CN107154034B - State detection method and system for stay wire positioning hook of high-speed rail contact network - Google Patents
State detection method and system for stay wire positioning hook of high-speed rail contact network Download PDFInfo
- Publication number
- CN107154034B CN107154034B CN201610120479.1A CN201610120479A CN107154034B CN 107154034 B CN107154034 B CN 107154034B CN 201610120479 A CN201610120479 A CN 201610120479A CN 107154034 B CN107154034 B CN 107154034B
- Authority
- CN
- China
- Prior art keywords
- area
- region
- image
- positioning
- positioning hook
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a state detection method and system for a stay wire positioning hook of a high-speed rail contact network, and belongs to the field of safety detection of electrified high-speed rail contact networks. The method comprises the following steps: firstly, acquiring an interested area image of each strut of a high-speed rail contact network in real time through image acquisition equipment; the image of the region of interest comprises a positioning pipe, an inclined stay wire and an inclined stay wire positioning hook; then separating a positioning hook area in the image of the region of interest; the positioning hook area comprises an inclined pull positioning hook and an inclined pull, and is divided into a left area and a right area by calculating the direction of the inclined pull in the positioning hook area, and the state of the inclined pull positioning hook is judged according to the direction of the inclined pull and the number of communicated areas in the left area and the right area. By the method and the system provided by the invention, the efficiency and the accuracy of the fault detection of the diagonal positioning hook are effectively improved, the safety of a high-speed rail overhead line system is guaranteed, and the potential safety hazard can be effectively reduced.
Description
Technical Field
The invention relates to the field of safety detection of electrified high-speed rail contact networks, in particular to a method and a system for detecting the state of a stay wire positioning hook of a high-speed rail contact network.
Background
With the further development and wide application of the high-speed railway transportation technology, the high-speed railway catenary is also receiving more and more attention as an important facility for providing electric energy for locomotives, whether the high-speed railway catenary is in a safe working state or not. The stay wire positioning hook is an important component of a positioning device in a contact net, and the good state of the stay wire positioning hook directly determines the stability of a supporting device so as to determine the normal power supply of the electric locomotive. At present, the contact network detection fault mode is manual on-line inspection during skylight operation, and is also the same for the detection of a diagonal cable positioning hook, but because the environment of a line is complex, the condition of missed detection is probably caused by factors such as high risk of manual observation, uneven quality of workers and the like, and potential safety hazards are caused. Therefore, how to rapidly and accurately detect the state of the end part of the diagonal brace of the high-speed rail contact network is a problem to be solved urgently.
Disclosure of Invention
Aiming at the defects in the prior art and the requirements of practical application, the invention aims to provide a method and a system for detecting the state of a stay cable positioning hook of a high-speed rail contact network, so as to realize the real-time and rapid detection of the state of the stay cable positioning hook.
In order to achieve the purpose, the invention adopts the technical scheme that: a state detection method for a stay wire positioning hook of a high-speed rail contact network comprises the following steps:
(1) acquiring an interested area image of each strut of a high-speed rail contact network in real time through image acquisition equipment; the interested area image comprises a positioning pipe, an inclined stay wire and an inclined stay wire positioning hook;
(2) separating a positioning hook region in the region-of-interest image; the positioning hook area comprises an inclined stay wire positioning hook and an inclined stay wire; the way of separating out the positioning hook area is as follows:
①, carrying out binarization processing on the region-of-interest image to obtain a binarized image;
②, performing morphological corrosion treatment on the binary image to obtain a corrosion image, and determining the positioning tube region according to the characteristics of each communication region in the corrosion image, wherein the characteristics of the communication region in the corrosion image comprise the area, the rectangular degree and the angle of the communication region, and the angle of the communication region refers to the included angle between the minimum circumscribed affine rectangle of the communication region and the horizontal plane;
③, according to the preset first rectangular structural element, performing first morphological expansion processing on the positioning tube area in the binary image to obtain a first expanded image, and according to the preset second rectangular structural element, performing second morphological expansion processing on the positioning tube area in the binary image to obtain a second expanded image, wherein the height of the second rectangular structural element is less than that of the first rectangular element;
④ calculating the intersection region of the first expanded image and the binary image, calculating the difference region of the intersection region and the second expanded image, and determining the positioning hook region in the difference region according to the characteristics of each connected region in the difference region, wherein the characteristics of the connected regions in the difference region comprise the area, the rectangular degree, the width and the height of the connected regions;
(3) calculating the direction of a diagonal cable in a positioning hook area, dividing the positioning hook area into a left area and a right area, and judging the state of the diagonal cable positioning hook according to the direction of the diagonal cable and the number of communicated areas in the left area and the right area; the state of the diagonal cable positioning hook comprises normal positioning hook and reverse positioning hook installation.
Further, the method for detecting the state of the positioning hook of the stay wire of the overhead line system of the high-speed rail as described above, before performing the first morphological expansion and the second morphological expansion on the positioning tube region in the binarized image, further includes: horizontally correcting the positioning tube region in a correction mode that:
calculating the horizontal inclination of the positioning pipe area, and horizontally correcting the positioning pipe area according to the horizontal inclination; the way to calculate the horizontal inclination of the localizer region is:
and calculating the included angle between the minimum circumscribed affine rectangle of the positioning pipe area and the horizontal plane, wherein the included angle is the horizontal gradient of the positioning pipe area.
