CN117728570A - Power grid video analysis system and method based on edge calculation - Google Patents
Power grid video analysis system and method based on edge calculation Download PDFInfo
- Publication number
- CN117728570A CN117728570A CN202311690571.8A CN202311690571A CN117728570A CN 117728570 A CN117728570 A CN 117728570A CN 202311690571 A CN202311690571 A CN 202311690571A CN 117728570 A CN117728570 A CN 117728570A
- Authority
- CN
- China
- Prior art keywords
- video
- power grid
- data
- cloud platform
- platform server
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 73
- 238000004364 calculation method Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000007781 pre-processing Methods 0.000 claims abstract description 26
- 238000004891 communication Methods 0.000 claims abstract description 15
- 230000003068 static effect Effects 0.000 claims description 26
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 abstract description 10
- 230000008569 process Effects 0.000 abstract description 8
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a power grid video analysis system and a method based on edge calculation, which relate to the technical field of power grid video monitoring data processing, wherein a video acquisition unit uploads video data acquired in an area to an area edge calculation terminal; the regional edge computing terminal is used for carrying out preprocessing video analysis on the video data uploaded by the video acquisition unit and uploading the result of the preprocessing video analysis to the power grid cloud platform server through a special communication protocol; the power grid cloud platform server is used for further carrying out secondary analysis on the result of the preprocessing video analysis of the regional edge computing terminal and storing the final video analysis result; the method solves the technical problems that in the existing process of monitoring the power grid video, the data transmission time is too long, the feedback efficiency is affected, and when the number of the power grid video acquisition devices is large, the calculation force of the power grid cloud platform is extremely high.
Description
Technical Field
The invention relates to the technical field of power grid video monitoring data processing, in particular to a power grid video analysis system and method based on edge calculation.
Background
The power grid video monitoring is to collect and summarize field images and video data of various parts of a power grid (including a power plant, a transformer substation, a power transmission line and the like) so as to realize monitoring and control on the operation of the power grid. At present, the power grid video monitoring is mainly realized by a power grid video monitoring system.
The existing power grid video monitoring mostly obtains power grid video image information through a plurality of video acquisition devices, and then a unified power grid cloud platform server (power grid cloud platform) performs data processing on the video image information. However, the following technical problems exist in the process of power grid video monitoring: (1) When the video acquisition equipment is far away from the power grid cloud platform, the data transmission time length is long, and the feedback efficiency is affected; (2) With the increasing number of power grid video acquisition devices, the requirements on the data computing power processing capacity of the power grid cloud platform are higher and higher, and thus, the computing power of the power grid cloud platform is subjected to great pressure.
Disclosure of Invention
The invention provides a power grid video analysis system and a method based on edge calculation, which solve the technical problems that in the process of monitoring power grid video, when video acquisition equipment is far away from a power grid cloud platform, the data transmission time is too long, the feedback efficiency is affected, and when the number of the power grid video acquisition equipment is large, the calculation force on the power grid cloud platform is extremely high.
The invention provides a grid video analysis system based on edge calculation, which comprises:
the video acquisition unit is in communication connection with the regional edge computing terminal, and uploads the video data acquired in the region to the regional edge computing terminal;
the regional edge computing terminal is in communication connection with the power grid cloud platform server, and is used for carrying out preprocessing video analysis on the video data uploaded by the video acquisition unit and uploading a preprocessing video analysis result to the power grid cloud platform server through a special communication protocol;
the power grid cloud platform server is used for carrying out further secondary analysis on the result of the video analysis preprocessed by the regional edge computing terminal and storing the final video analysis result.
Optionally, the video acquisition unit comprises a 360 intelligent camera and a power network camera;
the 360 intelligent cameras and the power network cameras are in communication connection with the regional edge computing terminal;
the plurality of 360 intelligent cameras and the power network camera are arranged in a power grid monitoring preset range.
