from the junction point of the contact line and the busbar to the farthest point of the contact line matching point, and the eccentric wear angle is equal to the included angle between the horizontal line and the connecting line between the two points of the contact line matching point;
and S62, taking the contact surface width, the abrasion allowance and the eccentric wear angle as the detection result of the contact net abrasion.
Example two
Fig. 2 is a schematic flow chart of a method for detecting wear of a rigid catenary in another embodiment of the present application, and this embodiment describes in detail a specific implementation process of this embodiment on the basis of the first embodiment. As shown in fig. 2, the method may include:
s1, shooting the contact line and the bus bar to obtain a depth image;
s2, carrying out Y-median filtering on the acquired image along the vertical direction;
s3, selecting a line of image data, converting the line of image data into two-dimensional point cloud data, and performing twice statistical filtering to obtain C;
s4, screening point cloud data of the contact line surface
And obtaining the left and right end points P of the contact line surfaceA、PB；
S5, respectively screening the point cloud data C at the bus bar groove of the real data and the template data according to the distance between the point cloud data C and the contact line centerG、CG T；
S6, bus bar groove point cloud data C based on real data and template dataG、CG TMatching a two-dimensional point cloud template to obtain transformation matrixes R and t;
s7, calculating two end points P of the contact line surface according to the transformation matrixes R and tA、PBTransformed point PA’、PB’；
S8, converting the surface of the contact line in the real data into a point PA’、PB', the junction Q of the contact line and the bus bar in the sum template dataTAnd respectively calculating to obtain the contact surface width, the abrasion allowance and the eccentric wear angle as characteristic points.
The respective steps will be specifically described below.
Fig. 3 is a schematic diagram of a line structured light camera shooting the bottom of a bus carrying a contact line according to another embodiment of the present application, as shown in fig. 3, in step S1, an initial depth image is obtained by providing a rail moving device on the bus, and the device can move along the bus. The device is obtained by imaging the bottom of the bus bar 1 on which the contact wire 2 is mounted, using a 3D line structured optical camera 3. Fig. 4 shows that the corresponding depth image I is obtained, and fig. 4 is an exemplary diagram of a depth image in another embodiment of the present application.
In S2, when performing median filtering, k is 1, the size of the sliding window is 3 × 1, fig. 5 is an exemplary diagram of a median filtering process in another embodiment of the present application, and as shown in fig. 5, the median filtering result of 31, 22, and 7 is 22. The window is turned downwards to obtain the filtering results 22, 22 and 29 in sequence.
In S3, when performing statistical filtering twice, the number n of the nearest neighboring points is 20 and 10, and α is 2 and 1, respectively.
In S4, the first order difference and the second order difference in the X direction are calculated
Curvature in the X direction; selecting N (20) points with the maximum curvature value, applying k-mean clustering (class 2) to obtain two class centers, namely the left end point and the right end point P of the contact line surfaceA、PBFig. 6 is an exemplary diagram of positions of feature points in another embodiment of the present application, and as shown in fig. 6, dots are left and right endpoints.
In S5, the point cloud data C at the bus bar groove of the real data and the template data are respectively screened according to the distance interval gamma between the bus bar groove and the center of the contact lineG、CG TAs shown in FIG. 6And as shown, the circle area is point cloud data at the groove of the busbar.
In S6, the template matching method uses an iterative closest point algorithm.
In S8, the point P after surface transformation is passed through the contact line in the real dataA’、PB', the junction Q of the contact line and the bus bar in the sum template dataT(shown as square points in figure 6), calculating the contact surface width, the abrasion allowance and the eccentric wear angle respectively, wherein the contact surface width is equal to the point PA’、PBThe Euclidean distance of' the wear margin equals point QTTo point PA’、PB' farthest y-direction distance, eccentric wear angle equal to point PA’、PB' angle of line to horizontal.
The method provided by the invention is based on the acquisition of a depth image by a 3D structured light camera, the data of a busbar and a contact line are denoised by using Y-median filtering and statistical filtering, the characteristic end points of the contact line are extracted by combining the surface curvature and K-means clustering of the contact line, and the contact line abrasion parameters including the contact surface width, the abrasion allowance and the eccentric abrasion angle are measured by a template matching method, so that the problems that the existing contact line abrasion detection method cannot adapt to the real field environment and the measurement precision is low are solved.
