CN115984770A - Remote monitoring method for converter station based on image recognition - Google Patents
Remote monitoring method for converter station based on image recognition Download PDFInfo
- Publication number
- CN115984770A CN115984770A CN202211622520.7A CN202211622520A CN115984770A CN 115984770 A CN115984770 A CN 115984770A CN 202211622520 A CN202211622520 A CN 202211622520A CN 115984770 A CN115984770 A CN 115984770A
- Authority
- CN
- China
- Prior art keywords
- image
- data center
- converter station
- image recognition
- camera
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Image Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a remote monitoring method for a converter station based on image recognition. The invention comprises the following steps: setting a camera to shoot images of all physical assets in the converter station, and marking the position information of the physical assets; extracting images shot by a camera from a database to a data center for image recognition of the real assets needing to be checked; setting vital signs of millimeter wave radar detection personnel; carrying out image identification to judge whether smoke appears; if smoke exists, judging whether the smoke has vital signs of personnel by using a millimeter wave radar; and constructing an electronic fence for the set working area of the converter station, then carrying out image recognition, and recognizing personnel and vehicles entering and exiting the set working area. The invention can remotely check the real assets in the converter station and improve the checking efficiency and timeliness.
Description
Technical Field
The invention relates to the technical field of converter station monitoring systems, in particular to a remote monitoring method for a converter station based on image recognition.
Background
A converter station is a station in a high voltage direct current transmission system that converts alternating current to direct current or direct current to alternating current. The monitoring in the converter station refers to checking various real assets, and the re-checking refers to re-checking the assets by a person different from the monitoring.
When a conventional converter station performs an inventory, an associated staff member is required to perform the inventory in the field. Although the field checking has a wide application range, most property and materials can adopt the method, the workload is large, the efficiency is not high, and the checking result is not fed back timely.
In the prior art, a monitoring system for a converter station, for example, chinese patent No. 201510661510.8, discloses a converter station panoramic state monitoring system, which includes a data acquisition module, a data storage module, a data analysis processing module, and an application module, wherein various device monitoring data are effectively fused and subjected to relevance analysis, so as to realize panoramic monitoring and multidimensional analysis of the device state in an extra-high voltage converter station. However, the prior art does not include checking of the physical assets, monitoring and checking whether the physical assets and the safety signboard are illegally moved, and does not recognize personnel and vehicles entering the converter station, so that it is difficult to ensure that the personnel entering the working area are authorized and allowed.
Disclosure of Invention
In order to solve one or more defects or problems in the prior art, the invention aims to provide a remote monitoring method of a converter station based on image recognition, so as to overcome the problems of manual checking and the defect that the existing monitoring system lacks a real object asset checking function.
The technical scheme of the invention is as follows:
a remote monitoring method of a converter station based on image recognition comprises the following steps:
the method comprises the steps that a plurality of cameras connected with a data center are arranged in a converter station, the cameras shoot images of all physical assets in the converter station, the images of the physical assets are stored in a database of the data center, and position information of the physical assets is marked in the database;
setting a safety signboard when a person operates the physical asset, then extracting a person operation image shot by a camera from a database to a data center for image recognition, and obtaining a mechanical on-off state and an electrical indication state of the corresponding physical asset after the person operation through the image recognition, thereby realizing the inventory of the corresponding physical asset;
a plurality of millimeter wave radars connected with a data center are arranged in the converter station, data of the millimeter wave radars are stored in a database of the data center, and the millimeter wave radars are used for detecting vital signs of personnel;
extracting an image shot by a camera from a database to a data center for image recognition, and judging whether smoke occurs or not; if smoke exists, detecting the smoke by using a millimeter wave radar, and judging whether the smoke has vital signs of personnel according to data of the millimeter wave radar; if the smoke has vital signs of people, the data center gives an alarm;
the method comprises the steps of utilizing images of the whole convertor station in a data center to construct an electronic fence for a set working area of the convertor station, then extracting images shot by a camera from a database to carry out image recognition, recognizing personnel and vehicles entering and exiting the set working area, and establishing station entering and exiting data in the database.
