CN104616020A - Method and system for detecting icing of transmission line based on clustering analysis - Google Patents
Method and system for detecting icing of transmission line based on clustering analysis Download PDFInfo
- Publication number
- CN104616020A CN104616020A CN201410484919.2A CN201410484919A CN104616020A CN 104616020 A CN104616020 A CN 104616020A CN 201410484919 A CN201410484919 A CN 201410484919A CN 104616020 A CN104616020 A CN 104616020A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- image
- electricity
- icing
- pixel
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Abstract
The invention provides a method for detecting icing of a transmission line based on clustering analysis. The method is characterized by comprising the steps of (1) extracting adjacent frame images from a video monitoring terminal or a video record; (2) preprocessing the extracted adjacent frame images; (3) segmenting a transmission line image based on the clustering analysis theory; (4) comparing with the non-icing transmission line to determine whether the transmission line suffers from icing; (5) locating the position of the transmission line through a communication area mark according to the characteristics of the transmission line in the image. According to the method, the adjacent frame images are extracted from the video monitoring terminal or the video record and then are preprocessed, the transmission line image is segmented based on the clustering analysis theory, the location of the transmission line is located through communication area mark according to the characteristic of the transmission line in the image, and finally the comparison is performed with the non-icing transmission line so as to determine whether the transmission line suffers from icing. With the adoption of the method, both the detection time and detection effect are obvious, and the actual application demand can be met.
Description
Technical field
The invention belongs to polling transmission line field, relate to digital image processing techniques and mode identification technology, particularly relate to a kind of powerline ice-covering detection method based on cluster analysis and system.
Background technology
For overhead transmission line, owing to being chronically exposed in physical environment, existing artificial or naturally destroy and aging circuit problem, also will stand the infringement of the extraneous factors such as filth, thunderbolt, wind and snow, flood and bird pest.Above factor can impel ageing equipment on circuit, if find and eliminate these hidden danger not in time, just likely causing various fault even occurs accident, can affect safe operation and the power system stability of electrical network.Icing on overhead transmission line, brings a lot of impact to the overhead transmission line in many places in the world.In recent years, China had been subjected to large-scale ice damage accident too.The serious harms such as icing can cause insulator to damage to overhead transmission line, broken string, shaft tower collapse.By transmission line online monitoring system, staff can understand the field conditions of transmission line of electricity in time, so that when icing is blocked up on transmission line of electricity, takes deicing measure in time, avoids the generation of major accident, for the safe operation of electric system provides safeguard.But staff needs to stand fast in front of the monitor for a long time, causes the waste of human resources, and easily dangerous situation is caused not to be found in time by human factor.
Traditional icing monitoring method of power transmission line great majority adopt analog detection law technology, the advantage of analog detection method be draw materials very simple, easy for installation, only need to place near transmission line of electricity, but the shortcoming of this method obtains the icing data simulating material to be difficult to.Name is called that the patent of " a kind of ice covering thickness Forecasting Methodology based on fuzzy logic " is open a kind of according to transmission line of electricity scene temperature, humidity, wind speed and conductor temperature data, thus comprehensively draws the method for electric power line ice-covering thickness.Described method adopts tension measurement mode, but the feature of the material of pulling force sensor own makes serial connection insulator, and difficulty of construction is high, can have influence on insulator, there is impact to line security.
In the last few years, along with the fast development of computer technology and image processing techniques, researchist started progressively to adopt the icing detection technique based on image, thus the accuracy rate impelling coated by ice of overhead power transmission line to detect and reliability are improved to a certain extent.Disclosed in the patent that name is called " visible detection method of ice coating thickness of overhead lines ", method is: first carry out Iamge Segmentation, obtain the region of image transmission line of electricity, then based on Makkonen model, ice coating load, ice covering thickness are carried out to transmission line of electricity, shaft tower is stressed and wire is stressed monitors in real time and monitor, the thickness of icing is calculated by the pixel ratio of adding up transmission line of electricity region and entire image, but the method is when splitting image and obtaining transmission line of electricity region, and segmentation effect is undesirable; What name was called " transmission line of electricity image collecting device and electric power line ice-covering thickness detection system " patent discloses a kind of detection system, described system is directly measured wire and ice coating wire thickness by being arranged on by shooting part on transmission line of electricity, achieve the relative position of fixing transmission line of electricity image collecting device and transmission line of electricity, the image that this system obtains is more stable, image debounce that it goes without doing, denoising operation, but this device is at complex condition, as strong wind, dust and sand weather, shooting part job insecurity.
Summary of the invention
The object of the present invention is to provide a kind of powerline ice-covering detection method based on cluster analysis and system, this detection method all achieves significant achievement from detection time or Detection results, can meet actual complex environmental applications needs.
For achieving the above object, the invention provides a kind of powerline ice-covering detection method based on cluster analysis,
It is characterized in that comprising the following steps:
1, from Video Monitoring Terminal or video record, consecutive frame image is extracted;
2, extraction consecutive frame image is carried out to the pre-service of image;
3, utilize based on cluster analysis theory, Iamge Segmentation is carried out to transmission line of electricity image;
4, Yu without icing transmission line of electricity contrast, judge transmission line of electricity whether icing;
5, according to transmission line of electricity feature in the picture, connected component label is adopted to locate the position of transmission line of electricity.
Described pre-service extraction consecutive frame image being carried out to image, first detects critical area relevant with transmission line of electricity in image, then the image of critical area is carried out gray processing, obtain gray-scale map;
(1)
Wherein
for pixel coordinate in image,
, m is picture altitude,
, n is picture traverse,
being respectively pixel coordinate is
the pixel value of red, green, blue passage,
for pixel coordinate
gray-scale value, carry out image smoothing, filtered noise to the image of critical area again after gray level image, image smoothing adopts the method for medium filtering.
Described carries out Iamge Segmentation based on cluster analysis theory to transmission line of electricity image, adopts a kind of Fuzzy C-Means Clustering Algorithm of improvement, if sample set
belong to
pdimension theorem in Euclid space, namely
,
. first by sample set
be divided into different classes, namely
cindividual mutually disjoint subclass
, wherein
cfor classification number, the feature being reflected in image in each class has very strong cohesion, and have between class and class between larger class poor, namely
In formula,
, be weighted index,
nfor the pixel count in image or pattern count,
cfor the classification number pre-set
1<
c≤
n;
illustrate all kinds of in sample to the Weighted distance quadratic sum of cluster centre, its value is reflected in the class degree of consistency under the definition of the specified difference opposite sex,
less, cluster is compacter, and algorithm is alternately upgraded by iteration
,
, when the norm of the difference of the subordinated-degree matrix of adjacent twice iteration
time, iteration stopping, wherein
tfor the number of times of iteration,
for the convergence threshold pre-set, at this moment objective function reaches minimum approx;
for the set that all in image non-" edge " is put,
for the set that all " edge " is put, so:
First non-" edge " part is divided into mutually disjoint piece, then point of " edge " part is divided in adjacent block, forms that some are mutually disjoint, continuous print subclass, complete the primary segmentation of an image, obtain the individual mutually disjoint subclass of c:
, wherein
, then when
be positioned at
class
time, then
, otherwise
Work as a little
, when being marginal point, its computing formula is consistent with general Fuzzy C-Means Clustering Algorithm fuzzy c-means algorithm and FCM, employing be the method for obfuscation membership; Work as a little
, when being non-edge point, no matter be which takes turns iteration, its degree of membership does not change, and no longer recalculates, and therefore, recalculate and determine just those marginal points belonged to;
Described contrasts with without icing transmission line of electricity, judge transmission line of electricity whether icing, piece image when first gathering the non-icing of transmission line of electricity is as standard picture, pre-service and segmentation are carried out to image, the sum of all pixels in transmission line of electricity region in computed image again, in video monitoring process, pre-service and image segmentation operations are carried out to the realtime graphic collected, obtain the sum of all pixels in transmission line of electricity region, judge whether the pixel value of realtime graphic exceeds corresponding to 15% of image during icing, when its pixel count exceed without during icing 15% time, think that monitored transmission line of electricity has icing, rower of going forward side by side shows,
Described according to transmission line of electricity feature in the picture, connected component label is adopted to locate the position of transmission line of electricity, be specially: after Iamge Segmentation, transmission line of electricity region can be obtained, connected component label is adopted to identify transmission line of electricity profile, namely transmission line of electricity edge is marked, 8-neighborhood mode is adopted to mark, hypothetical target is white, value is 255, background is black, value is 0, first complete scanning is carried out once to bianry image, mark all target pixel points, then each pixel is carried out to the mark of 8-connected region, namely upper to each pixel, under, left, right, upper left, upper right, bottom right, lower-left, totally 8 neighbors compare, then mark according to comparative result, special processing is carried out for there is no 8 adjacent pixels.
In addition the present invention also provides a kind of powerline ice-covering detection system based on cluster analysis, comprise video image load module, transmission line of electricity image pre-processing module, transmission line of electricity image segmentation module, powerline ice-covering detection module and transmission line of electricity mark module, wherein:
Video acquisition module, extracts consecutive frame image from Video Monitoring Terminal or video record;
Transmission line of electricity image pre-processing module, carries out the pre-service of image to extraction consecutive frame image;
Transmission line of electricity image segmentation module, utilizes based on cluster analysis theory, proposes a kind of FCM image segmentation algorithm of improvement, carries out Iamge Segmentation to transmission line of electricity image;
Powerline ice-covering detection module, adopt the mode of image of scanning by column, before and after computing electric power line ice-covering, the pixel ratio of image, contrasts with without icing transmission line of electricity, judges transmission line of electricity whether icing;
Transmission line of electricity mark module, according to transmission line of electricity feature in the picture, adopts connected component label to locate the position of transmission line of electricity.
The present invention extracts consecutive frame image from Video Monitoring Terminal or video record, then extraction consecutive frame image is carried out to the pre-service of image, utilize based on cluster analysis theory, Iamge Segmentation is carried out to transmission line of electricity image, according to transmission line of electricity feature in the picture, adopt connected component label to locate the position of transmission line of electricity, last with contrast without icing transmission line of electricity, judge transmission line of electricity whether icing.The method all achieves good result from detection time or Detection results, can meet practical application needs.
Accompanying drawing explanation
Fig. 1 is based on the powerline ice-covering detection method block diagram of cluster analysis;
Fig. 2 is based on the powerline ice-covering detection system structural drawing of cluster analysis;
The FCM algorithm flow chart that Fig. 3 improves.
concrete implementation
As shown in Figure 1, detection method comprises the following steps:
In step S101, from Video Monitoring Terminal or video record, extract consecutive frame image.
In step S102, extraction consecutive frame image is carried out to the pre-service of image.First detect critical area relevant with transmission line of electricity in image, then the image of critical area is carried out gray processing, obtain gray-scale map.
(1)
Wherein
for pixel coordinate in image,
, m is picture altitude,
, n is picture traverse,
being respectively pixel coordinate is
the pixel value of red, green, blue passage,
for pixel coordinate
gray-scale value.
Carry out image smoothing, filtered noise to the image of critical area again after gray level image, image smoothing adopts the method for medium filtering.
In step S103, based on cluster analysis theory, Iamge Segmentation is carried out to transmission line of electricity image.In numerous fuzzy clustering algorithm, Fuzzy C-Means Clustering Algorithm fuzzy c-means algorithm(FCM) most widely used general and more successful, it obtains the degree of membership of each sample point to all class centers by optimization object function, thus determines that the generic of sample point is to reach the object of automatically classifying to data sample.
For the feature of transmission line of electricity image, in the present invention, design a kind of Fuzzy C-Means Clustering Algorithm of improvement.
If sample set
belong to
pdimension theorem in Euclid space, namely
,
. first by sample set
be divided into different classes, namely
cindividual mutually disjoint subclass
, wherein
cfor classification number, the feature being reflected in image in each class has very strong cohesion, and have between class and class between larger class poor.Namely
In formula,
, be weighted index, n is pixel count in image or pattern count, and c is the classification number 1< pre-set
c≤
n;
(3)
Wherein
for sample
with
ithe cluster centre of class
between Euclidean distance, due to
, and
,
it is one
p×
ccluster centre matrix.And
represent sample
whether
iin the cluster of class, i.e. sample
for
degree of membership.
Wherein
value be 0 or 1.Therefore
it is exactly the 0-1 matrix of a c × n.And meet constraint condition:
(4)
Therefore, also meet:
(5)
illustrate all kinds of in sample to the Weighted distance quadratic sum of cluster centre, its value is reflected in the class degree of consistency under the definition of the specified difference opposite sex,
less, cluster is compacter.Algorithm is alternately upgraded by iteration
,
, when the norm of the difference of the subordinated-degree matrix of adjacent twice iteration
time, iteration stopping, wherein
tfor the number of times of iteration,
for the convergence threshold pre-set, at this moment objective function reaches minimum approx.
Each sample of FCM algorithm serves certain sucking action to cluster centre, but it also brings the slow weakness of speed of convergence, and in order to address this problem, the present invention devises a kind of FCM algorithm correction of improvement
to improve the speed of convergence of cluster centre.
for the set that all in image non-" edge " is put,
for the set that all " edge " is put, so:
First non-" edge " part is divided into mutually disjoint piece, then point of " edge " part is divided in adjacent block, forms that some are mutually disjoint, continuous print subclass, complete the primary segmentation of an image, obtain the individual mutually disjoint subclass of c:
, wherein,
, then when
be positioned at
class
time, then
, otherwise
.When carrying out iteration, degree of membership more new formula is:
(6)
Class center more new formula is:
(7)
Work as a little
, when being marginal point, its computing formula is consistent with general FCM, employing be the method for obfuscation membership; Work as a little
, when being non-edge point, no matter be which takes turns iteration, its degree of membership does not change, and no longer recalculates.Therefore, recalculate and determine just those marginal points belonged to.
In step S104, contrast with without icing transmission line of electricity, judge transmission line of electricity whether icing.
How to judge that whether icing is crucial to transmission line of electricity, is constant according to its angle of inclination before and after powerline ice-covering, therefore can adopts the mode scanning by column image, the pixel ratio of image before and after computing electric power line ice-covering, specific as follows:
Piece image when first gathering the non-icing of transmission line of electricity, as standard picture, carries out pre-service and segmentation to image, then the sum of all pixels in transmission line of electricity region in computed image.In video monitoring process, pre-service and image segmentation operations are carried out to the realtime graphic collected, obtain the sum of all pixels in transmission line of electricity region.Judge whether the pixel value of realtime graphic exceeds corresponding to 15% of image during icing, when its pixel count exceed without during icing 15% time, think that monitored transmission line of electricity has icing, rower of going forward side by side shows.
In step S105, according to transmission line of electricity feature in the picture, connected component label is adopted to locate the position of transmission line of electricity.Be specially: after Iamge Segmentation, transmission line of electricity region can be obtained, adopt connected component label to identify transmission line of electricity profile, namely transmission line of electricity edge is marked.8-neighborhood mode is adopted to mark.Hypothetical target is white, and value is 255, and background is black, and value is 0.First complete scanning is carried out once to bianry image, mark all target pixel points, then each pixel is carried out to the mark of 8-connected region, namely to the upper and lower, left and right of each pixel, upper left, upper right, bottom right, lower-left, totally 8 neighbors compare, and then mark according to comparative result.Special processing is carried out for there is no 8 adjacent pixels.
As shown in Figure 2, present system comprises video image load module, transmission line of electricity image pre-processing module, transmission line of electricity image segmentation module, powerline ice-covering detection module and transmission line of electricity mark module, wherein:
Video acquisition module, extracts consecutive frame image from Video Monitoring Terminal or video record;
Transmission line of electricity image pre-processing module, carries out the pre-service of image to extraction consecutive frame image;
Transmission line of electricity image segmentation module, utilizes based on cluster analysis theory, proposes a kind of FCM image segmentation algorithm of improvement, carries out Iamge Segmentation to transmission line of electricity image;
Powerline ice-covering detection module, adopt the mode of image of scanning by column, before and after computing electric power line ice-covering, the pixel ratio of image, contrasts with without icing transmission line of electricity, judges transmission line of electricity whether icing.
Transmission line of electricity mark module, according to transmission line of electricity feature in the picture, adopts connected component label to locate the position of transmission line of electricity.
Fig. 3 is the FCM algorithm flow chart of a kind of improvement that the present invention proposes, and idiographic flow is as follows:
Step starts from S201
In step S202, environmentally c is set, the initial value of m, n, and t=0 is set;
In step S203, according to the initiation parameter that step S202 is arranged, by degree of membership
with
substitute into formula 6;
In step S204, if result is "Yes", then enter step S205;
In step S205, degree of membership
;
If the result of step S204 is "No", then enter step S206;
If the result of step S206 is "Yes", then enter step S207;
In step S207, degree of membership
;
If the result of step S206 is "No", then enter step S208;
In step S208, degree of membership
;
In step S209, according to the degree of membership that step S205, S207, S208 obtain, calculate
, specific formula for calculation is as follows:
In step S210, choose a suitable matrix norm and compare
with
, judge whether
if result is "No", then
, turn back to step S203, if result is "Yes", then enter step S211;
Step S211, flow process terminates.
Claims (6)
1., based on a powerline ice-covering detection method for cluster analysis, it is characterized in that comprising the following steps:
(1) from Video Monitoring Terminal or video record, consecutive frame image is extracted;
(2) extraction consecutive frame image is carried out to the pre-service of image;
(3) utilize based on cluster analysis theory, Iamge Segmentation is carried out to transmission line of electricity image;
(4) Yu without icing transmission line of electricity contrast, judge transmission line of electricity whether icing;
(5) according to transmission line of electricity feature in the picture, connected component label is adopted to locate the position of transmission line of electricity.
2. a kind of powerline ice-covering detection method based on cluster analysis according to claim 1, it is characterized in that: described pre-service extraction consecutive frame image being carried out to image, first critical area relevant with transmission line of electricity in image is detected, then the image of critical area is carried out gray processing, obtain gray-scale map;
(1)
Wherein
for pixel coordinate in image,
, m is picture altitude,
, n is picture traverse,
being respectively pixel coordinate is
the pixel value of red, green, blue passage,
for pixel coordinate
gray-scale value, carry out image smoothing, filtered noise to the image of critical area again after gray level image, image smoothing adopts the method for medium filtering.
3. a kind of powerline ice-covering detection method based on cluster analysis according to claim 1, it is characterized in that: described carries out Iamge Segmentation based on cluster analysis theory to transmission line of electricity image, adopt a kind of Fuzzy C-Means Clustering Algorithm of improvement, if sample set
belong to
pdimension theorem in Euclid space, namely
,
. first by sample set
be divided into different classes, namely
cindividual mutually disjoint subclass
, wherein
cfor classification number, the feature being reflected in image in each class has very strong cohesion, and have between class and class between larger class poor, namely
In formula,
, be weighted index,
nfor the pixel count in image or pattern count,
cfor the classification number pre-set
1<
c≤
n;
illustrate all kinds of in sample to the Weighted distance quadratic sum of cluster centre, its value is reflected in the class degree of consistency under the definition of the specified difference opposite sex,
less, cluster is compacter, and algorithm is alternately upgraded by iteration
,
, when the norm of the difference of the subordinated-degree matrix of adjacent twice iteration
time, iteration stopping, wherein
tfor the number of times of iteration,
for the convergence threshold pre-set, at this moment objective function reaches minimum approx;
for the set that all in image non-" edge " is put,
for the set that all " edge " is put, so:
First non-" edge " part is divided into mutually disjoint piece, then point of " edge " part is divided in adjacent block, forms that some are mutually disjoint, continuous print subclass, complete the primary segmentation of an image, obtain the individual mutually disjoint subclass of c:
, wherein,
, then when
be positioned at
class
time, then
, otherwise
;
Work as a little
, when being marginal point, its computing formula is consistent with general Fuzzy C-Means Clustering Algorithm fuzzy c-means algorithm and FCM, employing be the method for obfuscation membership; Work as a little
, when being non-edge point, no matter be which takes turns iteration, its degree of membership does not change, and no longer recalculates, and therefore, recalculate and determine just those marginal points belonged to.
4. a kind of powerline ice-covering detection method based on cluster analysis according to claim 1, it is characterized in that: described contrasts with without icing transmission line of electricity, judge transmission line of electricity whether icing, piece image when first gathering the non-icing of transmission line of electricity is as standard picture, pre-service and segmentation are carried out to image, the sum of all pixels in transmission line of electricity region in computed image again, in video monitoring process, pre-service and image segmentation operations are carried out to the realtime graphic collected, obtain the sum of all pixels in transmission line of electricity region, judge whether the pixel value of realtime graphic exceeds corresponding to 15% of image during icing, when its pixel count exceed without during icing 15% time, think that monitored transmission line of electricity has icing, rower of going forward side by side shows.
5. a kind of powerline ice-covering detection method based on cluster analysis according to claim 1, it is characterized in that: described according to transmission line of electricity feature in the picture, connected component label is adopted to locate the position of transmission line of electricity, be specially: after Iamge Segmentation, transmission line of electricity region can be obtained, connected component label is adopted to identify transmission line of electricity profile, namely transmission line of electricity edge is marked, 8-neighborhood mode is adopted to mark, hypothetical target is white, value is 255, background is black, value is 0, first complete scanning is carried out once to bianry image, mark all target pixel points, then each pixel is carried out to the mark of 8-connected region, namely upper to each pixel, under, left, right, upper left, upper right, bottom right, lower-left, totally 8 neighbors compare, then mark according to comparative result, special processing is carried out for there is no 8 adjacent pixels.
6. the powerline ice-covering detection system based on cluster analysis, it is characterized in that: comprise video image load module, transmission line of electricity image pre-processing module, transmission line of electricity image segmentation module, powerline ice-covering detection module and transmission line of electricity mark module, wherein:
Video acquisition module, extracts consecutive frame image from Video Monitoring Terminal or video record;
Transmission line of electricity image pre-processing module, carries out the pre-service of image to extraction consecutive frame image;
Transmission line of electricity image segmentation module, utilizes based on cluster analysis theory, proposes a kind of FCM image segmentation algorithm of improvement, carries out Iamge Segmentation to transmission line of electricity image;
Powerline ice-covering detection module, adopt the mode of image of scanning by column, before and after computing electric power line ice-covering, the pixel ratio of image, contrasts with without icing transmission line of electricity, judges transmission line of electricity whether icing;
Transmission line of electricity mark module, according to transmission line of electricity feature in the picture, adopts connected component label to locate the position of transmission line of electricity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410484919.2A CN104616020A (en) | 2014-09-22 | 2014-09-22 | Method and system for detecting icing of transmission line based on clustering analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410484919.2A CN104616020A (en) | 2014-09-22 | 2014-09-22 | Method and system for detecting icing of transmission line based on clustering analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104616020A true CN104616020A (en) | 2015-05-13 |
Family
ID=53150457
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410484919.2A Pending CN104616020A (en) | 2014-09-22 | 2014-09-22 | Method and system for detecting icing of transmission line based on clustering analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104616020A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106908008A (en) * | 2017-03-13 | 2017-06-30 | 贵州电网有限责任公司电力科学研究院 | A kind of transmission line of electricity distribution ice-melt monitoring method |
CN111916089A (en) * | 2020-07-27 | 2020-11-10 | 南京信息工程大学 | Hail detection method and device based on acoustic signal characteristic analysis |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5772153A (en) * | 1995-10-17 | 1998-06-30 | Abaunza; John T. | Aircraft icing sensors |
CN101556142A (en) * | 2009-03-11 | 2009-10-14 | 湖南大学 | Visual detection method of ice coating thickness of overhead lines |
-
2014
- 2014-09-22 CN CN201410484919.2A patent/CN104616020A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5772153A (en) * | 1995-10-17 | 1998-06-30 | Abaunza; John T. | Aircraft icing sensors |
CN101556142A (en) * | 2009-03-11 | 2009-10-14 | 湖南大学 | Visual detection method of ice coating thickness of overhead lines |
Non-Patent Citations (2)
Title |
---|
张爱华: "基于模糊聚类分析的图像分割技术研究", 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 * |
王鹤: "输电线路覆冰图像处理与识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106908008A (en) * | 2017-03-13 | 2017-06-30 | 贵州电网有限责任公司电力科学研究院 | A kind of transmission line of electricity distribution ice-melt monitoring method |
CN111916089A (en) * | 2020-07-27 | 2020-11-10 | 南京信息工程大学 | Hail detection method and device based on acoustic signal characteristic analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
CN108307146B (en) | System and method for detecting potential safety hazard of high-voltage transmission line | |
CN103442209B (en) | Video monitoring method of electric transmission line | |
CN106680285B (en) | Method for recognizing insulator contamination state based on infrared image assisted visible light image | |
CN105976368B (en) | A kind of insulator localization method | |
CN101556142B (en) | Visual detection method of ice coating thickness of overhead lines | |
CN102252623B (en) | Measurement method for lead/ground wire icing thickness of transmission line based on video variation analysis | |
CN111754465B (en) | Insulator positioning and string dropping detection method | |
CN104463904A (en) | High-voltage line foreign matter invasion target detection method | |
CN106570863A (en) | Power transmission line detection method and device | |
CN111814686A (en) | Vision-based power transmission line identification and foreign matter invasion online detection method | |
CN103413150A (en) | Power line defect diagnosis method based on visible light image | |
CN103063166B (en) | Detection method and device for wind deflection angle of suspension type composite insulator chain | |
CN102519846B (en) | Hyperspectrum-based composite insulator hydrophobicity detection method | |
CN103940824A (en) | Air electric transmission line insulator detecting method | |
CN104601965A (en) | Camera shielding detection method | |
CN110493574B (en) | Security monitoring visualization system based on streaming media and AI technology | |
CN105096305A (en) | Method and device for analyzing state of insulators | |
CN103852018A (en) | Electric transmission line icing thickness measuring algorithm based on image processing | |
CN109523543A (en) | A kind of wire strand breakage detection method based on Edge Distance | |
CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
CN113744267B (en) | Method for detecting icing and estimating thickness of transmission conductor based on deep learning | |
CN104616020A (en) | Method and system for detecting icing of transmission line based on clustering analysis | |
Wang et al. | Study on edge extraction methods for image-based icing on-line monitoring on overhead transmission lines | |
CN114283126B (en) | Method for detecting deviation of monitoring equipment of power transmission line |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150513 |