Optionally, the region edge computing terminal comprises a gain processing module, an overlap filtering module and a boundary extracting module;
the gain processing module is used for performing gain processing on the acquired video data to enable the acquired fuzzy video information to be clear;
the overlapping filtering module is used for obtaining monitoring overlapping areas corresponding to the video acquisition units and filtering the monitoring overlapping areas to obtain monitoring videos to be analyzed;
and the boundary extraction module is used for extracting boundary pixels of the monitoring video to be analyzed to obtain a corresponding monitoring boundary image.
Optionally, the boundary extraction module determines a monitoring area static video image and a monitoring area dynamic video image of the monitoring video to be analyzed by extracting the video monitoring boundary image.
Optionally, the region edge computing terminal further comprises a format conversion module;
the format conversion module is used for converting the video data storage format into a format required by the video processing software in the corresponding power grid cloud platform server.
Optionally, the power grid cloud platform server comprises a data conversion module, a video analysis module and an information storage module;
the data conversion module performs format unification processing on the preprocessed feature related data acquired from the regional edge computing terminal, defines a data structure in the data conversion module, classifies data types, and performs unified processing on data formats;
the video analysis module is used for carrying out image recognition on the video data of the power grid path through a preset video processing model, extracting relevant information data carried in the video data and carrying out calculation and analysis;
the information storage module is used for storing the data analyzed and processed by the video analysis module in a classified mode, and the power grid cloud platform server is convenient to call.
Optionally, the power grid cloud platform server further comprises a power grid GIS geographic information module;
the power grid GIS geographic information module is used for acquiring the position information of equipment in the power distribution network and correlating the position information with video acquisition information corresponding to the equipment.
The second aspect of the present invention provides an analysis method applied to the above-mentioned edge-calculation-based power grid video analysis system, where the edge-calculation-based power grid video analysis system includes a video acquisition unit, an area edge calculation terminal, and a power grid cloud platform server, and the analysis method includes:
optionally, the step of preprocessing the power grid video data information through the regional edge computing terminal, generating preprocessed data and sending the preprocessed data to a power grid cloud platform server includes:
gain processing is carried out on the obtained fuzzy video image through the regional edge computing terminal, and a processed clear video image is obtained;
acquiring a monitoring overlapping area corresponding to each video acquisition unit according to the clear video image through the area edge computing terminal, and filtering the monitoring overlapping area to generate a filtered video monitoring image;
and classifying the static image and the dynamic image by the filtered video monitoring image through the regional edge computing terminal, generating preprocessing data and sending the preprocessing data to the power grid cloud platform server.
Optionally, the step of comparing and analyzing the received preprocessed video data by the power grid cloud platform server, and sending out an early warning notification or automatically storing data includes:
extracting feature data of the preprocessed video data through the power grid cloud platform server to obtain a target extract;
the obtained target extract is subjected to data comparison and analysis with standard data characteristic information in a database through the power grid cloud platform server;
when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is smaller than a preset threshold value, the system is judged to be normal;
and when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is greater than a preset threshold value, the system automatically alarms.
From the above technical scheme, the invention has the following advantages:
(1) According to the edge calculation-based power grid video analysis system and method, a video monitoring architecture of the regional edge calculation terminal and the power grid cloud platform server (power grid cloud platform) is adopted, the regional edge calculation terminal is arranged at the equipment end, the regional edge calculation terminal is used for carrying out data preprocessing on video data information, the preprocessed data information is used for carrying out video data analysis on the power grid cloud platform server, invalid data transmission quantity is greatly reduced, and data processing pressure of the power grid cloud platform server is greatly reduced.
(2) According to the grid video analysis system and method based on edge calculation, the regional edge calculation terminal obtains the video monitoring image to be analyzed by filtering the monitoring overlapping area, so that the analysis processing process of redundant repeated images is reduced, the problems of calculation cost and time rise caused by repeated analysis of the monitoring overlapping area are solved, and the problem of high calculation pressure of a grid cloud platform server is further solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic block diagram of an edge-calculation-based video analysis system for a power grid according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a region edge computing terminal according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a power grid cloud platform server according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating steps of an analysis method according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a power grid video analysis system and a method based on edge calculation, which are used for solving the technical problems that when a video acquisition device is far away from a power grid cloud platform in the process of monitoring power grid video, the data transmission time is too long, the feedback efficiency is affected, and when the number of the power grid video acquisition devices is large, the calculation force on the power grid cloud platform causes extremely high pressure.
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the power grid video analysis system based on edge computing provided by the invention specifically includes a video acquisition unit 100, an area edge computing terminal 200 and a power grid cloud platform server 300, and the following technical description is made on specific functions and actions of the video acquisition unit 100, the area edge computing terminal 200 and the power grid cloud platform server 300:
it should be noted that, the video capturing unit 100 is in communication connection with the region edge computing terminal 200 (through wired or infinite communication connection), and the video capturing unit 100 uploads the video data captured in the region to the region edge computing terminal 200.
Referring to fig. 1, the video acquisition unit 100 includes 360 intelligent cameras and power network cameras, the 360 intelligent cameras and the power network cameras are all in communication connection with the regional edge computing terminal 200, and a plurality of 360 intelligent cameras and the power network cameras are arranged in a power grid monitoring preset range.
In this embodiment, the electric power network camera is adopted to transmit data and images through the power line, the network does not need to be erected again, the data transmission can be performed only by the electric wire, meanwhile, the electric power network camera is convenient and fast to use, plug and play, installation by a professional team is not needed, and 24-hour real-time monitoring can be achieved by the original electric power network. The plurality of crossed video acquisition units 100 are arranged according to the condition of a power grid (including a power plant, a transformer substation, a power transmission line and the like) so as to realize dead angle-free coverage of the area.
It should be noted that, the regional edge computing terminal 200 is communicatively connected to the grid cloud platform server 300, and the regional edge computing terminal 200 is configured to perform a preprocessing video analysis on the video data uploaded by the video capturing unit 100, and upload the result of the preprocessing video analysis to the grid cloud platform server 300 through a dedicated communication protocol.
Referring to fig. 2, the region edge computing terminal 200 includes a gain processing module 201, an overlap filtering module 202, a boundary extraction module 203, and a format conversion module 204.
In this embodiment, the gain processing module 201 is configured to perform video image gain processing on the collected video data, so as to make the collected blurred video information clear. In this embodiment, the gain processing module 201 is configured to perform gain processing and preliminary segmentation on video images captured by the intelligent camera 360 and/or the power network camera, so that the video image information can reflect real situations more easily, and further, the subsequent data processing is easier, and the computation load of the data processing is reduced.
In this embodiment, the overlapping filtering module 202 is configured to obtain a monitoring overlapping area corresponding to each video capturing unit 100, and filter the monitoring overlapping area to obtain a monitoring video to be analyzed. In this embodiment, filtering the video monitoring overlapping area based on the monitoring video acquisition quality of the 360 intelligent camera and/or the power network camera; the video monitoring basic information mainly includes an installation position of the video acquisition unit 100, an effective acquisition range of the video acquisition unit 100, and the like. The overlapping filtering module 202 is used for filtering the monitoring overlapping area to obtain a video monitoring image to be analyzed, so that the analysis processing process of redundant repeated images is reduced, and the problems of calculation cost and time rise caused by repeated analysis of the monitoring overlapping area are solved.