Preferably, the checking is performed by image recognition when a person operates the physical material, and the specific steps include:
each person entering a set working area in the converter station is allowed to replace a working clothes;
in a set working area, placing the operated physical assets and the operated safety signboard in a view finding range of a camera and marking position coordinates of the physical assets and the safety signboard;
after the images shot by the camera are transmitted to the data center, the data center performs image recognition on the work clothes to obtain the number of personnel entering a set work area and the human body outline of the personnel;
when a person operates the physical asset, the data center identifies the behavior of the person according to the image shot by the camera, and judges whether the behavior of the corresponding physical asset of illegal operation occurs or not;
and the data center records whether the illegal behaviors occur, and identifies and records the mechanical on-off state and the electrical indication state of the physical asset after the operation of personnel by using the image.
Further, the to-be-operated physical asset and the safety signboard are placed in a view finding range of the camera and mark position coordinates of the physical asset and the safety signboard, and the specific steps include:
adjusting the position of the camera to enable the physical assets and the safety identification plate to be positioned in the view finding range of the identification camera;
the data center establishes a coordinate system by taking the lower left corner of a viewing frame of the camera as an origin, calculates the position coordinates of the physical assets and the safety signboard in the image in the coordinate system, and marks the position coordinates of the corresponding physical assets and the safety signboard in the image.
Further, the image recognition of the work clothes to obtain the number of the personnel entering the set work area and the human body contour of the personnel comprises the following steps:
the data center carries out image recognition, and when the working clothes are recognized, the number of the working clothes in the set working area is recognized;
the data center updates the background of the image to obtain a human body foreground image, and simultaneously removes holes and white dots in the human body foreground image;
and setting the distance between the left point and the right point in the human body foreground image as the width of the recognition frame of the human body outline, and setting the distance between the upper point and the lower point in the human body foreground image as the height of the recognition frame of the human body outline, thereby obtaining the recognition frame of the human body outline.
Further, the method for judging whether behaviors of corresponding physical assets and safety signboard of illegal operation occur comprises the following specific steps:
carrying out image recognition in a data center, and calculating whether the position coordinates of the physical assets and/or the safety signboard change or not;
if the position coordinates of the physical asset and/or the safety signboard change, calculating the position coordinates of the central point of the human body contour recognition frame in the set working area, and then calculating the distance between the position coordinates of the central point of the human body contour recognition frame and the position coordinates of the physical asset and/or the safety signboard;
and if the distance between the position coordinate of the central point of the human body contour recognition frame and the position coordinate of the physical asset and/or the safety signboard is smaller than a set threshold value, indicating that a person illegally operates the corresponding physical asset and/or the safety signboard.
Further, after recognizing the behavior of illegal operation in the set working area, the data center sends a warning message to personnel in the set working area.
Further, the data center detects smoke through image recognition, and the specific steps are as follows:
processing an image shot by a camera by using a Gaussian model to obtain a motion area of the image;
processing the image shot by the camera by using a dark channel defogging algorithm to obtain a smokeless image model;
carrying out difference processing on the image processed by the Gaussian model and the image processed by the dark channel defogging algorithm to obtain a difference image; carrying out binarization processing on the difference image to obtain a smoke area to be identified in the image, and acquiring an intersection area between the smoke area and the motion area of the image;
and identifying the smoke region to be identified in the image by using a smoke classification model trained through deep learning, and judging whether smoke appears in the image.
Further, the data center uses data of the millimeter wave radar, after the fact that the vital signs of the personnel exist in smoke of the set working area is detected, whether the vital signs of the personnel are higher than a set value or not is judged, and if the vital signs of the personnel are lower than the set value, rescue messages are sent to other personnel.
Further, after the electronic fence is constructed, image recognition is carried out on personnel who enter and exit a set working area, and the specific steps are as follows:
a camera matched with the height of a person is arranged, and the face images of the person entering and exiting the station are captured and transmitted to a data center;
the method comprises the following steps that a data center writes face images and identity data of people with the authority of entering and exiting a convertor station into a database in advance;
the data center compares the face images of the captured personnel with the face images of the personnel with the authority of entering and exiting the converter station in the database, marks whether the captured personnel have the authority of entering and exiting the converter station in the captured images, and counts the number of the personnel.
Further, after the electronic fence is constructed, image recognition is carried out on vehicles entering and exiting a set working area, and the specific steps are as follows:
a camera matched with the height of the license plate of the vehicle is arranged, and the images of the license plate of the vehicle entering and exiting the station are captured and transmitted to a data center;
the data center converts the captured license plate image into a gray image and denoises the image;
extracting the contour of the gray image by using a sobel operator to obtain a gray contour image, and obtaining a gray contour image according to the length-width ratio of 1:2.5, cutting out characters in the gray contour image according to the projection of the gray value of the image in the horizontal direction and the vertical direction;
and identifying the license plate number from the cut characters through a template matching algorithm.
Compared with the prior art, the invention has the beneficial effects that:
through an image recognition mode, physical assets in the convertor station can be checked remotely; the position coordinates of the physical asset, the safety signboard and the human body outline are calculated to judge whether a person unauthorized moves the physical asset and the safety signboard, and an alarm is given when the physical asset and the safety signboard have position or state errors, so that efficient remote checking is realized, illegal operation behaviors are corrected in time, and the problems of low manual checking efficiency and untimely checking result feedback are avoided; through the camera and the millimeter wave radar, whether people are trapped in smoke or not can be found in time when a smoke fire disaster occurs in a set working area, so that rescue is commanded; through identifying the information of the personnel and the vehicles in the converter station, whether the personnel and the vehicles with authority enter the set working area or not is determined, and the safety of the set working area is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a general flow chart of a method for remote monitoring of a converter station based on image recognition according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments thereof. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
As shown in fig. 1, the remote monitoring method for a converter station based on image recognition of this embodiment includes the following steps:
the method comprises the following steps that S1, a plurality of cameras connected with a data center are arranged in a converter station, the cameras shoot images of all physical assets in the converter station, the images of the physical assets are stored in a database of the data center, and position information of the physical assets is marked in the database; wherein the physical assets comprise equipment such as a disconnecting link, a grounding switch and a switch;
s2, setting a safety signboard when a person operates the physical asset, then extracting a person operation image shot by a camera from a database to perform image recognition on a data center, and obtaining a mechanical on-off state and an electrical indication state of the corresponding physical asset after the person operation through the image recognition, thereby realizing the checking of the corresponding physical asset;
checking of the converter station refers to real-time monitoring of a series of operation processes and a repeated operation of equipment such as a disconnecting link, a grounding switch and a switch in the power failure and power transmission processes of the converter station; the power outage operation may involve an operation from a running to a hot standby state, an operation from a hot standby to a cold standby state, an operation from a cold standby to a maintenance state; the power transmission operation may further involve an operation of switching from a service state to a cold standby state, an operation of switching from a cold standby state to a hot standby state, and an operation of switching from a hot standby state to a running state;
in this embodiment, it is preferable that the specific steps of performing the inventory through image recognition when the person operates the physical material include:
s21, enabling each person entering a set working area in the converter station to replace a working clothes;
s22, in a set working area, placing the operated physical assets and the operated safety signboard in a view finding range of a camera and marking position coordinates of the physical assets and the operated safety signboard; the method specifically comprises the following steps:
adjusting the position or angle of the camera to make the physical assets and the safety identification plate positioned in the view finding range of the identification camera; the size of a lens frame is 4mm, and the distance between cameras with an irradiation angle of 70 degrees is about 6 meters; the size of the lens frame is 6mm, and the distance between cameras with the irradiation angle of 50 degrees is 6-10 meters; the size of the lens frame is 8mm, and the distance between cameras with the irradiation angle of 38 degrees is 10-20 meters; the data center establishes a coordinate system by taking the lower left corner of a viewing frame of the camera as an origin, calculates the position coordinates of the physical assets and the safety signboard in the image in the coordinate system, and marks the position coordinates of the corresponding physical assets and the safety signboard in the image;
s23, after the image shot by the camera is transmitted to the data center, the data center performs image recognition on the work clothes to obtain the number of personnel entering a set work area and the human body outline of the personnel; the method specifically comprises the following steps:
when the work clothes are identified, the data center adds one bit to the number of the personnel in the set work area;
the data center carries out modeling and background updating on the background of the image, subtracts the current frame from the background to obtain a human body foreground image, and removes holes and white points in the human body foreground image;
setting the distance between the left point and the right point in the human body foreground image as the width of an identification frame of the human body contour, and setting the distance between the upper point and the lower point in the human body foreground image as the height of the identification frame of the human body contour, thereby obtaining the identification frame of the human body contour;
s24, when the physical assets are operated by personnel, the data center identifies and analyzes the behaviors of the personnel according to the images shot by the camera, and judges whether the behaviors of the corresponding physical assets which are operated in an illegal way occur or not; the method specifically comprises the following steps:
carrying out image recognition in a data center, and calculating whether the position coordinates of the physical assets and/or the safety signboard change or not; if the position coordinates of the physical asset and/or the safety signboard change, calculating the position coordinates of the central point of the human body contour recognition frame in the set working area, and then calculating the distance between the position coordinates of the central point of the human body contour recognition frame and the position coordinates of the physical asset and/or the safety signboard; if the distance between the position coordinate of the central point of the human body contour recognition frame and the position coordinate of the physical asset and/or the safety signboard is smaller than a set threshold value, indicating that a person illegally operates the corresponding physical asset and/or the safety signboard;
s25, the data center records whether the illegal behaviors occur, and the mechanical on-off state and the electrical indication state of the real asset after the operation of personnel are identified by using the image and recorded; after recognizing the behavior of illegal operation in the set working area, the data center sends an alarm message, specifically an acousto-optic alarm signal, to personnel in the set working area;
s3, arranging a plurality of millimeter wave radars connected with a data center in the converter station, and storing data of the millimeter wave radars in a database of the data center, wherein the millimeter wave radars are used for detecting vital signs of personnel; the millimeter wave radar has extremely high working frequency and short wavelength, can have higher resolution and can still be normally used in a smoke environment, the millimeter wave radar transmits electromagnetic waves with specific waveforms through an antenna, the electromagnetic waves are intercepted by a target in an effective radiation range, the target reflects the electromagnetic waves to a plurality of directions, part of energy returns to the antenna to be received by the radar, and information such as the position, the moving speed and the direction of the target relative to the radar is finally calculated through processes such as amplification and signal processing, so that a data center can calculate vital signs of personnel targets by using the information;
s4, extracting an image shot by a camera from the database to a data center for image recognition, and judging whether smoke occurs or not; if smoke exists, detecting the smoke by using a millimeter wave radar, and judging whether the smoke has vital signs of personnel according to data of the millimeter wave radar; if the smoke has vital signs of people, the data center gives an alarm; the method specifically comprises the following steps:
s41, detecting smoke through image identification by the data center; processing an image shot by a camera by using a Gaussian model to obtain a motion area of the image; processing the image shot by the camera by using a dark channel defogging algorithm to obtain a smokeless image model; carrying out difference processing on the image processed by the Gaussian model and the image processed by the dark channel defogging algorithm to obtain a difference image; carrying out binarization processing on the difference image to obtain a smoke area to be identified in the image, and acquiring an intersection area between the smoke area and the motion area of the image; identifying a smoke region to be identified in the image by using a smoke classification model trained through deep learning, and judging whether smoke appears in the image; if smoke exists, the data center sends a message to inform people in a set smoke area to evacuate;
s42, the data center uses data of a millimeter wave radar, after the fact that the vital signs of the personnel exist in smoke of a set working area is detected, whether the vital signs of the personnel are higher than a set value or not is judged, if the vital signs of the personnel are lower than the set value, the fact that the vital signs of the personnel are not stable is indicated, then a rescue message is sent to other personnel, and the other personnel are informed to rescue the personnel with unstable vital signs;
s5, constructing an electronic fence in a set working area of the convertor station by utilizing the image of the whole convertor station in the data center, then extracting the image shot by a camera from the database for image recognition, recognizing personnel and vehicles entering and exiting the set working area, and establishing station entering and exiting data in the database; the method specifically comprises the following steps:
s51, after the electronic fence is constructed, carrying out image recognition on personnel entering and exiting a set working area, setting a camera matched with the height of the personnel, capturing face images of the personnel entering and exiting the station, and transmitting the face images to a data center; the data center writes face images and identity data of people with the authority of entering and exiting the converter station into a database in advance; the data center compares the face images of the captured personnel with the face images of the personnel with the permission to enter and exit the convertor station in the database, marks whether the captured personnel have the permission to enter and exit the convertor station in the feared images, and counts the number of the personnel;
s52, after the electronic fence is constructed, carrying out image recognition on vehicles entering and exiting a set working area, setting a camera matched with the height of a license plate of the vehicle, capturing images of the license plate of the vehicles entering and exiting the station, and transmitting the images to a data center; the data center converts the captured license plate image into a gray image and denoises the image; extracting the contour of the gray image by using a sobel operator to obtain a gray contour image, and according to the length-width ratio of 1:2.5, removing the suspected non-license plate number area of the gray-scale outline image, and then cutting out characters in the gray-scale outline image according to the projection of the gray-scale value of the image in the horizontal direction and the vertical direction; and identifying the license plate number from the cut characters through a template matching algorithm.
Compared with the prior art, the embodiment has the advantages that:
by means of image recognition, physical assets, safety signboards and position information in the converter station can be checked remotely; the position coordinates of the physical asset and the safety signboard and the position coordinates of the human body outline recognition frame of the personnel are calculated to judge whether the personnel unauthorized move the physical asset or the safety signboard, so that the physical asset or the safety signboard is prevented from being disordered in position, accurate remote checking is realized, meanwhile, the personnel unauthorized move of related equipment can be prevented, the equipment is lost, efficient remote checking is realized, illegal operation behaviors are corrected in time, and the problems of low manual checking efficiency and untimely checking result feedback are avoided; by combining the detection means of the millimeter wave radar with the camera, whether people are trapped in smoke or not can be found in time when smoke fire occurs in a set working area, and then rescue can be informed in time; by inputting the information of the personnel and the vehicles entering the convertor station, the personnel without permission can be prevented from entering the working area.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (10)
1. A remote monitoring method of a converter station based on image recognition is characterized by comprising the following steps:
the method comprises the steps that a plurality of cameras connected with a data center are arranged in a converter station, the cameras shoot images of all physical assets in the converter station, the images of the physical assets are stored in a database of the data center, and position information of the physical assets is marked in the database;
setting a safety signboard when a person operates the physical asset, then extracting a person operation image shot by a camera from a database to a data center for image recognition, and obtaining a mechanical on-off state and an electrical indication state of the corresponding physical asset after the person operation through the image recognition, thereby realizing the inventory of the corresponding physical asset;
a plurality of millimeter wave radars connected with a data center are arranged in the converter station, data of the millimeter wave radars are stored in a database of the data center, and the millimeter wave radars are used for detecting vital signs of personnel;
extracting an image shot by a camera from a database to a data center for image recognition, and judging whether smoke occurs or not; if smoke exists, detecting the smoke by using a millimeter wave radar, and judging whether the smoke has vital signs of personnel according to data of the millimeter wave radar; if the smoke has vital signs of people, the data center gives an alarm;
the method comprises the steps of utilizing images of the whole convertor station in a data center to construct an electronic fence for a set working area of the convertor station, then extracting images shot by a camera from a database to carry out image recognition, recognizing personnel and vehicles entering and exiting the set working area, and establishing station entering and exiting data in the database.
2. The image recognition-based remote monitoring method for the converter station according to claim 1, wherein the checking is performed by image recognition when a person operates a real asset, and the specific steps include:
each person entering a set working area in the converter station is allowed to replace a working clothes;
in a set working area, placing the operated physical assets and the operated safety signboard in a view finding range of a camera and marking position coordinates of the physical assets and the operated safety signboard;
after the image shot by the camera is transmitted to the data center, the data center performs image recognition on the work clothes to obtain the number of personnel entering a set work area and the human body outline of the personnel;
when a person operates the physical asset, the data center identifies the behavior of the person according to the image shot by the camera, and judges whether the behavior of the corresponding physical asset of illegal operation occurs or not;
and the data center records whether the illegal behavior occurs, and identifies and records the mechanical on-off state and the electrical indication state of the physical asset after the operation of personnel by using the image.
3. The image recognition-based remote monitoring method for the converter station according to claim 2, wherein the physical asset and the safety signboard to be operated are placed in a view range of the camera and mark position coordinates of the physical asset and the safety signboard, and the method comprises the following specific steps:
adjusting the position of the camera to enable the physical assets and the safety identification plate to be positioned in the view finding range of the identification camera;
the data center establishes a coordinate system by taking the lower left corner of a viewing frame of the camera as an origin, calculates the position coordinates of the physical assets and the safety signboard in the image in the coordinate system, and marks the position coordinates of the corresponding physical assets and the safety signboard in the image.
4. The image recognition-based remote monitoring method for the converter station according to claim 3, wherein the image recognition is performed on the work clothes to obtain the number of the personnel entering the set work area and the human body contour of the personnel, and the method comprises the following steps:
the data center carries out image recognition, and when the working clothes are recognized, the number of the working clothes in the set working area is recognized;
the data center updates the background of the image to obtain a human body foreground image, and simultaneously removes holes and white dots in the human body foreground image;
and setting the distance between the left point and the right point in the human body foreground image as the width of the recognition frame of the human body outline, and setting the distance between the upper point and the lower point in the human body foreground image as the height of the recognition frame of the human body outline, thereby obtaining the recognition frame of the human body outline.
5. The image recognition-based remote monitoring method for the converter station according to claim 4, wherein the steps of judging whether the behaviors of operating corresponding physical assets and safety signboard in violation occur are as follows:
carrying out image recognition in a data center, and calculating whether the position coordinates of the physical assets and/or the safety signboard change or not;
if the position coordinates of the physical asset and/or the safety signboard change, calculating the position coordinates of the central point of the human body contour recognition frame in the set working area, and then calculating the distance between the position coordinates of the central point of the human body contour recognition frame and the position coordinates of the physical asset and/or the safety signboard;
and if the distance between the position coordinate of the central point of the human body contour recognition frame and the position coordinate of the physical asset and/or the safety signboard is smaller than a set threshold value, indicating that a person illegally operates the corresponding physical asset and/or the safety signboard.
6. The image recognition-based remote monitoring method for the converter station according to claim 5, wherein the data center sends out a warning message to personnel in the set working area after recognizing the behavior of illegal operation in the set working area.
7. The image recognition-based remote monitoring method for the converter station according to claim 5, wherein the data center detects smoke through image recognition, and the method comprises the following specific steps:
processing an image shot by a camera by using a Gaussian model to obtain a motion area of the image;
processing the image shot by the camera by using a dark channel defogging algorithm to obtain a smokeless image model;
carrying out difference processing on the image processed by the Gaussian model and the image processed by the dark channel defogging algorithm to obtain a difference image; carrying out binarization processing on the difference image to obtain a smoke area to be identified in the image, and acquiring an intersection area between the smoke area and the motion area of the image;
and identifying the smoke region to be identified in the image by using the smoke classification model trained through deep learning, and judging whether smoke appears in the image.
8. The image-recognition-based remote monitoring method for the converter station according to claim 7, wherein the data center uses data of millimeter wave radar, and after detecting that vital signs of people exist in smoke in a set working area, judges whether the vital signs of the people are higher than a set value, and if the vital signs of the people are lower than the set value, sends out a rescue message to other people.
9. The image recognition-based remote monitoring method for the converter station according to claim 8, wherein after the electronic fence is constructed, image recognition is performed on personnel who enter and exit a set working area, and the specific steps are as follows:
a camera matched with the height of a person is arranged, and the face images of the person entering and exiting the station are captured and transmitted to a data center;
the data center writes face images and identity data of people with the authority of entering and exiting the converter station into a database in advance;
the data center compares the face images of the captured people with face images of people with the authority of getting in and out of the converter station in the database, marks whether the captured people have the authority of getting in and out of the converter station in the images which are afraid of getting in and out of the converter station, and counts the number of the people.
10. The image recognition-based remote monitoring method for the converter station according to claim 9, wherein after the electronic fence is constructed, the image recognition is performed on vehicles entering and exiting the set working area, and the specific steps are as follows:
a camera matched with the height of the license plate of the vehicle is arranged, and the images of the license plate of the vehicle entering and exiting the station are captured and transmitted to a data center;
the data center converts the captured license plate image into a gray image and denoises the image;
extracting the contour of the gray image by using a sobel operator to obtain a gray contour image, and obtaining a gray contour image according to the length-width ratio of 1:2.5, cutting out characters in the gray outline image according to the projection of the gray value of the image in the horizontal direction and the vertical direction;
and identifying the license plate number from the cut characters through a template matching algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211622520.7A CN115984770A (en) | 2022-12-16 | 2022-12-16 | Remote monitoring method for converter station based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211622520.7A CN115984770A (en) | 2022-12-16 | 2022-12-16 | Remote monitoring method for converter station based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115984770A true CN115984770A (en) | 2023-04-18 |
Family
ID=85960449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211622520.7A Pending CN115984770A (en) | 2022-12-16 | 2022-12-16 | Remote monitoring method for converter station based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115984770A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117351499A (en) * | 2023-12-04 | 2024-01-05 | 深圳市铁越电气有限公司 | Split-combined indication state identification method, system, computer equipment and medium |
-
2022
- 2022-12-16 CN CN202211622520.7A patent/CN115984770A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117351499A (en) * | 2023-12-04 | 2024-01-05 | 深圳市铁越电气有限公司 | Split-combined indication state identification method, system, computer equipment and medium |
| CN117351499B (en) * | 2023-12-04 | 2024-02-02 | 深圳市铁越电气有限公司 | Split-combined indication state identification method, system, computer equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507308B (en) | Transformer substation safety monitoring system and method based on video identification technology | |
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN112396658B (en) | Indoor personnel positioning method and system based on video | |
| CN106157507B (en) | A kind of transmission line of electricity solid protective device based on radar and video fusion | |
| CN106448181B (en) | Non-motor vehicle management method, device and system | |
| CN109856643B (en) | Movable type non-inductive panoramic sensing method based on 3D laser | |
| CN103259206A (en) | Transformer substation operation safety management and control system based on computer vision locating technology | |
| KR100956978B1 (en) | The system which integrated manages a traffic accident notice area | |
| CN109996182B (en) | Positioning method, device and system based on combination of UWB positioning and monitoring | |
| CN114140503A (en) | Power distribution network dangerous area identification device and method based on deep learning | |
| CN115984770A (en) | Remote monitoring method for converter station based on image recognition | |
| CN110390784A (en) | A kind of transmission line of electricity external force damage prevention monitoring system based on deep learning | |
| CN114267011A (en) | Distribution room live equipment misoperation detection system | |
| CN114170272A (en) | Accident reporting and storing method based on sensing sensor in cloud environment | |
| CN113034828A (en) | System for realizing target detection and identification based on embedded computing terminal and layout method | |
| CN113505704B (en) | Personnel safety detection method, system, equipment and storage medium for image recognition | |
| CN115880231A (en) | Power transmission line hidden danger detection method and system based on deep learning | |
| KR102500474B1 (en) | System for providing smart intelligence safety management service | |
| CN113965733A (en) | Binocular video monitoring method, system, computer equipment and storage medium | |
| CN113963373A (en) | Video image dynamic detection and tracking algorithm based system and method | |
| CN211427457U (en) | Intelligent security system for important places | |
| CN116993265A (en) | Intelligent warehouse safety management system based on Internet of things | |
| CN116311034A (en) | Robot inspection system based on contrast detection | |
| CN116012939A (en) | Method and device for determining illegal behaviors, storage medium and electronic device |
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 |