CN110930415B - Method for detecting spatial position of track contact net - Google Patents
Method for detecting spatial position of track contact net Download PDFInfo
- Publication number
- CN110930415B CN110930415B CN201911113547.1A CN201911113547A CN110930415B CN 110930415 B CN110930415 B CN 110930415B CN 201911113547 A CN201911113547 A CN 201911113547A CN 110930415 B CN110930415 B CN 110930415B
- Authority
- CN
- China
- Prior art keywords
- image
- contact network
- network cable
- contact
- area
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application provides a method for detecting the spatial position of a track contact net, which is applied to a photoelectric measurement system device 1 and comprises the following steps: acquiring an original image through an area-array camera 11 and a line laser 13, and sending the original image to an image computer 12; the image computer 12 obtains a connected domain where the contact network cable is located by performing image processing on the original image; segmenting the connected domain where the contact network cable is located by using an image segmentation method to obtain the region where the actual contact network cable is located; calculating the gray scale gravity center coordinate of the area where the actual contact network cable is located by using a gray scale gravity center method; converting the gray gravity center coordinates through image coordinates to obtain contact net space coordinates; and calculating the space position parameters of the track overhead line system according to the space coordinates of the overhead line system.
Description
Technical Field
The invention belongs to the technical field of photoelectric detection, and particularly relates to a non-contact rail contact net space position detection method.
Background
The pantograph of an electric locomotive acquires running electric energy uninterruptedly by means of a contact network erected along a railway. Because the pantograph of the electric locomotive is in sliding contact with the contact line, certain lifting force is applied to the contact line during normal operation, the contact line is separated from the contact line to form an off-line when a certain speed is reached, and the contact suspension has difference in different degrees along the span. The contact net is open-air equipment, can produce skew or wave under the strong wind effect, can produce in some cases and scrape the bow trouble. The pull-out value is too small, so that the aims of uniformly wearing the sliding plate and prolonging the service life of the pantograph are not fulfilled; too large pull-out value is easy to cause the accidents of scraping or drilling bow. Therefore, in order to ensure good contact and reliable current collection between the pantograph and the contact line, it is necessary to perform routing inspection on the conduction height and the pull-out height of the contact net.
For a special contact net detection train, the current non-contact detection method of contact line guide height and pull-out value is a linear array camera image processing method, the basic method is to utilize a binocular triangle method formed by two cameras and match with the illumination of a light supplement source, obtain working state images of a pantograph and a contact line through a binocular recognition technology, process the pantograph and the contact line images by adopting a certain image processing algorithm, and obtain the pull-out value and the guide height of the contact line. Although the detection method of the linear array camera has high measurement precision, the environment adaptability of the measurement device is poor, the data analysis amount is large, and the measurement speed is low.
Disclosure of Invention
The invention provides a photoelectric measurement system of a non-contact rapid subway overhead line system space position detection device, which realizes detection of the lead-height and pull-out value of a contact network and provides detection data.
The application provides a method for detecting the spatial position of a track contact net, which is applied to a photoelectric measurement system device (1), wherein the photoelectric measurement system device (1) is arranged on the central line position of a track walking detection platform relative to a track (1); the photoelectric measurement system device (1) comprises an area-array camera (11), an image computer (12) and a line laser (13), wherein the area-array camera (11) and the line laser (13) are connected with the image computer (12); the area-array camera (11) is used for shooting an image of a rail contact net, the line laser (13) is used for an illumination compensation light source of a photoelectric measurement system, and the detection method comprises the following steps:
acquiring an original image through an area-array camera (11) and a line laser (13), and sending the original image to an image computer (12);
the image computer (12) performs image processing on the original image to obtain a connected domain where the contact network cable is located;
segmenting the connected domain where the contact network cable is located by using an image segmentation method to obtain the region where the actual contact network cable is located;
calculating the gray scale gravity center coordinates of the area where the actual contact network cable is located by using a gray scale gravity center method;
converting the gray scale gravity center coordinate into a contact net space coordinate through an image coordinate;
and calculating the space position parameters of the track overhead line system according to the space coordinates of the overhead line system.
Preferably, the image computer (12) obtains the connected domain where the contact network cable is located by performing image processing on the original image, and specifically includes:
the image computer (12) carries out median filtering processing, global binarization processing and morphology processing on the original image to obtain a connected domain where the contact network cable is located.
Preferably, the segmenting the connected domain where the contact network cable is located by using an image segmentation method to obtain the region where the actual contact network cable is located specifically includes:
and segmenting the connected domain where the contact network cable is located by utilizing a gama transformation and Otsu binarization method to obtain the area where the actual contact network cable is located.
Preferably, the segmenting the connected domain where the contact network cable is located by using an image segmentation method specifically includes:
and segmenting a communication domain where the contact network cable is located by separating the contact network cable from an image region of the contact network cable mounting base by using an image segmentation method.
Preferably, the method further comprises:
according to the optical structure parameters of the photoelectric measurement system device (1), the distance between the area-array camera (11) and the line laser (13), the camera elevation angle of the area-array camera (11) and the lens focal length are determined.
Preferably, the obtaining of the catenary space coordinate by converting the gray scale barycentric coordinate through an image coordinate specifically includes:
calibrating the photoelectric measurement system device (1), and calculating coordinate conversion calibration parameters of gray-scale gravity center coordinates and contact network space coordinates;
and converting the gray scale gravity center coordinate to obtain a contact net space coordinate through image coordinate according to the coordinate conversion calibration parameter.
Preferably, the calibration of the photoelectric measurement system device (1) specifically comprises:
the photoelectric measurement system device (1) is calibrated by utilizing a two-axis linear sliding table.
Preferably, the spatial position parameter of the rail contact system comprises a pull-out value and a lead-up value of the rail contact system.
Compared with the prior art, the invention belongs to the technical characteristics different from the prior art scheme:
1. the method comprises the steps of utilizing image acquisition devices such as an area-array camera and a line laser, adopting a two-axis linear sliding table calibration method, utilizing an image processing algorithm of an actual contact net image area divided by an image, obtaining a mapping relation between two-dimensional coordinates of a contact net wire and space coordinates of the contact net wire under a camera image through two-axis linear sliding table calibration fitting, and further obtaining the space position of the contact net wire.
2. The acquisition computer is miniaturized, and inside realizes power supply control by oneself, and the cable is walked the line in this detection device inside.
The invention relates to a contact net space position detection module in an intelligent track detection vehicle, which is based on an optical structure method, is a photoelectric measurement system consisting of an area array camera, a line laser and an image computer, and can realize non-contact measurement of the contact net space position by adopting an image processing algorithm suitable for a structure after accurate calibration.
Drawings
Fig. 1 is a structure of a photoelectric measurement system for detecting a contact network according to an embodiment of the present application;
fig. 2 is a schematic diagram of calculating a mounting position of a line laser and a camera according to an embodiment of the present disclosure;
FIG. 3 is a block diagram illustrating an operation process of an optoelectronic measurement system according to an embodiment of the present disclosure;
fig. 4 is a data processing process based on a total station calibration method according to an embodiment of the present application;
fig. 5 is an effect diagram of an original image of a contact network provided in an embodiment of the present application;
fig. 6 is a diagram of an image processing effect of a catenary provided in an embodiment of the present application;
fig. 7 is a diagram illustrating a segmentation effect of a contact network connection area according to an embodiment of the present disclosure;
in the figure: the system comprises a 1-photoelectric measurement system, an 11-area-array camera, a 12-image computer, a 13-line laser, a 2-mounting base, a horizontal distance between the center of the front end of an L-camera lens and the plane of the laser, an included angle between an optical axis of a theta-camera and the horizontal plane, a d 0-camera working depth, a distance between the front end of the d 1-camera lens and a first measurement plane, a distance between the front end of the d 2-camera lens and a second measurement plane, a height of a lower bound of a contact net lead height, a height of an upper bound of the contact net lead height, a center point of the front end of the camera lens, a 01-first reference point and a 02-second reference point.
Detailed Description
The invention relates to a contact net detection device, which is a photoelectric measurement system for contact net detection and mainly comprises: area-array camera, line laser, image computer. The line laser is used as a contact line lighting device, so that the interference influence of natural light is solved, and the stability of the photoelectric measurement system is improved. The area array camera shoots the contact network illuminated by the line laser to obtain an image of the contact network, and the image acquisition device is used for detecting the contact network. The image computer is used as a control center and a data storage center of the whole detection device and used for controlling the camera to collect and store image data of the camera, and the image computer is connected with the area-array camera, collects and processes images of the camera.
The photoelectric detection system is arranged in a mounting structure, and the mounting mechanical structure comprises a camera, a light source mounting platform assembly and a positioning component. The camera and light source installation platform assembly is in an inverted M shape, and the camera and the line laser are respectively installed on the supporting arms at the two ends. Because the contact net is erected along the railway direction, the camera and the line laser are oppositely arranged on the mounting platform assembly along the contact net, and the mounting platform assembly is accurately positioned and arranged on the detection platform of the detection vehicle through the positioning component.
In the early detection period, the photoelectric detection system is subjected to optical structure parameter design and system calibration, and firstly, the area-array camera can be ensured to shoot an image of the overhead contact system with the guide height of 4000-5300mm and the pull-out value of +/-200 mm on the installation position relation, and sufficient measurement accuracy is ensured. From this perspective, the design is performed with the size of the camera pixel, the size of the target surface, and the like as initial conditions. After the installation distance between the camera and the line laser is determined, the installation included angle range between the camera and the horizontal plane is determined according to the measured height leading and pulling value ranges, and the optimal spatial resolution and the corresponding camera focal length of the system are determined by traversing in the included angle range, so that the installation included angle of the camera is determined, and the optical structure parameters of the system can be obtained under the condition that the depth of field of the camera is guaranteed. And the feasibility and the detection precision are ensured.
In order to obtain the mapping relation between the gray scale center coordinates of the camera image and the space coordinates of the overhead line system, the relation is utilized in the image processing in the later detection period, and therefore overhead line system leading-up and pulling-out values are calculated by the camera image directly through a formula. The system calibration method of the detection device comprises the following steps: the system utilizes a two-axis linear sliding table calibration method, in an equipment measurement range, the marker moves on the sliding table at equal intervals along the pull-out and lead-up directions to obtain a coordinate point set of the marker under a sliding table coordinate system, then a total station is utilized to measure and calculate the conversion relation between the equipment coordinate system of the sliding table and a contact network equipment coordinate system, and the lead-up and pull-out values of the marker are calculated in batches by using the mapping calibration relation, so that the rapid calibration is realized.
The detection work flow of the photoelectric detection system for the conduction height and the pull-out value of the contact net is as follows: when the detection vehicle enters a running detection state, an area-array camera, an image computer and a line laser which are arranged in the relative positions and have the same direction as the contact network line are put into operation, the line laser illuminates the contact network line vertically above, the area-array camera shoots a section of illuminated contact line at a certain angle, a gray level image obtained by shooting is transmitted back to the image computer, the image computer obtains the coordinates of the gray level center of the actual contact network area under an image coordinate system by an image processing algorithm, namely, after median filtering of the camera image, global binarization, connected domain processing and segmentation and separation are carried out, the image area of the contact network line and a contact network line installation base is finally obtained, the coordinates of the gray level center of the actual contact network area under the image coordinate system are obtained by calculation, and the spatial coordinates of the contact network lead-up value and the pull-out value can be calculated by using the mapping formula obtained by calibration.
The invention relates to a contact net space position detection module in a miniaturized dynamic intelligent track detection vehicle, which relates to the technical scheme of a photoelectric measurement system of a contact net detection device, and comprises the following steps:
firstly, the whole structure of the photoelectric measurement system of the contact net detection device comprises:
referring to fig. 1, in the process of the present invention, the inventor designs a structure of an optoelectronic measurement subsystem for detecting the spatial position of a touch screen, wherein the optoelectronic detection subsystem is in a mounting structure relationship, and a mounting mechanical structure comprises a camera and light source mounting platform assembly and a positioning component. The camera and light source installation platform assembly is in an inverted M shape, and the camera and the line laser are respectively installed on the supporting arms at the two ends. Because the contact net is erected along the railway direction, the camera and the line laser are oppositely arranged on the mounting platform assembly along the contact net, and the mounting platform assembly is accurately positioned and arranged on the detection platform of the detection vehicle through the positioning component. The mounting platform assembly provides a mounting base for each object in the photoelectric measuring device. The area-array camera and the line laser are respectively arranged in the mounting hole of the device; the image computer is arranged in the base at the middle part, and the image computer for acquisition is miniaturized.