In this embodiment, the boundary extraction module 203 is configured to extract boundary pixels of the monitoring video to be analyzed to obtain a corresponding monitoring boundary image. And extracting boundary pixels of the monitoring image to be analyzed to obtain a corresponding monitoring boundary image, so as to determine a power grid static video image and a power grid dynamic video image of the monitoring image to be analyzed based on the monitoring boundary image. In this embodiment, the power grid static video image is mainly used for reflecting the running state conditions of power grid equipment (including power plants, substations, transmission lines, etc.); the dynamic video image of the power grid is mainly used for reflecting the dynamic conditions (such as wire aging and breakage or spark at a wiring position, whether people or animals intrude into dangerous areas such as a transformer substation or a power transmission line by mistake) which are about to happen or occur in the power grid equipment, and the motion state of an object in a monitoring video can be changed when potential safety hazards occur under the general conditions.
In this embodiment, the format conversion module 204 is configured to convert the preprocessed video data storage format into a format required by the video processing software in the corresponding grid cloud platform server 300. The operation amount of the subsequent data processing can be further reduced by performing the preformatted processing through the format conversion module 204.
It should be noted that, the power grid cloud platform server 300 is configured to perform further secondary analysis on the result of the preprocessing video analysis by the regional edge computing terminal 200, and store the final video analysis result.
Referring to fig. 3, the power grid cloud platform server 300 includes a data conversion module 301, a video analysis module 302, an information storage module 303, and a power grid GIS geographic information module.
In this embodiment, the data conversion module 301 performs format unification processing on the preprocessed feature related data acquired from the region edge computing terminal 200, defines a data structure inside the data conversion module 301, classifies data types, and performs unified processing on the data format.
In this embodiment, the video analysis module 302 is configured to perform image recognition on video data of the power grid path through a preset video processing model, extract relevant information data carried in the video data, and perform calculation and analysis. The video analysis module 302 calculates and analyzes the power grid equipment feature extraction information data returned by the extracted feature video image, and compares and analyzes the monitoring data with database information in the information storage module 303.
In this embodiment, the information storage module 303 stores the standard static video image and dynamic video image of the power grid in the area, uses the standard static video image and dynamic video image of the power grid as the judging basis, and compares the data information obtained by the boundary extraction module 203 with the standard static video image and dynamic video image of the power grid, so as to judge whether the power grid is abnormal. Specifically, when feature information of a target extract extracted by features (namely, a power grid static video image and a power grid dynamic video image extracted by features) is compared with standard data feature information in a database, if the feature information is smaller than a preset threshold (for example, the preset threshold is 0-5%), the system is judged to be normal; and when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of standard data in the database is greater than a preset threshold value (more than 5%), the system automatically alarms and automatically stores alarm information.
Further optimizing the embodiment, the video analysis module 302 performs real-time feature comparison processing on the power grid static video image extracted through the features, and confirms whether the current power grid static video image is in a normal working state or not; when judging the current power grid static video image (such as that no cable outer surface is damaged or a power equipment box door is not closed, and the like), extracting video fragments to which the current identified static image belongs to perform large-scale (such as one hour before and one hour after the other) static state and dynamic state identification, and outputting a final judging and identifying result through judgment. In the embodiment, real-time feature comparison processing is performed on the power grid static video image, and whether the current power grid static video image is in a normal working state or not is confirmed; the method specifically comprises the following steps: extracting features of the power grid static video image to be processed, inputting the extracted image features into a trained static recognition model, classifying the power grid static video image features by the static recognition model, and using the output classification result to represent whether the power grid static video image features are in a normal state or not. In this embodiment, static recognition may be performed on the model using an algorithm such as RMP23033487E, openpose, R-CNN. The static video image of the power grid is transmitted to the traditional model which is already pre-trained for recognition, and then the result is transmitted back.
The video analysis module 302 performs real-time feature comparison processing on the power grid dynamic video image extracted through the features, and confirms whether the current power grid dynamic video image is in a normal working state or not; when judging that the current power grid dynamic video image (such as smoke emission of a cable or leakage spark of equipment, and the like) is generated, extracting video fragments to which the current identified power grid dynamic video image belongs to perform large-range (such as one hour before and one hour after the other) static state and dynamic state identification, and outputting a final judgment identification result through judgment. In the embodiment, real-time feature comparison processing is performed on the power grid dynamic video image, and whether the current power grid dynamic video image is in a normal working state or not is confirmed; the method specifically comprises the following steps: and extracting features of the power grid dynamic video image to be processed, inputting the extracted image features into a trained dynamic recognition model, wherein the dynamic recognition model is used for classifying the power grid dynamic video image features, and the output classification result is used for representing whether the power grid dynamic video image features are in a normal state or not. In this embodiment, the dynamic recognition model adopts a cyclic neural network model, and a power grid dynamic video is transmitted into the cyclic neural network in the form of a file stream, and the trained cyclic neural network is used for dynamically recognizing the video stream and recording a response result.
The information storage module 303 is configured to store standard data feature information, and establish a standard data feature information database in the data storage module 304 to facilitate the data analysis module 302 to call and store the data analyzed and processed by the video analysis module 302 in a classified manner, so as to facilitate the power grid cloud platform server 300 to call.
The power grid GIS geographic information module 304 is used for acquiring position information of equipment in the power distribution network and correlating the position information with video acquisition information corresponding to the equipment. The power grid GIS geographic information module 304 may be further fused with other video monitoring data, for example: real-time monitoring of power failure events, identification of external hidden trouble points, monitoring of high-risk cable ditches and the like. Of course, the method may also be used to obtain location information of each power grid device from the power grid GIS geographic information module 304, and determine a distribution state of the target device according to the location information.
Referring to fig. 4, the analysis method applied to a grid video analysis system based on edge calculation provided by the invention includes a video acquisition unit, a regional edge calculation terminal and a grid cloud platform server, and the analysis method includes:
s1, the collected power grid video data information is sent to an area edge computing terminal through the 360 intelligent cameras and the power network cameras in the video collecting unit.
S2, preprocessing the power grid video data information through the regional edge computing terminal, generating preprocessing data and sending the preprocessing data to the power grid cloud platform server.
And S3, comparing and analyzing the received preprocessed video data through the power grid cloud platform server, and sending out early warning notification or automatically storing the data.
In the embodiment of the invention, the acquired power grid video data information is sent to the regional edge computing terminal through the 360 intelligent cameras and the power network cameras in the video acquisition unit 100; the regional edge computing terminal preprocesses the video data information in the step S1, and sends preprocessed data to the power grid cloud platform server; and the power grid cloud platform server compares and analyzes the received preprocessed video data, and sends out an early warning notice or automatically stores the data.
Further, S2 comprises the following sub-steps:
and S21, performing gain processing on the acquired blurred video image through the regional edge computing terminal to obtain a processed clear video image.
S22, acquiring a monitoring overlapping area corresponding to each video acquisition unit according to the clear video image through the area edge computing terminal, and filtering the monitoring overlapping area to generate a filtered video monitoring image.
S23, classifying the filtered video monitoring images into static images and dynamic images through the regional edge computing terminal, generating preprocessing data and sending the preprocessing data to the power grid cloud platform server.
In the embodiment of the invention, the specific preprocessing process of the video data information is as follows: a. gain processing is carried out on the obtained fuzzy video image, so that the processed video image is clear and bright; b, acquiring a monitoring overlapping area corresponding to each video acquisition unit according to the video image processed in the step a, and filtering the monitoring overlapping area; and c, classifying the video monitoring images processed in the step b into static images and dynamic images, and sending the processed video data to a power grid cloud platform server.
Further, S3 comprises the following sub-steps:
and S31, extracting feature data of the preprocessed video data through a power grid cloud platform server to obtain a target extract.
S32, carrying out data comparison and analysis on the obtained target extract and standard data characteristic information in a database through a power grid cloud platform server.
S33, when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is smaller than a preset threshold value, the system judges that the system is normal.
S34, when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is larger than a preset threshold value, the system automatically alarms.
In the embodiment of the invention, the data processing process of the power grid cloud platform server is as follows: (1) Extracting feature data of the video image information preprocessed in the step S2 to obtain a target extract; (2) Comparing and analyzing the obtained target extract with standard data characteristic information in a database; (3) When the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is smaller than a preset threshold value, the system is judged to be normal; and when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is larger than a preset threshold value, the system automatically alarms.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An edge-computation-based grid video analysis system, the edge-computation-based grid video analysis system comprising:
the video acquisition unit is in communication connection with the regional edge computing terminal, and uploads the video data acquired in the region to the regional edge computing terminal;
the regional edge computing terminal is in communication connection with the power grid cloud platform server, and is used for carrying out preprocessing video analysis on the video data uploaded by the video acquisition unit and uploading a preprocessing video analysis result to the power grid cloud platform server through a special communication protocol;
the power grid cloud platform server is used for carrying out further secondary analysis on the result of the video analysis preprocessed by the regional edge computing terminal and storing the final video analysis result.
2. The edge-computation-based grid video analysis system of claim 1, wherein the video acquisition unit comprises a 360 intelligent camera and a power network camera;
the 360 intelligent cameras and the power network cameras are in communication connection with the regional edge computing terminal;
the plurality of 360 intelligent cameras and the power network camera are arranged in a power grid monitoring preset range.
3. The edge-calculation-based power grid video analysis system according to claim 1, wherein the regional edge calculation terminal comprises a gain processing module, an overlap filtering module and a boundary extraction module;
the gain processing module is used for performing gain processing on the acquired video data to enable the acquired fuzzy video information to be clear;
the overlapping filtering module is used for obtaining monitoring overlapping areas corresponding to the video acquisition units and filtering the monitoring overlapping areas to obtain monitoring videos to be analyzed;
and the boundary extraction module is used for extracting boundary pixels of the monitoring video to be analyzed to obtain a corresponding monitoring boundary image.
4. The edge computation-based grid video analysis system of claim 3, wherein the boundary extraction module determines a surveillance area still video image and a surveillance area dynamic video image of the surveillance video to be analyzed by extracting the video surveillance boundary image.
5. The edge-computing-based grid video analytics system of claim 1, wherein the regional edge computing terminal comprises a format conversion module;
the format conversion module is used for converting the video data storage format into a format required by the video processing software in the corresponding power grid cloud platform server.
6. The edge computing-based grid video analysis system of claim 1, wherein the grid cloud platform server comprises a data conversion module, a video analysis module, and an information storage module;
the data conversion module performs format unification processing on the preprocessed feature related data acquired from the regional edge computing terminal, defines a data structure in the data conversion module, classifies data types, and performs unified processing on data formats;
the video analysis module is used for carrying out image recognition on the video data of the power grid path through a preset video processing model, extracting relevant information data carried in the video data and carrying out calculation and analysis;
the information storage module is used for storing the data analyzed and processed by the video analysis module in a classified mode, and the power grid cloud platform server is convenient to call.
7. The edge computing-based grid video analytics system of claim 1, wherein the grid cloud platform server further comprises a grid GIS geographic information module;
the power grid GIS geographic information module is used for acquiring the position information of equipment in the power distribution network and correlating the position information with video acquisition information corresponding to the equipment.
8. An analysis method applied to the edge-calculation-based power grid video analysis system as set forth in any one of claims 1 to 7, wherein the edge-calculation-based power grid video analysis system includes a video acquisition unit, a regional edge calculation terminal, and a power grid cloud platform server, the analysis method comprising:
the acquired power grid video data information is sent to the regional edge computing terminal through the 360 intelligent cameras and the power network cameras in the video acquisition unit;
preprocessing the power grid video data information through the regional edge computing terminal, generating preprocessing data and sending the preprocessing data to the power grid cloud platform server;
and comparing and analyzing the received preprocessed video data through the power grid cloud platform server, and sending out an early warning notice or automatically storing the data.
9. The analysis method according to claim 8, wherein the step of preprocessing the power grid video data information by the region edge computing terminal, generating preprocessed data, and transmitting the preprocessed data to the power grid cloud platform server includes:
gain processing is carried out on the obtained fuzzy video image through the regional edge computing terminal, and a processed clear video image is obtained;
acquiring a monitoring overlapping area corresponding to each video acquisition unit according to the clear video image through the area edge computing terminal, and filtering the monitoring overlapping area to generate a filtered video monitoring image;
and classifying the static image and the dynamic image by the filtered video monitoring image through the regional edge computing terminal, generating preprocessing data and sending the preprocessing data to the power grid cloud platform server.
10. The analysis method according to claim 8, wherein the step of comparing and analyzing the received preprocessed video data by the power grid cloud platform server, sending out an early warning notice or automatically storing data comprises:
extracting feature data of the preprocessed video data through the power grid cloud platform server to obtain a target extract;
the obtained target extract is subjected to data comparison and analysis with standard data characteristic information in a database through the power grid cloud platform server;
when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is smaller than a preset threshold value, the system is judged to be normal;
and when the comparison of the characteristic information of the target extract extracted by the characteristics and the characteristic information of the standard data in the database is greater than a preset threshold value, the system automatically alarms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311690571.8A CN117728570A (en) | 2023-12-08 | 2023-12-08 | Power grid video analysis system and method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311690571.8A CN117728570A (en) | 2023-12-08 | 2023-12-08 | Power grid video analysis system and method based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117728570A true CN117728570A (en) | 2024-03-19 |
Family
ID=90206349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311690571.8A Pending CN117728570A (en) | 2023-12-08 | 2023-12-08 | Power grid video analysis system and method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117728570A (en) |
-
2023
- 2023-12-08 CN CN202311690571.8A patent/CN117728570A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN112968816B (en) | Method and system for screening abnormality of Internet of things equipment through flow abnormality detection | |
| CN111050114A (en) | Low-power-consumption camera, monitoring management control system and control method thereof | |
| CN109560610A (en) | A kind of transformer substation video and environmental monitoring system | |
| CN110807460B (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN101329804A (en) | A security device and system | |
| CN111047824B (en) | Indoor child nursing linkage control early warning method and system | |
| CN114243932B (en) | Intelligent operation and maintenance terminal of substation video and environment monitoring station end system | |
| CN112688434A (en) | Monitoring and early warning method and device for power transmission and distribution line, computer equipment and medium | |
| CN113792578A (en) | Method, device and system for detecting abnormity of transformer substation | |
| CN113177614A (en) | Image recognition system and method for power supply switch cabinet of urban rail transit | |
| CN114445782A (en) | Power transmission line image acquisition system based on edge AI and Beidou short messages | |
| CN102355575A (en) | Distributed video monitoring device with pre-warning function | |
| CN116580362B (en) | Transmission operation cross-system fusion data acquisition method and digital asset processing system | |
| CN105376535A (en) | Transformer substation intelligent system based on soft-measuring technology | |
| CN112001810A (en) | Intelligent forestry patrolling system and method based on machine vision | |
| CN117728570A (en) | Power grid video analysis system and method based on edge calculation | |
| CN111274876B (en) | Scheduling monitoring method and system based on video analysis | |
| CN113705364B (en) | Power transmission line external hidden danger early warning system and method based on artificial intelligence | |
| CN112966552B (en) | Routine inspection method and system based on intelligent identification | |
| CN115150559A (en) | Remote vision system with acquisition self-adjustment calculation compensation and calculation compensation method | |
| CN113188662A (en) | Infrared thermal imaging fault automatic identification system and method | |
| CN115277757B (en) | Smart tower state analysis method and system based on wide-band and narrow-band data fusion | |
| CN113065416A (en) | Leakage monitoring device integrated with transformer substation video monitoring device, method and medium | |
| CN106296442A (en) | A kind of power facility simulation monitoring method and system |
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 |