CN107918941B - Visual monitoring system and method for power transmission channel external damage protection - Google Patents
Visual monitoring system and method for power transmission channel external damage protection Download PDFInfo
- Publication number
- CN107918941B CN107918941B CN201711057539.0A CN201711057539A CN107918941B CN 107918941 B CN107918941 B CN 107918941B CN 201711057539 A CN201711057539 A CN 201711057539A CN 107918941 B CN107918941 B CN 107918941B
- Authority
- CN
- China
- Prior art keywords
- image
- module
- haar
- power transmission
- main control
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 230000005540 biological transmission Effects 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000000007 visual effect Effects 0.000 title claims abstract description 20
- 238000004891 communication Methods 0.000 claims abstract description 26
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 18
- 229910052742 iron Inorganic materials 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 238000012800 visualization Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 4
- 238000009529 body temperature measurement Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 239000003990 capacitor Substances 0.000 claims description 2
- 238000012806 monitoring device Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a visual monitoring system and a method for the outer damage protection of a power transmission channel, wherein the system comprises a plurality of monitoring modules and a control center, the monitoring modules comprise a power module, an acousto-optic alarm module, an image monitoring module, a main control system and a communication module, and the image monitoring module detects images of line channels on two sides of an iron tower and transmits the images to the main control system; the main control system adopts an image matching method based on a Haar feature density map to detect hidden dangers, and informs an acousto-optic alarm module to give an alarm when the hidden dangers are detected; the invention adopts Haar characteristic density graph filtering, can effectively remove discrete pixel points which are failed to be matched and caused by micro disturbance, ensures that a large connected domain is not lost, and can well keep the discrete points inside and around the large connected domain to be matched with the pixel image.
Description
Technical Field
The invention relates to a visual monitoring system and method for power transmission channel external damage protection.
Background
With the development of national economy, the demand of various industries on electric power is continuously expanded, and the loss caused by power failure caused by various human and natural accidents is more and more large. How to find, process and prevent natural disasters and accidents damaging the power transmission line in advance and ensure normal power supply all the time becomes the focus of attention of people.
At present, in many places of China, an image/video monitoring device is mounted on a tower of each high-voltage transmission line to monitor the line channel environment, so that the traditional manual line patrol is replaced. The original image/video monitoring has short service life, low reliability and unintelligent hidden danger detection. The on-site image/video monitoring device transmits the shot video back to the server, and then hidden dangers are eliminated through manual observation, so that the workload is very large, the subjectivity is strong, and the efficiency is low.
With the development of intelligent information processing technology, people begin to explore methods for security detection by using image matching technology, and certain progress is made. However, because the power transmission lines or the channels are mostly arranged in a complex field scene, and the meteorological conditions are not good, the tower itself can shake to a certain extent, especially for a large iron tower with a high voltage level, the shaking range is larger, the target in the background can shake or wave, the weather, the cloud, the illumination and the like can influence the photo shooting effect, the affected image is obtained, and the protection effect on the external damage of the power transmission channel is not good.
Disclosure of Invention
The invention aims to solve the problems and provides a visual monitoring system and a visual monitoring method for the outer broken protection of a power transmission channel.
In order to achieve the purpose, the invention adopts the following technical scheme:
the utility model provides a visual monitoring system for outer broken protection of transmission channel, includes a plurality of monitoring module and control center, monitoring module all includes power module, reputation warning module, image monitoring module, main control system and communication module, wherein:
the power supply module provides electric energy for the integral monitoring module;
the image monitoring module is configured to be arranged on an iron tower of each power transmission line, detect images of line channels on two sides of the iron tower and transmit the images to the main control system;
the main control system is configured to control the acquisition control of the image detection module, detect hidden danger by adopting an image matching method based on a Haar feature density map, and inform the acousto-optic alarm module to alarm when the hidden danger is detected;
the communication module is configured to provide a communication channel for the main control system and the control center, and transmit and feed back the hidden danger information.
Further, power module includes power supply module and power storage module, the power supply module adopts solar cell panel to carry out the electric energy collection, links to each other with main control system, and power storage module includes battery and super capacitor, stores the electric energy that the module was gathered with the power supply, links to each other with main control system.
Furthermore, the acousto-optic warning module comprises a tweeter and a light flashing device.
Furthermore, the monitoring module also comprises a temperature measuring module, the communication mode between the monitoring module and the master control system is a wireless communication mode, and the temperature of the electric transmission line lead, the strain clamp and/or the drainage plate is measured.
Furthermore, the image monitoring module adopts a photographing lens with physical pixels larger than 500 ten thousand pixels, comprises two lenses, respectively monitors line channels on two sides of the iron tower, and is connected with the main control system.
Further, the main control system comprises a control unit and a data preprocessing unit, wherein the control unit is configured to perform photographing control, communication module, temperature measurement control, video control, power control and acousto-optic alarm control; the data preprocessing unit is configured to perform hidden danger detection by adopting an image matching method based on a Haar feature density map.
Furthermore, the communication module is connected with the main control system and comprises a data encryption module and a wireless communication module, and the data encryption module adopts an MD5 algorithm to encrypt data; the wireless communication module adopts a mode of a communication operator Internet of things card and a VPN channel to carry out data transmission.
Furthermore, the control center comprises a background master station system, receives and displays the data of the monitoring modules, and realizes the visualization of the distribution, the visualization of the line channel and the alarm query of each monitoring module.
The image matching method based on the system comprises the following steps:
(1) converting the image to be matched and the reference image into a plurality of color spaces to obtain corresponding differential images;
(2) carrying out weighted fusion on the obtained difference images, and separating each channel in each color space;
(3) carrying out binarization processing on the image;
(4) calculating Haar characteristics of the difference image after binarization to obtain a corresponding Haar characteristic density graph;
(5) and filtering the binarized image based on the Haar feature density graph to obtain a final matching result.
In the step (1), the image to be matched and the reference image are converted into four color spaces of RGB, HSV, YUV and Lab, and differential images are respectively obtained in the four color spaces.
In the step (2), the difference images of the channels except the difference image of the hue channel are weighted and fused.
Further, separating the channels, and performing weighted fusion on the remaining 11 channel difference images except the difference image of the H channel, wherein the fusion process is as follows:
wherein, Il(x, y) represents coordinates in the differential image of the l-th channelPixel values of image I at (x, y); f (x, y) represents a pixel value of the fused image F at the coordinates (x, y); n represents the number of images needing to be fused; k is a radical ofiSize of the dimension Window, αiThe weight of the scale is expressed, N is 11.
Further, in the step (3), the binarization processing includes:
(3-1) counting the number of pixels of each gray level in the image, and carrying out normalization processing on the number of pixels;
(3-2) determining an optimal threshold value of binarization according to the statistical pixel quantity normalization result;
and (3-3) carrying out gray level binarization processing on the image according to the determined optimal threshold value.
In the step (3-2), according to the normalization result of the number of pixels of the gray level, the background probability and the foreground probability and the corresponding gray mean value at each threshold are determined, the background and foreground variances, the between-class variance and the within-class variance are obtained, and the threshold with the largest between-class variance and the smallest within-class variance is determined as the optimal threshold.
In the step (4), for the binary image, the gray difference feature of the Haar feature is regarded as binary jump between pixels.
In the step (4), the Haar feature templates are as follows:
gcrepresenting a pixel with a grey value of 255, gpIs gcEight neighborhoods of; gpValue of (a) and gcPoint g, when not identicalcPlus one.
In the step (4), the specific process of obtaining the Haar feature density map of the image comprises the following steps:
(4-1) constructing a two-dimensional image H with the same size as the fused differential image, and assigning all pixel values in the image to be 0;
and (4-2) taking the Haar feature number of the pixels in the differential image after binarization as the gray value of the pixels at the corresponding position in the image H, wherein the image H is the Haar feature density map of the differential image.
In the step (5), the filtering process includes:
(5-1) counting the number of effective pixels and the number of Haar features in a window with the width L by taking a pixel P as a center;
(5-2) taking the ratio of the number of Haar features to the number of effective pixels in the window as the Haar feature frequency of the pixel P.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention adopts Haar characteristic density graph filtering, can effectively remove discrete pixel points which are failed to be matched and caused by micro disturbance, can well keep the discrete points inside and around the large connected domain and can be matched with pixel images while ensuring no loss of the large connected domain;
(2) the invention has good description capacity for the discrete and dense degrees of the pixels by utilizing the Haar characteristic density graph, so that the Haar characteristic density graph can be utilized to filter the image to filter discrete noise points, and the super-pixel-level matching of local fine non-rigid change areas in the pixel-level matching result is realized.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of an efficient algorithm of the present invention;
FIG. 2 is a difference image and Haar feature density map after binarization;
FIG. 3 shows the filtering results obtained by different methods;
fig. 4 is a visual monitoring device for protection against external damage to a power transmission channel.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present invention, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only terms of relationships determined for convenience of describing structural relationships of the parts or elements of the present invention, and are not intended to refer to any parts or elements of the present invention, and are not to be construed as limiting the present invention.
In the present invention, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be determined according to specific situations by persons skilled in the relevant scientific or technical field, and are not to be construed as limiting the present invention.
As introduced in the background art, the prior art has the disadvantages of short service life, low reliability and unintelligent hidden danger detection due to the existence of original image/video monitoring. The on-site image/video monitoring device transmits shot videos back to the server, hidden dangers are eliminated through manual observation, the workload is very large, the subjectivity is strong, the efficiency is low, and in order to solve the technical problems, the visual monitoring device and the data processing method for the outer damage protection of the power transmission channel are provided.
In an exemplary embodiment of the present application, as shown in fig. 4, the following aspects are mainly included:
1. installing a power supply module, a power storage module, an acousto-optic alarm module, a temperature measurement module, an image monitoring module, a main control system and a communication module on a power transmission line iron tower;
2. deploying the power transmission line visualization system on a server;
3. opening a VPN channel, and communicating an Internet of things card installed on a debugging device with data of a power transmission line visualization system;
4. setting device acquisition parameters, which mainly comprise an acquisition time period, an acquisition cycle, a line name, a pole tower name, a card number, an installation date, attention hidden danger types and the like;
5. the device starts a photographing function, and the photo is transmitted to the power transmission line visualization system through the data preprocessing unit and the VPN channel.
6. The data preprocessing unit carries out hidden danger detection on the channel image by adopting an image matching method based on a Haar feature density graph, and when hidden danger information exists in the image, the device sends alarm information to a power transmission line visualization system, otherwise normal information is transmitted.
As shown in FIG. 1, the image matching method based on the Haar feature density map comprises the following steps:
step 1: calculating a difference image of the image to be matched and the reference image;
the first step is as follows: converting the image to be matched and the reference image into four color spaces of RGB, HSV, YUV and Lab, and obtaining a differential image in the four color spaces;
the second step is that: separating channels, and performing weighted fusion on the rest 11 channel differential images except the differential image of the H channel, wherein the fusion process is as follows:
wherein, Il(x, y) represents the pixel value of image I at coordinate (x, y) in the differential image of the l-th channel; f (x, y) represents the pixel value of the fused image F at the coordinates (x, y)(ii) a N represents the number of images needing to be fused; k is a radical ofiSize of the dimension Window, αiThe weight of the scale is expressed, and in this patent, N is 11, k is {1,2,3}, and α is {0.1,0.2,0.7 }.
Step 2: binaryzation;
the first step is as follows: counting the number of pixels with a gray level i in the image, which is recorded as niFor computational convenience, the normalization process is as follows:
wherein M represents the gray level of the image, such as 256 for 8-bit single-channel image gray level M;
the second step is that: calculating a binarization threshold value t (t is more than or equal to 1 and less than or equal to M):
w0representing the background probability with threshold t, w1Is the foreground probability;
μ0(t) represents the threshold and the background mean value of the gray level at t, μ1(t) is the gray level mean of the foreground;
w 2＝w0 0 2+w1 1 2
B 2＝w0*(u0(t)-u)2+w1*(u1(t)-u)2
wherein0 2Which represents the variance of the background,1 2which represents the variance of the foreground and the variance of the foreground,B 2the inter-class variance is represented as,W 2representing the intra-class variance, and u representing the overall mean of the image; make itB 2At the maximum, the number of the first,W 2the minimum threshold value t is the optimal threshold value;
the third step: and after the optimal threshold t is obtained through calculation, binarization is carried out according to the optimal threshold t, the gray value larger than t is set to be 1, the gray value smaller than t is set to be 0, and image binarization is completed.
And step 3: calculating Haar characteristics of the difference image after binarization;
the Haar characteristic is a description method of gray difference characteristics of a rectangular region in an image, and for a binary image, the gray difference characteristics can be regarded as binary jump among pixels; haar feature templates are as follows:
gcrepresenting a pixel with a grey value of 255, gpIs gcEight neighborhoods of; gpValue of (a) and gcPoint g, when not identicalcPlus one.
And 4, step 4: obtaining a Haar characteristic density graph of the image;
the first step is as follows: constructing a two-dimensional image H with the same size as the fused differential image, and assigning all pixel values in the image as 0;
the second step is that: and taking the Haar feature number of the pixels in the difference image after binarization as the gray value of the pixels at the corresponding position in the image H, wherein the image H is the Haar feature density map of the difference image.
And 5: filtering the image based on the Haar feature density graph;
the first step is as follows: counting the number N of effective pixels and the number M of Haar features in a window with the width of L by taking a pixel P as a center;
the second step is that: and calculating Q-M/N (when N is not equal to 0) as the Haar characteristic frequency of P. The calculation process is as follows:
q is a Haar characteristic frequency number graph of B obtained through calculation, and the value range of pixel values in Q is [0,8 ]. And B is a binary image to be filtered, the value of the pixel value of the binary image is {0,1}, 0 represents a black pixel, and 1 represents a white pixel (effective pixel). H is a Haar feature density map of B. l is the size of the filter window, and is 25 in this patent.
7. The communication module is connected with the main control system and comprises a data encryption module and a wireless communication module. The data encryption module encrypts data by adopting an MD5 algorithm; the wireless communication module transmits data in a mode of a communication operator Internet of things card and a VPN channel;
8. the power transmission line visualization system is a background master station system, receives and displays data of the front-end device, and comprises device distribution visualization, line channel visualization, device management and alarm query.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (11)
1. A visual monitoring system for outer broken protection of transmission channel, characterized by: including a plurality of monitoring module and control center, monitoring module all includes power module, reputation warning module, image monitoring module, main control system and communication module, wherein:
the power supply module provides electric energy for the integral monitoring module; the image monitoring module is configured to be arranged on an iron tower of each power transmission line, detect images of line channels on two sides of the iron tower and transmit the images to the main control system;
the main control system is configured to control the acquisition control of the image detection module, perform hidden danger detection by adopting an image matching method based on a Haar feature density map, and perform binarization processing on the image: counting the number of pixels of each gray level in the image, and carrying out normalization processing on the pixels; determining a binaryzation optimal threshold value according to the statistical pixel quantity normalization result; according to the normalization result of the number of pixels of the gray level, determining the background probability and the foreground probability and the corresponding gray mean value when each threshold value is used, solving the background and foreground variances, the between-class variance and the within-class variance, and determining the threshold value when the between-class variance is maximum and the within-class variance is minimum as the optimal threshold value; performing gray level binarization processing on the image according to the determined optimal threshold value; when the existence of hidden danger is detected, the acousto-optic alarm module is informed to alarm;
the image matching method based on the Haar feature density graph comprises the following steps:
(1) converting the image to be matched and the reference image into a plurality of color spaces to obtain corresponding differential images; (2) carrying out weighted fusion on the obtained difference images, and separating each channel in each color space; (3) carrying out binarization processing on the image; (4) calculating Haar characteristics of the difference image after binarization by using a Haar characteristic template to obtain a corresponding Haar characteristic density map; haar feature templates are as follows:
gcrepresenting a pixel with a grey value of 255, gpIs gcEight neighborhoods of; gpValue of (a) and gcPoint g, when not identicalcThe Haar feature number of (1) plus one;
(5) filtering the binarized image based on the Haar feature density map to obtain a final matching result;
the communication module is configured to provide a communication channel for the main control system and the control center, and transmit and feed back the hidden danger information;
the main control system comprises a control unit and a data preprocessing unit, wherein the control unit is configured to perform photographing control, a communication module, temperature measurement control, video control, power control and acousto-optic alarm control; the data preprocessing unit is configured to perform hidden danger detection by adopting an image matching method based on a Haar feature density map; the communication module is connected with the main control system and comprises a data encryption module and a wireless communication module, and the data encryption module encrypts data by adopting an MD5 algorithm; the wireless communication module adopts a mode of a communication operator Internet of things card and a VPN channel to carry out data transmission.
2. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: the power module comprises a power supply module and a power storage module, the power supply module adopts a solar cell panel to collect electric energy and is connected with the main control system, the power storage module comprises a storage battery and a super capacitor, and the electric energy collected by the power supply module is stored and is connected with the main control system.
3. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: the acousto-optic warning module comprises a tweeter and a light flashing device.
4. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: the monitoring module further comprises a temperature measuring module, the communication mode between the temperature measuring module and the main control system is a wireless communication mode, and the temperature of the power transmission line lead, the strain clamp and/or the drainage plate is measured.
5. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: the image monitoring module adopts a photographing lens with physical pixels larger than 500 ten thousand pixels, comprises two lenses, respectively monitors line channels on two sides of the iron tower, and is connected with the main control system.
6. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: the control center comprises a background master station system, receives and displays data of the monitoring modules, and realizes the visualization of distribution, the visualization of line channels and the alarm query of each monitoring module.
7. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: in the image matching method based on the Haar feature density graph, in the step (1), an image to be matched and a reference image are converted into four color spaces of RGB, HSV, YUV and Lab, and differential images are respectively obtained in the four color spaces.
8. A visual monitoring system for transmission channel outer damage protection as claimed in claim 7, wherein: in the step (2) of the image matching method based on the Haar feature density map, the difference images of the other channels except the difference image of the hue channel are weighted and fused, namely, the channels are separated, and the difference images of the other 11 channels except the difference image of the H channel are weighted and fused, wherein the fusion process is as follows:
wherein, Il(x, y) represents the pixel value of image I at coordinate (x, y) in the differential image of the I-th channel; f (x, y) represents a pixel value of the fused image F at the coordinates (x, y); n represents the number of images needing to be fused; k is a radical ofiRepresenting the size of the scale window, aiWeight representing scale, N-11, i, j representing from-kiTo kiBetweenThe value of (c).
9. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: in the step (4) of the image matching method based on the Haar feature density map, for a binary image, the gray difference features of the Haar features are regarded as binary jump between pixels.
10. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: in the step (4) of the image matching method based on the Haar feature density map, the specific process of obtaining the Haar feature density map of the image comprises the following steps:
(4-1) constructing a two-dimensional image H with the same size as the fused differential image, and assigning all pixel values in the image to be 0;
and (4-2) taking the Haar feature number of the pixels in the differential image after binarization as the gray value of the pixels at the corresponding position in the image H, wherein the image H is the Haar feature density map of the differential image.
11. A visual monitoring system for protection against external damage to a power transmission conduit as claimed in claim 1, wherein: in step (5) of the image matching method based on the Haar feature density map, the filtering process comprises the following steps:
(5-1) counting the number of effective pixels and the number of Haar features in a window with the width L by taking a pixel P as a center;
(5-2) taking the ratio of the number of Haar features to the number of effective pixels in the window as the Haar feature frequency of the pixel P.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711057539.0A CN107918941B (en) | 2017-11-01 | 2017-11-01 | Visual monitoring system and method for power transmission channel external damage protection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711057539.0A CN107918941B (en) | 2017-11-01 | 2017-11-01 | Visual monitoring system and method for power transmission channel external damage protection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107918941A CN107918941A (en) | 2018-04-17 |
| CN107918941B true CN107918941B (en) | 2020-10-13 |
Family
ID=61895975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711057539.0A Active CN107918941B (en) | 2017-11-01 | 2017-11-01 | Visual monitoring system and method for power transmission channel external damage protection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107918941B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717552B (en) * | 2019-10-23 | 2020-07-28 | 智洋创新科技股份有限公司 | Method for determining visible mechanical continuous alarm of power transmission line channel |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120328160A1 (en) * | 2011-06-27 | 2012-12-27 | Office of Research Cooperation Foundation of Yeungnam University | Method for detecting and recognizing objects of an image using haar-like features |
| CN105512662A (en) * | 2015-06-12 | 2016-04-20 | 北京卓视智通科技有限责任公司 | Detection method and apparatus for unlicensed vehicle |
-
2017
- 2017-11-01 CN CN201711057539.0A patent/CN107918941B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于多特征融合的图像匹配算法及应用;郭玉坤;《济南大学硕士学位论文》;20170830;5-39 * |
| 智能视频预警***在输电线路防外破中的应用;陈怡等;《中国高新技术企业》;20160331(第3期);36-38 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107918941A (en) | 2018-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112381784B (en) | Equipment detecting system based on multispectral image | |
| CN108307146B (en) | System and method for detecting potential safety hazard of high-voltage transmission line | |
| CN112379231B (en) | Equipment detection method and device based on multispectral image | |
| CN101620676B (en) | Fast image recognition method of insulator contour | |
| CN108109385A (en) | A kind of vehicle identification of power transmission line external force damage prevention and hazardous act judgement system and method | |
| CN203455912U (en) | System for on-line monitoring foreign matter interference of power transmission line | |
| CN103413150A (en) | Power line defect diagnosis method based on visible light image | |
| CN112149522A (en) | Intelligent visual external-damage-prevention monitoring system and method for cable channel | |
| CN113887412B (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
| CN104601956A (en) | Power transmission line online monitoring system and method based on fixed-wing unmanned aerial vehicle | |
| CN109297978B (en) | Binocular imaging-based power line unmanned aerial vehicle inspection and defect intelligent diagnosis system | |
| CN110913102A (en) | Image processing device for alum blossom acquisition and recognition | |
| CN107895365B (en) | Image matching method and monitoring system for power transmission channel external damage protection | |
| CN104994347A (en) | Intelligent security video monitoring system and detection processing method thereof | |
| CN105096305A (en) | Method and device for analyzing state of insulator | |
| CN103945197A (en) | Electric power facility external damage prevention warming scheme based on video motion detecting technology | |
| CN116111721A (en) | Smart grid power equipment safety monitoring system and method based on big data | |
| CN113485432A (en) | Photovoltaic power station electroluminescence intelligent diagnosis system and method based on unmanned aerial vehicle | |
| CN104700405A (en) | Foreground detection method and system | |
| CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
| CN106846304A (en) | Electrical equipment detection method and device based on infrared detection | |
| CN115936672A (en) | Smart power grid online safety operation and maintenance management method and system | |
| CN107918941B (en) | Visual monitoring system and method for power transmission channel external damage protection | |
| CN105376535A (en) | Transformer substation intelligent system based on soft-measuring technology | |
| CN111416964B (en) | Remote image intelligent identification method for hydraulic engineering deformation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |