CN112651276A - Power transmission channel early warning system based on double-light fusion and early warning method thereof - Google Patents
Power transmission channel early warning system based on double-light fusion and early warning method thereof Download PDFInfo
- Publication number
- CN112651276A CN112651276A CN202010919187.0A CN202010919187A CN112651276A CN 112651276 A CN112651276 A CN 112651276A CN 202010919187 A CN202010919187 A CN 202010919187A CN 112651276 A CN112651276 A CN 112651276A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- early warning
- visible light
- infrared
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 30
- 230000004927 fusion Effects 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 230000007797 corrosion Effects 0.000 claims description 16
- 238000005260 corrosion Methods 0.000 claims description 16
- 230000009977 dual effect Effects 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a power transmission channel early warning system based on double-light fusion and an early warning method thereof, wherein the early warning system comprises: the image acquisition module comprises an infrared acquisition module and a visible light acquisition module and is used for acquiring infrared images and visible light images near the power transmission channel; the processing module is connected with the image acquisition module and is used for processing the infrared image and the visible light image; and the early warning target recognition module is connected with the processing module and is a trained machine learning model, and the processed infrared image and the processed visible light image are input into the early warning target recognition module to output a warning target. According to the power transmission channel early warning system and the early warning method based on double-light fusion, disclosed by the invention, the intelligentization of the identification of the dangerous source target is realized by combining the fusion of the infrared image and the visible light image with the machine learning, and the accuracy of the identification of the early warning target of the power transmission channel is improved.
Description
Technical Field
The invention relates to the technical field of power distribution equipment monitoring, in particular to a power transmission channel early warning system based on double-light fusion and an early warning method thereof.
Background
With the increase of national economy and the improvement of living standard in China, the demand of electric power is increasing day by day, and the possibility of accidents such as equipment burning loss and the like caused by damage, failure and serious accidents of electric power equipment is increased due to the enlargement of the power grid scale of an electric power system and the improvement of electric power load. In order to avoid various electric power accidents as far as possible and reduce the major economic loss caused by the accidents, the method is imperative and is not slow.
The thermal imaging system can only locate the dangerous source of heating, but cannot judge the type of the dangerous source. The traditional video monitoring technology only provides simple functions of video capture, storage, playback and the like, does not have video analysis function and abnormity judgment capability, is not high enough in intelligent degree, and hardly plays roles of early warning and alarming.
Disclosure of Invention
In order to solve the problems, the invention provides a power transmission channel early warning system based on double-light fusion and an early warning method thereof, which realize the intellectualization of the identification of the target of a dangerous source by combining the fusion of an infrared image and a visible light image with machine learning, can locate the dangerous source by the infrared image and identify the type of the dangerous source by combining the visible light image, and improve the accuracy of the identification of the early warning target of the power transmission channel.
In order to achieve the above purpose, the invention adopts a technical scheme that:
a transmission channel early warning system based on dual optical fusion comprises: the image acquisition module comprises an infrared acquisition module and a visible light acquisition module and is used for acquiring infrared images and visible light images near the power transmission channel; the processing module is connected with the image acquisition module and is used for processing the infrared image and the visible light image; and the early warning target recognition module is connected with the processing module and is a trained machine learning model, and the processed infrared image and the processed visible light image are input into the early warning target recognition module to output a warning target.
Further, the processing module comprises an image calibration module, a binary processing module and a corrosion processing module, the image calibration module is connected with the acquisition module, the binary processing module is connected with the infrared acquisition module, the input end of the corrosion module is connected with the binary processing module, the output end of the corrosion module is connected with the calibration module, and the calibration module outputs the result to the early warning target identification module.
Furthermore, the infrared collection module is an infrared camera, and the visible light collection module is a visible light camera.
The invention also provides a power transmission channel early warning method based on double-light fusion, which comprises the following steps: s10, collecting data, namely collecting an infrared image and a visible light image near a power transmission channel through an infrared shooting collection module and a visible light collection module; s20, processing the infrared image and the visible light image through a processing module to obtain a target image to be recognized; and S30, recognizing the alarm target, inputting the target image to be recognized into an early warning target recognition module, and outputting the alarm target.
Further, the step S20 includes the following steps: s21, calibrating the corresponding relation between the infrared image and the pixel points of the visible light image; s22, performing image binarization processing, namely performing binarization processing on the infrared image to obtain a binarized image B; s23, carrying out image corrosion treatment, namely carrying out corrosion treatment on the binary image B to eliminate isolated points and obtain a corroded image; and S24, processing external rectangles, calculating the external rectangles of the corroded image, converting each external rectangle into a visible light image according to the corresponding relation of the step S21, and confirming the corresponding position of each external rectangle in the visible light image.
Further, the early warning target recognition module is a machine learning model trained by using standard images.
Furthermore, the infrared collection module is an infrared camera, and the visible light collection module is a visible light camera.
Compared with the prior art, the technical scheme of the invention has the following advantages:
according to the power transmission channel early warning system and the early warning method based on double-light fusion, the corresponding relation between the infrared image and the pixel point of the visible light image is obtained through fusion of the infrared image and the visible light image, the target image to be recognized, which is obtained by comparing the infrared image with the corresponding relation after being processed, is input into the early warning target recognition module to output the warning target, and the intellectualization of the target recognition of the dangerous source is realized through the fusion of the infrared image and the visible light image and the machine learning, so that the heating dangerous source in the infrared image positioning monitoring can be used, the type of the dangerous source can be recognized through the combination of the visible light image, and the accuracy of the early warning target recognition of the power transmission channel is improved.
Drawings
The technical solution and the advantages of the present invention will be apparent from the following detailed description of the embodiments of the present invention with reference to the accompanying drawings.
Fig. 1 is a structural diagram of a power transmission channel early warning system based on dual optical fusion according to an embodiment of the present invention;
fig. 2 is a flowchart of a power transmission channel early warning method based on dual optical fusion according to an embodiment of the present invention.
Reference numbers in the figures:
the system comprises an image acquisition module 1, an infrared acquisition module 11, a visible light acquisition module 12, a processing module 2, an image calibration module 21, a binary processing module 22, a corrosion processing module 23 and an early warning target identification module 3.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment provides a power transmission channel early warning method based on dual-light fusion, which comprises an image acquisition module 1, a processing module 2 and an early warning target identification module 3 which are sequentially connected as shown in fig. 1.
The image acquisition module 1 comprises an infrared acquisition module 11 and a visible light acquisition module 12 and is used for acquiring infrared images and visible light images near a power transmission channel, the infrared acquisition module 11 is an infrared camera, and the visible light acquisition module 12 is a visible light camera.
The processing module 2 is connected with the image acquisition module 1 and is used for processing the infrared image and the visible light image. The processing module 2 comprises an image calibration module 21, a binary processing module 22 and a corrosion processing module 23, the image calibration module 21 is connected with the acquisition module, the binary processing module 22 is connected with the infrared acquisition module 11, the input end of the corrosion module is connected with the binary processing module 22, the output end of the corrosion module is connected with the calibration module, and the calibration module outputs the data to the early warning target identification module 3.
The early warning target recognition module 3 is connected with the processing module 2 and is a trained machine learning model, and the processed infrared image and the processed visible light image are input into the early warning target recognition module 3 to output an alarm target.
The invention also provides a power transmission channel early warning method based on double-light fusion, as shown in fig. 2, comprising the following steps: and S10, acquiring data, namely acquiring an infrared image and a visible light image near the power transmission channel through the infrared camera acquisition module and the visible light acquisition module 12. And S20, processing the infrared image and the visible light image through a processing module 2 to obtain a target image to be recognized. And S30, recognizing the alarm target, inputting the target image to be recognized into the early warning target recognition module 3, and outputting the alarm target.
In step S10, the infrared collection module 11 is an infrared camera, and the visible light collection module 12 is a visible light camera.
The step S20 includes the following steps: and S21, calibrating the corresponding relation between the infrared image and the pixel points of the visible light image. And S22, performing image binarization processing, namely performing binarization processing on the infrared image to obtain a binarized image B. The binarization of the image is to set the gray value of a pixel point on the image to be 0 or 255, that is, the whole image has an obvious visual effect of only black and white. One image includes a target object, a background, etc., and in order to directly extract the target object from a multi-valued digital image, a common method is to set a threshold T, and divide the data of the image into two parts by T: pixel groups larger than T and pixel groups smaller than T. This is the most specific method for studying gray scale transformation, called Binarization (Binarization) of the image. The binarization formula is as follows:
wherein, T is a temperature value preset by the system.
And S23, carrying out image corrosion treatment, namely carrying out corrosion treatment on the binary image B to eliminate isolated points and obtain a corroded image. S24 processing the external rectangles, calculating the circumscribed rectangles of the corroded images, converting each circumscribed rectangle into a visible light image according to the corresponding relation of the step S21, and confirming the corresponding position of each circumscribed rectangle in the visible light image. Calculating circumscribed rectangles R of the image obtained in step S23, for each circumscribed rectangle RiTaking the coordinate P of the upper left cornerLAnd the coordinates P of the lower right cornerRAnd converting the infrared image into a visible light image according to the corresponding relation parameter of the step S21 to obtain the corresponding position of the infrared image in the visible light image. The early warning target recognition module 3 is a machine learning model trained by using standard images.
The above description is only an exemplary embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes that are transformed by the content of the present specification and the attached drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. The utility model provides a transmission of electricity passageway early warning system based on two optical fusion which characterized in that includes:
the image acquisition module comprises an infrared acquisition module and a visible light acquisition module and is used for acquiring infrared images and visible light images near the power transmission channel;
the processing module is connected with the image acquisition module and is used for processing the infrared image and the visible light image; and
and the early warning target recognition module is connected with the processing module and is a trained machine learning model, and the processed infrared image and the processed visible light image are input into the early warning target recognition module to output a warning target.
2. The dual-light fusion-based power transmission channel early warning system according to claim 1, wherein the processing module comprises an image calibration module, a binary processing module and a corrosion processing module, the image calibration module is connected with the acquisition module, the binary processing module is connected with the infrared acquisition module, an input end of the corrosion module is connected with the binary processing module, an output end of the corrosion module is connected with the calibration module, and the calibration module outputs the result to the early warning target recognition module.
3. The dual light fusion-based power transmission channel early warning system according to claim 2, wherein the infrared collection module is an infrared camera and the visible light collection module is a visible light camera.
4. A power transmission channel early warning method based on double-light fusion is characterized by comprising the following steps:
s10, collecting data, namely collecting an infrared image and a visible light image near a power transmission channel through an infrared shooting collection module and a visible light collection module;
s20, processing the infrared image and the visible light image through a processing module to obtain a target image to be recognized; and
and S30, recognizing the alarm target, inputting the target image to be recognized into an early-warning target recognition module, and outputting the alarm target.
5. The dual optical fusion-based power transmission channel warning method as claimed in claim 4, wherein the step S20 includes the steps of:
s21, calibrating the corresponding relation between the infrared image and the pixel points of the visible light image;
s22, performing image binarization processing, namely performing binarization processing on the infrared image to obtain a binarized image B;
s23, carrying out image corrosion treatment, namely carrying out corrosion treatment on the binary image B to eliminate isolated points and obtain a corroded image; and
s24 processing the external rectangles, calculating the circumscribed rectangles of the corroded images, converting each circumscribed rectangle into a visible light image according to the corresponding relation of the step S21, and confirming the corresponding position of each circumscribed rectangle in the visible light image.
6. The dual light fusion-based power transmission channel early warning method according to claim 5, wherein the early warning target recognition module is a machine learning model trained using standard images.
7. The double-light fusion-based power transmission channel early warning method according to claim 6, wherein the infrared acquisition module is an infrared camera, and the visible light acquisition module is a visible light camera.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010919187.0A CN112651276A (en) | 2020-09-04 | 2020-09-04 | Power transmission channel early warning system based on double-light fusion and early warning method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010919187.0A CN112651276A (en) | 2020-09-04 | 2020-09-04 | Power transmission channel early warning system based on double-light fusion and early warning method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112651276A true CN112651276A (en) | 2021-04-13 |
Family
ID=75346191
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010919187.0A Pending CN112651276A (en) | 2020-09-04 | 2020-09-04 | Power transmission channel early warning system based on double-light fusion and early warning method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112651276A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113566976A (en) * | 2021-08-09 | 2021-10-29 | 中车大连机车车辆有限公司 | Overtemperature early warning device for electric wiring terminal of locomotive converter cabinet |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110619293A (en) * | 2019-09-06 | 2019-12-27 | 沈阳天眼智云信息科技有限公司 | Flame detection method based on binocular vision |
WO2020171281A1 (en) * | 2019-02-22 | 2020-08-27 | 써모아이 주식회사 | Visible light and infrared fusion image-based object detection method and apparatus |
-
2020
- 2020-09-04 CN CN202010919187.0A patent/CN112651276A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020171281A1 (en) * | 2019-02-22 | 2020-08-27 | 써모아이 주식회사 | Visible light and infrared fusion image-based object detection method and apparatus |
CN110619293A (en) * | 2019-09-06 | 2019-12-27 | 沈阳天眼智云信息科技有限公司 | Flame detection method based on binocular vision |
Non-Patent Citations (1)
Title |
---|
陈兵旗 等: "实用数字图像处理与分析", 28 February 2014, 中国农业大学出版社, pages: 105 - 106 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113566976A (en) * | 2021-08-09 | 2021-10-29 | 中车大连机车车辆有限公司 | Overtemperature early warning device for electric wiring terminal of locomotive converter cabinet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
CN109271844B (en) | Electrical cabinet electrical symbol recognition method based on OpenCV | |
Liu et al. | A method of segmenting apples at night based on color and position information | |
CN102509100B (en) | Knife switch connecting-disconnecting reliability recognition method based on image pattern recognition | |
CN116721107B (en) | Intelligent monitoring system for cable production quality | |
CN110458041B (en) | Face recognition method and system based on RGB-D camera | |
CN111460988A (en) | Illegal behavior identification method and device | |
CN112183313A (en) | SlowFast-based power operation field action identification method | |
CN115861987B (en) | Intelligent electric power fitting defect identification method for online monitoring of power transmission line | |
CN104573713A (en) | Mutual inductor infrared image recognition method based on image textual features | |
CN111127445A (en) | Distribution network line high-temperature area detection method and system based on deep learning | |
CN111563896B (en) | Image processing method for detecting abnormality of overhead line system | |
CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
CN112651276A (en) | Power transmission channel early warning system based on double-light fusion and early warning method thereof | |
CN112101365A (en) | Power equipment key feature extraction method and system based on infrared thermal image processing | |
CN114092378A (en) | Animal health detection method, device, equipment and storage medium | |
CN112634179B (en) | Camera shake prevention power transformation equipment image change detection method and system | |
CN111967323B (en) | Electric power live working safety detection method based on deep learning algorithm | |
CN113255519A (en) | Crane lifting arm identification system and multi-target tracking method for power transmission line dangerous vehicle | |
CN111626104B (en) | Cable hidden trouble point detection method and device based on unmanned aerial vehicle infrared thermal image | |
CN113283276A (en) | Linkage thermal imaging self-learning fire point detection method and system | |
CN115082504B (en) | Light spot identification method for solar photovoltaic panel | |
CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
CN114549822A (en) | Disconnecting switch closing state detection method based on preset position camera | |
CN113536895A (en) | Disc pointer meter identification method |
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 |