CN105825619B - A kind of high-voltage line floating material alarm method based on image procossing - Google Patents
A kind of high-voltage line floating material alarm method based on image procossing Download PDFInfo
- Publication number
- CN105825619B CN105825619B CN201610174707.3A CN201610174707A CN105825619B CN 105825619 B CN105825619 B CN 105825619B CN 201610174707 A CN201610174707 A CN 201610174707A CN 105825619 B CN105825619 B CN 105825619B
- Authority
- CN
- China
- Prior art keywords
- voltage line
- floating material
- image
- floating
- warning message
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
Abstract
The present invention relates to digital image processing fields, are related specifically to a kind of high-voltage line floating material alarm method based on image procossing.A kind of high-voltage line floating material alarm method based on image procossing includes the following steps, image obtains, high-voltage line detection, floating analyte detection and warning message automatically generate.High-voltage line floating material alarm method provided by the invention based on image procossing, the floating material near high-voltage line and high-voltage line can be accurately identified by intelligent camera of the frame on steel tower, and warning message can be automatically pushed to main website, meet requirement of the Utilities Electric Co. in external force damage prevention system engineering application aspect.
Description
Technical field
The present invention relates to digital image processing fields, are related specifically to a kind of high-voltage line floating material based on image procossing
Alarm method, and applied in embedded engineering product.
Background technology
With the development of science and technology, digital image processing techniques have penetrated into each side of social production and life
Face appears in workshop, instead of many especially in terms of industrial production by the product of representative of industrial intelligent video camera
Manual labor, reduces the human cost of enterprise, while also improving working efficiency.
And wherein, floating material automatic alarm is the active demand that each Utilities Electric Co. faces on realization high-voltage line.Currently, big portion
Caused by dividing High Voltage Electricity Transfer Circuit failure to be all external force destruction, and the external fault caused by drift, proportion are reaching 30%
Left and right.Since Utilities Electric Co. also rests on the floating material occurred on high-voltage line the stage of manual inspection, this not still one it is numerous
Trivial work, and situations such as there is also missing inspection, flase drop, processing is easy to happen the loss of power accident not in time, is affected.
Invention content
In order to solve problem above, the present invention provides a kind of high-voltage line floating material alarm method based on image procossing,
Include mainly the following steps：
Step 1: image obtains, video camera of the fixed placement on steel tower is initialized, a width is obtained and does not float
The high-tension line graph picture of object remembers I as Background1, it then proceedes to take out image to be detected from the video flowing of intelligent camera,
It is denoted as I2；
Step 2: high-voltage line detects, from I1Gray level image progress is converted thereof into after middle acquisition high-voltage line area image
Processing, then does edge detection to it, obtains high-voltage line edge image；
Step 3: floating analyte detection, the detection of high-voltage line floating material is realized by frame difference method, first, by I1And I2It cuts
To the two images of same area, frame difference operation then is done to this two images and is taken absolute value, obtained a width frame difference figure, pass through frame
Poor figure is to judge the appearance on high-voltage line whether there is or not floating material, then starts to frame difference figure progress gray processing, binaryzation and morphology
Calculation process obtains the image of only 0 and 1 expression, and 0 indicates the background of image, and floating material is meant that if there is floating material, 1；
Step 4: warning message automatically generates, first, it may determine that whether there is or not floating materials on high-voltage line by step 3, if
There is no floating material, then need not send warning message；If there is floating material, then can further determine that according to the following steps is
It is no to send warning message：（1）The center of gravity for calculating floating material in step 3, is denoted as（x0,y0）, then calculate the weight of next frame floating material
The heart（x1,y1）, and compare with（x0,y0）The distance between, if in the horizontal direction or vertical direction be less than some distance threshold
（Dis_thresh）, then it is assumed that it is continuous floating material；Otherwise it is assumed that being that floating material is hovered, such case is not alarmed；（2）Meter
It calculates（x0,y0）The distance of all high-voltage lines generated to step 2, is denoted as D (i), i=1,2 ... ..., N；N is the number of high-voltage line；
（3）D (i) is found out, the minimum value of i=1,2 ... ..., N are denoted as D_min；（4）If D_min is less than given distance threshold, that
It meets first condition of alarm；（5）If（4）State be continued for be more than time threshold（Time_thresh）, that
It meets second condition of alarm；（6）If two conditions all meet, warning message is sent, while updating background image
I1；Otherwise, every time threshold（Time_thresh）Update background image I1。
High-voltage line floating material alarm method provided by the invention based on image procossing, is taken the photograph by intelligence of the frame on steel tower
Camera can accurately identify the floating material near high-voltage line and high-voltage line, and can automatically push warning message to master
It stands, meets requirement of the Utilities Electric Co. in external force damage prevention system engineering application aspect.