EXAMPLE III
A second aspect of the present application provides, by way of a third embodiment, an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the steps of the method for detecting wear of a rigid catenary as in any one of the above embodiments.
Fig. 7 is a schematic architecture diagram of an electronic device in another embodiment of the present application.
The electronic device shown in fig. 7 may include: at least one processor 101, at least one memory 102, at least one network interface 104, and other user interfaces 103. The various components in the electronic device are coupled together by a bus system 105. It is understood that the bus system 105 is used to enable communications among the components. The bus system 105 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 105 in FIG. 7.
The user interface 103 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball (trackball), or touch pad, among others.
It will be appreciated that the memory 102 in this embodiment may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a programmable Read-only memory (PROM), an erasable programmable Read-only memory (erasabprom, EPROM), an electrically erasable programmable Read-only memory (EEPROM), or a flash memory. The volatile memory may be a Random Access Memory (RAM) which functions as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (staticiram, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (syncronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM ), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DRRAM). The memory 102 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 102 stores elements, executable units or data structures, or a subset thereof, or an expanded set thereof as follows: an operating system 1021, and application programs 1022.
The operating system 1021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application 1022 includes various applications for implementing various application services. Programs that implement methods in accordance with embodiments of the invention can be included in application 1022.
In the embodiment of the present invention, the processor 101 is configured to execute the method steps provided in the first aspect by calling a program or an instruction stored in the memory 102, which may be specifically a program or an instruction stored in the application 1022.
The method disclosed by the above embodiment of the present invention can be applied to the processor 101, or implemented by the processor 101. The processor 101 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 101. The processor 101 described above may be a general purpose processor, a digital signal processor, an application specific integrated circuit, an off-the-shelf programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 102, and the processor 101 reads the information in the memory 102 and completes the steps of the method in combination with the hardware thereof.
In addition, with reference to the rigid catenary wear detection method in the foregoing embodiments, an embodiment of the present invention may provide a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the method for detecting the wear of the rigid catenary in the foregoing embodiment is implemented.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. The use of the terms first, second, third and the like are for convenience only and do not denote any order. These words are to be understood as part of the name of the component.
Furthermore, it should be noted that in the description of the present specification, the description of the term "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc., means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the claims should be construed to include preferred embodiments and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include such modifications and variations.
Claims (9)
1. A rigid contact net abrasion detection method is characterized by comprising the following steps:
s10, acquiring depth images of the contact line and the busbar to be detected, and taking the acquired depth images as depth images to be detected;
s20, converting the depth image data of each row in the depth image to be detected into two-dimensional point cloud data; screening the two-dimensional point cloud data based on a preset threshold value to obtain contact line point cloud data and bus bar groove point cloud data;
s30, based on the contact line point cloud data, obtaining a left end point and a right end point of the contact line surface through a k-mean clustering algorithm;
s40, matching the busbar groove point cloud data with pre-established contact line and corresponding template point cloud data in a busbar template to determine a matching transformation relation;
s50, obtaining contact line matching points, matched with the left end point and the right end point of the contact line surface, in the contact line and busbar template based on the matching transformation relation;
and S60, obtaining a contact net abrasion detection result based on the contact line matching point and the intersection point of the contact line and the busbar in the busbar template.
2. The rigid catenary wear detection method of claim 1, wherein S10 comprises:
s11, acquiring initial depth images of the contact line and the bus bar acquired by the line structured light camera;
s12, carrying out median filtering on the initial depth image to obtain a depth image to be detected, wherein the median filtering method comprises the following steps:
setting a window with the size of (2k +1) multiplied by 1, and performing sliding window operation with the step length of 1 on the window along the X direction and the Y direction of the initial depth image respectively;
and taking the median of the gray values of all pixels in the current window as the gray value of the center point of the current window.
3. The rigid catenary wear detection method of claim 1, wherein S20 further comprises removing outliers in the two-dimensional point cloud data by statistical filtering, and the statistical filtering comprises:
traversing all the point cloud data, and calculating the average distance between each point and the nearest point with the nearest preset number n;
calculating the mean value and standard deviation of all average distances and setting a distance threshold value Dmax
Dmax＝μ+α×δ；
Where μ is the mean of all mean distances, δ is the standard deviation of all mean distances, and α is the distance threshold parameter
Traversing all point clouds, eliminating n adjacent points with average distance larger than DmaxPoint (2) of (c).