Further, in the method for detecting the state of the positioning hook of the diagonal cable of the overhead line system of the high-speed rail, before the binarization processing is performed on the region of interest in step ①, the method further includes performing enhancement processing on the region of interest by using linear transformation, where a formula of the enhancement processing is as follows:
g′=g×Mult+Mult×GMin
Mult=255/(GMax-GMin)
wherein g is the gray value of a pixel point in the image before enhancement processing, and g' is the gray value of a pixel point in the image after enhancement processing; mult is a linear transform coefficient; GMax and GMin represent the maximum and minimum grayscale values, respectively, in the image before enhancement processing.
Further, according to the method for detecting the state of the stay cable positioning hook of the overhead line system of the high-speed rail, in the step (3), the way of calculating the direction of the stay cable in the positioning hook area is as follows:
1) dividing a positioning hook area into an upper area and a lower area; the upper area is an area only containing diagonal cables;
2) calculating an included angle Phi between the minimum circumscribed rectangle of the area where the diagonal cables are located in the upper area and the horizontal plane, wherein the included angle is the direction of the diagonal cables,Phi>0 indicates that the opening of the angle Phi is oriented to the right, Phi<0 indicates that the opening of the angle Phi is oriented to the left; wherein, the side of the interested area image where the support is positioned is the right side.
Further, according to the method for detecting the state of the stay wire positioning hook of the overhead line system of the high-speed rail, in the step 1), the positioning hook area is divided into an upper area and a lower area in a manner that:
and setting an upper area height threshold according to the size of the positioning hook area, and dividing the upper area according to the area height threshold.
Further, according to the state detection method for the stay wire positioning hook of the high-speed rail overhead line system, in the step (3), the positioning hook area is divided into the left area and the right area in the following manner:
3.1) calculating a column coordinate ColumnStart at the leftmost end and a column coordinate ColumnEnd at the rightmost end of the minimum right circumscribed rectangle in the area where the stay wire positioning hook is positioned in the lower area; the minimum positive circumscribed rectangle is a minimum circumscribed rectangle with an included angle with the horizontal plane being zero; the column coordinates are transverse coordinates;
3.2) the lower region is divided equally into two regions, left and right, with a vertical line passing through the coordinates (ColumStart + ColumEnd)/2.
Further, according to the method for detecting the state of the diagonal positioning hook of the overhead line system of the high-speed rail, in the step (3), the mode of judging the state of the diagonal positioning hook according to the direction of the diagonal and the number of the communicated areas in the left area and the right area is as follows:
the Number of the connected areas of the left area in the left area and the right area is set as NumberleftThe number of connected regions in the right region isNumberright;
When the following condition I is met, the state of the inclined stay wire positioning hook is normal, and when the following condition II is met, the state of the inclined stay wire positioning hook is reversely installed;
the first condition is as follows: numberleft>NumberrightAnd Phi>0, or, alternatively,
Numberleft<Numberrightand Phi<0;
And a second condition: numberleft≥NumberrightAnd Phi is less than or equal to 0, or,
Numberleft≤Numberrightand Phi is more than or equal to 0, or,
Numberleft=Numberrightand Phi is 0.
Further, the method for detecting the state of the stay wire positioning hook of the overhead line system of the high-speed rail as described above further includes, in step (1), before the step of segmenting the region of interest in the image, the step of: and carrying out scaling processing on the image.
In order to achieve the above object, an embodiment of the present invention further provides a state detection system for a diagonal positioning hook of a high-speed rail contact system, including:
the interesting region acquisition module is used for acquiring an interesting region image of each strut of the high-speed rail overhead line system in real time through image acquisition equipment; the interested area image comprises a positioning pipe, an inclined stay wire and an inclined stay wire positioning hook;
the positioning hook region separation module is used for separating a positioning hook region in the region-of-interest image; the positioning hook area comprises an inclined stay wire positioning hook and an inclined stay wire; the positioning hook area separating module includes:
the image binarization unit is used for carrying out binarization processing on the region-of-interest image to obtain a binarized image;
the image corrosion processing unit is used for performing morphological corrosion processing on the binary image and determining a positioning tube region according to the characteristics of each communication region in the corrosion image; the characteristics of the connected region in the corrosion image comprise the area, the rectangular degree and the angle of the connected region; the angle of the communication area refers to the included angle between the minimum circumscribed affine rectangle of the communication area and the horizontal plane;
the image expansion processing unit is used for carrying out first morphological expansion processing on a positioning tube area in the binary image according to a preset first rectangular structural element to obtain a first expanded image; the positioning tube expansion processing device is also used for carrying out second morphological expansion processing on the positioning tube area in the binary image according to a preset second rectangular structural element to obtain a second expansion image; the height of the second rectangular structural element is smaller than that of the first rectangular element;
the positioning hook area determining unit is used for determining a positioning hook area, and the determining mode is as follows: calculating an intersection region of the first expanded image and the binary image, calculating a difference region of the intersection region and the second expanded image, and determining a positioning hook region in the difference region according to the characteristics of each communicated region in the difference region; the characteristics of the connected region in the difference region comprise the area, the rectangular degree, the width and the height of the connected region;
the positioning hook state judgment module is used for judging the state of the diagonal positioning hook in a mode of: calculating the direction of a diagonal cable in a positioning hook area, dividing the positioning hook area into a left area and a right area, and judging the state of the diagonal cable positioning hook according to the direction of the diagonal cable and the number of communicated areas in the left area and the right area; the state of the diagonal cable positioning hook comprises normal positioning hook and reverse positioning hook installation.
Further, as above the state detecting system of the diagonal positioning hook of the overhead line system of the high-speed rail, the positioning hook area separation module further includes:
the horizontal correction unit is used for calculating the horizontal inclination of the positioning tube area before the first morphological expansion and the second morphological expansion processing are carried out on the positioning tube area in the binary image, and carrying out horizontal correction on the positioning tube area according to the horizontal inclination; the way to calculate the horizontal inclination of the localizer region is:
and calculating the included angle between the minimum circumscribed affine rectangle of the positioning pipe area and the horizontal plane, wherein the included angle is the horizontal gradient of the positioning pipe area.
The invention has the beneficial effects that: the method and the system provided by the invention can rapidly complete the rapid detection of the state of the diagonal positioning hook, improve the efficiency and the accuracy of the fault detection of the diagonal positioning hook, find the fault in the high-speed rail contact network as early as possible, provide guarantee for the safety of the high-speed rail contact network and effectively reduce the potential safety hazard.
Drawings
Fig. 1 is a flowchart of a state detection method for a diagonal positioning hook of a high-speed rail contact network in an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a supporting device part in a high-speed rail overhead line system;
fig. 3 is a block diagram of a state detection system of a diagonal positioning hook of a high-speed rail contact network in a specific embodiment of the present invention;
FIG. 4 is an image of a region of interest in an embodiment;
FIG. 5 is the binarized image of FIG. 4;
FIG. 6 is a schematic illustration of a localized tube region in a first erosion expansion image in an example embodiment;
FIG. 7 is a second erosion dilation image of an example;
FIG. 8 is a diagram illustrating an image of an intersection region in an embodiment;
FIG. 9 is a schematic diagram of an image of a difference region in an embodiment;
FIG. 10 is an enlarged view of the area of the positioning hook of the embodiment;
FIGS. 11(a) and (b) are schematic views showing the directions of diagonal cables and diagonal cables in the example;
fig. 12(a) and (b) are schematic views of the left and right regions in the example, respectively.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
The invention provides a method and a system for detecting the state of a diagonal positioning hook of a high-speed rail contact network, aiming at the problems of low efficiency, high cost and missed detection in the conventional manual online inspection mode adopted in the fault detection of the high-speed rail contact network.
Fig. 1 shows a flowchart of a method for detecting a state of a diagonal positioning hook of a high-speed rail catenary according to an embodiment of the present invention, and as can be seen from the diagram, the method may include the following steps:
step S100: acquiring an interested area image of each strut of a high-speed rail contact network in real time through image acquisition equipment;
in order to realize real-time monitoring and judgment of the state of a stay cable positioning hook in a high-speed rail contact network, a high-definition image acquisition device is used for acquiring an ROI (region of interest) image of each strut of the high-speed rail contact network in a high-speed rail running line in real time, wherein the ROI comprises a positioning pipe, a stay cable positioning hook and the like.
In the embodiment, firstly, a high-definition image of the positioning device part of each strut of the high-speed rail contact network is acquired through high-definition image acquisition equipment, and the high-definition image can be directly used as an image of the region of interest. In practical application, in order to improve the speed of data processing and analysis, the acquired original high-definition image can be zoomed and then roughly segmented, a part of background image in the image and other parts except the positioning tube, the inclined stay wire and the inclined stay wire positioning hook are cut off, and the image with the cut-off part of the background image is used as an image of the region of interest. Fig. 2 shows a simple structure schematic diagram of a part of a supporting device and a positioning device of a high-speed rail overhead line system, and the diagram includes structures such as a positioning pipe 1, a diagonal cable 2, a diagonal cable positioning hook 3, and the like. In actual operation, the high-definition images of each contact net positioning device in a high-speed rail running line can be acquired in real time through outdoor image acquisition equipment arranged on the roof of a detection vehicle, and the acquired high-definition images need to be determined to comprise a positioning pipe 1, an inclined stay wire 2, an inclined stay wire positioning hook 3 and other structures.
When the image scaling processing is performed, the scaling multiple of the image can be set according to actual needs. In actual operation, specific scaling factors and image segmentation modes can be determined according to the actual conditions of the acquired images.
After the images of the interested areas are cut out, in order to more highlight the characteristics of the positioning pipes, the inclined stay wires and the inclined stay wire positioning hooks, the images of interest can be subjected to image enhancement processing. In this embodiment, linear transformation is adopted to perform enhancement processing on the region of interest, and the formula of the enhancement processing is as follows:
g′=g×Mult+Add
Add=Mult×GMin
Mult=255/(GMax-GMin)
wherein g is the gray value of a pixel point in the image before enhancement processing, and g' is the gray value of a pixel point in the image after enhancement processing; mult is a linear transform coefficient; add is a linear transformation increment, and GMax and GMin represent the maximum gray value and the minimum gray value, respectively, in the image before enhancement processing.
Step S200: separating a positioning hook area in the image of the region of interest;
in order to judge the state of the positioning hook, a positioning hook area is firstly separated from an image of an area of interest, and the positioning hook area comprises a diagonal positioning hook and a diagonal connected with the diagonal positioning hook. In this embodiment, the manner of separating the positioning hook region is:
①, carrying out binarization processing on the region-of-interest image to obtain a binarized image;
②, performing morphological erosion processing on the binary image to obtain an erosion image, determining a positioning tube region according to the characteristics of each communication region in the erosion image, wherein the characteristics of the communication region in the erosion image comprise the area, the rectangle degree and the angle of the communication region, the angle of the communication region refers to the included angle between the minimum circumscribed affine rectangle of the communication region and the horizontal plane, and because the region-of-interest image comprises some other positioning support components besides the positioning tube, the positioning hook and the diagonal cable connected with the positioning hook, in order to separate the concerned positioning tube, the positioning hook and the section of the diagonal cable directly connected with the positioning hook, in the embodiment, the positioning tube region is separated by erosion, and the separated positioning tube region mainly comprises the positioning tube, the positioning hook and the section of the diagonal cable directly connected with the positioning hook.
