CN104408459A - Image identification method applied to power equipment monitoring - Google Patents
Image identification method applied to power equipment monitoring Download PDFInfo
- Publication number
- CN104408459A CN104408459A CN201410580984.5A CN201410580984A CN104408459A CN 104408459 A CN104408459 A CN 104408459A CN 201410580984 A CN201410580984 A CN 201410580984A CN 104408459 A CN104408459 A CN 104408459A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- value
- threshold
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
Disclosed is an image identification method applied to power equipment monitoring. The remote image monitoring systems occurring in recent years realize regular inspection through fixed infrared cameras, send obtained images back to a control chamber and then carry out manual analysis, thereby reducing the labor amount to a certain extent, yet these methods all neglect research on diagnosis intelligentization, cannot get rid of reliance on the manual analysis, are time-consuming and labor-consuming, and cannot obtain timely and accurate diagnosis results easily. The method provided by the invention comprises the following steps: first of all, extracting characteristics of power equipment, carrying out image preprocessing on images, removing dark interference objects in the images, then performing image segmentation, merging segmented areas, determining fault areas of the power equipment, and carrying out detection identification on object area faults. The image identification method applied to power equipment monitoring is applied to image identification of the power equipment in terms of fault detection.
Description
technical field:
the present invention relates to the image-recognizing method used in a kind of electric apparatus monitoring.
background technology:
video monitoring system has been installed in power plant, transformer station by some Utilities Electric Co. at present, can realize monitoring field apparatus, controlling the functions such as remote camera action.But these video monitoring systems only have video monitoring function, there is no video image identification function.For giving full play to the function of video monitoring system, judge the reason of the on-the-spot alarm that has an accident more accurately, remote digital video monitoring and digital image acquisition system should be adopted, to realize the image recognition of equipment alarm, new means are provided, for crash analysis provides reliable foundation for accident detects.
along with the sustainable development of national economy, the electric system of China to take extra-high voltage as trunk rack, the strong intelligent grid future development mutually coordinated of electrical network at different levels, and " self-healing " is one of essential characteristic of intelligent grid.So-called " self-healing ", not only require that electrical network can fast isolated fault recover the power supply of healthy sections automatically, but also requirement can carry out on-line monitoring and safe early warning to electrical network, can Timeliness coverage fault take measures to remove a hidden danger, make power system restoration health run to avoid accident that [2] occur.
according to statistics, in electric system, the fault of 70% is caused by electrical equipment malfunction, and exceed that electrical equipment malfunction more than half all with because of Leakage Current, leakage field, connection loosens, heating that loose contact etc. causes is relevant.Electrical equipment is in abnormal heating state for a long time can cause hardware " creep ", insulating material ageing and inferior, finally causes serious device damage and causes electric network fault.Thus, how to utilize high-tech means to carry out systematization, standardized management, eliminate danger a little, be the new problem of pendulum in face of electric system R&D institution, this has great importance to minimizing accident generation raising equipment operational reliability.
infrared detection technology utilizes infrared detection equipment to obtain temperature value and the temperature space distribution characteristics of power equipment, and the fault of hiding in analyzing and processing equipment and hidden danger, can prevent trouble before it happens.In recent years, because infrared detection technology has untouchable, easy to operate, that traditional common detection methods such as security is high, response is fast, accuracy of judgement, applied range is incomparable advantage, be widely used in the on-line monitoring of electric system, achieved good effect.
at present, domestic infrared Image Segmentation is mostly that the image processing method of visible ray directly or is in addition changed aftertreatment infrared image, a little so segmentation effect is difficult to reach expection requirement.So, according to the feature of electrical equipment infrared image self, be the prerequisite realizing New Generation of Intelligent monitoring using infrared image as the development of the image Segmentation Technology of handling object.Around us, Video Supervision Technique has boundless application prospect, it plays day by day main effect, so will welcome unprecedented development and progress as the infrared Image Segmentation technology of precondition in the daily life and work of electric system, national defence, field of traffic and the people.
but most infrared detection method still adopts the hand-held infrared measurement of temperature of staff or Image-forming instrument regularly to patrol and examine equipment, and then manual analysis is carried out to the temperature data obtained and infrared image.The remote image monitoring system occurred in recent years, realizes regular patrolling and examining by fixing infrared camera, gained image is beamed back pulpit and carries out manual analysis again, can say and decrease manual labor's amount [15] to a certain extent.But these methods above-mentioned are still all negligent of the research to intelligent diagnosis, fail to break away from the dependence to manual analysis, time and effort consuming, be also difficult to obtain accurate diagnostic result in time.
summary of the invention:
the object of this invention is to provide the image-recognizing method used in a kind of electric apparatus monitoring.
above-mentioned object is realized by following technical scheme:
the image-recognizing method used in a kind of electric apparatus monitoring, the method comprises the steps: first to extract the feature of power equipment, Image semantic classification is carried out to image, remove the dark interfering object in image, then Iamge Segmentation is carried out, by the merging of cut zone, determine the fault zone of electrical equipment, carry out the detection identification of target area fault.