4. The method for detecting abrasion of the rigid contact net according to claim 1, wherein the step of screening contact line point cloud data from the two-dimensional point cloud data based on a preset threshold comprises the following steps:
determining the maximum value Y of the two-dimensional point cloud data in the Y directionmax；
Contact line point cloud data for screening out contact line surfaces based on preset depth threshold T
As shown in the formula:
wherein C is all two-dimensional point cloud data, p is one point in the point cloud data, and p isyThe coordinate value of the point cloud data in the y direction is shown.
5. The rigid catenary wear detection method of claim 1, wherein S30 comprises:
s31, respectively carrying out first-order difference and second-order difference operation on the contact line point cloud data along the X direction, and calculating the curvature of the contact line point cloud data in the X direction through the following formula:
wherein f isx' is the result of a first order difference operation, fx"is the second order difference operation result;
and S32, selecting the point cloud data with the maximum preset number in the curvature values, clustering by applying a k-mean clustering algorithm, and taking the two obtained clustering centers as the left end point and the right end point of the contact line surface.
6. The method for detecting wear of a rigid catenary of claim 1, wherein S40 comprises:
s41, taking the busbar groove point cloud as a point cloud to be matched, calculating the closest points of each point in the contact line and the busbar template in the point cloud to be matched, and forming a point pair;
s42, calculating a rotation matrix and a translation matrix;
s43, converting the contact line and the point cloud in the busbar template through a rotation matrix and a translation matrix to obtain a converted template point cloud;
s44, calculating an error function by:
wherein n is the number of nearest neighbor point pairs, piFor the point to be matched in the ith pair of nearest neighbors, qiTemplate points in the ith pair of nearest neighbor points;
s45, repeating S42-S44 until the error function is smaller than the set error threshold or the set iteration number is reached;
and S46, taking the rotation matrix and the translation matrix obtained by the last iteration as matching matrices.
7. The rigid catenary wear detection method of claim 1, wherein S60 comprises:
s61, respectively calculating a contact surface width, a wear allowance and an eccentric wear angle based on the contact line matching point and the intersection point of the contact line and the busbar in the busbar template, wherein the contact surface width is equal to the Euclidean distance between two points of the contact line matching point, the wear allowance is equal to the y-direction distance from the intersection point of the contact line and the busbar to the farthest point of the contact line matching point, and the eccentric wear angle is equal to the included angle between the horizontal line and the connecting line between the two points of the contact line matching point;
and S62, taking the contact surface width, the abrasion allowance and the eccentric wear angle as the detection result of the contact net abrasion.
8. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the rigid contact net wear detection method according to any one of the preceding claims 1 to 7.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, realizes the steps of the rigid catenary wear detection method according to any of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210273351.4A CN114693619A (en) | 2022-03-18 | 2022-03-18 | Rigid contact net abrasion detection method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210273351.4A CN114693619A (en) | 2022-03-18 | 2022-03-18 | Rigid contact net abrasion detection method, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114693619A true CN114693619A (en) | 2022-07-01 |
Family
ID=82138340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210273351.4A Pending CN114693619A (en) | 2022-03-18 | 2022-03-18 | Rigid contact net abrasion detection method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114693619A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115077387A (en) * | 2022-08-22 | 2022-09-20 | 成都岁生科技有限责任公司 | Wedge detection method based on point cloud technology |
| CN115937320A (en) * | 2023-02-21 | 2023-04-07 | 深圳市华亿明投资发展有限公司 | Visual positioning method for polishing mobile phone shell |
| CN116147525A (en) * | 2023-04-17 | 2023-05-23 | 南京理工大学 | Pantograph contour detection method and system based on improved ICP algorithm |
| CN116309280A (en) * | 2022-12-16 | 2023-06-23 | 上海药明康德新药开发有限公司 | Lymphocyte labeling method and system |
| CN116958099A (en) * | 2023-07-27 | 2023-10-27 | 微牌科技(浙江)有限公司 | Cable abrasion detection method, system, device and computer equipment |
| CN117029696A (en) * | 2023-10-08 | 2023-11-10 | 天津津铁供电有限公司 | Abrasion detection method and detection equipment for rigid suspension contact net |
| CN116958099B (en) * | 2023-07-27 | 2024-05-24 | 微牌科技(浙江)有限公司 | Cable abrasion detection method, system, device and computer equipment |
-
2022
- 2022-03-18 CN CN202210273351.4A patent/CN114693619A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115077387A (en) * | 2022-08-22 | 2022-09-20 | 成都岁生科技有限责任公司 | Wedge detection method based on point cloud technology |
| CN115077387B (en) * | 2022-08-22 | 2022-10-28 | 成都岁生科技有限责任公司 | Wedge detection method based on point cloud technology |
| CN116309280A (en) * | 2022-12-16 | 2023-06-23 | 上海药明康德新药开发有限公司 | Lymphocyte labeling method and system |
| CN115937320A (en) * | 2023-02-21 | 2023-04-07 | 深圳市华亿明投资发展有限公司 | Visual positioning method for polishing mobile phone shell |
| CN115937320B (en) * | 2023-02-21 | 2023-05-05 | 深圳市华亿明投资发展有限公司 | Visual positioning method for polishing mobile phone shell |
| CN116147525A (en) * | 2023-04-17 | 2023-05-23 | 南京理工大学 | Pantograph contour detection method and system based on improved ICP algorithm |
| CN116147525B (en) * | 2023-04-17 | 2023-07-04 | 南京理工大学 | Pantograph contour detection method and system based on improved ICP algorithm |
| CN116958099A (en) * | 2023-07-27 | 2023-10-27 | 微牌科技(浙江)有限公司 | Cable abrasion detection method, system, device and computer equipment |
| CN116958099B (en) * | 2023-07-27 | 2024-05-24 | 微牌科技(浙江)有限公司 | Cable abrasion detection method, system, device and computer equipment |
| CN117029696A (en) * | 2023-10-08 | 2023-11-10 | 天津津铁供电有限公司 | Abrasion detection method and detection equipment for rigid suspension contact net |
| CN117029696B (en) * | 2023-10-08 | 2024-01-02 | 天津津铁供电有限公司 | Abrasion detection method and detection equipment for rigid suspension contact net |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114693619A (en) | Rigid contact net abrasion detection method, equipment and storage medium | |
| KR101143218B1 (en) | Color segmentation-based stereo 3d reconstruction system and process | |
| JP4613994B2 (en) | Dynamic estimation device, dynamic estimation method, program | |
| DE102020122943A1 (en) | HARDWARE-BASED ACCELERATION OF AN OPTICAL RIVER | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| JP2010171976A (en) | Method and system for correcting distorted document image | |
| Panigrahy et al. | Image texture surface analysis using an improved differential box counting based fractal dimension | |
| CN109712071B (en) | Unmanned aerial vehicle image splicing and positioning method based on track constraint | |
| CN108256445B (en) | Lane line detection method and system | |
| US20080123958A1 (en) | Computer-implemented method for efficient image segmentation using automated saddle-point detection | |
| CN107424166B (en) | Point cloud segmentation method and device | |
| CN1272747C (en) | Method and device for tracking moving object in image | |
| CN113592923A (en) | Batch image registration method based on depth local feature matching | |
| CN113723399A (en) | License plate image correction method, license plate image correction device and storage medium | |
| CN113793309B (en) | Subpixel level ellipse detection method based on morphological characteristics | |
| CN112801021B (en) | Method and system for detecting lane line based on multi-level semantic information | |
| CN107194994B (en) | Method and device for reconstructing cylindrical surface by using point cloud data without calibration curved surface | |
| CN115346016A (en) | Point cloud model processing method and device and readable storage medium | |
| CN112036232B (en) | Image table structure identification method, system, terminal and storage medium | |
| CN111435117B (en) | Crack line detection device, crack line detection method, and recording medium | |
| CN113409242A (en) | Intelligent monitoring method for point cloud of rail intersection bow net | |
| JP4143149B2 (en) | Region extraction apparatus, region extraction method, and computer-readable recording medium | |
| US20070280555A1 (en) | Image registration based on concentric image partitions | |
| CN117291790A (en) | SAR image registration method, SAR image registration device, SAR image registration equipment and SAR image registration medium | |
| Damjanović et al. | Local stereo matching using adaptive local segmentation |
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 |