③, according to the preset first rectangular structural element, performing first morphological expansion processing on the positioning tube area in the binary image to obtain a first expanded image, and according to the preset second rectangular structural element, performing second morphological expansion processing on the positioning tube area in the binary image to obtain a second expanded image, wherein the height of the second rectangular structural element is less than that of the first rectangular element;
④ calculating the intersection region of the first expanded image and the binary image, calculating the difference region of the intersection region and the second expanded image, and determining the positioning hook region in the difference region according to the characteristics of each connected region in the difference region, wherein the characteristics of the connected regions in the difference region comprise the area, the rectangular degree, the width and the height of the connected regions.
In this embodiment, in order to separate the foreground (the positioning hook, the diagonal cable, and the diagonal cable positioning hook) from the background in the region-of-interest image, after the morphological erosion processing is performed on the binarized image, a plurality of connected regions may appear in the eroded image in step ①, and since the positioning tube structure (including the diagonal cable positioning hook and a part of the diagonal cable thereon) and its position in the positioning device are significantly different from other structures, the characteristics of the connected region in the region in which the positioning tube is located may also be significantly different from the connected regions corresponding to other structures, and therefore, the region in which the positioning tube is located may be determined according to the characteristics (area, rectangularity, and angle) of each connected region in the eroded expanded image.
It should be noted that, the morphological dilation processing in step ③ is processing of the original image in the binarized image, and is not performed on the basis of the eroded image, the purpose of the morphological erosion processing in step ② is to separate the positioning tube and the structures in a certain range around the positioning tube through the intersection of the processed image and the binarized image, the separation precision is not high, as long as the positioning tube, the positioning hooks on the positioning tube and part of the diagonal lines in the separated image are included, the purpose of the second morphological dilation processing in step ③ is to more accurately separate the region of the positioning tube itself, so as to obtain the region of the positioning hooks by comparing the region of the positioning tube itself with the intersection region.
In this embodiment, in order to horizontally position the diagonal positioning hooks for the purpose of calculating the diagonal direction in the following step ③, before performing the first morphological dilation process and the second morphological dilation process on the positioning tube region in the region-of-interest image, the method further includes a step of horizontally correcting the positioning tube region, where the correction method is:
and calculating the horizontal inclination of the positioning pipe area, and horizontally correcting the positioning pipe area according to the horizontal inclination to horizontally place the positioning hooks, so that the inclined pull positioning hooks are horizontally placed. The way to calculate the horizontal inclination of the localizer region is: and calculating the included angle between the minimum circumscribed rectangle of the positioning pipe area and the horizontal plane, wherein the included angle is the horizontal inclination of the positioning pipe area.
And step S300, calculating the direction of the inclined stay wire, dividing the positioning hook area into a left area and a right area, and judging the state of the inclined stay wire positioning hook according to the inclined stay wire direction and the number of the communicated areas in the left area and the right area.
In practical applications, there are many interesting region images to be processed, and in order to increase the processing speed of a large amount of data, it is usually necessary to adjust the images to be processed to a uniform image format requirement. In this case, if the pillar is on the left side in the original image acquired in step S100, the image needs to be horizontally flipped first so that the pillar is on the right side, and as shown in the schematic diagram of fig. 2, it is necessary to first horizontally flip the image and then perform step S300 in the present embodiment.
Of course, the side away from the pillar may be defined as left, and in this case, the subsequent determinations of the left and right regions in the present embodiment need only be interchanged.
In this embodiment, the method of calculating the direction of the diagonal cable in the positioning hook region is:
1) dividing a positioning hook area into an upper area and a lower area; the upper area is an area only containing diagonal cables; in practical application, the upper and lower regions of the positioning hook region can be divided in different manners, so long as the upper region is ensured to only contain the inclined pull wire. One of the dividing methods provided in this embodiment is: and setting an upper area height threshold according to the size of the positioning hook area, and dividing the upper area of the positioning hook area according to the area height threshold.
2) Calculating an included angle Phi between the minimum circumscribed rectangle of the area where the diagonal cables are located in the upper area and the horizontal plane, wherein the included angle is the direction of the diagonal cables,Phi>0 indicates that the opening of the angle Phi is oriented to the right, Phi<0 indicates that the opening of the angle Phi is oriented to the left. In the present embodiment, the angle is expressed in terms of radian.
In actual operation, the positioning hook area can be divided into a left area and a right area in a plurality of modes, and the positioning hook structure can be divided into a left part and a right part. In this embodiment, the method of dividing the hook area into two areas, i.e., the left area and the right area, is as follows:
1) calculating a column coordinate ColumnStart at the leftmost end and a column coordinate ColumnEnd at the rightmost end of a minimum right circumscribed rectangle in the area where the stay cable positioning hook is located in the lower area; the minimum positive circumscribed rectangle is a minimum circumscribed rectangle with an included angle with the horizontal plane being zero; in this embodiment, the origin of the coordinate system is the upper left corner coordinate of the image of the region of interest, and the column coordinate refers to the horizontal coordinate;
2) the lower region is divided equally into two regions on the left and right by a vertical line passing (ColumnStart + ColumnEnd)/2.
Then, the mode of judging the state of the inclined stay wire positioning hook according to the direction of the inclined stay wire and the number of the communication areas in the left area and the right area is as follows:
the Number of the connected areas of the left area in the left area and the right area is set as NumberleftThe Number of connected areas of the right area is Numberright;
When the following condition I is met, the state of the inclined stay wire positioning hook is normal, and when the following condition II is met, the state of the inclined stay wire positioning hook is reversely installed;
the first condition is as follows: numberleft>NumberrightAnd Phi>0, or, alternatively,
Numberleft<Numberrightand Phi<0;
And a second condition: numberleft≥NumberrightAnd Phi is less than or equal to 0, or,
Numberleft≤Numberrightand Phi is more than or equal to 0, or,
Numberleft=Numberrightand Phi is 0.
The state detection method for the stay cable positioning hook provided by the embodiment can realize the quick real-time detection of the state of the stay cable positioning hook, provides a basis for early finding of the faults of the contact network and giving early warning information, and ensures that the contact network is in a good working state, so as to be beneficial to the safe operation of the electrified railway.
Corresponding to the method shown in fig. 1, the embodiment of the present invention further provides a state detection system for a diagonal positioning hook of a high-speed rail contact network, and as shown in fig. 3, the system may include an interested area obtaining module 100, a positioning hook area separating module 200, and a positioning hook state determining module 300.
The interested area acquisition module 100 is used for acquiring an interested area image of each strut of the high-speed rail overhead line system in real time through image acquisition equipment; the interested area image comprises a positioning pipe, an inclined stay wire and an inclined stay wire positioning hook;
a location hook region separation module 200, configured to separate a location hook region in the region of interest image; the positioning hook area comprises an inclined stay wire positioning hook and an inclined stay wire; the hook area module includes:
an image binarization unit 201, configured to perform binarization processing on the region-of-interest image to obtain a binarized image;
a horizontal correction unit 202, configured to calculate a horizontal inclination of the localization tube region before subjecting the localization tube region in the binarized image to the first morphological dilation and the second morphological dilation, and perform horizontal correction on the localization tube region according to the horizontal inclination; the way to calculate the horizontal inclination of the localizer region is: calculating an included angle between the minimum circumscribed affine rectangle of the positioning pipe area and the horizontal plane, wherein the included angle is the horizontal inclination of the positioning pipe area;
the image corrosion processing unit 203 is used for performing morphological corrosion processing on the binary image and determining a positioning tube region according to the characteristics of each communication region in the corrosion image; the characteristics of the connected region in the corrosion image comprise the area, the rectangular degree and the angle of the connected region; the angle of the communication area refers to the included angle between the minimum circumscribed affine rectangle of the communication area and the horizontal plane;
the image expansion processing unit 204 is configured to perform first morphological expansion processing on a positioning tube region in the binarized image according to a preset first rectangular structural element to obtain a first expanded image; the positioning tube expansion processing device is also used for carrying out second morphological expansion processing on the positioning tube area in the binary image according to a preset second rectangular structural element to obtain a second expansion image; the height of the second rectangular structural element is smaller than that of the first rectangular element;
a location hook area determination unit 205, configured to determine a location hook area in a manner that: calculating an intersection region of the first expanded image and the binary image, calculating a difference region of the intersection region and the second expanded image, and determining a positioning hook region in the difference region according to the characteristics of each communicated region in the difference region; the characteristics of the connected region in the difference region comprise the area, the rectangular degree, the width and the height of the connected region;
the positioning hook state judgment module 300 is configured to judge a state of a diagonal positioning hook in the following manner: calculating the direction of a diagonal cable in a positioning hook area, dividing the positioning hook area into a left area and a right area, and judging the state of the diagonal cable positioning hook according to the direction of the diagonal cable and the number of communicated areas in the left area and the right area; the state of the diagonal cable positioning hook comprises normal positioning hook and reverse positioning hook installation.
In order that the invention may be better understood, the invention will now be further described with reference to specific examples.
Examples
Firstly, an image of an area of interest of a contact net of each strut of a high-speed rail running line is acquired through image acquisition equipment. Fig. 4 shows an image of the region of interest acquired in this embodiment, where the size of the image is 1000 × 1000, and the image includes the positioning tube 1, the oblique stay wires 2, and the oblique stay wire positioning hooks 3. Then, the image is subjected to enhancement processing, and then binarization processing is performed to obtain a binarized image, and fig. 5 is a binarized image obtained by binarizing fig. 4.
After the image binarization processing is completed, morphological erosion processing is performed on the binarized image shown in fig. 5, the positioning tube regions where the positioning tubes, the positioning hooks and part of the diagonal lines are located in fig. 5 are separated according to the comparison between the area (the area in the embodiment is the total number of pixels in the image), the rectangle degree and the angle of each connected region in the eroded image and the preset area threshold value, the rectangle degree threshold value and the angle threshold value of the connected region of the positioning tube, and the separated positioning tube regions are horizontally corrected according to the horizontal gradient of the positioning tube regions so as to be horizontally placed. In the present embodiment, the communication area of the predetermined positioning pipe area is in the area range of [20000,99999], the rectangular degree range of [0.5,1], and the angular range of [ -0.3,0.3 ].
After the registration pipe region is separated, the morphological dilation process is performed twice on the partial region in the binary image, the size of the first rectangular structural element of the first morphological dilation process in this embodiment is 70 × 160 (number of pixels), 70 is the width, and 160 is the height, and the registration pipe region subjected to the first dilation process in this embodiment is as shown in fig. 6. The rectangular structural element of the second morphological dilation process is 70 x 1 and the resulting second dilated image is shown in fig. 7.
Then, determining a positioning hook area (a positioning hook and a part of diagonal wires connected with the positioning): first, the intersection region of the first erosion image and the binarized image is calculated, and fig. 8 is an intersection region image of the first expansion image shown in fig. 6 and the binarized image shown in fig. 5 in this embodiment. Then, the intersection region shown in fig. 8 and the difference region of the second expanded image shown in fig. 7 are calculated, the difference region image is shown in fig. 9, and finally the area, the squareness, the width and the height of each connected region in the difference region shown in fig. 9 are compared with the threshold values of the preset features to determine the location hook region in the difference region, in this embodiment, the area range of the connected region of the preset location hook is [330,400], the squareness range is [0.35,0.65], the height and width ranges are [50,80] and [25,50], and the location hook region is determined by comparing the feature of each connected region in the difference image with the ranges of the preset features, and fig. 10 shows an enlarged view of the location hook region in this embodiment.
For the positioning hook region, the direction of the diagonal lines in the positioning hook region, i.e. the included angle between the minimum bounding rectangle of the region where the diagonal lines are located and the horizontal plane, is calculated, first, the positioning hook region is divided into an upper region and a lower region, in this embodiment, the upper and lower regions are divided into an upper region and a lower region in a manner that the minimum positive bounding rectangle (the included angle between the rectangle and the horizontal plane) of the positioning hook region is calculated, first, the upper left corner of the positioning hook region is taken as the image coordinate origin, the width direction of the image is taken as the COLUMN coordinate (positive right), the height direction is taken as the ROW coordinate (positive downward), the upper left corner coordinate of the minimum positive bounding rectangle of the positioning hook region is taken as (ROW1, COLUMN1), the lower right corner coordinate is taken as (ROW2, COLUMN2), a preset upper region height threshold value in this embodiment is n pixels, then, the upper left corner coordinate of the upper region is taken as (ROW1, COLUMN1), the lower right corner coordinate is taken as a rectangle 56sw 7 + n, colunn 2, and certainly, as the left and right corner of the horizontal range of the positioning hook region is taken as the extended range, i, the left and right angle of the left-diagonal line of the positioning hook region is taken as the schematic drawing 11, and the left-right angle of the schematic drawing 11, which is taken as the schematic drawing of the drawing of.
Dividing the positioning hook area into a left area and a right area: in this embodiment, the column coordinate ColumnStart at the leftmost end and the column coordinate ColumnEnd at the rightmost end of the minimum right circumscribed rectangle in the region where the diagonal positioning hooks are located in the lower region are calculated, the lower region is divided into two regions on the left and right by the vertical line of (ColumnStart + ColumnEnd)/2 point, and fig. 12(a) and 12(b) are the two regions on the left and right in this embodiment, and it can be seen that the Number of connected regions in the left region of 12(a) is NumberleftNumber of connected regions in right region is 1right2, therefore, the Number in the condition one is satisfiedleft<NumberrightAnd Phi<0, therefore, the state of the positioning hook is normal and not reversed.
The state detection method for the stay cable positioning hook provided by the embodiment can realize the quick real-time detection of the state of the stay cable positioning hook, provides a basis for early finding of the faults of the contact network and giving early warning information, and ensures that the contact network is in a good working state, so as to be beneficial to the safe operation of the electrified railway.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is intended to include such modifications and variations.
Claims (9)
1. A state detection method for a stay wire positioning hook of a high-speed rail contact network comprises the following steps:
(1) acquiring an interested area image of each strut of a high-speed rail contact network in real time through image acquisition equipment; the interested area image comprises a positioning pipe, an inclined stay wire and an inclined stay wire positioning hook;
(2) separating a positioning hook region in the region-of-interest image; the positioning hook area comprises an inclined stay wire positioning hook and an inclined stay wire; the way of separating out the positioning hook area is as follows:
①, carrying out binarization processing on the region-of-interest image to obtain a binarized image;
②, performing morphological corrosion treatment on the binary image to obtain a corrosion image, and determining the positioning tube region according to the characteristics of each communication region in the corrosion image, wherein the characteristics of the communication region in the corrosion image comprise the area, the rectangular degree and the angle of the communication region, and the angle of the communication region refers to the included angle between the minimum circumscribed affine rectangle of the communication region and the horizontal plane;
③, according to the preset first rectangular structural element, performing first morphological expansion processing on the positioning tube area in the binary image to obtain a first expanded image, and according to the preset second rectangular structural element, performing second morphological expansion processing on the positioning tube area in the binary image to obtain a second expanded image, wherein the height of the second rectangular structural element is less than that of the first rectangular element;
④ calculating the intersection region of the first expanded image and the binary image, calculating the difference region of the intersection region and the second expanded image, and determining the positioning hook region in the difference region according to the characteristics of each connected region in the difference region, wherein the characteristics of the connected regions in the difference region comprise the area, the rectangular degree, the width and the height of the connected regions;
(3) calculating the direction of a diagonal cable in a positioning hook area, dividing the positioning hook area into a left area and a right area, and judging the state of the diagonal cable positioning hook according to the direction of the diagonal cable and the number of communicated areas in the left area and the right area; the states of the diagonal bracing positioning hooks comprise normal positioning hooks and reverse positioning hook installation;
the way of calculating the direction of the diagonal cable in the positioning hook area is as follows:
1) dividing a positioning hook area into an upper area and a lower area; the upper area is an area only containing diagonal cables;
2) calculating an included angle Phi between the minimum circumscribed rectangle of the area where the diagonal cables are located in the upper area and the horizontal plane, wherein the included angle is the direction of the diagonal cables,phi & gt 0 represents that the opening orientation of the included angle Phi is right, and Phi & lt 0 represents that the opening orientation of the included angle Phi is left; wherein, the side of the interested area image where the pillar is located is the right side.
2. The state detection method for the stay wire positioning hook of the high-speed rail overhead line system according to claim 1, characterized by comprising the following steps: in the step (2), before the first morphological dilation and the second morphological dilation are performed on the positioning tube region in the binarized image, the method further includes: horizontally correcting the positioning tube region in a correction mode that:
calculating the horizontal inclination of the positioning pipe area, and horizontally correcting the positioning pipe area according to the horizontal inclination; the way to calculate the horizontal inclination of the localizer region is:
and calculating the included angle between the minimum circumscribed affine rectangle of the positioning pipe area and the horizontal plane, wherein the included angle is the horizontal gradient of the positioning pipe area.
3. The method for detecting the state of the positioning hook of the inclined stay wire of the overhead line system of the high-speed rail according to claim 2, wherein in the step ①, before the binarization processing is performed on the region of interest, the method further comprises the step of performing enhancement processing on the region of interest by adopting linear transformation, wherein the enhancement processing formula is as follows:
g′=g×Mult+Mult×GMin
Mult=255/(GMax-GMin)
wherein g is the gray value of a pixel point in the image before enhancement processing, and g' is the gray value of a pixel point in the image after enhancement processing; mult is a linear transform coefficient; GMax and GMin represent the maximum and minimum grayscale values, respectively, in the image before enhancement processing.
4. The state detection method for the stay wire positioning hook of the high-speed rail overhead line system according to claim 1, characterized by comprising the following steps: in step 1), the positioning hook region is divided into an upper region and a lower region in the following manner:
and setting an upper area height threshold according to the size of the positioning hook area, and dividing the upper area according to the area height threshold.
5. The state detection method for the stay wire positioning hook of the high-speed rail overhead line system according to claim 1, characterized by comprising the following steps: in the step (3), the mode of dividing the positioning hook area into a left area and a right area is as follows:
3.1) calculating a column coordinate ColumnStart at the leftmost end and a column coordinate ColumnEnd at the rightmost end of the minimum right circumscribed rectangle in the area where the stay wire positioning hook is positioned in the lower area; the minimum positive circumscribed rectangle is a minimum circumscribed rectangle with an included angle with the horizontal plane being zero; the column coordinates are transverse coordinates;
3.2) the lower region is divided equally into two regions, left and right, with a vertical line passing through the coordinates (ColumStart + ColumEnd)/2.
6. The state detection method for the stay wire positioning hook of the high-speed rail overhead line system according to claim 1, characterized by comprising the following steps: in the step (3), the mode of judging the state of the diagonal positioning hook according to the direction of the diagonal and the number of the communicated areas in the left area and the right area is as follows:
the Number of the connected areas of the left area in the left area and the right area is set as NumberleftThe Number of connected areas of the right area is Numberright;
When the following condition I is met, the state of the inclined stay wire positioning hook is normal, and when the following condition II is met, the state of the inclined stay wire positioning hook is reversely installed;
conditionFirstly, the method comprises the following steps: numberleft>NumberrightAnd Phi > 0, or alternatively,
Numberleft<Numberrightand Phi is less than 0;
and a second condition: numberleft≥NumberrightAnd Phi is less than or equal to 0, or,
Numberleft≤Numberrightand Phi is more than or equal to 0, or,
Numberleft=Numberrightand Phi is 0.
7. The method for detecting the state of the stay wire positioning hook of the high-speed rail overhead line system according to one of claims 1 to 6, wherein the method comprises the following steps: in step (1), before segmenting out the region of interest in the image, the method further includes: and carrying out scaling processing on the image.
8. The utility model provides a state detecting system of high-speed railway contact net stay wire location hook, includes:
the interesting region acquisition module is used for acquiring an interesting region image of each strut of the high-speed rail overhead line system in real time through image acquisition equipment; the interested area image comprises a positioning pipe, an inclined stay wire and an inclined stay wire positioning hook;
the positioning hook region separation module is used for separating a positioning hook region in the region-of-interest image; the positioning hook area comprises an inclined stay wire positioning hook and an inclined stay wire; the hook area module includes:
the image binarization unit is used for carrying out binarization processing on the region-of-interest image to obtain a binarized image;
the image corrosion processing unit is used for performing morphological corrosion processing on the binary image and determining a positioning tube region according to the characteristics of each communication region in the corrosion image; the characteristics of the connected region in the corrosion image comprise the area, the rectangular degree and the angle of the connected region; the angle of the communication area refers to the included angle between the minimum circumscribed affine rectangle of the communication area and the horizontal plane;
the image expansion processing unit is used for carrying out first morphological expansion processing on a positioning tube area in the binary image according to a preset first rectangular structural element to obtain a first expanded image; the positioning tube expansion processing device is also used for carrying out second morphological expansion processing on the positioning tube area in the binary image according to a preset second rectangular structural element to obtain a second expansion image; the height of the second rectangular structural element is smaller than that of the first rectangular element;
the positioning hook area determining unit is used for determining a positioning hook area, and the determining mode is as follows: calculating an intersection region of the first expanded image and the binary image, calculating a difference region of the intersection region and the second expanded image, and determining a positioning hook region in the difference region according to the characteristics of each communicated region in the difference region; the characteristics of the connected region in the difference region comprise the area, the rectangular degree, the width and the height of the connected region;
the positioning hook state judgment module is used for judging the state of the diagonal positioning hook in a mode of: calculating the direction of a diagonal cable in a positioning hook area, dividing the positioning hook area into a left area and a right area, and judging the state of the diagonal cable positioning hook according to the direction of the diagonal cable and the number of communicated areas in the left area and the right area; the states of the diagonal bracing positioning hooks comprise normal positioning hooks and reverse positioning hook installation;
the way of calculating the direction of the diagonal cable in the positioning hook area is as follows:
1) dividing a positioning hook area into an upper area and a lower area; the upper area is an area only containing diagonal cables;
2) calculating an included angle Phi between the minimum circumscribed rectangle of the area where the diagonal cables are located in the upper area and the horizontal plane, wherein the included angle is the direction of the diagonal cables,phi & gt 0 represents that the opening orientation of the included angle Phi is right, and Phi & lt 0 represents that the opening orientation of the included angle Phi is left; wherein, the side of the interested area image where the pillar is located is the right side.
9. The state detection system of the stay wire positioning hook of the high-speed rail contact network according to claim 8, characterized in that: the positioning hook area separating module further comprises:
the horizontal correction unit is used for calculating the horizontal inclination of the positioning tube area before the first morphological expansion and the second morphological expansion processing are carried out on the positioning tube area in the binary image, and carrying out horizontal correction on the positioning tube area according to the horizontal inclination; the way to calculate the horizontal inclination of the localizer region is:
and calculating the included angle between the minimum circumscribed affine rectangle of the positioning pipe area and the horizontal plane, wherein the included angle is the horizontal gradient of the positioning pipe area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610120479.1A CN107154034B (en) | 2016-03-03 | 2016-03-03 | State detection method and system for stay wire positioning hook of high-speed rail contact network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610120479.1A CN107154034B (en) | 2016-03-03 | 2016-03-03 | State detection method and system for stay wire positioning hook of high-speed rail contact network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107154034A CN107154034A (en) | 2017-09-12 |
CN107154034B true CN107154034B (en) | 2020-02-14 |
Family
ID=59791610
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610120479.1A Active CN107154034B (en) | 2016-03-03 | 2016-03-03 | State detection method and system for stay wire positioning hook of high-speed rail contact network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107154034B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108681729B (en) * | 2018-05-08 | 2023-06-23 | 腾讯科技(深圳)有限公司 | Text image correction method, device, storage medium and equipment |
CN108876784B (en) * | 2018-06-27 | 2021-07-30 | 清华大学 | Image processing method and device for removing connecting part of planar workpiece |
CN111273136A (en) * | 2020-02-20 | 2020-06-12 | 山东万腾智能科技有限公司 | Online overhead line system arc discharge detection system and method based on image processing |
CN111462045B (en) * | 2020-03-06 | 2022-07-01 | 西南交通大学 | Method for detecting defects of catenary support assembly |
CN112001908B (en) * | 2020-08-25 | 2021-03-09 | 哈尔滨市科佳通用机电股份有限公司 | Railway freight car sleeper beam hole carried foreign matter detection method |
CN115496750B (en) * | 2022-11-14 | 2023-04-18 | 诺比侃人工智能科技(成都)股份有限公司 | Neural network-based overhead contact system defect testing method and system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103196372A (en) * | 2013-04-11 | 2013-07-10 | 北京和润科仪科技有限公司 | Optical imaging detection method of electrified railway overhead line system supporting device |
CN204801541U (en) * | 2015-07-23 | 2015-11-25 | 山东三友电力设备有限公司 | Contact net support |
-
2016
- 2016-03-03 CN CN201610120479.1A patent/CN107154034B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103196372A (en) * | 2013-04-11 | 2013-07-10 | 北京和润科仪科技有限公司 | Optical imaging detection method of electrified railway overhead line system supporting device |
CN204801541U (en) * | 2015-07-23 | 2015-11-25 | 山东三友电力设备有限公司 | Contact net support |
Non-Patent Citations (1)
Title |
---|
网定位管斜拉线受力状态检测研究;蔡博宇;《中国新技术新产品》;20151231;第122-123页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107154034A (en) | 2017-09-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107154034B (en) | State detection method and system for stay wire positioning hook of high-speed rail contact network | |
CN106290388B (en) | A kind of insulator breakdown automatic testing method | |
CN103196372B (en) | A kind of optical imagery detection method of electrification railway contact net supportive device | |
CN107154033B (en) | Method and system for detecting missing of rotating double-lug vertical cotter pin of high-speed rail contact network | |
CN104318582A (en) | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning | |
CN110288562B (en) | Method for detecting joint twitching of steel wire rope core conveying belt based on X-ray image | |
CN105719305A (en) | Assembly falloff defect identification method and system of overhead contact system | |
CN110567680B (en) | Track fastener looseness detection method based on angle comparison | |
CN103500459A (en) | Printed circuit board defect detecting method based on regularization parameters | |
CN108445009B (en) | Crack detection method for solar cell panel | |
CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
CN111462045B (en) | Method for detecting defects of catenary support assembly | |
CN111523607B (en) | Abnormal detection method and system for catenary hanger | |
CN107169951B (en) | A kind of the missing detection method and system of the inclined cantilever end pipe cap based on image | |
CN112288717A (en) | Method for detecting foreign matters on side part of motor train unit train | |
CN110782411B (en) | Anti-vibration hammer slip identification method based on image processing | |
CN113393430B (en) | Thermal imaging image enhancement training method and device for fan blade defect detection | |
CN116843686B (en) | Method and device for detecting defects of wire clamps and nuts of contact net locator | |
CN114399518A (en) | Method for monitoring tightness of vehicle bottom bolt and electronic equipment | |
CN111626104B (en) | Cable hidden trouble point detection method and device based on unmanned aerial vehicle infrared thermal image | |
CN117333696A (en) | Bolt detection method and device based on machine vision | |
CN104700387A (en) | Image borderline detection method and system | |
CN106875378B (en) | A kind of power line foreign matter detecting method | |
CN116071726A (en) | Road inspection system and method based on edge calculation | |
CN115115820A (en) | Image feature extraction method, system and device for shield tail gap intelligent monitoring |
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 |