The area-array camera automatically realizes power supply control from the interior of the detection device; the laser generating device is arranged on one side of the linear laser mounting arm, and power supply control is automatically realized from the inside of the laser generating device.
The area-array camera is used as an image acquisition device of the photoelectric measurement system to shoot images of the contact network.
The image computer is used as a control center and a data storage center of the whole detection device and is used for controlling the camera to collect and store the returned image data. The image computer is used for receiving the image collected by the area-array camera and processing and resolving the image.
The installation platform assembly is arranged on a detection photoelectric measurement system structure of the contact net through a positioning component, the detection photoelectric measurement system structure of the contact net travels on the detection platform along the track, and the contact net is detected along the track direction through an area array camera, an image computer, a line laser and an internal cable which are arranged on the installation platform assembly.
The positioning component is used for accurately mounting the photoelectric measurement system on the detection platform of the detection vehicle.
The installation relation of the device and the detection vehicle on the whole is as follows: the contact net is erected along the railway direction, in order to enable the camera and the line laser to completely shoot the contact net in motion, the camera and the line laser are required to be oppositely installed on the installation platform assembly along the direction of the contact net, and the installation platform assembly is accurately positioned and installed on the detection platform of the detection vehicle through the positioning component. Namely, the visual fields of the camera and the laser are on the same plane, and the connecting line is perpendicular to the wiring direction of the contact network. Because the line laser is installed vertically to illuminate the contact net line above the track, in order to enable the camera to photograph the laser-illuminated contact net line, the camera is installed at a certain angle to the horizontal plane and at a certain horizontal distance from the line laser.
Therefore, in order to ensure that the area-array camera can shoot an image of the overhead line system in the installation position relation, and to ensure sufficient measurement accuracy in consideration of optical parameters inside the camera, it is necessary to determine the horizontal distance between the center of the front end of the camera lens and the laser plane, i.e. the distance between two installation holes of the device, the included angle between the optical axis of the camera and the horizontal plane, and the focal length of the camera lens in the design stage. The following is the optical structure design phase installation and layout calculation process:
referring to fig. 2, a schematic diagram of the calculation of the installation positions of the line laser and the camera of the photoelectric measurement system of the present invention is shown:
the optical structure design and layout calculation principle is as follows: the method is designed by taking the pixel size of a camera, the size of a target surface and the like as initial conditions. After the installation distance between the camera and the line laser is determined, the installation included angle range of the camera and the horizontal plane is determined according to the measured height guiding and pulling value range, the optimal spatial resolution of the system and the corresponding camera focal length are determined by traversing in the included angle range, so that the installation included angle of the camera is determined, and the optical structure parameters of the system can be obtained under the condition of ensuring the shooting depth of field of the camera. And the feasibility and the detection precision are ensured. The specific calculation process is as follows: when the detection vehicle enters an operation detection state, an area array camera, an image computer and a line laser which are arranged in the relative position and have the same direction as the contact network line are installed and put into operation, the line laser illuminates the contact network line vertically above, the area array camera shoots the illuminated contact line, an obtained camera image is transmitted back to the image computer, the image computer obtains the gray center coordinate of an actual contact network area through an image processing algorithm, namely, firstly, binaryzation, filtering, connected domain segmentation processing and separation of the image area of the contact network line and a contact network line installation base are carried out on the camera image, finally, the area where the actual contact network line is located is separated, and then the space coordinate of the contact network height and the pull-out value can be calculated by using a mapping formula obtained through calibration.
The user performs the acquisition process by using the system as follows:
referring to fig. 3 and 4, a block diagram of an operation flow and a data processing flow of the photoelectric measurement system are shown. In the collecting process, the working process of the contact net space position detection device is as follows:
in the operation process of the detection vehicle, the laser illuminates the overhead contact network, the camera shoots the overhead contact network of the line laser under the control of the image computer, the image is transmitted to the image computer, the image computer extracts and processes the characteristic points of the overhead contact network of the camera image, then the processing result is stored on the hard disk in a certain data storage format, the processing result can be sent to the comprehensive computer of a user, an output waveform and a report form are generated, and historical data analysis and overrun early warning are provided. The method and the device realize the acquisition and processing of the contact network image data and the storage and transmission of the processed data.
The contact net detection system is based on the contact net image gray scale center coordinates of the CCD camera and is mapped to the space coordinates of the contact net pull-out value and the lead-up value. The pull-out value and the lead-up value of the contact network cable can be calculated.
The mathematical model on which the measurement of the contact net space position depends is as the following system calibration formula:
Height＝(p 0 +p 1 x+p 2 x 2 +p 3 x 3 )(q 0 +q 1 y+q 2 y 2 +q 3 y 3 )
Taggcr-d|p 0 x|p 1 x 2 |p 2 x 3 |q 0 y|q 1 y 2 |q 1 y 2 |c 0 xy|c 1 x 2 y 2 |c 2 x 2 y|c 3 xy 2
in the formula, x and y are coordinates of a contact net line lower tangent point in an image coordinate system, and p i 、q i 、c i And d is a calibrated parameter.
In the calibration process and the collected image computer image processing process, because the original camera image has interference objects such as salt particle noise, gaps and holes, contact network cable installation bases and the like, the camera image needs to be subjected to image processing, and an actual contact network characteristic area is separated. The image computer in the embodiment of the present invention further describes the algorithm for extracting the contact network feature points of the camera image in detail.
Since the contact net image feature area is located at the lowest part of the camera image, the following algorithm needs to be designed for finding the lower edge position of the contact net line:
1. removing salt particle noise of the image by median filtering, then carrying out global binarization, removing fine gaps and cavities by using closed operation, and searching a connected domain;
2. calculating the center coordinate of each communication region, and sequencing the communication regions from large to small according to the y-axis coordinate value of the center point of each communication region;
3. traversing the sorted connected domain set in the step 2 by taking variables such as the area and the moment of inertia of the connected domain as screening conditions, eliminating the connected domain of the interference object, wherein the connected domain which can meet the screening conditions and has the minimum subscript serial number is the connected domain where the contact network cable is located;
4. and segmenting the communication area where the contact network cable is located, and separating the contact network cable from the image area of the contact network cable installation base.
Referring to fig. 5, 6, and 7, the effects of dividing the contact network connection region are shown. The separation thought adopted is as follows:
the middle and two ends of the image of the connected domain where the contact network cable is located are bright, the middle part corresponds to the target contact network cable, and the left and right sides and the folded-wing-shaped areas of the contact network cable area correspond to the installation bases of the contact network cable. Since the lower end of the cross section of the contact screen line is circular, the light intensity of the line laser on the two sides of the contact screen line is low, and therefore, a darker transition zone is arranged between the middle area and the two side areas of the image where the contact screen line is located, as shown in the darker part in fig. 5.
The Gama transformation of fig. 5 is performed to perform a nonlinear operation, so that the gray values of the input image and the output image are in an exponential relationship, the Gama value is greater than 1, the lighter area is stretched, the darker area is compressed to become darker, the contrast of the image is enhanced, the threshold value is solved by using the Otsu method, and then binarization processing is performed to obtain the image shown in fig. 6, wherein the middle area and the two side areas are interrupted. The further processing of fig. 6 is performed to find the left and right split columns of the mounting base and the contact patch cord on the image. Since the symmetry of the light intensity distribution in the middle portion is poor, and the shape stability of the middle region is poor, it is necessary to perform a line-by-line scan from both sides of the image to find two divided lines. The column division process is to count the number of pixels with the gray scale of 1 in each column in the column-by-column scanning process, for the two side areas, the distribution of the 1-value pixel number has two changes of low and high, and the columns of the two side areas can be removed by identifying the mode, so as to obtain the column of the contact network line image in the middle of the image. The resulting connected domain according to this method is shown as the gray area in fig. 7.
5. And calculating the gray gravity center coordinates of the extracted area where the contact network cable is located, wherein the calculation formula is as follows:
in the formula, m and n are respectively the row number and column number of the divided detection line regions, and x i Denotes the i-th line coordinate, y j Denotes the coordinates of the j-th column, f ij Representing the gray value of the ith row and jth column pixels.
Based on the area where the contact network cable is located and the gray scale gravity center coordinates of the area, which are obtained by the segmentation of the image processing algorithm, in the calibration process, the total station is used for dotting to measure the leading height and the pull-out value of the marker point of the contact network marker, namely, the following formula can be used for fitting all calibration parameters in the mapping formula;
similarly, when the system collects image processing data, the system can automatically calculate the contact network cable pull-out value and the leading height value corresponding to the collecting point by combining the contact network image coordinate obtained after image processing with the finished calibration formula.
The image coordinate and space coordinate mapping formula adopted in the software is as follows:
Height＝(p 0 +p 1 x+p 2 x 2 +p 3 x 3 )(q 0 +q 1 y+q 2 y 2 +q 3 y 3 )
Tagger＝d+p 0 x+p 1 x 2 +p 2 x 3 +q 0 y+q1y 2 +q 2 y 3 +c 0 xy+c 1 x 2 y 2 +c 2 x 2 y+c 3 xy 2
in the formula, x and y are coordinates of a contact net line lower tangent point in an image coordinate system, and p i 、q i 、c i And d is a constant. The value is obtained after calibration.
After the contact net feature points are extracted by the image processing algorithm, the detection software can respectively store the processed contact net image data and the calculated contact net spatial position data on a local hard disk of the image computer. And meanwhile, the data can be sent to a comprehensive computer of the user, and the comprehensive computer is gathered and fused. This contact net detection device can be to contact net geometric parameters such as contact line lead height, pulling value on-line output waveform and report form, provides historical data analysis and transfinite early warning, not only can in time discover hidden danger to for carrying out subway contact net and overhaul and provide data, effectively guarantee railway lines's maintenance and maintenance.
Claims (8)
1. The method for detecting the spatial position of the rail contact network is characterized in that the method is applied to a photoelectric measurement system device (1), the photoelectric measurement system device (1) is arranged on a central line position of a rail walking detection platform relative to a rail (1) and is connected with the rail walking detection platform through a mounting base (2); the photoelectric measurement system device (1) comprises an area-array camera (11), an image computer (12) and a line laser (13), wherein the area-array camera (11) and the line laser (13) are connected with the image computer (12); the area-array camera (11) is used for shooting an image of a rail contact net, the line laser (13) is used for an illumination compensation light source of a photoelectric measurement system, and the detection method comprises the following steps:
acquiring an original image through an area-array camera (11) and a line laser (13), and sending the original image to an image computer (12);
the image computer (12) performs image processing on the original image to obtain a connected domain where the contact network cable is located;
segmenting the connected domain where the contact network cable is located by using an image segmentation method to obtain the region where the actual contact network cable is located;
calculating the gray scale gravity center coordinate of the area where the actual contact network cable is located by using a gray scale gravity center method;
converting the gray gravity center coordinates through image coordinates to obtain contact net space coordinates;
and calculating the space position parameters of the track contact net according to the space coordinates of the contact net.
2. The detection method according to claim 1, wherein the image computer (12) obtains the connected domain where the contact network cable is located by performing image processing on the original image, and specifically comprises:
the image computer (12) carries out median filtering processing, global binarization processing and morphology processing on the original image to obtain a connected domain where the contact network cable is located.
3. The detection method according to claim 1, wherein the segmenting the connected domain where the contact network cable is located by using an image segmentation method to obtain the region where the actual contact network cable is located specifically comprises:
and segmenting the connected domain where the contact network cable is located by utilizing a gama transformation and Otsu binarization method to obtain the area where the actual contact network cable is located.
4. The detection method according to claim 1, wherein the segmenting the connected domain where the contact network cable is located by using an image segmentation method specifically comprises:
and segmenting a communication domain where the contact network cable is located by separating the contact network cable from an image region of the contact network cable mounting base by using an image segmentation method.
5. The detection method according to claim 1, further comprising:
according to the optical structure parameters of the photoelectric measurement system device (1), the distance between the area-array camera (11) and the line laser (13), the camera elevation angle of the area-array camera (11) and the lens focal length are determined.
6. The detection method according to claim 1, wherein the obtaining of the catenary space coordinates by converting the gray scale barycentric coordinates through image coordinates specifically comprises:
calibrating the photoelectric measurement system device (1), and calculating coordinate conversion calibration parameters of gray-scale gravity center coordinates and contact network space coordinates;
and converting the gray gravity center coordinates according to the coordinate conversion calibration parameters to obtain the space coordinates of the overhead line system through image coordinate conversion.
7. The detection method according to claim 6, wherein the calibration of the photoelectric measurement system device (1) comprises in particular:
the photoelectric measurement system device (1) is calibrated by utilizing a two-axis linear sliding table.
8. The detection method according to claim 1, wherein the spatial position parameters of the overhead contact system include a pull-out value and a lead-in height value of the overhead contact system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113547.1A CN110930415B (en) | 2019-11-14 | 2019-11-14 | Method for detecting spatial position of track contact net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113547.1A CN110930415B (en) | 2019-11-14 | 2019-11-14 | Method for detecting spatial position of track contact net |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110930415A CN110930415A (en) | 2020-03-27 |
| CN110930415B true CN110930415B (en) | 2022-11-22 |
Family
ID=69852943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911113547.1A Active CN110930415B (en) | 2019-11-14 | 2019-11-14 | Method for detecting spatial position of track contact net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930415B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111609917B (en) * | 2020-05-22 | 2022-03-15 | 成都唐源电气股份有限公司 | Contact net vibration measurement method and system based on linear array camera |
| CN111723794B (en) * | 2020-06-24 | 2022-07-22 | 西南交通大学 | Real-time flexible contact net positioning point identification method |
| CN112782193A (en) * | 2021-02-02 | 2021-05-11 | 成都国铁电气设备有限公司 | Performance test platform and method for contact net suspension state detection and monitoring device |
| CN113063361A (en) * | 2021-03-29 | 2021-07-02 | 长安大学 | Symmetrical rail contact net detection device and detection method |
| CN117036359B (en) * | 2023-10-10 | 2023-12-08 | 成都中轨轨道设备有限公司 | Contact net geometric parameter measurement method based on binocular machine vision |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104567684B (en) * | 2015-01-20 | 2017-08-25 | 中国铁道科学研究院 | A kind of contact net geometric parameter detection method and device |
| CN107703513B (en) * | 2017-08-15 | 2021-05-14 | 株洲嘉成科技发展有限公司 | Non-contact net relative position detection method based on image processing |
| CN108801149B (en) * | 2018-03-06 | 2020-01-10 | 北京交通大学 | Contact net geometric parameter measuring method based on geometric amplification principle and monocular computer vision |
-
2019
- 2019-11-14 CN CN201911113547.1A patent/CN110930415B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110930415A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110930415B (en) | Method for detecting spatial position of track contact net | |
| CN111855664B (en) | Adjustable three-dimensional tunnel defect detection system | |
| CN106871805B (en) | vehicle-mounted rail gauge measuring system and measuring method | |
| CN104567684B (en) | A kind of contact net geometric parameter detection method and device | |
| CN105133471B (en) | Linear structured light pavement surface detection system-based pavement depth image production method | |
| CN106679567A (en) | Contact net and strut geometric parameter detecting measuring system based on binocular stereoscopic vision | |
| CN111485475B (en) | Pavement pit recognition method and device | |
| CN104406521A (en) | Vision measurement technology-based catenary geometric parameter measurement instrument and detection method | |
| CN105158257A (en) | Sliding plate measurement method and device | |
| CN107941170A (en) | Road detection apparatus and system | |
| CN105571508A (en) | Deformation detecting method and deformation detecting system for pantograph of overhead contact system | |
| CN104239904A (en) | Non-contact detection method for external outline of railway vehicle | |
| CN108765393B (en) | Method for detecting vibration behavior of high-speed railway contact net | |
| CN114549440A (en) | Method and device for detecting dynamic geometric parameters of contact network and electronic equipment | |
| CN116989881A (en) | Contact line vibration measurement system and method based on line laser target identification | |
| CN113295094B (en) | Pantograph dynamic envelope intrusion detection method, device and system | |
| CN111609917B (en) | Contact net vibration measurement method and system based on linear array camera | |
| JP2014169940A (en) | Overhead wire position measuring apparatus and method | |
| CN114119355B (en) | Method and system for early warning of blocking dropping risk of shield tunnel | |
| CN116481430A (en) | Real-time detection method for geometric parameters of contact line | |
| JPH09118153A (en) | Method and device for inspecting stringing | |
| CN113963053A (en) | Method for detecting height of contact net | |
| CN113701628A (en) | Dynamic measuring method and device for contact line abrasion | |
| You | A study on dynamic measurement system of contact wire wear in electrified railway | |
| CN207751450U (en) | Road detection apparatus and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |