CN109712116B - Fault identification method for power transmission line and accessories thereof - Google Patents
Fault identification method for power transmission line and accessories thereof Download PDFInfo
- Publication number
- CN109712116B CN109712116B CN201811477413.3A CN201811477413A CN109712116B CN 109712116 B CN109712116 B CN 109712116B CN 201811477413 A CN201811477413 A CN 201811477413A CN 109712116 B CN109712116 B CN 109712116B
- Authority
- CN
- China
- Prior art keywords
- transmission line
- power transmission
- image
- line
- line segments
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000011159 matrix material Substances 0.000 claims abstract description 38
- 230000007547 defect Effects 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 7
- 230000011218 segmentation Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 7
- 230000008447 perception Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 125000006850 spacer group Chemical group 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000035040 seed growth Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Image Analysis (AREA)
Abstract
The application discloses a fault identification method for a power transmission line and accessories thereof, which comprises the following steps: forming a power transmission line image by extracting and connecting a plurality of line segments shot with the power transmission line image; after identifying the tower in the image of the power transmission line, removing the image of the tower area; and identifying the power transmission line and the power transmission line accessory in the remaining image area, and carrying out defect inspection on the power transmission line accessory and the power transmission line. Compared with the prior art, the method for line characteristic connection based on matrix operation solves the defects of low efficiency and poor fitting effect of solving a large number of line characteristic connection problems by using circulation, and overcomes the problem that the photographed power transmission line cannot be automatically identified in the prior art by respectively identifying faults of the obtained power transmission line image and the power transmission line accessory image after performing image semantic segmentation on the power transmission line and accessories thereof, thereby saving a large amount of human resources.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a fault recognition method for a power transmission line and accessories of the power transmission line.
Background
The transmission line has the possibility of generating faults under the influence of natural environment, so the transmission line needs to be regularly inspected. For a long time, the routing inspection of the power transmission line is usually completed by manual routing inspection, but the routing inspection mode of the power transmission line is low in routing inspection efficiency and has certain safety risks.
In order to solve the problems, the unmanned aerial vehicle technology is adopted to replace the manpower to carry out power transmission line inspection in the prior art. But when carrying out transmission line through prior art and patrolling and examining, discovery unmanned aerial vehicle can only carry out the photo and shoot, still needs a large amount of manpowers to go to inspect the picture that unmanned aerial vehicle shot with the trouble of discovery transmission line.
Disclosure of Invention
The technical problem to be solved by the embodiment of the application is how to identify the fault of the power transmission line, so that human resources are saved.
In order to solve the above problem, an embodiment of the present application provides a method for identifying a fault of a power transmission line and an accessory thereof, which is suitable for being executed in a computing device, and at least includes the following steps:
collecting and shooting a color image of the power transmission line, converting the data of the color image into a gray image, extracting all line segments in the gray image one by one to be used as intermittent line segments, and fitting the connectable intermittent line segments in pairs to obtain a power transmission line image;
dividing the image of the power transmission line into a plurality of image areas with the same size according to the preset image area dividing quantity, marking the line segments which exceed the first preset length and are in the preset included angle interval with the horizontal axis in each image area as line segments to be processed, dividing the image areas of which the quantity of the line segments to be processed exceeds the preset quantity into tower areas, and then dividing the image areas which are not divided into the tower areas into a first to-be-processed area set;
extracting line segments of which the concentrated length, the end point and the horizontal included angle with a horizontal axis of the first to-be-processed area reach a preset range, obtaining a power transmission line image of the power transmission line, and searching component images of the power transmission line accessory positioned below the power transmission line image in the concentrated first to-be-processed area according to an accessory template of the power transmission line accessory;
after the searched images of the components are combined, judging whether the power transmission line accessory has defects according to the combination result between every two images of the components, and marking the first to-be-processed area set with all the images of the components removed as a second to-be-processed area set;
and after marking the line segments which do not form the power transmission line image in the second to-be-processed area as the to-be-recognized line segments, extending the to-be-recognized line segments by a seed growing method, and marking the to-be-recognized line segments which are extended to exceed a second preset length and are judged as foreground by a background filter as broken strands of the power transmission line.
Further, the method also comprises the following steps:
and clustering all the line segments of the second to-be-processed region set into a plurality of line feature groups according to the end point distance between every two line segments in the second to-be-processed region set, and marking the linear feature groups which are judged as foregrounds by the background filter as foreign body images.