the image-recognizing method used in described electric apparatus monitoring, described Image semantic classification key step is image gray processing, de-noising is gone to cut and is compensated with image irradiation, the coloured image of input is converted into gray level image by described image gray processing, coloured image becomes grayscale format, it is the colouring information will throwing away image, by the monochrome information of gray scale chart diagram picture, the each pixel of coloured image accounts for 3 bytes (24), and after becoming gray level image, each pixel accounts for 1 byte (accounting for 8), the gray-scale value of pixel is the brightness of current color image pixel, in gray level image, Y is called as gray-scale value, it is positioned within certain scope:
, require that Y is only positive in theory, and be finite value, interval
be called gray level, general conventional gray level is (0,255), Y here
min
=0 is black, Y
max
=225 is white, and all intermediate values are the various gray scales from black to white, 256 grades altogether,
described image is RGB pattern, described RGB represents RGB, one width RGB image is exactly M × N × 3 array of colour element, wherein each color pixel cell is at the corresponding red, green, blue three-component of the coloured image of particular spatial location, RGB model is the gray-scale value that the RGB component of each pixel in image distributes in 0 to 255 scope, mainly contains three kinds to the method for its gray processing:
(1) maximum value process: using the gray-scale value of the maximal value of the three-component brightness in coloured image as gray-scale map,
（1）；
(2) mean value method: the three-component brightness in coloured image is averaging and obtains a gray-scale map;
（2）；
(3) three components are weighted on average with different weights by method of weighted mean: according to importance and other index, because the sensitivity of human eye to green is the highest, minimum to blue-sensitive, therefore, by formula (3), average energy is weighted to RGB three-component and obtains more rational gray level image
（3） 。
the image-recognizing method used in described electric apparatus monitoring, described de-noising go tapping medium filtering overcome under certain condition linear filter as neighbor smoothing filtering the image detail that brings fuzzy, and to filtering impulse disturbances and image scanning noise the most effective; Medium filtering is exactly the moving window with an odd point, is replaced by the Mesophyticum of each point in the value window of window center point;
be provided with an one-dimensional sequence
, getting length of window is m, and wherein, m is odd number, carries out medium filtering to it, in succession extracts m number out exactly from list entries, then by this m number by the sequence of its numerical values recited, gets that number put centered by its sequence number and export as filtering, be expressed as with mathematical formulae:
（4）
the filtering method of medium filtering does size sequence to the pixel in glide filter window (2N+1), and the output pixel value of filter result is defined as the intermediate value of sequence.
the image-recognizing method used in described electric apparatus monitoring, described Iamge Segmentation adopts the dividing method based on gray threshold, first optimal threshold is determined, optimal threshold is the key of segmentation, set a certain threshold value T, two parts are divided into: be greater than the pixel group of T and be less than the pixel group of T with by the data of image
if
be grayscale image, T is segmentation threshold, and
represent bianry image, then the result of image in threshold value can be expressed as:
（5）
here it is Threshold segmentation, object asks a threshold value T, and with T by image
be divided into object and background two fields; When actual treatment, generally representing background with 255 to show needs, representing object with 0,
owing to being not necessarily merely distributed in two tonal ranges between the actual image object that obtains and background, now just need two or more threshold value to extract target, such as select an interval
as threshold value, carry out image binaryzation process by formula (6),
（6）
threshold value is write as following form:
（7）
wherein (x, y) is pixel space coordinate,
represent pixel
the gray-scale value (x, y) at place represents the local characteristics of this vertex neighborhood; Limit according to the difference of T, three kinds of dissimilar threshold values can be obtained, that is:
(1) global threshold
: threshold value is only relevant with the gray-scale value of this point;
(2) local threshold
: threshold value is relevant with the local domain feature of this point with the gray-scale value of point;
(3) dynamic threshold
: the position of threshold value and this point, gray-scale value and local feature have relation;
global threshold is whole pictures is all split with a gray threshold, therefore generally needs to choose optimal threshold to split, and when image grey level histogram has double-hump characteristics, need choose gray scale corresponding to two peak-to-peak paddy as threshold value;
described optimal threshold adopts iterative Threshold selection method, and its step is as follows:
1. obtain maximum gradation value and the minimum gradation value of image, be designated as Z respectively
max
and Z
min
, make threshold value be:
(8)
2. according to threshold value T0, image is divided into prospect and background, obtains both average gray value oZ and bZ respectively, obtaining new threshold value is:
(9)
if 3. two average gray values
with
no longer change or T no longer change, then T is threshold value; Otherwise go to step 2., iterative computation.
the image-recognizing method used in described electric apparatus monitoring, line by line scan to input picture in the fault zone of described equipment, if target is black, background is white; The point of connected region different in image is labeled as different pixel values, and records the area in this region simultaneously, described area and statistical pixel number, area obtained here comprises the element on border;
in the algorithm, need an interim stack and interim chained list, be used for preserving all elements of a certain connected region; Also need an array, record the area of different connected region; After all elements of image has traveled through, then the internal memory release shared by interim stack, interim chained list and array, to accelerate travelling speed; In addition, after mark connected region, according to the different pixels number in image, the number of the connected region comprised in this image can directly be obtained; After opening up interim memory field, target is marked, at this moment need to judge that whether connected region is too many, if too much, the threshold value preset need be increased; Judge that whether a region is the method for connected region and is exactly: if current pixel point is stain, when eight points are all stains around it, be then a connected region;
calculate damaged condition:
fault degree refers to that fault zone area accounts for the number percent of the target total area, that is:
（10）
wherein Z is fault degree, and A is fault zone area, and S is the target total area.
beneficial effect:
1. the present invention adopts digital image processing techniques, first carries out filtering, denoising to image, then carries out rim detection to target, carries out ellipse fitting according to target signature, finally by the oil level data arranging thermometric line acquisition transformer.
the State Maintenance of the present invention based on condition monitoring and fault diagnosis technology, be not regulation time between overhauls(TBO), but regularly or continuously will carry out status monitoring to equipment, and according to the result of condition monitoring and fault diagnosis, equipment of finding out is with or without deterioration or failure symptom, where necessary place under repair again.It can have existing fault by diagnosis and detection before equipment failure; and the reliability time run continuously can be estimated more exactly; thus service life of equipment is the longest; hang-up accident is minimum; also have because surplus maintenance is controlled; and decrease spare parts consumption and maintenance load, also can prevent the man-made fault occurred because of maintenance, thus finally make maintenance cost minimum.
accompanying drawing illustrates:
accompanying drawing 1 is the schematic diagram that the present invention uses equipment.
embodiment:
embodiment 1:
the image-recognizing method used in a kind of electric apparatus monitoring, the method comprises the steps: first to extract the feature of power equipment, Image semantic classification is carried out to image, remove the dark interfering object in image, then Iamge Segmentation is carried out, by the merging of cut zone, determine the fault zone of electrical equipment, carry out the detection identification of target area fault.
embodiment 2:
the image-recognizing method used in electric apparatus monitoring according to embodiment 1, described Image semantic classification key step is image gray processing, de-noising is gone to cut and is compensated with image irradiation, the coloured image of input is converted into gray level image by described image gray processing, coloured image becomes grayscale format, it is the colouring information will throwing away image, by the monochrome information of gray scale chart diagram picture, the each pixel of coloured image accounts for 3 bytes (24), and after becoming gray level image, each pixel accounts for 1 byte (accounting for 8), the gray-scale value of pixel is the brightness of current color image pixel, in gray level image, Y is called as gray-scale value, it is positioned within certain scope:
, require that Y is only positive in theory, and be finite value, interval
be called gray level, general conventional gray level is (0,255), Y here
min
=0 is black, Y
max
=225 is white, and all intermediate values are the various gray scales from black to white, 256 grades altogether,
described image is RGB pattern, described RGB represents RGB, one width RGB image is exactly M × N × 3 array of colour element, wherein each color pixel cell is at the corresponding red, green, blue three-component of the coloured image of particular spatial location, RGB model is the gray-scale value that the RGB component of each pixel in image distributes in 0 to 255 scope, mainly contains three kinds to the method for its gray processing:
(1) maximum value process: using the gray-scale value of the maximal value of the three-component brightness in coloured image as gray-scale map,
（1）；
(2) mean value method: the three-component brightness in coloured image is averaging and obtains a gray-scale map;
（2）；
(3) three components are weighted on average with different weights by method of weighted mean: according to importance and other index, because the sensitivity of human eye to green is the highest, minimum to blue-sensitive, therefore, by formula (3), average energy is weighted to RGB three-component and obtains more rational gray level image
（3） 。
embodiment 3:
the image-recognizing method used in electric apparatus monitoring according to embodiment 2, described de-noising go tapping medium filtering overcome under certain condition linear filter as neighbor smoothing filtering the image detail that brings fuzzy, and to filtering impulse disturbances and image scanning noise the most effective; Medium filtering is exactly the moving window with an odd point, is replaced by the Mesophyticum of each point in the value window of window center point;
be provided with an one-dimensional sequence
, getting length of window is m, and wherein, m is odd number, carries out medium filtering to it, in succession extracts m number out exactly from list entries, then by this m number by the sequence of its numerical values recited, gets that number put centered by its sequence number and export as filtering, be expressed as with mathematical formulae:
（4）
the filtering method of medium filtering does size sequence to the pixel in glide filter window (2N+1), and the output pixel value of filter result is defined as the intermediate value of sequence.
embodiment 4:
the image-recognizing method used in electric apparatus monitoring according to embodiment 1, described Iamge Segmentation adopts the dividing method based on gray threshold, first optimal threshold is determined, optimal threshold is the key of segmentation, set a certain threshold value T, two parts are divided into: be greater than the pixel group of T and be less than the pixel group of T with by the data of image
if
be grayscale image, T is segmentation threshold, and
represent bianry image, then the result of image in threshold value can be expressed as:
（5）
here it is Threshold segmentation, object asks a threshold value T, and with T by image
be divided into object and background two fields; When actual treatment, generally representing background with 255 to show needs, representing object with 0,
owing to being not necessarily merely distributed in two tonal ranges between the actual image object that obtains and background, now just need two or more threshold value to extract target, such as select an interval
as threshold value, carry out image binaryzation process by formula (6),
（6）
threshold value is write as following form:
（7）
wherein (x, y) is pixel space coordinate,
represent pixel
the gray-scale value (x, y) at place represents the local characteristics of this vertex neighborhood; Limit according to the difference of T, three kinds of dissimilar threshold values can be obtained, that is:
(1) global threshold
: threshold value is only relevant with the gray-scale value of this point;
(2) local threshold
: threshold value is relevant with the local domain feature of this point with the gray-scale value of point;
(3) dynamic threshold
: the position of threshold value and this point, gray-scale value and local feature have relation;
global threshold is whole pictures is all split with a gray threshold, therefore generally needs to choose optimal threshold to split, and when image grey level histogram has double-hump characteristics, need choose gray scale corresponding to two peak-to-peak paddy as threshold value;
described optimal threshold adopts iterative Threshold selection method, and its step is as follows:
1. obtain maximum gradation value and the minimum gradation value of image, be designated as Z respectively
max
and Z
min
, make threshold value be:
(8)
2. according to threshold value T0, image is divided into prospect and background, obtains both average gray value oZ and bZ respectively, obtaining new threshold value is:
(9)
if 3. two average gray values
with
no longer change or T no longer change, then T is threshold value; Otherwise go to step 2., iterative computation.
embodiment 5:
the image-recognizing method used in electric apparatus monitoring according to embodiment 1, line by line scan to input picture in the fault zone of described equipment, if target is black, background is white; The point of connected region different in image is labeled as different pixel values, and records the area in this region simultaneously, described area and statistical pixel number, area obtained here comprises the element on border;
in the algorithm, need an interim stack and interim chained list, be used for preserving all elements of a certain connected region; Also need an array, record the area of different connected region; After all elements of image has traveled through, then the internal memory release shared by interim stack, interim chained list and array, to accelerate travelling speed; In addition, after mark connected region, according to the different pixels number in image, the number of the connected region comprised in this image can directly be obtained; After opening up interim memory field, target is marked, at this moment need to judge that whether connected region is too many, if too much, the threshold value preset need be increased; Judge that whether a region is the method for connected region and is exactly: if current pixel point is stain, when eight points are all stains around it, be then a connected region;
calculate damaged condition:
fault degree refers to that fault zone area accounts for the number percent of the target total area, that is:
（10）
wherein Z is fault degree, and A is fault zone area, and S is the target total area.
embodiment 6:
the equipment that the image-recognizing method used in electric apparatus monitoring described in a kind of claim 1-5 uses, its composition comprises: one group of visible image capturing 1, infrared camera 2, described visible image capturing head, described infrared camera respectively optical transmitter and receiver 3 connect, described optical transmitter and receiver is connected with server 4, described server is connected with switch 5, and described switch is connected with one group of workstation 6.
Claims (5)
1. the image-recognizing method used in an electric apparatus monitoring, it is characterized in that: the method comprises the steps: first to extract the feature of power equipment, Image semantic classification is carried out to image, remove the dark interfering object in image, then Iamge Segmentation is carried out, by the merging of cut zone, determine the fault zone of electrical equipment, carry out the detection identification of target area fault.
2. the image-recognizing method used in electric apparatus monitoring according to claim 1, it is characterized in that: described Image semantic classification key step is image gray processing, de-noising is gone to cut and is compensated with image irradiation, the coloured image of input is converted into gray level image by described image gray processing, coloured image becomes grayscale format, it is the colouring information will throwing away image, by the monochrome information of gray scale chart diagram picture, the each pixel of coloured image accounts for 3 bytes, 24, and after becoming gray level image, each pixel accounts for 1 byte, account for 8, the gray-scale value of pixel is the brightness of current color image pixel, in gray level image, Y is called as gray-scale value, it is positioned within certain scope:
, require that Y is only positive in theory, and be finite value, interval
be called gray level, general conventional gray level is (0,255), Y here
min=0 is black, Y
max=225 is white, and all intermediate values are the various gray scales from black to white, 256 grades altogether,
Described image is RGB pattern, described RGB represents RGB, one width RGB image is exactly M × N × 3 array of colour element, wherein each color pixel cell is at the corresponding red, green, blue three-component of the coloured image of particular spatial location, RGB model is the gray-scale value that the RGB component of each pixel in image distributes in 0 to 255 scope, mainly contains three kinds to the method for its gray processing:
(1) maximum value process: using the gray-scale value of the maximal value of the three-component brightness in coloured image as gray-scale map,
（1）；
(2) mean value method: the three-component brightness in coloured image is averaging and obtains a gray-scale map;
（2）；
(3) three components are weighted on average with different weights by method of weighted mean: according to importance and other index, because the sensitivity of human eye to green is the highest, minimum to blue-sensitive, therefore, by formula (3), average energy is weighted to RGB three-component and obtains more rational gray level image
（3） 。
3. the image-recognizing method used in electric apparatus monitoring according to claim 2, it is characterized in that: described de-noising go tapping medium filtering overcome under certain condition linear filter as neighbor smoothing filtering the image detail that brings fuzzy, and to filtering impulse disturbances and image scanning noise the most effective; Medium filtering is exactly the moving window with an odd point, is replaced by the Mesophyticum of each point in the value window of window center point;
Be provided with an one-dimensional sequence
, getting length of window is m, and wherein, m is odd number, carries out medium filtering to it, in succession extracts m number out exactly from list entries, then by this m number by the sequence of its numerical values recited, gets that number put centered by its sequence number and export as filtering, be expressed as with mathematical formulae:
（4）
The filtering method of medium filtering does size sequence to the pixel in glide filter window (2N+1), and the output pixel value of filter result is defined as the intermediate value of sequence.
4. the image-recognizing method used in electric apparatus monitoring according to claim 1, it is characterized in that: described Iamge Segmentation adopts the dividing method based on gray threshold, first optimal threshold is determined, optimal threshold is the key of segmentation, set a certain threshold value T, two parts are divided into: be greater than the pixel group of T and be less than the pixel group of T with by the data of image
If
be grayscale image, T is segmentation threshold, and
represent bianry image, then the result of image in threshold value can be expressed as:
（5）
Here it is Threshold segmentation, object asks a threshold value T, and with T by image
be divided into object and background two fields; When actual treatment, generally representing background with 255 to show needs, representing object with 0,
Owing to being not necessarily merely distributed in two tonal ranges between the actual image object that obtains and background, now just need two or more threshold value to extract target, such as select an interval
as threshold value, carry out image binaryzation process by formula (6),
（6）
Threshold value is write as following form:
（7）
Wherein (x, y) is pixel space coordinate,
represent pixel
the gray-scale value (x, y) at place represents the local characteristics of this vertex neighborhood; Limit according to the difference of T, three kinds of dissimilar threshold values can be obtained, that is:
(1) global threshold
: threshold value is only relevant with the gray-scale value of this point;
(2) local threshold
: threshold value is relevant with the local domain feature of this point with the gray-scale value of point;
(3) dynamic threshold
: the position of threshold value and this point, gray-scale value and local feature have relation;
Global threshold is whole pictures is all split with a gray threshold, therefore generally needs to choose optimal threshold to split, and when image grey level histogram has double-hump characteristics, need choose gray scale corresponding to two peak-to-peak paddy as threshold value;
Described optimal threshold adopts iterative Threshold selection method, and its step is as follows:
1. obtain maximum gradation value and the minimum gradation value of image, be designated as Z respectively
maxand Z
min, make threshold value be:
(8)
2. according to threshold value T0, image is divided into prospect and background, obtains both average gray value oZ and bZ respectively, obtaining new threshold value is:
(9)
If 3. two average gray values
with
no longer change or T no longer change, then T is threshold value; Otherwise go to step 2., iterative computation.
5. the image-recognizing method used in electric apparatus monitoring according to claim 1, is characterized in that: line by line scan to input picture in the fault zone of described equipment, if target is black, background is white; The point of connected region different in image is labeled as different pixel values, and records the area in this region simultaneously, described area and statistical pixel number, area obtained here comprises the element on border;
In the algorithm, need an interim stack and interim chained list, be used for preserving all elements of a certain connected region; Also need an array, record the area of different connected region; After all elements of image has traveled through, then the internal memory release shared by interim stack, interim chained list and array, to accelerate travelling speed; In addition, after mark connected region, according to the different pixels number in image, the number of the connected region comprised in this image can directly be obtained; After opening up interim memory field, target is marked, at this moment need to judge that whether connected region is too many, if too much, the threshold value preset need be increased; Judge that whether a region is the method for connected region and is exactly: if current pixel point is stain, when eight points are all stains around it, be then a connected region;
Calculate damaged condition:
Fault degree refers to that fault zone area accounts for the number percent of the target total area, that is:
（10）
Wherein Z is fault degree, and A is fault zone area, and S is the target total area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410580984.5A CN104408459A (en) | 2014-10-27 | 2014-10-27 | Image identification method applied to power equipment monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410580984.5A CN104408459A (en) | 2014-10-27 | 2014-10-27 | Image identification method applied to power equipment monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104408459A true CN104408459A (en) | 2015-03-11 |
Family
ID=52646090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410580984.5A Pending CN104408459A (en) | 2014-10-27 | 2014-10-27 | Image identification method applied to power equipment monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104408459A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881820A (en) * | 2015-06-08 | 2015-09-02 | 安徽中兴继远信息技术股份有限公司 | Electric power equipment external damage hidden danger troubleshooting system utilizing intelligent mobile phone and control method thereof |
| CN105631835A (en) * | 2016-02-23 | 2016-06-01 | 安徽创世科技有限公司 | Graying method for night weak light color image |
| CN106094827A (en) * | 2016-07-01 | 2016-11-09 | 蔡雄 | One can independent navigation power equipment cruiser |
| CN106680217A (en) * | 2016-12-21 | 2017-05-17 | 四川华雁信息产业股份有限公司 | Method and device for monitoring failure of transformer respirator |
| CN107103606A (en) * | 2017-02-27 | 2017-08-29 | 口碑控股有限公司 | A kind of image-recognizing method and device |
| CN107180242A (en) * | 2017-05-25 | 2017-09-19 | 上海地铁第运营有限公司 | Security against fire hidden danger image-recognizing method based on embedded system |
| CN107331096A (en) * | 2017-06-26 | 2017-11-07 | 国网山东省电力公司蓬莱市供电公司 | A kind of safety and protection system for electricity customer service center |
| CN107392889A (en) * | 2017-06-22 | 2017-11-24 | 国网山东省电力公司菏泽供电公司 | A kind of power equipment running state monitoring method and system based on infrared image |
| CN107392886A (en) * | 2017-06-14 | 2017-11-24 | 国网山东省电力公司菏泽供电公司 | A kind of power equipment image processing method |
| CN107610128A (en) * | 2017-09-26 | 2018-01-19 | 山东鲁能智能技术有限公司 | The method for inspecting and device of a kind of oil level indicator |
| CN107907217A (en) * | 2017-11-11 | 2018-04-13 | 成都市龙泉星源机械厂 | A kind of Novel welder transformer On-line Fault monitoring system and monitoring method |
| CN109066992A (en) * | 2018-09-07 | 2018-12-21 | 广东中粤电力科技有限公司 | A kind of monitoring method and system in intelligent power distribution room |
| CN109165233A (en) * | 2018-09-06 | 2019-01-08 | 江苏佳源科技有限公司 | A kind of intelligent low-pressure branch monitoring system |
| CN109309528A (en) * | 2017-07-27 | 2019-02-05 | 阿里巴巴集团控股有限公司 | State indication method, device and the optical module and test macro of optical module |
| CN109448009A (en) * | 2018-11-21 | 2019-03-08 | 国网江苏省电力有限公司扬州供电分公司 | Infrared Image Processing Method and device for transmission line faultlocating |
| CN109493292A (en) * | 2018-10-29 | 2019-03-19 | 平高集团有限公司 | Enhancing treating method and apparatus based on power equipment infrared measurement of temperature image |
| CN109782214A (en) * | 2019-01-26 | 2019-05-21 | 段俊杰 | Electric energy meter status remote transmitting mechanism |
| CN109816656A (en) * | 2019-02-01 | 2019-05-28 | 辽宁工程技术大学 | A kind of thermal power plant's negative pressure side system leak source accurate positioning method |
| CN110261703A (en) * | 2019-07-08 | 2019-09-20 | 厦门理工学院 | A kind of transformer fault method for early warning, terminal device and storage medium |
| CN111202547A (en) * | 2020-02-11 | 2020-05-29 | 新疆医科大学第三附属医院 | Multi-point biopsy sampling device for minimally invasive breast tumor surgery |
| CN111815545A (en) * | 2020-07-14 | 2020-10-23 | 南京信息工程大学 | Intelligent terminal-based color image rapid processing method |
| CN112085037A (en) * | 2020-09-21 | 2020-12-15 | 国网吉林省电力有限公司电力科学研究院 | Infrared thermal fault feature extraction and digital expression method for power transformation equipment |
| CN112560729A (en) * | 2020-12-22 | 2021-03-26 | 成都中科信息技术有限公司 | Vote processing method and system |
| CN112669287A (en) * | 2020-12-29 | 2021-04-16 | 重庆大学 | Electrical equipment temperature monitoring method based on image recognition |
| CN112819775A (en) * | 2021-01-28 | 2021-05-18 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and reinforcement method for damage detection image of aerospace composite material |
| CN113064373A (en) * | 2021-04-07 | 2021-07-02 | 四川中鼎智能技术有限公司 | Industrial hydroelectric equipment logic signal control method, system, terminal and storage medium based on video image recognition |
| CN113218986A (en) * | 2021-04-09 | 2021-08-06 | 河南五建建设集团有限公司 | System and method for detecting compactness after prestressed grouting construction |
| CN113688679A (en) * | 2021-07-22 | 2021-11-23 | 南京视察者智能科技有限公司 | Key personnel prevention, control and early warning method |
| CN114842002A (en) * | 2022-07-04 | 2022-08-02 | 山东华尚电气有限公司 | Method for detecting fault of oil-immersed transformer |
| CN116612121A (en) * | 2023-07-20 | 2023-08-18 | 济宁川昊电气科技有限公司 | Transformer fault rapid detection method based on artificial intelligence |
| CN117857822A (en) * | 2024-03-07 | 2024-04-09 | 石家庄学院 | Image communication control method for data service |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7283669B2 (en) * | 2003-01-29 | 2007-10-16 | Lockheed Martin Corporation | Fine segmentation refinement for an optical character recognition system |
| CN101739694A (en) * | 2010-01-07 | 2010-06-16 | 北京智安邦科技有限公司 | Image analysis-based method and device for ultrahigh detection of high voltage transmission line |
| CN101793501A (en) * | 2010-04-14 | 2010-08-04 | 华中科技大学 | Transmission line ice coating status detection method based on image |
| CN102252623A (en) * | 2011-06-24 | 2011-11-23 | 西安工程大学 | Measurement method for lead/ground wire icing thickness of transmission line based on video variation analysis |
| CN102663358A (en) * | 2012-03-29 | 2012-09-12 | 山西省电力公司晋中供电分公司 | Video image identification method of operating state of secondary protection equipment of substation |
-
2014
- 2014-10-27 CN CN201410580984.5A patent/CN104408459A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7283669B2 (en) * | 2003-01-29 | 2007-10-16 | Lockheed Martin Corporation | Fine segmentation refinement for an optical character recognition system |
| CN101739694A (en) * | 2010-01-07 | 2010-06-16 | 北京智安邦科技有限公司 | Image analysis-based method and device for ultrahigh detection of high voltage transmission line |
| CN101793501A (en) * | 2010-04-14 | 2010-08-04 | 华中科技大学 | Transmission line ice coating status detection method based on image |
| CN102252623A (en) * | 2011-06-24 | 2011-11-23 | 西安工程大学 | Measurement method for lead/ground wire icing thickness of transmission line based on video variation analysis |
| CN102663358A (en) * | 2012-03-29 | 2012-09-12 | 山西省电力公司晋中供电分公司 | Video image identification method of operating state of secondary protection equipment of substation |
Non-Patent Citations (1)
| Title |
|---|
| 杨淑莹: "《VC++图像处理程序设计》", 31 January 2005 * |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881820A (en) * | 2015-06-08 | 2015-09-02 | 安徽中兴继远信息技术股份有限公司 | Electric power equipment external damage hidden danger troubleshooting system utilizing intelligent mobile phone and control method thereof |
| CN105631835A (en) * | 2016-02-23 | 2016-06-01 | 安徽创世科技有限公司 | Graying method for night weak light color image |
| CN106094827A (en) * | 2016-07-01 | 2016-11-09 | 蔡雄 | One can independent navigation power equipment cruiser |
| CN106680217A (en) * | 2016-12-21 | 2017-05-17 | 四川华雁信息产业股份有限公司 | Method and device for monitoring failure of transformer respirator |
| CN106680217B (en) * | 2016-12-21 | 2019-09-06 | 四川华雁信息产业股份有限公司 | Transformer breather fault monitoring method and device |
| CN107103606A (en) * | 2017-02-27 | 2017-08-29 | 口碑控股有限公司 | A kind of image-recognizing method and device |
| CN107180242A (en) * | 2017-05-25 | 2017-09-19 | 上海地铁第运营有限公司 | Security against fire hidden danger image-recognizing method based on embedded system |
| CN107392886A (en) * | 2017-06-14 | 2017-11-24 | 国网山东省电力公司菏泽供电公司 | A kind of power equipment image processing method |
| CN107392889A (en) * | 2017-06-22 | 2017-11-24 | 国网山东省电力公司菏泽供电公司 | A kind of power equipment running state monitoring method and system based on infrared image |
| CN107331096A (en) * | 2017-06-26 | 2017-11-07 | 国网山东省电力公司蓬莱市供电公司 | A kind of safety and protection system for electricity customer service center |
| CN109309528A (en) * | 2017-07-27 | 2019-02-05 | 阿里巴巴集团控股有限公司 | State indication method, device and the optical module and test macro of optical module |
| CN107610128A (en) * | 2017-09-26 | 2018-01-19 | 山东鲁能智能技术有限公司 | The method for inspecting and device of a kind of oil level indicator |
| CN107907217A (en) * | 2017-11-11 | 2018-04-13 | 成都市龙泉星源机械厂 | A kind of Novel welder transformer On-line Fault monitoring system and monitoring method |
| CN109165233A (en) * | 2018-09-06 | 2019-01-08 | 江苏佳源科技有限公司 | A kind of intelligent low-pressure branch monitoring system |
| CN109165233B (en) * | 2018-09-06 | 2019-07-12 | 江苏佳源科技有限公司 | A kind of intelligent low-pressure branch monitoring system |
| CN109066992B (en) * | 2018-09-07 | 2022-02-18 | 广东中粤电力科技有限公司 | Monitoring method and system for intelligent power distribution room |
| CN109066992A (en) * | 2018-09-07 | 2018-12-21 | 广东中粤电力科技有限公司 | A kind of monitoring method and system in intelligent power distribution room |
| CN109493292A (en) * | 2018-10-29 | 2019-03-19 | 平高集团有限公司 | Enhancing treating method and apparatus based on power equipment infrared measurement of temperature image |
| CN109448009A (en) * | 2018-11-21 | 2019-03-08 | 国网江苏省电力有限公司扬州供电分公司 | Infrared Image Processing Method and device for transmission line faultlocating |
| CN109782214A (en) * | 2019-01-26 | 2019-05-21 | 段俊杰 | Electric energy meter status remote transmitting mechanism |
| CN109816656A (en) * | 2019-02-01 | 2019-05-28 | 辽宁工程技术大学 | A kind of thermal power plant's negative pressure side system leak source accurate positioning method |
| CN110261703A (en) * | 2019-07-08 | 2019-09-20 | 厦门理工学院 | A kind of transformer fault method for early warning, terminal device and storage medium |
| CN111202547A (en) * | 2020-02-11 | 2020-05-29 | 新疆医科大学第三附属医院 | Multi-point biopsy sampling device for minimally invasive breast tumor surgery |
| CN111815545A (en) * | 2020-07-14 | 2020-10-23 | 南京信息工程大学 | Intelligent terminal-based color image rapid processing method |
| CN112085037A (en) * | 2020-09-21 | 2020-12-15 | 国网吉林省电力有限公司电力科学研究院 | Infrared thermal fault feature extraction and digital expression method for power transformation equipment |
| CN112085037B (en) * | 2020-09-21 | 2024-04-09 | 国网吉林省电力有限公司电力科学研究院 | Infrared thermal fault feature extraction and digital expression method for power transformation equipment |
| CN112560729A (en) * | 2020-12-22 | 2021-03-26 | 成都中科信息技术有限公司 | Vote processing method and system |
| CN112560729B (en) * | 2020-12-22 | 2023-12-26 | 成都中科信息技术有限公司 | Vote processing method and system |
| CN112669287A (en) * | 2020-12-29 | 2021-04-16 | 重庆大学 | Electrical equipment temperature monitoring method based on image recognition |
| CN112669287B (en) * | 2020-12-29 | 2024-04-23 | 重庆大学 | Electrical equipment temperature monitoring method based on image recognition |
| CN112819775A (en) * | 2021-01-28 | 2021-05-18 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and reinforcement method for damage detection image of aerospace composite material |
| CN112819775B (en) * | 2021-01-28 | 2022-07-19 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and reinforcement method for damage detection image of aerospace composite material |
| CN113064373A (en) * | 2021-04-07 | 2021-07-02 | 四川中鼎智能技术有限公司 | Industrial hydroelectric equipment logic signal control method, system, terminal and storage medium based on video image recognition |
| CN113064373B (en) * | 2021-04-07 | 2022-04-15 | 四川中鼎智能技术有限公司 | Industrial hydroelectric equipment logic signal control method, system, terminal and storage medium based on video image recognition |
| CN113218986A (en) * | 2021-04-09 | 2021-08-06 | 河南五建建设集团有限公司 | System and method for detecting compactness after prestressed grouting construction |
| CN113688679B (en) * | 2021-07-22 | 2024-03-08 | 南京视察者智能科技有限公司 | Method for preventing and controlling early warning of key personnel |
| CN113688679A (en) * | 2021-07-22 | 2021-11-23 | 南京视察者智能科技有限公司 | Key personnel prevention, control and early warning method |
| CN114842002B (en) * | 2022-07-04 | 2022-09-09 | 山东华尚电气有限公司 | Method for detecting fault of oil-immersed transformer |
| CN114842002A (en) * | 2022-07-04 | 2022-08-02 | 山东华尚电气有限公司 | Method for detecting fault of oil-immersed transformer |
| CN116612121A (en) * | 2023-07-20 | 2023-08-18 | 济宁川昊电气科技有限公司 | Transformer fault rapid detection method based on artificial intelligence |
| CN116612121B (en) * | 2023-07-20 | 2023-10-27 | 济宁川昊电气科技有限公司 | Transformer fault rapid detection method based on artificial intelligence |
| CN117857822A (en) * | 2024-03-07 | 2024-04-09 | 石家庄学院 | Image communication control method for data service |
| CN117857822B (en) * | 2024-03-07 | 2024-04-30 | 石家庄学院 | Image communication control method for data service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104408459A (en) | Image identification method applied to power equipment monitoring | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN103412246B (en) | Based on the Automatic detection method of abnormal discharge of power equipment of ultraviolet video | |
| CN101625723B (en) | Rapid image-recognizing method of power line profile | |
| CN105868722A (en) | Identification method and system of abnormal power equipment images | |
| CN104331521B (en) | Transformer anomaly identification method based on image procossing | |
| CN202085261U (en) | Intelligent video diagnosing and monitoring system | |
| CN102927448B (en) | Pipeline non-destructive testing method | |
| CN103196380B (en) | Transmission line of electricity image collecting device and electric power line ice-covering thickness detection system | |
| CN103067740B (en) | Video monitoring equipment intelligent fault detection method and detection system thereof | |
| CN107392889A (en) | A kind of power equipment running state monitoring method and system based on infrared image | |
| CN105447471A (en) | Infrared detection based device gas leakage identification method and apparatus | |
| CN103954897A (en) | Intelligent power grid high voltage insulation damage monitoring system and method based on ultraviolet imagery | |
| CN105957088B (en) | Transformer composite insulator casing monitoring method and system based on computer vision | |
| CN106680285A (en) | Infrared image-assisted method of recognizing contamination condition of insulator by visible light image | |
| CN107563263A (en) | Video image identification method and system based on instrument | |
| CN104346626A (en) | SF6 gas leakage online mode recognition method based on image recognition | |
| CN102831393A (en) | Rapid image recognizing method of power tower pole outline | |
| CN109345586A (en) | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology | |
| He et al. | Detection and fault diagnosis of power transmission line in infrared image | |
| CN113536440B (en) | Data processing method based on BIM operation and maintenance management system | |
| CN112257632A (en) | Transformer substation monitoring system based on edge calculation | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
| CN116388379A (en) | Remote infrared intelligent inspection method and system for transformer substation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150311 |