Description of the drawings
Fig. 1 is the overview flow chart of the present invention.
Fig. 2 is the video flowing original graph of the present invention.
Fig. 3 is the high-voltage line detection figure of the present invention.
Fig. 4 is the background original graph of the present invention.
Fig. 5 is the floating material original graph of the present invention.
Fig. 6 is the floating analyte detection figure of the present invention.
Specific implementation mode
In order to be best understood from the implementation process of the present invention, the present invention is carried out below in conjunction with attached drawing and embodiment detailed
Description.
Fig. 1 is the overview flow chart of the present invention, and Fig. 2 is the original image obtained on some steel tower on high-voltage line, from Fig. 1
In it can be seen that the present invention has 4 main implementation steps, i.e., image obtain, high-voltage line detection, floating analyte detection and alarm
It automatically generates, the specific implementation mode of each section is as follows：
Step 1: image obtains
First, the video camera to fixed placement on steel tower initializes, and obtaining a width does not have the high-voltage line of floating material
Image remembers I as Background1, it will constantly be updated according to subsequent alarm condition, be conducive to grasp site environment
Actual conditions；It then proceedes to take out image to be detected from the video flowing of intelligent camera, is denoted as I2, for detecting high-voltage line
It is upper to whether there is floating material.
Step 2: high-voltage line detects
From I1Gray level image is converted thereof into after middle acquisition high-voltage line area image to be handled, and canny is then selected
Edge detection operator does edge detection to it, obtains high-voltage line edge image I3, each height can be significantly seen in I3
The edge feature situation of crimping, clearer lines in order to obtain, by I3Mathematical mor-phology closed operation processing is carried out, in the present invention
In, closed operation uses the oval structure element of 20*20, the image I obtained in this way4In unidirectional high-voltage line reform into one
Line, then by I4The high-tension line graph of single pixel is just obtained by micronization processes as I5, finally, by I5It is examined into line with Hough transformation
It surveys, testing result is exactly that the present invention needs obtained high-voltage line, as shown in Figure 3.
Step 3: floating analyte detection
In view of state of the floating material on high-voltage line may be movement or static, therefore will to pass through frame difference method real by the present invention
The detection of existing high-voltage line floating material, first, by I1And I2Cutting obtains the two images of same area, as shown in Figures 4 and 5, then
Frame difference operation is done to this two images to take absolute value, and obtains a width frame difference image I6, I can be passed through in this way6To judge on high-voltage line
Whether there is or not the appearance of floating material；Again to I6Gray processing and binary conversion treatment are carried out, binary image I is obtained7, since frame difference method is to light
The variation of line is more sensitive, obtained image I7Many unrelated information are will produce, so in order to eliminate these interference informations, are needed
It will be to I7Morphology opening operation processing is carried out again, and in the present invention, opening operation uses the rectangular configuration element of 3*3；Finally again to I7
Largest connected domain is extracted, the image I of only 0 and 1 expression is obtained8, as shown in fig. 6,0 indicates the background of image, if there is drift
Float, then 1 means that floating material.
In the present invention, it is provided with the threshold value for indicating floating material area, the number of pixels of white area in first statistical chart 6,
It is denoted as Num, the threshold value of minimum floating material area is denoted as Area_thresh1, the threshold value of maximum floating material area is denoted as
Area_thresh2, if Num<Area_thresh1 or Num>Area_thresh2, then Fig. 6 is set to 0, this example
In, the image Area_thresh1 for acquiring 720P takes 100 and Area_thresh2 takes 10000, can be controlled by this threshold value
The size of floating material area on high-voltage line processed does not consider the too small or too big floating material present invention.
Step 4: alarm automatically generates
First, it may determine that whether there is or not floating materials on high-voltage line by step 3, if without floating material, need not send
Warning message；If there is floating material, then warning message to be sent can be further determined whether according to the following steps.
（1）The center of gravity for calculating floating material in step 3, is denoted as（x0,y0）, then calculate the center of gravity of next frame floating material（x1,
y1）, and compare with（x0,y0）The distance between, if in the horizontal direction or vertical direction be less than some distance threshold（Dis_
thresh）, then it is assumed that it is continuous floating material；Otherwise it is assumed that being that floating material is hovered, such case is not alarmed；
（2）It calculates（x0,y0）The distance of all high-voltage lines generated to step 2, is denoted as D (i), i=1,2 ... ..., N；N is
The number of high-voltage line；
（3）D (i) is found out, the minimum value of i=1,2 ... ..., N are denoted as D_min；
（4）If D_min is less than given distance threshold, meet first condition of alarm；
（5）If（4）State be continued for be more than time threshold（Time_thresh）, then it meets the of alarm
Two conditions；
（6）If two conditions all meet, i.e., transmittable warning message, while updating background image I1；Otherwise, often
Every time threshold（Time_thresh）Update background image I1。
The invention discloses a kind of high-voltage line floating material alarm method based on image procossing, the technology can be examined accurately
The floating material near high-voltage line and high-voltage line is measured, and can automatically push warning message to main website, meets Utilities Electric Co.
In the requirement of external force damage prevention system engineering application aspect, the inconvenience and mode of taking photo by plane that previous manual inspection mode is brought are overcome
The high efficiency at low cost brought.
Claims (2)
1. a kind of high-voltage line floating material alarm method based on image procossing, includes the following steps：Step 1: image obtains, it is right
Video camera of the fixed placement on steel tower is initialized, and obtaining a width does not have the high-tension line graph picture of floating material, as Background,
Remember I1, then proceed to take out image to be detected from the video flowing of intelligent camera, be denoted as I2；Step 2：High-voltage line detects, from
I1Gray level image is converted thereof into after middle acquisition high-voltage line area image to be handled, and edge detection then is done to it, is obtained
High-voltage line edge image；Step 3: floating analyte detection, the detection of high-voltage line floating material is realized by frame difference method, first, by I1With
I2Cutting obtains the two images of same area, and then doing frame difference operation to this two images takes absolute value, and it is poor to obtain a width frame
Figure by frame difference figure to judge the appearance on high-voltage line whether there is or not floating material, then carries out gray processing, binaryzation and shape to frame difference figure
The processing of state opening operation obtains the image of only 0 and 1 expression, and 0 indicates the background of image, is meant that if there is floating material, 1
Floating material；Step 4: warning message automatically generates, first, it may determine that whether there is or not floating materials on high-voltage line by step 3, if
There is no floating material, then need not send warning message；If there is floating material, then can further determine that according to the following steps is
It is no to send warning message：（1）The center of gravity for calculating floating material in step 3, is denoted as（x0,y0）, then calculate next frame floating material
Center of gravity（x1,y1）, and compare with（x0,y0）The distance between, if in the horizontal direction or vertical direction be less than some distance threshold
（Dis_thresh）, then it is assumed that it is continuous floating material；Otherwise it is assumed that being that floating material is hovered, such case is not alarmed；（2）Meter
It calculates（x0,y0）The distance of all high-voltage lines generated to step 2, is denoted as D (i), i=1,2 ... ..., N；N is the number of high-voltage line；
（3）The minimum value of D (i) is found out, i=1,2 ... ..., N are denoted as D_min；（4）If D_min is less than given distance threshold, that
It meets first condition of alarm；（5）If（4）State be continued for be more than time threshold（Time_thresh）, that
It meets second condition of alarm；（6）If two conditions all meet, warning message is sent, while updating background image
I1；Otherwise, every time threshold（Time_thresh）Update background image I1。
2. the high-voltage line floating material alarm method based on image procossing as described in claim 1, it is characterised in that：In step 2
In, the high-voltage line edge image is subjected to mathematical mor-phology closed operation processing, then the high pressure of single pixel is obtained by refinement
The result Hough transformation of refinement is finally detected into line, obtains testing result by line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610174707.3A CN105825619B (en) | 2016-03-25 | 2016-03-25 | A kind of high-voltage line floating material alarm method based on image procossing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610174707.3A CN105825619B (en) | 2016-03-25 | 2016-03-25 | A kind of high-voltage line floating material alarm method based on image procossing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105825619A CN105825619A (en) | 2016-08-03 |
| CN105825619B true CN105825619B (en) | 2018-09-18 |
Family
ID=56524591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610174707.3A Active CN105825619B (en) | 2016-03-25 | 2016-03-25 | A kind of high-voltage line floating material alarm method based on image procossing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105825619B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113175955A (en) * | 2021-04-30 | 2021-07-27 | 广东电网有限责任公司 | System and method for detecting floaters in power system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NZ264972A (en) * | 1994-11-22 | 1997-03-24 | Dulmison Nz Ltd | Shield for electrical power line insulator and emergent lines |
| US7512258B2 (en) * | 2005-07-19 | 2009-03-31 | The Boeing Company | System and method for passive wire detection |
| CN104282011B (en) * | 2013-07-04 | 2018-05-25 | 浙江大华技术股份有限公司 | The method and device of interference stripes in a kind of detection video image |
| CN104590319B (en) * | 2014-06-11 | 2016-07-06 | 北京交通大学 | Foreign body invades detecting device and foreign body invades detection method |
| CN104021576A (en) * | 2014-06-18 | 2014-09-03 | 国家电网公司 | Method and system for tracking moving objects in scene |
| CN104463904A (en) * | 2014-09-22 | 2015-03-25 | 国家电网公司 | High-voltage line foreign matter invasion target detection method |
| CN105160363A (en) * | 2015-07-10 | 2015-12-16 | 国家电网公司 | Power transmission and distribution line channel color steel tile floater intelligent video identification method |
| CN105069397A (en) * | 2015-07-10 | 2015-11-18 | 国家电网公司 | Intelligent video identification method for out-of-control kite on power transmission and distribution line channel |
-
2016
- 2016-03-25 CN CN201610174707.3A patent/CN105825619B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105825619A (en) | 2016-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110642109B (en) | Vibration detection method and device for lifting equipment, server and storage medium | |
| CN104966304B (en) | Multi-target detection tracking based on Kalman filtering and nonparametric background model | |
| US9053385B2 (en) | Object detection device and object detection method | |
| EP2874100B1 (en) | Slow change detection system | |
| CN104573702A (en) | Method for automatically identifying sulfur hexafluoride pressure instrument image | |
| CN111008587A (en) | Intelligent visual recognition system based on deep learning and applied to robot | |
| CN104282011A (en) | Method and device for detecting interference stripes in video images | |
| CN116189103B (en) | Equipment monitoring automatic control method and control system based on visual image analysis | |
| CN112634254A (en) | Insulator defect detection method and related device | |
| CN107818563A (en) | A kind of transmission line of electricity bundle spacing space measurement and localization method | |
| CN117274722A (en) | Intelligent detection method for distribution box based on infrared image | |
| CN105825619B (en) | A kind of high-voltage line floating material alarm method based on image procossing | |
| CN108664886A (en) | A kind of fast face recognition method adapting to substation's disengaging monitoring demand | |
| CN112634179B (en) | Camera shake prevention power transformation equipment image change detection method and system | |
| CN107036545A (en) | A kind of dam body monitoring and pre-alarming method and device | |
| JP5792671B2 (en) | Abnormality detection method and abnormality detection device | |
| CN108573233B (en) | Power grid ceramic insulator identification method based on image processing technology | |
| CN107632126A (en) | A kind of Wastewater Sample monitoring system based on big data | |
| CN103326267A (en) | Routine inspection method and system of transformer substation | |
| CN107862245A (en) | A kind of method for monitoring abnormality of client power distribution room | |
| CN113920535A (en) | Electronic region detection method based on YOLOv5 | |
| CN113449599A (en) | Intelligent operation and maintenance auxiliary device of indoor substation based on image recognition technology | |
| CN111695492A (en) | Method and system for detecting fishing hidden danger of power transmission line | |
| CN113657165A (en) | Dangerous climbing behavior recognition algorithm in electric power field operation | |
| Pan | Intelligent image recognition research on status of power transmission lines |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |