CN116958099B - Cable abrasion detection method, system, device and computer equipment - Google Patents
Cable abrasion detection method, system, device and computer equipment Download PDFInfo
- Publication number
- CN116958099B CN116958099B CN202310934545.9A CN202310934545A CN116958099B CN 116958099 B CN116958099 B CN 116958099B CN 202310934545 A CN202310934545 A CN 202310934545A CN 116958099 B CN116958099 B CN 116958099B
- Authority
- CN
- China
- Prior art keywords
- abrasion
- network cable
- contact network
- cable
- value
- 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
- 238000005299 abrasion Methods 0.000 title claims abstract description 425
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 238000012545 processing Methods 0.000 claims abstract description 58
- 230000003287 optical effect Effects 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000004590 computer program Methods 0.000 claims description 38
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 238000003384 imaging method Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 18
- 230000005856 abnormality Effects 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 13
- 230000007547 defect Effects 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 10
- 239000000126 substance Substances 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application relates to a cable abrasion detection method, a system, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a light band image of a contact network cable; performing processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region; 3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained; when the abrasion value in the contact network cable is larger than a preset abrasion threshold, identifying a special abrasion area in the contact network cable, extracting the abrasion surface characteristics of the special abrasion area, and pushing the abrasion value and the corresponding abrasion surface characteristics. The whole scheme can realize accurate cable abrasion detection.
Description
Technical Field
The present application relates to the field of cable wear detection technology, and in particular, to a cable wear detection method, system, apparatus, computer device, storage medium, and computer program product.
Background
In the current receiving system, abrasion is necessarily generated in a high-speed sliding contact process of the pantograph and the contact net cable. The contact net overhauling is an important part in the maintenance of an electrified railway, the contact cable abrasion detection is an important point and a difficult point, the contact cable abrasion detection is directly related to the dynamic current-carrying quality of a contact net cable and a pantograph, the contact cable abrasion causes the cable section to be reduced, the cable resistance to be increased, the contact net cable heats, the cable abrasion is aggravated, and if the cable section is too small, the cable is broken, and huge losses are brought to railway operation.
The traditional conventional contact network cable abrasion detection scheme is that the contact network cable abrasion detection result is obtained through processing means such as manual scale measurement, radar, camera shooting and the like.
Although the above-described method can realize the cable abrasion detection, the detection accuracy is not high. Therefore, a high-precision cable wear detection scheme is urgently needed.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a high-precision cable abrasion detection method, system, apparatus, computer device, storage medium, and computer program product.
In a first aspect, the present application provides a cable wear detection method. The method comprises the following steps:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
Pushing the wear value of the contact net cable and the corresponding wear face characteristics.
In one embodiment, the acquiring an optical band image of the contact network cable includes:
The method comprises the steps of collecting a light band image of a contact network cable under irradiation of double-line laser through a binocular camera, wherein the double-line laser irradiates a preset point position of the contact network cable at a preset irradiation angle, and the binocular camera is arranged on a vertical line of the preset point position.
In one embodiment, the processing the optical band image to obtain the abrasion interested area of the contact network cable, and according to the abrasion interested area, obtaining the abrasion initial value of the contact network cable includes:
converting the light band image to a gray scale image;
Extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image;
Fusion matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable;
noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interest region, and the abrasion interest region of the contact network cable is obtained;
and acquiring an initial abrasion value of the contact net cable according to the abrasion interested region.
In one embodiment, the fusing the horizontal projection features and the vertical projection features to obtain the initial wear region of interest of the contact network cable includes:
fusion matching the horizontal projection characteristic and the vertical projection characteristic to obtain a V-shaped binarized image;
Acquiring bottom boundary information of the V-shaped binarized image;
And randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
In one embodiment, the 3D positioning the position of the contact network cable, and compensating the initial wear value based on the positioning result, to obtain the wear value of the contact network cable includes:
3D positioning is carried out on the position of the contact network cable, and the offset distance of the contact network cable in the space direction is obtained;
And converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
In one embodiment, the cable wear detection method further includes:
imaging abnormality identification is carried out on the light band image;
If the imaging abnormality identification is passed, the light band image is subjected to noise reduction processing based on strong and weak light noise, and the step of processing target matching is carried out on the light band image.
In one embodiment, when the abrasion value in the contact network cable is greater than a preset abrasion threshold, identifying a special abrasion area in the contact network cable, and extracting the abrasion surface characteristics of the special abrasion area includes:
When the abrasion value in the contact network cable is larger than a preset abrasion threshold value, carrying out feature recognition on the contact network cable to identify a special abrasion region in the contact network cable, wherein the feature recognition comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point connection recognition and arc burning generation chemical abrasion recognition;
and extracting the abrasion surface characteristics of the special abrasion region, and judging the abrasion section form.
In a second aspect, the present application also provides a cable wear detection system. The system comprises:
The image acquisition module is used for acquiring an optical band image of the contact network cable;
the matching module is used for carrying out processing target matching on the optical band images, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region;
the abrasion value acquisition module is used for carrying out 3D positioning on the position of the contact network cable and compensating the abrasion initial value based on a positioning result to obtain the abrasion value of the contact network cable;
the abrasion surface characteristic extraction module is used for identifying a special abrasion area in the contact network cable and extracting the abrasion surface characteristic of the special abrasion area when the abrasion value in the contact network cable is larger than a preset abrasion threshold value;
And the pushing module is used for pushing the abrasion value and the corresponding abrasion surface characteristic of the contact net cable.
In a third aspect, the present application also provides a cable wear detection device, including a dual-line laser, a binocular camera, and a controller;
The double-wire laser irradiates a contact network cable; the binocular camera collects the optical band images of the contact network cable and sends the optical band images to the controller; the controller performs cable wear detection using the method described above.
In a fourth aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
Pushing the wear value of the contact net cable and the corresponding wear face characteristics.
In a fifth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
Pushing the wear value of the contact net cable and the corresponding wear face characteristics.
In a sixth aspect, the application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
Pushing the wear value of the contact net cable and the corresponding wear face characteristics.
The above-described cable wear detection methods, systems, apparatus, computer devices, storage media, and computer program products acquire an optical band image of a contact network cable; performing processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region; 3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained; when the abrasion value in the contact network cable is larger than a preset abrasion threshold, identifying a special abrasion area in the contact network cable, extracting the abrasion surface characteristics of the special abrasion area, and pushing the abrasion value and the corresponding abrasion surface characteristics. In the whole process, the obtained abrasion initial value is compensated based on the position of the cable which is out of the net, so that a more accurate abrasion value is obtained, corresponding abrasion surface characteristics are extracted according to the condition that the abrasion value is large, and meanwhile, the more accurate abrasion value and the abrasion surface characteristics are fed back, so that accurate cable abrasion detection can be realized.
Drawings
FIG. 1 is an application environment diagram of a cable wear detection method in one embodiment;
FIG. 2 is a flow chart of a cable wear detection method according to one embodiment;
FIG. 3 is a schematic diagram of a sub-process of S200 in one embodiment;
FIG. 4 is a schematic diagram of a cable wear detection device in an example application;
FIG. 5 is a block diagram of a cable wear detection system in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The cable abrasion detection method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. The whole cable abrasion detection method is applied to a cable abrasion detection device, specifically, the whole cable abrasion detection device comprises a double-line laser, a binocular camera, a controller and a display assembly, wherein the double-line laser irradiates a contact network cable to generate a V-shaped light band, the binocular camera shoots a light band image and sends the light band image to the controller, and the controller acquires the light band image of the contact network cable; performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region; 3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained; when the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area; and pushing the abrasion value of the contact net cable and the corresponding abrasion surface characteristics to the display assembly, so that operators can know the abrasion detection result of the contact net cable through the display assembly (display screen).
In one embodiment, as shown in fig. 2, a cable abrasion detecting method is provided, and the method is applied to the controller in fig. 1 for illustration, and includes the following steps:
s100: an optical band image of the contacted net cable is acquired.
The optical band image of the contact network cable may be acquired by an image acquisition device. Specifically, the contact net cable can be irradiated by a light laser to generate a V-shaped light band, and then an image of the light band is acquired by an image acquisition device. Here, the image pickup apparatus may be a binocular camera by which an optical band image may be photographed at a high speed in real time.
S200: and performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region.
And (3) performing processing target matching on the optical band image to identify and intercept an abrasion interested region of the contact network cable, processing the abrasion interested region through an algorithm to obtain a pixel value corresponding to the abrasion width, and converting the pixel value into an abrasion initial value of the contact network cable. Specifically, the target matching is fusion matching of the binary projection of the V-shaped light band in the light band image in the horizontal direction and the binary projection in the vertical direction, and the abrasion region of interest can be determined after the fusion matching.
S300: and 3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained.
The camera positions of the rigid suspension and the electric train roof are constantly changed, and because the tunnel and the track laying construction are strictly required, the corresponding 3D positions of the rigid suspension and the electric train roof are changed, and the changes are in line with the linear changes, the conversion between the pixel and the actual distance can be realized by using the distance conversion coefficient, and the abrasion initial value is further compensated, so that the abrasion value of the contact network cable is more accurate. Specifically, the position of the contact network cable in the actual image acquisition process is subjected to 3D positioning, and the states of left and right pulling out or up and down floating and the like of the cable are detected in real time. And then the initial abrasion value is compensated by a compensation mechanism of the position of the contact net cable, so that the abrasion value is calculated more accurately, and the influence of various offsets of the contact net cable on the abrasion value calculation in actual use is eliminated.
S400: and when the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area.
The preset wear value threshold is a preset value, which can be understood as a corresponding wear value threshold when significant wear occurs to the contact network cable. When the abrasion value in the contact net cable is greater than the preset abrasion threshold, the current contact net cable is indicated to have more obvious abrasion, at this time, special abrasion areas are required to be further identified, the special abrasion areas can be specifically large abrasion, eccentric abrasion, broken abrasion and the like, the abrasion surface characteristics of the special abrasion areas are identified, and the abrasion section forms such as eccentric abrasion, broken abrasion, local abrasion, transverse abrasion, oblique abrasion and the like are judged, so that analysis processing of the abrasion state of the contact net cable is further realized.
S500: the wear value of the push contact net cable, and the corresponding wear face characteristics.
And pushing the abrasion value obtained in the step S300 and the abrasion surface characteristics obtained in the step S400 to external display equipment together, so that a user can intuitively know the abrasion condition of the contact network cable, and accurate contact network cable abrasion detection is realized.
According to the cable abrasion detection method, the optical band image of the contact network cable is obtained; performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region; 3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained; when the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, extracting the abrasion surface characteristics of the special abrasion area, and pushing the abrasion value and the corresponding abrasion surface characteristics. In the whole process, the obtained abrasion initial value is compensated based on the position of the cable which is out of the net, so that a more accurate abrasion value is obtained, corresponding abrasion surface characteristics are extracted according to the condition that the abrasion value is large, and meanwhile, the more accurate abrasion value and the abrasion surface characteristics are fed back, so that accurate cable abrasion detection can be realized. In one embodiment, acquiring an optical band image of a contact network cable includes:
The method comprises the steps of collecting a light band image of a contact network cable under irradiation of double-line laser through a binocular camera, wherein the double-line laser irradiates a preset point position of the contact network cable at a preset irradiation angle, and the binocular camera is arranged on a vertical line of the preset point position.
In this embodiment, the optical band image of the contact net cable under the irradiation of the two-wire laser is acquired by the binocular camera. Specifically, the preset position of the contact net cable can be irradiated by a double-line laser according to a certain angle, and then the optical band image is acquired by a binocular camera. Further, the preset irradiation angle refers to an angle between the horizontal axis and the two-wire laser emitted by the two-wire laser, and the angle can be specifically set according to the actual situation, for example, 30 °, 33 °,35 ° and the like. The binocular camera is arranged on the vertical line of the preset point position, so that the contact network cable is shot vertically to obtain a light band image. Further, the binocular camera may be disposed at a lower portion of the contact net cable, and the camera photographs the cable vertically upward. Optionally, the distance between the two-wire laser and the binocular camera, and the distance from the binocular camera to the contact network cable may be set according to the actual situation.
In practical application, as shown in fig. 3, the two-line laser, the binocular camera and other settings can be placed on the net inspection vehicle, the net inspection vehicle moves along the direction of the contact net cable, the two-line laser irradiates the contact net cable at an angle of 33 degrees, the binocular camera is placed under the irradiation position, the binocular camera shoots the contact net cable vertically upwards, and the light band image is acquired. The distance between the double-line laser and the binocular camera is 100 cm, and the height from the binocular camera to the contact network cable is 65 cm.
In one embodiment, as shown in fig. 4, S200 includes:
S210: converting the light band image into a gray scale image;
S220: extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image;
S230: fusing and matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable;
s240: noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interested region, and the abrasion interested region of the contact network cable is obtained;
s250: and acquiring an initial abrasion value of the contact net cable according to the abrasion region of interest.
The acquired light band image is converted into a grayscale image. In the gray level image, the distribution of the light bands in the horizontal direction accords with the Gaussian distribution state, so that the horizontal projection characteristic is obtained by carrying out Gaussian transformation interception processing according to the distribution area of the white part of the horizontal projection after the binarization of the gray level image. Similarly, the distribution of the light bands in the vertical direction also accords with the Gaussian distribution state, so that the interception processing of Gaussian transformation can be performed according to the distribution area of the vertical projection after the binarization of the gray level image, and the binary projection characteristic sum in the vertical direction is obtained, namely the vertical projection characteristic after the binarization of the gray level image is obtained. And carrying out fusion matching on the acquired horizontal projection characteristics and vertical projection characteristics, determining an initial abrasion interested region of the contact network cable, and then carrying out processing of a plurality of noise reduction algorithms and fine granularity algorithms to obtain the most suitable abrasion interested region. And acquiring the initial abrasion value of the contact net cable according to the abrasion interested region. Furthermore, in the fusion matching process, in order to accelerate the matching speed of the target, a probability prediction algorithm and a high-speed matching algorithm of poisson distribution can be used for realizing millisecond-level matching in the vertical direction.
In one embodiment, fusing the matched horizontal projection features and vertical projection features to obtain an initial wear region of interest for contacting the net cable includes:
Fusion matching of horizontal projection features and vertical projection features to obtain a V-shaped binarized image; acquiring bottom boundary information of a V-shaped binarized image; and randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
The horizontal projection characteristic and the vertical projection characteristic are fused and matched to obtain a V-shaped binary image, and the result of intercepting the region of interest is the central abrasion position of the lower part of the V-shape. Specifically, the whole interception includes: firstly, fusing and matching horizontal projection features and vertical projection features to obtain a V-shaped binarized image, and acquiring bottom boundary information of the V-shaped binarized image according to the V-shaped binarized image; then, selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point; and finally, screening and fine-tuning a plurality of initial interested rectangular areas based on the fusion matching result to obtain an initial abrasion interested area.