Further, the extracting all line segments in the gray level image one by one serves as an intermittent line segment, and the intermittent line segments which can be connected between every two line segments are fitted to each other to obtain the power transmission line image, and the method specifically comprises the following steps:
performing matrix transformation on all the intermittent line segments according to the Gestalt law, acquiring an approximation matrix, a colinearity matrix and a continuity matrix of all the intermittent line segments, and then performing logical sum on elements at the same positions in the approximation matrix, the colinearity matrix and the continuity matrix to obtain an adjacent matrix;
according to a graph theory method, after the adjacency matrix is divided into a plurality of connected domains, the end points of the discontinuous line segments corresponding to the elements in the connected domains one by one are fitted through a weighted least square method, and the image of the power transmission line is obtained.
Further, extracting line segments of which the second to-be-processed region concentration length, end points and horizontal included angles with a horizontal axis all reach a preset range to obtain the power transmission line image of the power transmission line, specifically:
extracting all line segments with the length being larger than a second preset length in the second region set to be processed as a first line segment set;
extracting all line segments in the first line segment set, wherein the minimum distance from an end point to the boundary of the power transmission line image is smaller than a preset distance, and the line segments are used as a second line segment set;
and extracting the outline formed by all the line segments with the included angles smaller than the preset included angle with the horizontal axis in the second line segment set as the power transmission line image.
Further, the transmission line accessory at least comprises a vibration damper.
Further, the searching, according to the accessory template of the power transmission line accessory, for the component part image of the power transmission line accessory located below the power transmission line image in the first to-be-processed area set includes:
extracting a 2AS template and a 3AS template of the shockproof hammer according to a kAS semantic model, extracting a plurality of 2AS images from an area below the power transmission line image in a centralized manner from the first area to be processed according to the 2AS template, combining the 2AS images of every two of the 2AS images into a first 3AS image, filtering the background of the first 3AS images to obtain a plurality of second 3AS images, and taking the second 3AS images successfully matched with the 3AS template AS component images of the shockproof hammer one by one.
Further, the obtaining a plurality of second 3AS images by filtering the plurality of first 3AS images through a background specifically includes:
after each first 3AS image is selected, the first 3AS image with pixels being non-foreground pixels is filtered out through a Grabcut algorithm, and a plurality of second 3AS images are obtained.
Further, after combining the searched images of the components, determining whether the accessory of the power transmission line has a defect, specifically:
combining the component images in pairs according to a preset distance range, judging the component images which are combined in pairs as complete anti-vibration hammers, and judging the component images which cannot be combined as the anti-vibration hammers with defects.
Further, the method also comprises the following steps:
judging whether a pair of line segment groups which are equal in length, parallel to each other and capable of vertically projecting a part larger than eighty percent of the first to-be-processed area set to the opposite side exist in the first to-be-processed area set or not; if the two connected line segments exist, two connected line segments are generated, and a quadrangle is formed by the two connected line segments and the line segment group.
Further, the image area is a rectangular area;
the first preset length is 1/3min (a, b); wherein a is the length of the rectangular area and b is the width of the rectangular area.
The embodiment of the application has the following beneficial effects:
the embodiment of the application provides a fault identification method for a power transmission line and accessories thereof, which comprises the following steps: forming an image of the power transmission line by extracting and connecting a plurality of line segments shot with the pictures of the power transmission line; after identifying the tower in the image of the power transmission line, removing the image of the tower area; and identifying the power transmission line and the power transmission line accessory in the remaining image area, and carrying out defect inspection on the power transmission line accessory and the power transmission line. Compared with the prior art, the method for identifying the faults of the power transmission line and the accessories of the power transmission line respectively adopts the method for identifying the faults of the obtained power transmission line image and the power transmission line accessory image after performing image semantic segmentation on the power transmission line and the accessories of the power transmission line, overcomes the problem that the shot power transmission line cannot be automatically identified in the prior art, and achieves the effect of automatically identifying the faults of the power transmission line.
Drawings
Fig. 1 is a schematic flowchart of a fault identification method for a power transmission line and accessories thereof according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a system for semantic segmentation of an image of a power transmission line and its accessories according to another embodiment of the present application;
FIG. 3 is a schematic diagram of Gestalt's perception law;
FIG. 4 is a schematic view of the effect of the connection of line features;
FIG. 5 is a schematic diagram of 2AS and 3 AS;
FIG. 6 is a schematic illustration of extracting 2AS and 3AS templates;
fig. 7 is a schematic diagram of the damper 2AS and the transmission line;
FIG. 8 is a schematic representation of seed growth methods identifying broken strands;
FIG. 9 is a graph comparing the speed of two line feature connections.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Please refer to fig. 1 and fig. 3-9.
Referring to fig. 1, which is a schematic flowchart of a fault identification method for a power transmission line and accessories thereof according to an embodiment of the present disclosure, as shown in fig. 1, the task processing method includes steps S11 to S15. The method comprises the following steps:
and S11, collecting and shooting a color image of the power transmission line, converting the color image data into a gray image, extracting all line segments in the gray image one by one to serve as intermittent line segments, and fitting the connectable intermittent line segments in pairs to obtain the power transmission line image.
Step S12, dividing the image of the power transmission line into a plurality of image areas with the same size according to the preset image area dividing quantity, marking the line segments which exceed the first preset length and are in the preset included angle interval with the horizontal axis in each image area as line segments to be processed, dividing the image areas of which the quantity of the line segments to be processed exceeds the preset quantity into tower areas, and then dividing the image areas which are not divided into the tower areas into a plurality of image areas to be processed to form a first set of the areas to be processed.
And S13, extracting line segments of which the concentrated length, the end point and the horizontal included angle with the horizontal axis of the first to-be-processed area reach a preset range, obtaining a power transmission line image of the power transmission line, and searching component images of power transmission line accessories positioned below the power transmission line image in the concentrated first to-be-processed area according to an accessory template of the power transmission line accessories.
And S14, combining the searched multiple component images, judging whether the power transmission line accessory has defects according to the combination result of the multiple component images, and marking the first to-be-processed area set with all the component images removed as a second to-be-processed area set.
And S15, concentrating the segments which do not form the power transmission line image in the second to-be-processed area, marking the segments as segments to be recognized, extending the segments to be recognized by a seed growing method, and marking the segments to be recognized, which are extended to exceed a second preset length and are judged as foreground by the background filter, as broken strands of the power transmission line.
For step S11, specifically, according to the getstalt law, performing matrix transformation on all the discontinuous line segments, obtaining an approximation matrix, a colinearity matrix, and a continuity matrix of all the discontinuous line segments, and then performing logical sum on elements at the same positions in the approximation matrix, the colinearity matrix, and the continuity matrix to obtain an adjacency matrix; according to the graph theory method, after the adjacency matrix is divided into a plurality of connected domains, the end points of the discontinuous line segments corresponding to each element in the connected domains one by one are fitted through a weighted least square method, and the image of the power transmission line is obtained.
In this embodiment, a color picture with a power transmission line is first converted into a gray picture, and then an LSD algorithm is called to extract all line segments from the picture. Since the LSD algorithm is weak in noise immunity, a complete linear contour often generates many broken and separated discontinuous line segments, and therefore, in this embodiment, the discontinuous line segments are processed by the approximation, collinearity and continuity in the getalt perception law.
As shown in fig. 3, the approximation is obtained, the collinearity is obtained, and the continuity is obtained. Wherein, the distance between the end points of the two line segments close to each other is a given threshold value, the distance is the included angle between the two line segments and the horizontal axis, the distance is a given threshold value, and the included angle is a point S 2 To L 1 Is a given threshold.
Because the LSD can extract thousands of line segments from the high-resolution image, in this embodiment, the thousands of line segments are fitted through matrix transformation, specifically:
using the endpoint coordinate (x) of the ith line 1 (i) ,y 1 (i) ,x 2 (i) ,y 2 (i) ) Express, define
And a radical of Y 1 、X 2 、Y 2 Is also similar to X 1 After the definition, calculate
D s1,s2 ＝min(D 1 ,D 2 ,D 3 ,D 4 )
Wherein,
D s1,s2 is the distance between the end points of two adjacent line segments among the plurality of line segments.
In the present embodiment, the threshold value of the end point distance between two line segments is set to D thr1 ＝[d thr1 ] n×n The line segment forms an angle with the horizontal axis
The angle threshold is set to theta thr1 ＝[θ thr1 ] n×n . Between every two line segments of the plurality of line segmentsCan be expressed as:
wherein,
in the present embodiment, the threshold value given for determining the proximity is D thr2 ＝[d thr2 ] n×n . Therefore, the Gestalt perception law of a plurality of line segments can be expressed in a matrix form, and the Gestalt perception law is specifically as follows:
D s1,s2 ＜D thr1
|θ-θ T |＜θ thr1
D v ＜D thr2
obtaining an approximation matrix M from the three matrix inequalities a Co-linear matrix M b And continuity matrix M c And then, performing logical sum operation on the elements at the same positions of the three Boolean matrixes to obtain a tie matrix M, which is specifically expressed as:
M＝M a ·M b ·M c 。
using graph theory, connected domains can be extracted from the adjacency matrix, and the elements of each connected domain represent the serial numbers of the line segments that can be connected with each other. Then, by the weighted least square method, the end points of the line segments can be connected with each other by fitting, the weight is in direct proportion to the length of the corresponding line segment, and finally, the complete line characteristics after connection are obtained, and the effect is shown in fig. 4.
For step S12, specifically, after dividing the image of the power transmission line into a plurality of rectangular image areas of the same size according to the preset number of image area divisions, in each image area, taking a line segment whose length is longer than 1/3min (a, b) and whose included angle with the horizontal axis is within a preset included angle interval, marking the line segment as a to-be-processed line segment, and dividing the image area whose number of the to-be-processed line segments exceeds the preset number into tower areas, and then, forming a first to-be-processed area set by a plurality of image areas which are not divided into tower areas.
Where a is the length of the image area and b is the width of the image area.
In this embodiment, since the transmission tower has the characteristics of a densely staggered steel structure, the transmission tower area is positioned according to the length, angle, and spatial arrangement information of the line characteristics.
Specifically, according to the angle interval shown in table 1, after the included angle between each line segment in the power transmission line image and the horizontal axis is divided into four groups A, B, C and D, the power transmission line image is divided into 8X6 areas, and it is determined whether the number of line segments in each area exceeds 1/3min (a, b) and belongs to two groups B, C, exceeds three, if it exceeds three. The area is divided into tower areas. Wherein, table 1 is:
| categories | A | B | C | D |
| Angle of rotation | (-5,5) | (5,85) | (-85,-5) | (-90,-85),(85,90) |
For step S13, specifically, all segments in the second set of regions to be processed, whose length is greater than a second preset length, are extracted as the first set of segments; extracting all line segments in the first line segment set, wherein the minimum distance from the end point to the boundary of the image of the power transmission line is smaller than a preset distance, and using all line segments as a second line segment set; extracting outlines formed by all line segments of which the included angles between the second line segment set and the horizontal axis are smaller than a preset included angle, taking the outlines AS power transmission line images, extracting 2AS templates and 3AS templates of power transmission line accessories according to a kAS semantic model, extracting a plurality of 2AS images from the first to-be-processed area set and the area below the power transmission line images according to the 2AS templates, combining every two 2AS images in the plurality of 2AS images into a first 3AS image, filtering the plurality of first 3AS images through backgrounds to obtain a plurality of second 3AS images, and taking each second 3AS image successfully matched with the 3AS template AS a component image of the power transmission line accessories. Combining the plurality of component images pairwise according to a preset distance range, judging the combined component images pairwise as complete transmission line accessories, and judging the component images which cannot be combined as defective transmission line accessories. And removing the image of the electric transmission line accessory from the first to-be-processed region set after the fault judgment of the electric transmission line accessory is completed.
It should be noted that, in the present embodiment, the power transmission line accessories include a vibration damper and a spacer.
In this embodiment, the basic water has a long length according to the transmission lineThe three characteristics of flatness and extension to the image boundary are adopted, the transmission line is extracted from the first region to be processed in a centralized way, and the line segment forming the transmission line is obtained by obtaining the length l of the line segment i ＞l thr The line segments of (a) as a first set of line segments; obtaining a first line set d i ＜d thr3 As a second set of line segments; obtaining a second line segment set theta i ＜θ thr2 The line segments form the transmission line.
Wherein l i Is the length of the line feature, d i Taking the shortest distance, theta, from the end point of the line segment to the image boundary i Is the angle of the line feature with the horizontal axis. l thr ，d thr3 ，θ thr2 Is a preset threshold.
In this example, the identification of the stockbridge or spacer is applied to the kAS semantic model, where k represents the number of segments of the class. For the damper example, the schematic diagrams of 2AS and 3AS are shown in FIG. 5, where (a) is the 2AS diagram and (b) is the 3AS diagram.
In this embodiment, the vector of 2AS is P 2as ＝(l 1 ,l 2 α, θ). Wherein l 1 Is a line segment L 1 Length of (l) 2 Is a line segment L 2 Length of, and L 1 Longer than L 2 (ii) a α is a line segment L 1 And L 2 The included angle between them; theta is L 1 Angle to the horizontal axis. Vector of 3AS is P 3as ＝(l 1 ,l 2 ,α 1 ,α 2 ). Wherein l 3 Is a line segment L 3 Length of, and L 1 Longer than L 3 ，α 1 Is a line segment L 1 And L 2 Angle between them, α 2 Is a line segment L 2 And L 3 The included angle therebetween.
In this embodiment, the two 2AS vector difference calculation methods are:
the two 3AS vector difference calculation methods are AS follows:
wherein, ω is θ Is an artificially given weight coefficient for balancing the weight of the length difference and the angle difference in the overall difference degree.
If D (a, b) < D thr Then two kAS are considered similar, where D thr Is a preset threshold value.
In the present embodiment, for example, with respect to the vibration damper, AS shown in fig. 6, after the 2AS template and the 3AS template of the vibration damper are extracted, a plurality of 2AS images are extracted from the first area to be processed. The 2AS image extraction method is shown in FIG. 7, and the 2AS image is screened through shape constraint, angle constraint, position constraint and size constraint, wherein the shape constraint is that the 2AS image extracted from the first region to be processed is similar to the 2AS template, and the angle constraint is that the direction of the 2AS image M is basically parallel to the transmission line, namely, the horizontal included angle theta is included t Equal to horizontal angle theta v The position constraint is that the 2AS image needs to be below the preset distance threshold d of the power line image 1 And the length of the long side l with the size constraint of 2AS is required to be within a preset range.
It should be noted that, since the LSD algorithm extracts two parallel line segments from two edges of the transmission line, after the line segments constituting the transmission line are extracted, the two parallel line segments need to be fitted into one line segment by using the least square method, and the distance between the two line segments, i.e., the width w of the transmission line, is recorded and is used as a reference distance for adjusting the preset distance threshold. Because the width of the power transmission line is in proportional constraint relation with the size of the accessory, the automatic adjustment of the preset distance threshold is realized.
In this embodiment, it is determined whether or not there is a shared edge in any of the two 2AS images screened, and if there is a shared edge, the two 2AS images having the shared edge are combined into a 3AS, which is compared with the 3AS template to see whether or not they are similar, thereby identifying the 3AS image of the vibration damper, i.e., the image of the component of the vibration damper.
Since the shooting position of the image may not be right in front of the transmission line accessory, which results in a problem that the profiles of the two sides of the transmission line accessory cannot be linearly extracted, in this embodiment, the method for supplementing the profile of the side of the vibration damper is shown by taking the vibration damper as an example, and specifically includes: judging whether a pair of line segment groups which are equal in length, parallel to each other and capable of vertically projecting a part larger than eighty percent of the first to-be-processed area set to the opposite side exist in the first to-be-processed area set or not; if the vibration damper exists, two connecting line segments are generated, and a quadrangle is formed by the connecting line segments and the line segment group, so that the line characteristics of the vibration damper missing are completed.
In an embodiment, the plurality of first 3AS images are filtered through a background to obtain a plurality of second 3AS images, specifically:
after each first 3AS image is selected, the first 3AS image with pixels being non-foreground pixels is filtered out through a Grabcut algorithm, and a plurality of second 3AS images are obtained.
Taking the background ditch AS an example, because the background ditch is a non-foreground image, when each first 3AS image is selected, grabcut algorithm is called to process each first 3AS image, and the 3AS image with the image AS the background ditch is excluded, thereby realizing the filtering of the complex background.
In step S14, specifically, the plurality of component images are combined in pairs according to a preset distance range, and after the component images combined in pairs are determined as complete accessories of the power transmission line, the component images that cannot be combined are determined as defective accessories of the power transmission line, after the determination is completed, all the component images are removed from the first to-be-processed area in a centralized manner, and the remaining area is marked as a second to-be-processed area set.
In this embodiment, taking the vibration damper AS an example, after identifying the 3AS image of the vibration damper, the extracted 3AS is clustered if the distance between the two 3AS is within a preset distance range, for example, d shown in FIG. 7 2 Then they will form a 3AS pair, the 3AS pair location corresponding to the possible presence of a stockbridge damper, and the single 3AS location that did not combine successfully corresponding to the possible presence of a missing stockbridge damper.
For step S15, in the present embodiment, a seed growing method is employed, as shown in fig. 8. Setting the line segment to be identified as a seed according toα i,j ＜α thr And d si,sj ＜d thr6 The seed is grown regularly. Wherein alpha is i,j Is the angle between line segment i and line segment j, d si,sj Is the shortest end point distance, α, between two line segments thr And d thr6 Is a preset threshold value. If a seed can grow to a length greater than 5 times the width of the transmission line according to the above rule and is judged to be a foreground by the background filter, the strand of the transmission line is judged to be broken.
The embodiment of the application provides a fault identification method for a power transmission line and accessories thereof, wherein a plurality of line segments with pictures of the power transmission line are extracted and connected to form an image of the power transmission line; after identifying the tower in the image of the power transmission line, removing the image of the tower area; identifying the power transmission line and the power transmission line accessory in the remaining image area, and carrying out defect inspection on the power transmission line accessory and the power transmission line; compared with the prior art, the method for connecting the line characteristics based on the matrix operation solves the defects of low efficiency and poor fitting effect of solving a large number of line characteristic connection problems by using circulation, and overcomes the problem that the photographed power transmission line cannot be subjected to fault identification in the prior art after image segmentation is respectively carried out on a tower area, the power transmission line and power transmission line accessories, so that a large number of human resources are saved, a background filter is used, the bad interference of a complex background is reduced, and the recall rate of the power transmission line accessory identification is improved by automatically complementing contour line characteristics.
Please refer to fig. 2.
Referring to fig. 2, which is a schematic structural diagram of a system for semantic segmentation of an image of a power transmission line and its accessories according to an embodiment of the present application, in addition to the steps shown in fig. 1, the system further includes:
and S16, clustering all the line segments of the second to-be-processed region set into a plurality of line feature groups according to the end point distance between every two line segments in the second to-be-processed region set, and marking the line feature groups judged as foregrounds by the background filter as foreign body images.
As an effect comparison of this embodiment, semantic segmentation is performed on the transmission line and its accessory images by using the original cycle-based method for the photo with the transmission line taken by the unmanned aerial vehicle, respectively, so as to obtain a comparison result as shown in fig. 9. When the number of the segments contained in 29 groups of segments is increased from 1 to 5052, the time consumption of the segments in the two connection methods is respectively tested, and the result shows that when the number of the online features is 5052, the time consumption of the original method is 169.4 seconds, the time consumption of the method proposed in the embodiment is 1.984 seconds, and the improvement is dozens of times. Where n =32 is represented in 29 sets of line segments, some of which contains 32 line segments.
The embodiment of the application provides a fault identification method for a power transmission line and accessories thereof, which comprises the following steps: forming a power transmission line image by extracting and connecting a plurality of line segments shot with the power transmission line image; after identifying the tower in the image of the power transmission line, removing the image of the tower area; taking the rest image areas as areas, identifying the transmission lines and the transmission line accessories in the first area to be processed in a centralized manner, and carrying out defect detection on the transmission line accessories and the transmission lines; and removing the accessory images of the power transmission line from the first to-be-processed area set to obtain a second to-be-processed area set, and performing foreign matter identification in the second to-be-processed area set. Compared with the prior art, the method for connecting the line characteristics based on the matrix operation solves the defects of low efficiency and poor fitting effect of solving a large number of line characteristic connection problems by using circulation, and overcomes the problem that the photographed power transmission line cannot be subjected to fault identification in the prior art after image segmentation is respectively carried out on a tower area, the power transmission line and power transmission line accessories, so that a large number of human resources are saved, a background filter is used, the bad interference of a complex background is reduced, and the recall rate of the power transmission line accessory identification is improved by automatically complementing contour line characteristics.
In addition, the line segments concentrated in the second to-be-processed area are divided into a plurality of line feature groups, and the plurality of line feature groups are judged through the background filter, so that foreign matter detection on the power transmission line is realized.
Still another embodiment of the present application further provides a configurable terminal device of a motion control apparatus, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor, when executing the computer program, implements the method for identifying faults of the power transmission line and its accessories as described in the above embodiments.
The foregoing is a preferred embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations are also regarded as the protection scope of the present application.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Claims (10)
1. A fault identification method for a power transmission line and accessories thereof is characterized by at least comprising the following steps:
collecting and shooting a color image of the power transmission line, converting the data of the color image into a gray image, extracting all line segments in the gray image one by one to be used as intermittent line segments, and fitting the connectable intermittent line segments in pairs to obtain a power transmission line image;
dividing the image of the power transmission line into a plurality of image areas with the same size according to the preset image area dividing quantity, marking the line segments which exceed the first preset length and have the included angles with the horizontal axis in the preset included angle interval in each image area as the line segments to be processed, dividing the image areas of which the number of the line segments to be processed exceeds the preset number into tower areas, and then dividing the plurality of the image areas which are not divided into the tower areas into a first set of areas to be processed;
extracting line segments of which the lengths, end points and horizontal included angles with a horizontal axis of the first to-be-processed areas reach preset ranges, obtaining a power transmission line image of the power transmission line, and searching component part images of the power transmission line accessories positioned below the power transmission line image in the first to-be-processed areas according to accessory templates of the power transmission line accessories;
after the searched images of the components are combined, judging whether the power transmission line accessory has defects according to the combination result between every two images of the components, and marking the first to-be-processed area set with all the images of the components removed as a second to-be-processed area set;
and after marking the line segments which do not form the power transmission line image in the second to-be-processed area as the to-be-recognized line segments, extending the to-be-recognized line segments by a seed growing method, and marking the to-be-recognized line segments which are extended to exceed a second preset length and are judged as foreground by a background filter as broken strands of the power transmission line.
2. The method for identifying faults of the power transmission line and accessories thereof according to claim 1, further comprising:
and clustering all the line segments of the second to-be-processed region set into a plurality of linear feature clusters according to the end point distance between every two line segments in the second to-be-processed region set, and marking the linear feature clusters which are judged as foregrounds by the background filter as foreign body images.
3. The method for identifying faults of the power transmission line and the accessories of the power transmission line according to claim 1, wherein all line segments in the gray level image are extracted one by one to serve as intermittent line segments, and the intermittent line segments which can be connected between every two are fitted in pairs to obtain the power transmission line image, and specifically the method comprises the following steps:
performing matrix transformation on all the intermittent line segments according to the Gestalt law, acquiring an approximation matrix, a colinearity matrix and a continuity matrix of all the intermittent line segments, and then performing logical sum on elements at the same positions in the approximation matrix, the colinearity matrix and the continuity matrix to obtain an adjacent matrix;
according to a graph theory method, after the adjacency matrix is divided into a plurality of connected domains, the end points of the discontinuous line segments corresponding to the elements in the connected domains one by one are fitted through a weighted least square method, and the power transmission line image is obtained.
4. The method for identifying the faults of the power transmission line and the accessories of the power transmission line according to claim 1, wherein line segments of which the concentration length, the end points and the horizontal included angle with the horizontal axis of the second region to be processed reach preset ranges are extracted to obtain a power transmission line image of the power transmission line, and the method specifically comprises the following steps:
extracting all line segments with the length being larger than a second preset length in the second region set to be processed as a first line segment set;
extracting all line segments in the first line segment set, wherein the minimum distance from an end point to the boundary of the image of the power transmission line is smaller than a preset distance, and the all line segments are used as a second line segment set;
and extracting the outline formed by all the line segments with the included angles smaller than the preset included angle with the horizontal axis in the second line segment set as the power transmission line image.
5. The method of claim 1, wherein the transmission line accessory comprises at least a vibration damper.
6. The method according to claim 5, wherein component images of the transmission line accessory located below the transmission line image are searched for in the first set of areas to be processed according to an accessory template of the transmission line accessory, and the method specifically includes:
extracting a 2AS template and a 3AS template of the shockproof hammer according to a kAS semantic model, extracting a plurality of 2AS images from an area below the power transmission line image in a centralized manner from the first area to be processed according to the 2AS template, combining the 2AS images of every two of the 2AS images into a first 3AS image, filtering the background of the first 3AS images to obtain a plurality of second 3AS images, and taking the second 3AS images successfully matched with the 3AS templates AS component images of the shockproof hammer one by one.
7. The method according to claim 6, wherein the plurality of first 3AS images are filtered through a background to obtain a plurality of second 3AS images, and specifically:
after each first 3AS image is selected, the first 3AS image with pixels being non-foreground pixels is filtered out through a Grabcut algorithm, and a plurality of second 3AS images are obtained.
8. The method according to claim 5, wherein the step of determining whether the accessory of the power transmission line has a defect after combining the searched images of the components is specifically as follows:
combining the component images in pairs according to a preset distance range, judging the component images which are combined in pairs as complete anti-vibration hammers, and judging the component images which cannot be combined as the anti-vibration hammers with defects.
9. The method of claim 1, further comprising:
judging whether a pair of line segment groups which are equal in length, parallel to each other and capable of vertically projecting a part larger than eighty percent of the first to-be-processed area set to the opposite side exist in the first to-be-processed area set or not; if the line segment exists, two connecting line segments are generated, and a quadrangle is formed by the two connecting line segments and the line segment group.
10. The method according to any one of claims 1 to 9, wherein the image area is a rectangular area;
the first preset length is 1/3min (a, b); wherein a is the length of the rectangular region and b is the width of the rectangular region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811477413.3A CN109712116B (en) | 2018-12-04 | 2018-12-04 | Fault identification method for power transmission line and accessories thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811477413.3A CN109712116B (en) | 2018-12-04 | 2018-12-04 | Fault identification method for power transmission line and accessories thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109712116A CN109712116A (en) | 2019-05-03 |
| CN109712116B true CN109712116B (en) | 2023-03-28 |
Family
ID=66255414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811477413.3A Active CN109712116B (en) | 2018-12-04 | 2018-12-04 | Fault identification method for power transmission line and accessories thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712116B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852320B (en) * | 2019-11-08 | 2022-06-24 | 积成电子股份有限公司 | Transmission channel foreign matter intrusion detection method based on deep learning |
| CN110956614B (en) * | 2019-11-11 | 2023-04-07 | 国网山东省电力公司电力科学研究院 | Ground wire foreign matter detection method and device based on iterative search and projection method |
| CN112669302B (en) * | 2020-12-30 | 2023-07-28 | 北京市商汤科技开发有限公司 | Hanger defect detection method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002024336A (en) * | 2000-07-05 | 2002-01-25 | Nippon Keisoku Kk | Method and system for managing power-transmission line drawing |
| CN102565625A (en) * | 2011-05-25 | 2012-07-11 | 上海大学 | Method for intelligently diagnosing thermal defects of high-voltage transmission line based on infrared image |
| CN105931233A (en) * | 2016-04-19 | 2016-09-07 | 长沙理工大学 | Bolt searching and identifying method for bolt fastening robot of power transmission line |
| CN107179479A (en) * | 2017-06-12 | 2017-09-19 | 西安工程大学 | Transmission pressure broken lot defect inspection method based on visible images |
| CN107944412A (en) * | 2017-12-04 | 2018-04-20 | 国网山东省电力公司电力科学研究院 | Transmission line of electricity automatic recognition system and method based on multilayer convolutional neural networks |
| CN108037133A (en) * | 2017-12-27 | 2018-05-15 | 武汉市智勤创亿信息技术股份有限公司 | A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image |
| CN108334844A (en) * | 2018-02-06 | 2018-07-27 | 贵州电网有限责任公司 | A kind of automatic tracking method along the line of polling transmission line |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118044B (en) * | 2015-06-16 | 2017-11-07 | 华南理工大学 | A kind of wheel shape cast article defect automatic testing method |
-
2018
- 2018-12-04 CN CN201811477413.3A patent/CN109712116B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002024336A (en) * | 2000-07-05 | 2002-01-25 | Nippon Keisoku Kk | Method and system for managing power-transmission line drawing |
| CN102565625A (en) * | 2011-05-25 | 2012-07-11 | 上海大学 | Method for intelligently diagnosing thermal defects of high-voltage transmission line based on infrared image |
| CN105931233A (en) * | 2016-04-19 | 2016-09-07 | 长沙理工大学 | Bolt searching and identifying method for bolt fastening robot of power transmission line |
| CN107179479A (en) * | 2017-06-12 | 2017-09-19 | 西安工程大学 | Transmission pressure broken lot defect inspection method based on visible images |
| CN107944412A (en) * | 2017-12-04 | 2018-04-20 | 国网山东省电力公司电力科学研究院 | Transmission line of electricity automatic recognition system and method based on multilayer convolutional neural networks |
| CN108037133A (en) * | 2017-12-27 | 2018-05-15 | 武汉市智勤创亿信息技术股份有限公司 | A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image |
| CN108334844A (en) * | 2018-02-06 | 2018-07-27 | 贵州电网有限责任公司 | A kind of automatic tracking method along the line of polling transmission line |
Non-Patent Citations (1)
| Title |
|---|
| 基于感知组织的输电线路结构识别方法;韩军等;《红外与激光工程》;20131225(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109712116A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784333B (en) | Three-dimensional target detection method and system based on point cloud weighted channel characteristics | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN106548463B (en) | Sea fog image automatic defogging method and system based on dark and Retinex | |
| CN108230264B (en) | Single image defogging method based on ResNet neural network | |
| CN104483326B (en) | High-voltage line defects of insulator detection method and system based on depth belief network | |
| WO2020107866A1 (en) | Text region obtaining method and apparatus, storage medium and terminal device | |
| CN109712116B (en) | Fault identification method for power transmission line and accessories thereof | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| JP6192271B2 (en) | Image processing apparatus, image processing method, and program | |
| CN107038416B (en) | Pedestrian detection method based on binary image improved HOG characteristics | |
| CN108564549A (en) | A kind of image defogging method based on multiple dimensioned dense connection network | |
| Selvakumar et al. | The performance analysis of edge detection algorithms for image processing | |
| CN108445009B (en) | Crack detection method for solar cell panel | |
| CN113962994B (en) | Method for detecting cleanliness of lock pin on three-connecting-rod based on image processing | |
| CN105740844A (en) | Insulator cracking fault detection method based on image identification technology | |
| CN117522863B (en) | Integrated box body quality detection method based on image features | |
| CN113409267A (en) | Pavement crack detection and segmentation method based on deep learning | |
| CN112991374A (en) | Canny algorithm-based edge enhancement method, device, equipment and storage medium | |
| CN113313107A (en) | Intelligent detection and identification method for multiple types of diseases on cable surface of cable-stayed bridge | |
| CN115620279A (en) | Pod phenotype analysis method, system and device based on computer vision | |
| CN111738931A (en) | Shadow removal algorithm for aerial image of photovoltaic array unmanned aerial vehicle | |
| CN111340833A (en) | Power transmission line extraction method based on least square interference-free random Hough transformation | |
| CN113610799B (en) | Artificial intelligence-based photovoltaic cell panel rainbow line detection method, device and equipment | |
| Wang et al. | Straight lane line detection based on the Otsu-Canny algorithm |
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 |