CN117029696A - Abrasion detection method and detection equipment for rigid suspension contact net - Google Patents
Abrasion detection method and detection equipment for rigid suspension contact net Download PDFInfo
- Publication number
- CN117029696A CN117029696A CN202311288612.0A CN202311288612A CN117029696A CN 117029696 A CN117029696 A CN 117029696A CN 202311288612 A CN202311288612 A CN 202311288612A CN 117029696 A CN117029696 A CN 117029696A
- Authority
- CN
- China
- Prior art keywords
- target
- abrasion
- light band
- rigid suspension
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000000725 suspension Substances 0.000 title claims abstract description 104
- 238000005299 abrasion Methods 0.000 title claims abstract description 99
- 238000001514 detection method Methods 0.000 title claims abstract description 72
- 230000003287 optical effect Effects 0.000 claims description 70
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000010586 diagram Methods 0.000 claims description 19
- 238000003384 imaging method Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 238000009826 distribution Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 15
- 230000035772 mutation Effects 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000001678 irradiating effect Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000004590 computer program Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the application provides a wear detection method and detection equipment for a rigid suspension contact net. The laser device irradiates the rigid suspension contact net according to a preset angle to generate a light band on the rigid suspension contact net, and the detection method comprises the following steps: acquiring a light band image of a rigid suspension contact net; extracting a plurality of texture features of the light band image to divide the light band image so as to obtain a target area corresponding to the abrasion position of the light band image; determining a target texture feature of the plurality of texture features to determine an abrasion zone of the target zone; and carrying out local clustering treatment on the abrasion area to obtain an abrasion end point, and then determining the abrasion width of the rigid suspension contact net. Based on special texture features in the light band images, the abrasion positions are identified, so that non-invasive detection can be realized, and the detection result has high precision and strong instantaneity. The detection is carried out under the condition that the normal operation of the railway train is not affected, and an effective guarantee means is provided for the power supply maintenance of the subway line.
Description
Technical Field
The application relates to the technical field of defect detection, in particular to a wear detection method and detection equipment for a rigid suspension contact net.
Background
In the subway train process, surface abrasion phenomenon can occur due to long-time use of the rigid suspension contact net and influence of severe environment. If the abrasion is excessive, the problems of poor contact, increased resistance and the like can be caused, so that the normal operation of the train is affected. Therefore, the abrasion detection of the rigid suspension catenary has important significance for subway operation and maintenance. In the prior art, a mode of detecting abrasion by a range finder is adopted, and the measuring result of the range finder can be directly influenced due to the intensity change of light rays in a train running tunnel, so that the accuracy and timeliness are low. And the method of deep learning detection abrasion is adopted, so that the high frame rate rapid identification requirement required by abrasion detection cannot be met due to the limited deployment speed of the neural network.
Disclosure of Invention
The embodiment of the application aims to provide a wear detection method, detection equipment, a storage medium and a processor for a rigid suspension catenary.
In order to achieve the above object, a first aspect of the present application provides a wear detection method for a rigid suspension catenary, wherein a laser device irradiates the rigid suspension catenary according to a preset angle to generate a light band on the rigid suspension catenary, the detection method comprising:
acquiring a light band image of a rigid suspension contact net;
extracting a plurality of texture features of the light band image;
dividing the light band image according to the texture features to obtain a target area corresponding to the abrasion position of the light band image;
determining target texture features of a plurality of texture features, wherein the target texture features comprise first target texture features corresponding to a first line segment included in a target line segment region in a light band and second target texture features corresponding to a second line segment included in the target line segment region, and the target line segment region refers to a region where a line segment perpendicular to a rigid suspension direction is located;
determining the abrasion area of the target area according to all the target texture features;
carrying out local clustering treatment on the abrasion areas to determine abrasion end points of the abrasion areas;
and determining the abrasion width of the rigid suspension contact net according to the abrasion end points.
In an embodiment of the present application, the first target texture feature is at least one of a first intersection point between the first line segment and the curves at both ends of the first line segment, a first imaging feature corresponding to a first target shape generated on the optical tape, and an offset distortion feature of the optical tape, and the second target texture feature is at least one of a second intersection point between the second line segment and the curves at both ends of the second line segment, a second imaging feature corresponding to a second target shape generated on the optical tape, and an offset distortion feature of the optical tape.
In an embodiment of the application, extracting the plurality of texture features of the light band image comprises: denoising the optical band image through a filter to obtain a denoised optical band image; processing the denoised light band image based on a histogram equalization algorithm to obtain a target image corresponding to the denoised light band image; and extracting features of the target image based on a local binary pattern algorithm or a gray level co-occurrence matrix algorithm to obtain a plurality of texture features of the light band image.
In an embodiment of the present application, dividing the optical band image according to a plurality of texture features to obtain a target area corresponding to a wear position of the optical band image includes: the texture features comprise global features and local features, and the optical band image is segmented according to the global features to obtain an optical band region in the optical band image; and dividing the light band region according to the local characteristics to obtain a target region corresponding to the abrasion position in the light band region.
In an embodiment of the application, determining the wear zone of the target zone from all of the target texture features comprises: converting the target area into a binary image; performing vertical projection on the binary image to obtain a pixel density distribution diagram corresponding to the binary image in the vertical direction; determining a mutation region in the pixel density distribution map according to all the target texture features; and determining the abrasion zone of the target zone according to the mutation zone.
In an embodiment of the present application, performing local clustering on an abrasion zone to determine an abrasion endpoint of the abrasion zone includes: performing dimension reduction processing on the second area image corresponding to the abrasion area to obtain a dimension-reduced second area image; and carrying out local clustering treatment on the second region image after dimension reduction based on a super-pixel segmentation algorithm so as to determine an abrasion endpoint.
In an embodiment of the present application, the preset angle is 30 degrees.
A second aspect of the application provides a processor configured to perform the above-described wear detection method for a rigid suspension catenary.
A third aspect of the present application provides a detection apparatus comprising:
the laser device is used for irradiating the rigid suspension contact net according to a preset angle so as to generate a light band on the rigid suspension contact net;
the image acquisition device is used for acquiring the light band image of the rigid suspension contact net; and
the processor.
A fourth aspect of the application provides a machine-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to be configured to perform the wear detection method for a rigid suspension catenary described above.
Through the technical scheme, the laser device irradiates the rigid suspension contact net according to the preset angle so as to generate a light band on the rigid suspension contact net, and the detection method comprises the following steps: acquiring a light band image of a rigid suspension contact net; extracting a plurality of texture features of the light band image to divide the light band image so as to obtain a target area corresponding to the abrasion position of the light band image; determining a target texture feature of the plurality of texture features to determine an abrasion zone of the target zone; and carrying out local clustering treatment on the abrasion area to obtain an abrasion end point, and then determining the abrasion width of the rigid suspension contact net. Based on special texture features in the light band images, the abrasion positions are identified, so that non-invasive detection can be realized, and the detection result has high precision and strong instantaneity. The detection is carried out under the condition that the normal operation of the railway train is not affected, and an effective guarantee means is provided for the power supply maintenance of the subway line.
Additional features and advantages of embodiments of the application will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain, without limitation, the embodiments of the application. In the drawings:
fig. 1 schematically shows an application environment schematic of a wear detection method for a rigid suspension catenary according to an embodiment of the present application;
fig. 2 schematically shows a flow diagram of a wear detection method for a rigid suspension catenary according to an embodiment of the present application;
FIG. 3a schematically shows a schematic view of a light band image 1 according to an embodiment of the application;
FIG. 3b schematically shows a schematic view of a light band image 2 according to an embodiment of the application;
FIG. 3c schematically shows a schematic view of a light band image 3 according to an embodiment of the application;
fig. 4 schematically shows a block diagram of the structure of a detection device according to an embodiment of the application;
fig. 5 schematically shows a block diagram of a wear detection device for a rigid suspension catenary according to an embodiment of the present application;
fig. 6 schematically shows an internal structural view of a computer device according to an embodiment of the present application.
Description of the reference numerals
10-laser device, 20-image acquisition device, A-target region, B-light band region, C-wearing region, a-first line segment, B-second line segment.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the detailed description described herein is merely for illustrating and explaining the embodiments of the present application, and is not intended to limit the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The abrasion detection method for the rigid suspension catenary can be applied to an application environment shown in figure 1. Wherein the detection device is integrated by the laser device 10 and the image acquisition device 20. The detection device keeps a preset distance from the rigid suspension contact net, and detects the rigid suspension contact so as to obtain clear and accurate images. The laser device 10 can irradiate the rigid suspension contact net according to a preset angle, and the image acquisition device 20 is arranged right in front of the light band. The image acquisition device acquires an image of the light band while the rigid suspension contact net generates the light band. The laser device 10 may be a structured light laser that emits light that exhibits a band of light in a rigid suspension catenary. The image acquisition device 20 may be an area camera. The area array camera mainly adopts continuous and planar scanning light to realize the detection of the rigid suspension contact net, and can acquire a complete light band image at one time. Specifically, the preset angle is 30 degrees.
Fig. 2 schematically shows a flow diagram of a wear detection method for a rigid suspension catenary according to an embodiment of the present application. As shown in fig. 2, in an embodiment of the present application, there is provided a wear detection method for a rigid suspension catenary, and the embodiment is mainly illustrated by applying the method to a processor, and includes the following steps:
s202, acquiring a light band image of a rigid suspension contact net;
s204, extracting a plurality of texture features of the light band image;
s206, dividing the light band image according to the texture features to obtain a target area corresponding to the abrasion position of the light band image;
s208, determining target texture features of a plurality of texture features, wherein the target texture features comprise first target texture features corresponding to a first line segment included in a target line segment region in a light band and second target texture features corresponding to a second line segment included in the target line segment region, and the target line segment region is a region where a line segment perpendicular to a rigid suspension direction is located;
s210, determining the abrasion area of the target area according to all the target texture features;
s212, carrying out local clustering treatment on the abrasion region to determine an abrasion endpoint of the abrasion region;
and S214, determining the abrasion width of the rigid suspension contact net according to the abrasion end points.
The rigid suspension structure of the overhead contact system is a novel railway vehicle overhead contact system construction technology. In conventional catenary configurations, the conduction between the vehicle and the catenary is accomplished by using conductive wires that pass through the roof of the vehicle. After the overhead line system rigid suspension technology is adopted, the telescopic drainage tube is arranged at the roof of the overhead line system, and conduction is transferred from the roof to the rigid suspension bracket at the side of the overhead line system, so that stable conduction between the railway vehicle and the overhead line system is realized. And because the contact cable is used for a long time and is influenced by severe environment, the contact network can have surface abrasion phenomenon.
In order to detect the abrasion of the rigid suspension catenary, a light cutting technology is adopted. The light cutting technology refers to projecting a beam of parallel light bands onto a surface to be measured at a certain angle, and the curve image of the intersection of the light bands and the surface profile reflects the microscopic geometry of the surface to be measured, so that the contact with the surface to be measured can be avoided. In the embodiment of the application, the rigid suspension catenary is irradiated by a laser device according to a preset angle to generate a light band on the rigid suspension catenary, and at the moment, an image of the light band of the rigid suspension catenary is acquired by an image acquisition device. As shown in fig. 1, the whole light band generated by the rigid suspension catenary is irradiated by laser in the light band image.
The processor may acquire the acquired light band image to extract a plurality of texture features of the light band image. Specifically, texture features include local features and global features. The manner in which the texture features for the light band image are extracted includes, but is not limited to: local Binary Pattern (LBP), gray level co-occurrence matrix (GLCM), etc. Then, the processor may segment the optical band image according to the plurality of texture features to obtain a target area corresponding to the abrasion location of the optical band image. The target area refers to the general area in which the worn out position on the optical tape in the optical tape image is located, and the area range is set by a technician. For accuracy of detection, the technician may set the area range of the target area to be greater than the area range of the worn area in the historical light band image. It will be appreciated that there may be multiple wear locations on the rigid suspension cable, as well as multiple corresponding target areas. The target area corresponding to each abrasion position is locked, and each abrasion position can be isolated for identification processing in a targeted manner. As shown in fig. 3a, region a is the target region of the optical band image.
Further, the processor may determine a target texture feature of the plurality of texture features. The target texture features comprise first target texture features corresponding to a first line segment included in a target line segment region in the light band and second target texture features corresponding to a second line segment included in the target line segment region, wherein the target line segment region refers to a region where a line segment perpendicular to the rigid suspension direction is located. When the rigid suspension contact net is worn, a line segment perpendicular to the rigid suspension direction, namely the position where the wear is located, exists on the light band. Because the laser device irradiates the rigid suspension contact net according to a preset angle, the target line segment area comprises a first line segment and a second line segment at two sides of the light band. The first target texture feature refers to a local feature contained in the first line segment, and the second target texture feature refers to a local feature contained in the second line segment. It will be appreciated that the first and second are relatively speaking. As shown in fig. 3b, a is a first line segment of the target line segment region, and b is a second line segment of the target line segment region.
The processor may then determine the wear zone of the target zone based on all of the first target texture feature and the second target texture feature. The abrasion region refers to the ROI region where the abrasion position is located. As shown in fig. 3a, region C is the worn area of the optical band image. Further, the processor may perform a local clustering process on the wear zone to determine wear endpoints at both ends of the wear zone to determine the wear width of the rigid suspension catenary.
In one embodiment, extracting the plurality of texture features of the light band image comprises: denoising the optical band image through a filter to obtain a denoised optical band image; processing the denoised light band image based on a histogram equalization algorithm to obtain a target image corresponding to the denoised light band image; and extracting features of the target image based on a local binary pattern algorithm or a gray level co-occurrence matrix algorithm to obtain a plurality of texture features of the light band image.
Specifically, texture features include local features and global features. The processor can firstly perform denoising treatment on the optical band image through the filter, and remove noise in the optical band image to obtain a denoised optical band image. Further, a histogram equalization algorithm can be adopted to perform image enhancement processing on the denoised light band image, so that the histogram distribution of the input light band image becomes uniform, the gray level of the image is increased, a target image corresponding to the denoised light band image is obtained, and the effect of integrally enhancing the image contrast is realized. In the target image, the area where the band of light is presented is more prominent than the denoised band of light image. The processor may extract a plurality of texture features of the target image according to a local binary pattern algorithm or a gray level co-occurrence matrix algorithm.
In one embodiment, segmenting the optical band image according to the plurality of texture features to obtain a target region corresponding to a wear location of the optical band image comprises: the texture features comprise global features and local features, and the optical band images are segmented according to the global features to obtain optical band areas of the optical band images; and dividing the light band region according to the local characteristics to obtain a target region corresponding to the abrasion position in the light band region. The processor firstly segments the light band image according to the global characteristics to obtain the light band region where the whole light band of the light band image is located, namely the image region where the rigid suspension contact net is located is found. Further, the image of the light band region is segmented according to the local features to determine a target region of the light band image. As shown in fig. 3a, region a is the target region of the optical band image, region B is the optical band region of the optical band image, and region C is the worn region of the optical band image.
In one embodiment, the first target texture feature is at least one of a first intersection between the first line segment and a curve at both ends of the first line segment, a first imaging feature corresponding to a first target shape generated on the optical tape, and an offset distortion feature of the optical tape, and the second target texture feature is at least one of a second intersection between the second line segment and a curve at both ends of the second line segment, a second imaging feature corresponding to a second target shape generated on the optical tape, and an offset distortion feature of the optical tape.
As shown in fig. 3b, there will be a line segment on the light strip perpendicular to the rigid suspension direction, the light strip at both ends of the line segment will typically appear as a curve, with an intersection point between the curve and the line segment. The intersection point of the first line segment a and the curves at the two ends of the first line segment is a first intersection point, and the intersection point of the second line segment b and the curves at the two ends of the second line segment is a second intersection point. Ideally, the number of the first intersecting points or the second intersecting points is two. However, since there is a disturbance in the shot image or the laser irradiation process, as shown in fig. 3c, the first intersection point or the second intersection point may not exist in the optical band image. As shown in fig. 3a, since the preset angle of laser irradiation is oblique, rather than perpendicular, the band of light generated by the worn area C has certain imaging characteristics. The first imaging feature corresponding to the first target shape refers to the imaging feature of the bottom end of the "V" shape corresponding to the first line segment. The second imaging feature corresponding to the second target shape refers to the imaging feature of the bottom end of the "V" shape corresponding to the second line segment. The offset distortion feature refers to a feature corresponding to image distortion generated based on camera parameters of the image capturing device.
In one embodiment, determining the wear zone of the target zone based on all of the target texture features comprises: converting the target area into a binary image; performing vertical projection on the binary image to obtain a pixel density distribution diagram corresponding to the binary image in the vertical direction; determining a mutation region in the pixel density distribution map according to all the target texture features; and determining the abrasion zone of the target zone according to the mutation zone.
The processor may convert the target region into a binary image in order to determine the ROI region in which the abrasion position is located in the target region. The binary image means that in the image, the gray level is only two, that is, the gray value of any pixel point in the image is 0 or 255, which respectively represents black and white. Then, the processor may perform vertical projection on the binary image to obtain a pixel density distribution map corresponding to the binary image in a vertical direction. Wherein the vertical projection of the binary image can be used to calculate the pixel density distribution of the image in the vertical direction. Specifically, the binary image may be divided into a plurality of strips along the vertical direction, and then the number of pixels in each strip is calculated to finally obtain a pixel density distribution diagram along the vertical direction, and the pixel density distribution diagram may be used to detect vertical lines or other vertical structures in the image. The target texture features used to characterize the worn area exhibit a density profile corresponding to the pixel density profile. The processor may identify the abrupt regions in the determined pixel density profile based on all of the target texture features. The abrupt region refers to an image region in which the pixel density distribution map corresponds to the target texture feature. The first target texture feature comprises a first intersection point between the first line segment and curves at two ends of the first line segment, a first imaging feature corresponding to a first target shape generated on the optical tape, and an offset distortion feature of the optical tape. The second target texture feature comprises a second intersection point between the second line segment and curves at two ends of the second line segment, a second imaging feature corresponding to a second target shape generated on the optical band, and an offset distortion feature of the optical band. The processor may then determine the wear zone of the target zone from the abrupt region.
In one embodiment, locally clustering the wear zone to determine wear end points of the wear zone includes: performing dimension reduction treatment on the abrasion region to obtain a dimension-reduced abrasion region; and carrying out local clustering treatment on the wear areas after dimension reduction based on a super-pixel segmentation algorithm so as to determine wear endpoints.
Further, due to the longer length of the rigid suspension catenary, rapid image recognition can be achieved by simplifying the complexity of the image calculation. In particular, the processor may image encode the worn region using a circular LBP operator, reducing the image dimension of the worn region. And then carrying out local clustering treatment on the wear area after dimension reduction by using a super-pixel segmentation algorithm in deep learning, and determining wear endpoints at two ends of the wear area. In another embodiment, the identification of the secondary pixel particles may also be performed by a Support Vector Machine (SVM) technique to identify anomalies in the wear area. Then, the processor may calculate the wear width from the wear end points obtained from the clustering result.
According to the technical scheme, the rigid suspension contact net is irradiated through the laser device according to the preset angle, so that a light band is generated on the rigid suspension contact net, a light band image of the rigid suspension contact net is obtained, and the abrasion width of the rigid suspension contact net is detected. The simple installation attribute of the area array camera enhances the adaptability to the intensity and the installation angle of light rays. Based on special texture features in the light band images, the abrasion positions are identified, so that non-invasive detection can be realized, and the detection result has high precision and strong instantaneity. The detection is carried out under the condition that the normal operation of the railway train is not affected, and an effective guarantee means is provided for the power supply maintenance of the subway line.
Fig. 2 is a flow chart of a wear detection method for a rigid suspension catenary in one embodiment. It should be understood that, although the steps in the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Fig. 4 schematically shows a block diagram of the structure of a detection device according to an embodiment of the application. As shown in fig. 4, an embodiment of the present application is a detection apparatus 400, including:
a laser device 410 for irradiating the rigid suspension catenary according to a preset angle to generate a light band at the rigid suspension catenary;
the image acquisition device 420 is used for acquiring the light band image of the rigid suspension catenary;
the processor 430 is configured to perform the wear detection method for rigid suspension catenary described above.
Specifically, the optimal angle between the light emitted by the laser device and the rigid suspension contact net is 30 degrees, and the image acquisition device is erected right in front of the light band. The optimal distance between the detection equipment and the rigid suspension contact net is 65cm, and the optimal distance between the laser device and the image acquisition device is 100cm, so that clear and accurate images can be acquired. The image acquisition device acquires an image of the light band while the rigid suspension contact net generates the light band. The laser device can be a structural light laser, and the emitted light presents a light band on the rigid suspension contact net. The image acquisition device may be an area camera. The area array camera mainly adopts continuous and planar scanning light to realize the detection of the rigid suspension contact net, and can acquire a complete light band image at one time.
Specifically, in one embodiment, the processor 430 may be configured to:
acquiring a light band image of a rigid suspension contact net;
extracting a plurality of texture features of the light band image;
dividing the light band image according to the texture features to obtain a target area corresponding to the abrasion position of the light band image;
determining target texture features of a plurality of texture features, wherein the target texture features comprise first target texture features corresponding to a first line segment included in a target line segment region in a light band and second target texture features corresponding to a second line segment included in the target line segment region, and the target line segment region refers to a region where a line segment perpendicular to a rigid suspension direction is located;
determining the abrasion area of the target area according to all the target texture features;
carrying out local clustering treatment on the abrasion areas to determine abrasion end points of the abrasion areas;
and determining the abrasion width of the rigid suspension contact net according to the abrasion end points.
In one embodiment, the processor 430 may be configured to: the first target texture feature is at least one of a first intersection point between the first line segment and curves at two ends of the first line segment, a first imaging feature corresponding to a first target shape generated on the optical tape, and an offset distortion feature of the optical tape, and the second target texture feature is at least one of a second intersection point between the second line segment and curves at two ends of the second line segment, a second imaging feature corresponding to a second target shape generated on the optical tape, and an offset distortion feature of the optical tape.
In one embodiment, the processor 430 may be configured to: extracting the plurality of texture features of the optical band image includes: denoising the optical band image through a filter to obtain a denoised optical band image; processing the denoised light band image based on a histogram equalization algorithm to obtain a target image corresponding to the denoised light band image; and extracting features of the target image based on a local binary pattern algorithm or a gray level co-occurrence matrix algorithm to obtain a plurality of texture features of the light band image.
In one embodiment, the processor 530 may be configured to: dividing the optical band image according to the texture features to obtain a target area corresponding to the abrasion position of the optical band image, wherein the steps comprise: the texture features comprise global features and local features, and the optical band image is segmented according to the global features to obtain an optical band region in the optical band image; and dividing the light band region according to the local characteristics to obtain a target region corresponding to the abrasion position in the light band region.
In one embodiment, the processor 430 may be configured to: determining the wear zone of the target zone based on all of the target texture features includes: converting the target area into a binary image; performing vertical projection on the binary image to obtain a pixel density distribution diagram corresponding to the binary image in the vertical direction; determining a mutation region in the pixel density distribution map according to all the target texture features; and determining the abrasion zone of the target zone according to the mutation zone.
In one embodiment, the processor 430 may be configured to: local clustering of the worn area to determine a wear endpoint of the worn area includes: performing dimension reduction processing on the second area image corresponding to the abrasion area to obtain a dimension-reduced second area image; and carrying out local clustering treatment on the second region image after dimension reduction based on a super-pixel segmentation algorithm so as to determine an abrasion endpoint.
In one embodiment, as shown in fig. 5, there is provided a wear detection device 500 for a rigid suspension catenary, including an image acquisition module, an image segmentation module, a wear identification module, and a width detection module, wherein:
the image acquisition module 520 is configured to acquire an optical band image of the rigid suspension catenary.
An image segmentation module 540 for extracting a plurality of texture features of the light band image; and dividing the light band image according to the texture features to obtain a target area corresponding to the abrasion position of the light band image.
The abrasion recognition module 560 is configured to determine target texture features of a plurality of texture features, where the target texture features include a first target texture feature corresponding to a first line segment included in a target line segment region in the optical band, and a second target texture feature corresponding to a second line segment included in the target line segment region, and the target line segment region is a region where a line segment perpendicular to the rigid suspension direction is located; and determining the abrasion area of the target area according to all the target texture features.
The width detection module 580 performs local clustering treatment on the abrasion region to determine an abrasion endpoint of the abrasion region; and determining the abrasion width of the rigid suspension contact net according to the abrasion end points.
In one embodiment, the first target texture feature is at least one of a first intersection between the first line segment and a curve at both ends of the first line segment, a first imaging feature corresponding to a first target shape generated on the optical tape, and an offset distortion feature of the optical tape, and the second target texture feature is at least one of a second intersection between the second line segment and a curve at both ends of the second line segment, a second imaging feature corresponding to a second target shape generated on the optical tape, and an offset distortion feature of the optical tape.
In one embodiment, the image segmentation module 540 is further configured to: denoising the optical band image through a filter to obtain a denoised optical band image; processing the denoised light band image based on a histogram equalization algorithm to obtain a target image corresponding to the denoised light band image; and extracting features of the target image based on a local binary pattern algorithm or a gray level co-occurrence matrix algorithm to obtain a plurality of texture features of the light band image.
In one embodiment, the image segmentation module 540 is further configured to: the texture features comprise global features and local features, and the optical band image is segmented according to the global features to obtain an optical band region in the optical band image; and dividing the light band region according to the local characteristics to obtain a target region corresponding to the abrasion position in the light band region.
In one embodiment, wear identification module 560 is further configured to: converting the target area into a binary image; performing vertical projection on the binary image to obtain a pixel density distribution diagram corresponding to the binary image in the vertical direction; determining a mutation region in the pixel density distribution map according to all the target texture features; and determining the abrasion zone of the target zone according to the mutation zone.
In one embodiment, the width detection module 580 is further to: performing dimension reduction processing on the second area image corresponding to the abrasion area to obtain a dimension-reduced second area image; and carrying out local clustering treatment on the second region image after dimension reduction based on a super-pixel segmentation algorithm so as to determine an abrasion endpoint.
In one embodiment, the predetermined angle is 30 degrees.
The abrasion detection device for the rigid suspension catenary comprises a processor and a memory, wherein the image acquisition module, the image segmentation module, the abrasion identification module, the width detection module and the like are all stored in the memory as program units, and the processor executes the program modules stored in the memory to realize corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The inner core can be provided with one or more than one, and the abrasion detection method for the rigid suspension catenary is realized by adjusting the parameters of the inner core.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
The embodiment of the application provides a storage medium, on which a program is stored, which when executed by a processor, implements the wear detection method for a rigid suspension catenary.
The embodiment of the application provides a processor which is used for running a program, wherein the abrasion detection method for the rigid suspension catenary is executed when the program runs.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor a01, a network interface a02, a memory (not shown) and a database (not shown) connected by a system bus. Wherein the processor a01 of the computer device is adapted to provide computing and control capabilities. The memory of the computer device includes internal memory a03 and nonvolatile storage medium a04. The nonvolatile storage medium a04 stores an operating system B01, a computer program B02, and a database (not shown in the figure). The internal memory a03 provides an environment for the operation of the operating system B01 and the computer program B02 in the nonvolatile storage medium a04. The database of the computer device is used for storing wear detection data for the rigid suspension catenary. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program B02, when executed by the processor a01, implements a wear detection method for a rigid suspension catenary.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the abrasion detection method for the rigid suspension catenary when executing the program.
The application also provides a computer program product adapted to perform a program initialized with the steps of the wear detection method for a rigid suspension catenary as described below when executed on a data processing device.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A wear detection method for a rigid suspension catenary, characterized in that a laser device irradiates the rigid suspension catenary at a preset angle to generate a light band at the rigid suspension catenary, the detection method comprising:
acquiring a light band image of the rigid suspension catenary;
extracting a plurality of texture features of the band image;
dividing the light band image according to the texture features to obtain a target area corresponding to the abrasion position of the light band image;
determining target texture features of the texture features, wherein the target texture features comprise first target texture features corresponding to a first line segment included in a target line segment region in the optical tape and second target texture features corresponding to a second line segment included in the target line segment region, and the target line segment region refers to a region where a line segment perpendicular to a rigid suspension direction is located;
determining an abrasion zone of the target zone according to all target texture features;
carrying out local clustering treatment on the abrasion area to determine an abrasion endpoint of the abrasion area;
and determining the abrasion width of the rigid suspension contact net according to the abrasion end points.
2. The wear detection method for a rigid suspension catenary of claim 1, wherein the first target texture feature is at least one of a first intersection between the first line segment and a curve at both ends of the first line segment, a first imaging feature corresponding to a first target shape generated on the optical strip, and an offset distortion feature of the optical strip, and the second target texture feature is at least one of a second intersection between the second line segment and a curve at both ends of the second line segment, a second imaging feature corresponding to a second target shape generated on the optical strip, and an offset distortion feature of the optical strip.
3. The method for wear detection of a rigid suspension catenary of claim 1, wherein the extracting the plurality of texture features of the light band image comprises:
denoising the light band image through a filter to obtain a denoised light band image;
processing the denoised light band image based on a histogram equalization algorithm to obtain a target image corresponding to the denoised light band image;
and extracting features of the target image based on a local binary pattern algorithm or a gray level co-occurrence matrix algorithm to obtain a plurality of texture features of the light band image.
4. The abrasion detection method for a rigid suspension catenary according to claim 1, wherein the dividing the light band image according to the plurality of texture features to obtain a target area corresponding to an abrasion position of the light band image comprises:
the plurality of texture features includes global features and local features,
dividing the light band image according to the global features to obtain a light band region of the light band image;
and dividing the light band region according to the local characteristics to obtain a target region corresponding to the abrasion position in the light band region.
5. The wear detection method for a rigid suspension catenary of claim 1, wherein the determining the wear area of the target area based on all target texture features comprises:
converting the target area into a binary image;
performing vertical projection on the binary image to obtain a pixel density distribution diagram corresponding to the binary image in a vertical direction;
determining a mutation region in the pixel density distribution map according to all target texture features;
and determining the abrasion area of the target area according to the mutation area.
6. The wear detection method for a rigid suspension catenary of claim 1, wherein the locally clustering the wear zone to determine a wear endpoint of the wear zone comprises:
performing dimension reduction treatment on the abrasion region to obtain a dimension-reduced second region image;
and carrying out local clustering treatment on the abrasion areas based on a super-pixel segmentation algorithm so as to determine the abrasion end points.
7. The wear detection method for a rigid suspension catenary according to claim 1, wherein the preset angle is 30 degrees.
8. A processor configured to perform the wear detection method for a rigid suspension catenary according to any one of claims 1 to 7.
9. A detection apparatus, characterized in that the detection apparatus comprises:
the laser device is used for irradiating the rigid suspension contact net according to a preset angle so as to generate a light band on the rigid suspension contact net;
the image acquisition device is used for acquiring the light band image of the rigid suspension contact net; and
the processor of claim 8.
10. A machine-readable storage medium having instructions stored thereon, which when executed by a processor, cause the processor to be configured to perform the wear detection method for a rigid suspension catenary according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311288612.0A CN117029696B (en) | 2023-10-08 | 2023-10-08 | Abrasion detection method and detection equipment for rigid suspension contact net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311288612.0A CN117029696B (en) | 2023-10-08 | 2023-10-08 | Abrasion detection method and detection equipment for rigid suspension contact net |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117029696A true CN117029696A (en) | 2023-11-10 |
| CN117029696B CN117029696B (en) | 2024-01-02 |
Family
ID=88641488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311288612.0A Active CN117029696B (en) | 2023-10-08 | 2023-10-08 | Abrasion detection method and detection equipment for rigid suspension contact net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117029696B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013008600B3 (en) * | 2013-05-22 | 2014-08-28 | Db Netz Ag | Method for optical contact wire strength measurement of a catenary of rail traffic |
| US20160025977A1 (en) * | 2014-07-22 | 2016-01-28 | Osterhout Group, Inc. | External user interface for head worn computing |
| CN106274979A (en) * | 2016-08-30 | 2017-01-04 | 大连民族大学 | Rail wear automatic detection device |
| CN109269403A (en) * | 2017-07-17 | 2019-01-25 | 成都唐源电气股份有限公司 | A kind of contact line conducting wire measurement of wear method and device based on machine vision |
| CN112284267A (en) * | 2020-12-18 | 2021-01-29 | 成都弓网科技有限责任公司 | Contact line abrasion detection method and system |
| CN113465541A (en) * | 2021-07-09 | 2021-10-01 | 北京运达华开科技有限公司 | Contact line abrasion measuring method and system |
| CN113701628A (en) * | 2021-08-20 | 2021-11-26 | 中国铁道科学研究院集团有限公司 | Dynamic measuring method and device for contact line abrasion |
| CN214893085U (en) * | 2021-05-12 | 2021-11-26 | 成都弓网科技有限责任公司 | Contact wire abrasion rapid measuring device |
| CN114693619A (en) * | 2022-03-18 | 2022-07-01 | 杭州申昊科技股份有限公司 | Rigid contact net abrasion detection method, equipment and storage medium |
| CN114964008A (en) * | 2022-04-14 | 2022-08-30 | 北京京港地铁有限公司 | Portable contact line continuous abrasion measuring instrument and measuring method for rigid contact net |
| CN115631194A (en) * | 2022-12-08 | 2023-01-20 | 首都医科大学附属北京天坛医院 | Method, device, equipment and medium for identifying and detecting intracranial aneurysm |
-
2023
- 2023-10-08 CN CN202311288612.0A patent/CN117029696B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013008600B3 (en) * | 2013-05-22 | 2014-08-28 | Db Netz Ag | Method for optical contact wire strength measurement of a catenary of rail traffic |
| US20160025977A1 (en) * | 2014-07-22 | 2016-01-28 | Osterhout Group, Inc. | External user interface for head worn computing |
| CN106274979A (en) * | 2016-08-30 | 2017-01-04 | 大连民族大学 | Rail wear automatic detection device |
| CN109269403A (en) * | 2017-07-17 | 2019-01-25 | 成都唐源电气股份有限公司 | A kind of contact line conducting wire measurement of wear method and device based on machine vision |
| CN112284267A (en) * | 2020-12-18 | 2021-01-29 | 成都弓网科技有限责任公司 | Contact line abrasion detection method and system |
| CN214893085U (en) * | 2021-05-12 | 2021-11-26 | 成都弓网科技有限责任公司 | Contact wire abrasion rapid measuring device |
| CN113465541A (en) * | 2021-07-09 | 2021-10-01 | 北京运达华开科技有限公司 | Contact line abrasion measuring method and system |
| CN113701628A (en) * | 2021-08-20 | 2021-11-26 | 中国铁道科学研究院集团有限公司 | Dynamic measuring method and device for contact line abrasion |
| CN114693619A (en) * | 2022-03-18 | 2022-07-01 | 杭州申昊科技股份有限公司 | Rigid contact net abrasion detection method, equipment and storage medium |
| CN114964008A (en) * | 2022-04-14 | 2022-08-30 | 北京京港地铁有限公司 | Portable contact line continuous abrasion measuring instrument and measuring method for rigid contact net |
| CN115631194A (en) * | 2022-12-08 | 2023-01-20 | 首都医科大学附属北京天坛医院 | Method, device, equipment and medium for identifying and detecting intracranial aneurysm |
Non-Patent Citations (4)
| Title |
|---|
| 彭朝勇;高晓蓉;: "国外接触网导线磨耗检测系统", 中国铁路, no. 04, pages 71 - 73 * |
| 王佳;王瑞锋;: "电气化铁路接触线磨耗动态检测系统研究", 郑铁科技, no. 04, pages 13 - 17 * |
| 艾力·居麦等: "视频图像中维吾尔文字的识别研究", 《计算机工程与应用》, vol. 47, no. 36, pages 190 - 192 * |
| 靳成等: "轨道交通接触线磨损实时在线检测研究", 《激光杂志》, vol. 41, no. 1, pages 26 - 30 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117029696B (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mu et al. | Lane detection based on object segmentation and piecewise fitting | |
| CN107871319B (en) | Method and device for detecting beam limiter area, X-ray system and storage medium | |
| CN111027535A (en) | License plate recognition method and related equipment | |
| CN111144228B (en) | Obstacle identification method based on 3D point cloud data and computer equipment | |
| Kocur et al. | Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement | |
| JP2012038318A (en) | Target detection method and device | |
| CN114529459A (en) | Method, system and medium for enhancing image edge | |
| US20150178573A1 (en) | Ground plane detection | |
| CN109583393A (en) | A kind of lane line endpoints recognition methods and device, equipment, medium | |
| CN115272852A (en) | Method, equipment and medium for identifying hidden danger of power transmission line protection area | |
| CN113158864A (en) | Method and device for determining included angle between truck head and trailer | |
| CN117952960B (en) | Electric power iron tower part defect detection method based on artificial intelligence | |
| CN113763412B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN115311631A (en) | Image acquisition method, device and medium in tunnel | |
| Balovsyak et al. | Segmentation of railway transport images using fuzzy logic | |
| CN108197622A (en) | A kind of detection method of license plate, device and equipment | |
| CN117029696B (en) | Abrasion detection method and detection equipment for rigid suspension contact net | |
| CN111127381B (en) | Non-parallel detection method for pantograph slide plate | |
| CN118196043A (en) | Whole vehicle component detection method based on machine vision and three-dimensional point cloud fusion | |
| CN114842166A (en) | Negative obstacle detection method, system, medium, and apparatus applied to structured road | |
| CN116342656B (en) | Space-time image speed measurement method and device based on self-adaptive edge detection | |
| CN117691592A (en) | Photovoltaic output prediction method and device, electronic equipment and storage medium | |
| Ikeda et al. | Traffic measurement with a roadside vision system-individual tracking of overlapped vehicles | |
| CN117854033A (en) | Target detection method and device and electronic equipment | |
| CN117095178A (en) | Water accumulation depth identification method and device, electronic equipment and readable storage medium |
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 |