In one embodiment, performing 3D positioning on a contact network cable position, and compensating for an initial wear value based on a positioning result, to obtain a wear value of the contact network cable includes:
3D positioning is carried out on the position of the contact network cable, and the offset distance of the contact network cable in the space direction is obtained; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
Specifically, the position of the contact network cable can be subjected to 3D positioning, the offset distances of the contact network cable in the upper, lower, left and right spatial directions are obtained, the offset distances are converted into coefficients, then the initial abrasion value is subjected to nonlinear change, the detection precision of the contact network cable in the spatial offset process is enhanced, and the more accurate abrasion value of the contact network cable is obtained.
In particular, the contact network cable position may be 3D located by a binocular camera. The whole treatment process comprises the following steps: obtaining depth of a target contact network cable in X, Y, Z directions, establishing a linear change function according to a mathematical model (the mathematical model is established according to cable position change of a binocular camera acquisition whole line), and obtaining a final coefficient by inputting parameters such as a target position parameter, an electronic map parameter and the like, wherein the coefficient is obtained by two parts, and the result is that the offset compensation value is added with a pixel value at the back; the second is the deformation coefficient (for later multiplication with the pixel value). For example, the rod number information of the target position (-12,9,2) and the corresponding whole line is Y32-18, the corresponding electronic map is obtained, and the offset value 2 and the coefficient 0.186311593 are finally obtained based on the target position, the electronic map and other parameters and correction parameters of other mathematical models, namely-0.1795268,0.02313175, -0.0011255, -0.0011191.
In one embodiment, the cable wear detection method further includes:
Imaging abnormality identification is carried out on the light band image; if the imaging abnormality identification is passed, the optical band image is subjected to noise reduction processing based on strong and weak optical noise, and the step of processing target matching of the optical band image is entered.
And when the imaging of the contact network cable is abnormal, such as the situation that the anchor section is connected, the cable is blocked, the cable is lost, the shot picture only has half of the outline of the light band, and the like, the special mode of the image algorithm is utilized for identification and alarm. If the imaging abnormality is identified, the current acquired effective image is indicated, the next processing can be continued, the light band image is subjected to noise reduction processing based on strong and weak light noise, and after the noise reduction processing, the subsequent processing target matching action of the light band image is performed. Specifically, if the imaging abnormality identification fails, that is, if the imaging abnormality is found to exist at the moment, a different identification mode is selected, for example, when the target is missing or is blocked by other objects, the target matching operation fails, then the blocking condition of the imaging light band can be determined according to a detection algorithm of a special mode, different types of identification algorithms are matched according to the blocking condition, and finally the corresponding identification result is notified to the system without carrying out subsequent abrasion value identification processing, and only abnormal alarm processing is carried out.
In addition, for abnormal pictures such as image noise caused by tunnel light and interference caused by laser irradiation, noise reduction processing is carried out by utilizing an image algorithm, the influence of noise on a light band is eliminated, and the region possibly having errors is accurately identified.
In one embodiment, when the wear value in the contact net cable is greater than the preset wear threshold, identifying a specific wear area in the contact net cable, and extracting the wear surface characteristics of the specific wear area includes:
When the abrasion value in the contact network cable is larger than a preset abrasion threshold value, carrying out feature recognition on the contact network cable to identify a special abrasion region in the contact network cable, wherein the feature recognition comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point connection recognition and arcing generation chemical abrasion recognition; and extracting the abrasion surface characteristics of the special abrasion area, and judging the abrasion section form.
The abrasion surface features are extracted by means of section identification. In particular, the method can be performed by using a 3D mode identification technology. In practical application, when the abrasion of the contact cable is abnormal or is detected as large abrasion, the lifting system can extract the characteristics of the abrasion surface of the cable, judge the abrasion section form (such as eccentric abrasion, broken abrasion, local abrasion, transverse abrasion, oblique abrasion and the like) and complete the analysis work of the abrasion state. Furthermore, the wear surface and the wear position of the line have a great relation with the line, and have influence on the driving habit of the vehicle, for example, the wear value near a platform is generally great, the curve area is seriously worn, and the matching degree of the section form is obtained by comparing the characteristics with the data processed by an algorithm, so that the purposes of identification and analysis are achieved.
In practical application, the feature recognition mainly comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point linking recognition and arcing generation chemical abrasion recognition. The following will be described separately for these recognition modes:
2D contour recognition: after smoothing the cross section texture, detecting a target contour area by using bilateral filtering detection, establishing an area coordinate value according to an edge point of the contour, and finally solving a square error and a center point distance according to an evaluation algorithm of the edge coordinate value to determine whether the contour is regular, smooth, abrupt change and irregular;
defect identification: detecting the mutation of the grinding surface on the space domain, wherein the black areas with irregular shapes exist in the textures, and the contour, the number and the positions of the black areas are judged to be the mutation abrasion in the local abrasion;
3D point cloud modality identification: according to the point cloud coordinates, clustering to obtain a wear plane, then finding out the normal line of the point cloud on the side surface of the cable, and judging whether the wear biased to one side exists or not by using whether the change of a normal line meets the linear change of radian;
Anchor point connection identification: the anchor point links out two V-shaped light bands, and the height change information and the position information of the two light bands are identified to identify whether the anchor point is an anchor point linking surface;
Identification of chemical abrasion generated by arcing: based on longitudinal and transverse texture recognition, the imaging effect is a continuous arc crescent contour, bilateral features of the crescent contour are utilized to convert the crescent contour into a form of point coordinates, and the distance between the crescent contour and the center coordinates is calculated to judge whether the condition is met.
Furthermore, the traditional technology adopts a manual mode to detect the abrasion of the cable, and has the defects of low continuity, complex structure, poor practicability and the like. The cable abrasion detection scheme is based on an image processing mode, can realize high-precision millisecond cable abrasion detection, is stable and reliable in structure, and is suitable for the requirement of subway high-speed uninterrupted abrasion detection.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order 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 the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a cable abrasion detection system for realizing the cable abrasion detection method. The implementation of the solution provided by the system is similar to that described in the above method, so specific limitations in one or more cable wear detection system embodiments provided below may be found in the limitations of the cable wear detection method described above, and will not be repeated here.
In one embodiment, as shown in fig. 5, there is provided a cable wear detection system comprising:
An image acquisition module 100 for acquiring an optical band image of a contact network cable;
the matching module 200 is used for performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region;
the abrasion value acquisition module 300 is used for performing 3D positioning on the position of the contact network cable and compensating an abrasion initial value based on a positioning result to obtain an abrasion value of the contact network cable;
The abrasion surface characteristic extraction module 400 is used for identifying a special abrasion area in the contact network cable and extracting the abrasion surface characteristic of the special abrasion area when the abrasion value in the contact network cable is larger than a preset abrasion threshold value;
the pushing module 500 is used for pushing the abrasion value of the contact network cable and the corresponding abrasion surface characteristic.
The cable abrasion detection system acquires a light band image of a contact network cable; performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region; 3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained; when the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, extracting the abrasion surface characteristics of the special abrasion area, and pushing the abrasion value and the corresponding abrasion surface characteristics. In the whole process, the obtained abrasion initial value is compensated based on the position of the cable which is out of the net, so that a more accurate abrasion value is obtained, corresponding abrasion surface characteristics are extracted according to the condition that the abrasion value is large, and meanwhile, the more accurate abrasion value and the abrasion surface characteristics are fed back, so that accurate cable abrasion detection can be realized.
In one embodiment, the image acquisition module 100 is further configured to acquire, by using a binocular camera, an optical band image of the contact network cable under irradiation of the two-line laser, where the two-line laser irradiates a preset point of the contact network cable at a preset irradiation angle, and the binocular camera is disposed on a vertical line of the preset point.
In one embodiment, the matching module 200 is further configured to convert the light band image to a grayscale image; extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image; fusing and matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable; noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interested region, and the abrasion interested region of the contact network cable is obtained; and acquiring an initial abrasion value of the contact net cable according to the abrasion region of interest.
In one embodiment, the matching module 200 is further configured to fuse the matching horizontal projection feature and the vertical projection feature to obtain a V-shaped binary image; acquiring bottom boundary information of a V-shaped binarized image; and randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
In one embodiment, the abrasion value obtaining module 300 is further configured to perform 3D positioning on the contact network cable position, and obtain an offset distance of the contact network cable in a spatial direction; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
In one embodiment, the matching module 200 is further configured to perform imaging anomaly identification on the light band image; if the imaging abnormality identification is passed, the optical band image is subjected to noise reduction processing based on strong and weak optical noise, and the processing of processing target matching of the optical band image is entered.
In one embodiment, the wear surface feature extraction module 400 is further configured to perform feature recognition on the contact network cable to identify a specific wear area in the contact network cable when the wear value in the contact network cable is greater than a preset wear threshold, where the feature recognition includes at least one of 2D contour recognition, defect recognition, 3D point cloud mode recognition, anchor point engagement recognition, and arcing generation chemical wear recognition; and extracting the abrasion surface characteristics of the special abrasion area, and judging the abrasion section form.
The various modules in the cable wear detection system described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In addition, the application also provides a cable abrasion detection device, which comprises a double-line laser, a binocular camera and a controller;
The double-wire laser irradiates the contact network cable; the binocular camera collects the optical band images of the contact network cable and sends the optical band images to the controller; the controller performs cable wear detection using the method described above.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by a processor implements a cable wear detection method.
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.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
the wear value of the push contact net cable, and the corresponding wear face characteristics.
In one embodiment, the processor when executing the computer program further performs the steps of:
The method comprises the steps of collecting a light band image of a contact network cable under irradiation of double-line laser through a binocular camera, wherein the double-line laser irradiates a preset point position of the contact network cable at a preset irradiation angle, and the binocular camera is arranged on a vertical line of the preset point position.
In one embodiment, the processor when executing the computer program further performs the steps of:
Converting the light band image into a gray scale image; extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image; fusing and matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable; noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interested region, and the abrasion interested region of the contact network cable is obtained; and acquiring an initial abrasion value of the contact net cable according to the abrasion region of interest.
In one embodiment, the processor when executing the computer program further performs the steps of:
Fusion matching of horizontal projection features and vertical projection features to obtain a V-shaped binarized image; acquiring bottom boundary information of a V-shaped binarized image; and randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
In one embodiment, the processor when executing the computer program further performs the steps of:
3D positioning is carried out on the position of the contact network cable, and the offset distance of the contact network cable in the space direction is obtained; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
In one embodiment, the processor when executing the computer program further performs the steps of:
Imaging abnormality identification is carried out on the light band image; if the imaging abnormality identification is passed, the optical band image is subjected to noise reduction processing based on strong and weak optical noise, and the step of processing target matching of the optical band image is entered.
In one embodiment, the processor when executing the computer program further performs the steps of:
When the abrasion value in the contact network cable is larger than a preset abrasion threshold value, carrying out feature recognition on the contact network cable to identify a special abrasion region in the contact network cable, wherein the feature recognition comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point connection recognition and arcing generation chemical abrasion recognition; and extracting the abrasion surface characteristics of the special abrasion area, and judging the abrasion section form.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
the wear value of the push contact net cable, and the corresponding wear face characteristics.
In one embodiment, the computer program when executed by the processor further performs the steps of:
The method comprises the steps of collecting a light band image of a contact network cable under irradiation of double-line laser through a binocular camera, wherein the double-line laser irradiates a preset point position of the contact network cable at a preset irradiation angle, and the binocular camera is arranged on a vertical line of the preset point position.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Converting the light band image into a gray scale image; extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image; fusing and matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable; noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interested region, and the abrasion interested region of the contact network cable is obtained; and acquiring an initial abrasion value of the contact net cable according to the abrasion region of interest.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Fusion matching of horizontal projection features and vertical projection features to obtain a V-shaped binarized image; acquiring bottom boundary information of a V-shaped binarized image; and randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
In one embodiment, the computer program when executed by the processor further performs the steps of:
3D positioning is carried out on the position of the contact network cable, and the offset distance of the contact network cable in the space direction is obtained; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Imaging abnormality identification is carried out on the light band image; if the imaging abnormality identification is passed, the optical band image is subjected to noise reduction processing based on strong and weak optical noise, and the step of processing target matching of the optical band image is entered.
In one embodiment, the computer program when executed by the processor further performs the steps of:
When the abrasion value in the contact network cable is larger than a preset abrasion threshold value, carrying out feature recognition on the contact network cable to identify a special abrasion region in the contact network cable, wherein the feature recognition comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point connection recognition and arcing generation chemical abrasion recognition; and extracting the abrasion surface characteristics of the special abrasion area, and judging the abrasion section form.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, acquiring an abrasion interest region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interest region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
the wear value of the push contact net cable, and the corresponding wear face characteristics.
In one embodiment, the computer program when executed by the processor further performs the steps of:
The method comprises the steps of collecting a light band image of a contact network cable under irradiation of double-line laser through a binocular camera, wherein the double-line laser irradiates a preset point position of the contact network cable at a preset irradiation angle, and the binocular camera is arranged on a vertical line of the preset point position.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Converting the light band image into a gray scale image; extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image; fusing and matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable; noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interested region, and the abrasion interested region of the contact network cable is obtained; and acquiring an initial abrasion value of the contact net cable according to the abrasion region of interest.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Fusion matching of horizontal projection features and vertical projection features to obtain a V-shaped binarized image; acquiring bottom boundary information of a V-shaped binarized image; and randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
In one embodiment, the computer program when executed by the processor further performs the steps of:
3D positioning is carried out on the position of the contact network cable, and the offset distance of the contact network cable in the space direction is obtained; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Imaging abnormality identification is carried out on the light band image; if the imaging abnormality identification is passed, the optical band image is subjected to noise reduction processing based on strong and weak optical noise, and the step of processing target matching of the optical band image is entered.
In one embodiment, the computer program when executed by the processor further performs the steps of:
When the abrasion value in the contact network cable is larger than a preset abrasion threshold value, carrying out feature recognition on the contact network cable to identify a special abrasion region in the contact network cable, wherein the feature recognition comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point connection recognition and arcing generation chemical abrasion recognition; and extracting the abrasion surface characteristics of the special abrasion area, and judging the abrasion section form.
The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1.A method of cable wear detection, the method comprising:
Acquiring a light band image of a contact network cable;
Performing processing target matching on the optical band image, obtaining an abrasion interested region of the contact network cable, and obtaining an abrasion initial value of the contact network cable according to the abrasion interested region, wherein the abrasion initial value is obtained based on a pixel value corresponding to an abrasion width, and the pixel value corresponding to the abrasion width is obtained based on the abrasion interested region;
3D positioning is carried out on the position of the contact network cable, and the abrasion initial value is compensated based on the positioning result, so that the abrasion value of the contact network cable is obtained;
When the abrasion value in the contact net cable is larger than a preset abrasion threshold value, identifying a special abrasion area in the contact net cable, and extracting the abrasion surface characteristics of the special abrasion area;
Pushing the abrasion value of the contact net cable and the corresponding abrasion surface characteristics;
The 3D positioning of the contact network cable position and the compensation of the abrasion initial value based on the positioning result are carried out, and the obtaining of the abrasion value of the contact network cable comprises the following steps: 3D positioning is carried out on the position of the contact network cable, and the offset distance of the contact network cable in the space direction is obtained; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
2. The method of claim 1, wherein the acquiring an optical band image of a contact network cable comprises:
The method comprises the steps of collecting a light band image of a contact network cable under irradiation of double-line laser through a binocular camera, wherein the double-line laser irradiates a preset point position of the contact network cable at a preset irradiation angle, and the binocular camera is arranged on a vertical line of the preset point position.
3. The method of claim 1, wherein the processing the optical band image to obtain an abrasion interest region of the contact network cable, and according to the abrasion interest region, obtaining an initial abrasion value of the contact network cable comprises:
converting the light band image to a gray scale image;
Extracting horizontal projection characteristics after binarization of the gray level image and vertical projection characteristics after binarization of the gray level image;
Fusion matching the horizontal projection characteristics and the vertical projection characteristics to obtain an initial abrasion interested region of the contact network cable;
noise reduction and fine granularity algorithm processing are carried out on the initial abrasion interest region, and the abrasion interest region of the contact network cable is obtained;
and acquiring an initial abrasion value of the contact net cable according to the abrasion interested region.
4. The method of claim 3, wherein the fusing the horizontal projection features and the vertical projection features to obtain an initial wear region of interest for the contact network cable comprises:
fusion matching the horizontal projection characteristic and the vertical projection characteristic to obtain a V-shaped binarized image;
Acquiring bottom boundary information of the V-shaped binarized image;
And randomly selecting a prediction center point according to the bottom boundary information, and expanding a plurality of initial interested rectangular areas by adopting a greedy algorithm based on the prediction center point to obtain an initial abrasion interested area of the contact network cable.
5. The method as recited in claim 1, further comprising:
imaging abnormality identification is carried out on the light band image;
If the imaging abnormality identification is passed, the light band image is subjected to noise reduction processing based on strong and weak light noise, and the step of processing target matching is carried out on the light band image.
6. The method of claim 1, wherein identifying a particular wear zone in the contact network cable when the wear value in the contact network cable is greater than a preset wear threshold, the extracting wear face characteristics of the particular wear zone comprises:
When the abrasion value in the contact network cable is larger than a preset abrasion threshold value, carrying out feature recognition on the contact network cable to identify a special abrasion region in the contact network cable, wherein the feature recognition comprises at least one of 2D contour recognition, defect recognition, 3D point cloud modal recognition, anchor point connection recognition and arc burning generation chemical abrasion recognition;
and extracting the abrasion surface characteristics of the special abrasion region, and judging the abrasion section form.
7. A cable wear detection system, the system comprising:
The image acquisition module is used for acquiring an optical band image of the contact network cable;
The matching module is used for carrying out processing target matching on the optical band image, acquiring an abrasion interested region of the contact network cable, and acquiring an abrasion initial value of the contact network cable according to the abrasion interested region, wherein the abrasion initial value is obtained based on a pixel value corresponding to an abrasion width, and the pixel value corresponding to the abrasion width is obtained based on the abrasion interested region;
the abrasion value acquisition module is used for carrying out 3D positioning on the position of the contact network cable and compensating the abrasion initial value based on a positioning result to obtain the abrasion value of the contact network cable;
the abrasion surface characteristic extraction module is used for identifying a special abrasion area in the contact network cable and extracting the abrasion surface characteristic of the special abrasion area when the abrasion value in the contact network cable is larger than a preset abrasion threshold value;
the pushing module is used for pushing the abrasion value of the contact net cable and the corresponding abrasion surface characteristics;
The abrasion value acquisition module is also used for carrying out 3D positioning on the position of the contact network cable to acquire the offset distance of the contact network cable in the space direction; and converting the offset distance into a coefficient, and performing nonlinear transformation on the abrasion initial value to obtain the abrasion value of the contact network cable.
8. The system of claim 7, wherein the image acquisition module is further configured to acquire an optical band image of a contact network cable under irradiation of a two-wire laser by a binocular camera, wherein the two-wire laser irradiates a preset point location of the contact network cable at a preset irradiation angle, and the binocular camera is disposed on a vertical line of the preset point location.
9. The cable abrasion detection device is characterized by comprising a double-line laser, a binocular camera and a controller;
The double-wire laser irradiates a contact network cable; the binocular camera collects the optical band images of the contact network cable and sends the optical band images to the controller; the controller performs cable wear detection using the method of any one of claims 1 to 6.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310934545.9A CN116958099B (en) | 2023-07-27 | 2023-07-27 | Cable abrasion detection method, system, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310934545.9A CN116958099B (en) | 2023-07-27 | 2023-07-27 | Cable abrasion detection method, system, device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116958099A CN116958099A (en) | 2023-10-27 |
| CN116958099B true CN116958099B (en) | 2024-05-24 |
Family
ID=88452509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310934545.9A Active CN116958099B (en) | 2023-07-27 | 2023-07-27 | Cable abrasion detection method, system, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958099B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117745537B (en) * | 2024-02-21 | 2024-05-17 | 微牌科技(浙江)有限公司 | Tunnel equipment temperature detection method, device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007235950A (en) * | 2006-02-28 | 2007-09-13 | Alpine Electronics Inc | Method and device for detecting vehicle position |
| CN104504529A (en) * | 2014-12-31 | 2015-04-08 | 北京太格时代自动化***设备有限公司 | Overhead line routing inspection electronic tag system based on wireless radio frequency technology |
| CN108830303A (en) * | 2018-05-29 | 2018-11-16 | 广州微牌智能科技有限公司 | Vehicle identification method, device, computer equipment and storage medium |
| 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 |
| CN113487543A (en) * | 2021-06-16 | 2021-10-08 | 成都唐源电气股份有限公司 | Contact net arcing firing detection method, device, computer equipment and storage medium |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3195262A4 (en) * | 2014-09-15 | 2018-09-19 | DTI Group Limited | Arc detection system and method |
-
2023
- 2023-07-27 CN CN202310934545.9A patent/CN116958099B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007235950A (en) * | 2006-02-28 | 2007-09-13 | Alpine Electronics Inc | Method and device for detecting vehicle position |
| CN104504529A (en) * | 2014-12-31 | 2015-04-08 | 北京太格时代自动化***设备有限公司 | Overhead line routing inspection electronic tag system based on wireless radio frequency technology |
| CN108830303A (en) * | 2018-05-29 | 2018-11-16 | 广州微牌智能科技有限公司 | Vehicle identification method, device, computer equipment and storage medium |
| CN113487543A (en) * | 2021-06-16 | 2021-10-08 | 成都唐源电气股份有限公司 | Contact net arcing firing detection method, device, computer equipment and storage medium |
| 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 |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| Application of computer vision system to the inspection of contact wire wear;S. Borromeo et al.;《WIT Transacitons on the Built Environment》;20050322;第175-183页 * |
| 基于改进Retinex算法的雾天车牌识别***的研究;李宗正;《中国优秀博硕士学位论文全文数据库(硕士)》;20190115(第1期);第1-88页 * |
| 基于机器视觉的高铁接触网磨耗检测***的研究;李先军;《中国优秀博硕士学位论文全文数据库(硕士)》;20140815(第8期);第1-50页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116958099A (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jang et al. | Automated crack evaluation of a high‐rise bridge pier using a ring‐type climbing robot | |
| CN110032962B (en) | Object detection method, device, network equipment and storage medium | |
| CN116958099B (en) | Cable abrasion detection method, system, device and computer equipment | |
| CN111292275B (en) | Point cloud data filtering method and device based on complex ground and computer equipment | |
| CN107004266A (en) | The method for detecting defect on surface of tyre | |
| Arjapure et al. | Deep learning model for pothole detection and area computation | |
| CN117492026B (en) | Railway wagon loading state detection method and system combined with laser radar scanning | |
| US20210232859A1 (en) | Vehicle damage estimation | |
| Buza et al. | Unsupervised method for detection of high severity distresses on asphalt pavements | |
| JP7226494B2 (en) | Contact wire wear detection method | |
| CN109919839B (en) | Tunnel graph splicing method | |
| Adu-Gyamfi et al. | Functional evaluation of pavement condition using a complete vision system | |
| CN110717910B (en) | CT image target detection method based on convolutional neural network and CT scanner | |
| Guan et al. | Multi-scale asphalt pavement deformation detection and measurement based on machine learning of full field-of-view digital surface data | |
| CN116681687A (en) | Wire detection method and device based on computer vision and computer equipment | |
| CN110751623A (en) | Joint feature-based defect detection method, device, equipment and storage medium | |
| KR101637977B1 (en) | Feature point detecting method of welding joint using laser vision system | |
| US11748876B2 (en) | Joint surface safety evaluation apparatus | |
| CN113920055A (en) | Defect detection method | |
| EP4285315A1 (en) | Systems and methods for paint defect detection using machine learning | |
| Ranyal et al. | AI assisted pothole detection and depth estimation | |
| Ashraf et al. | Efficient Pavement Crack Detection and Classification Using Custom YOLOv7 Model | |
| KR101904170B1 (en) | Coding Device and Method for Depth Information Compensation by Sphere Surface Modeling | |
| JP6488478B2 (en) | Overhead line inspection device | |
| CN116188973B (en) | Crack detection method based on cognitive generation mechanism |
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 |