CN113691783A - Converter station video monitoring method, system, device and computer equipment - Google Patents
Converter station video monitoring method, system, device and computer equipment Download PDFInfo
- Publication number
- CN113691783A CN113691783A CN202111251507.0A CN202111251507A CN113691783A CN 113691783 A CN113691783 A CN 113691783A CN 202111251507 A CN202111251507 A CN 202111251507A CN 113691783 A CN113691783 A CN 113691783A
- Authority
- CN
- China
- Prior art keywords
- image data
- information
- converter station
- analysis result
- 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
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to a converter station video monitoring method, a system, a device and computer equipment. The method comprises the following steps: determining idle thread information corresponding to the edge server; sending idle thread information to a scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to the converter station to be monitored to the target edge server; and when the image data is received, acquiring an image analysis result corresponding to the image data, sending the image analysis result to a monitoring center, and triggering the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result. In this embodiment, the image data is processed by the extensible edge servers, so that the processing of the image data in the monitoring process of the converter station is not limited by the hardware of the monitoring terminal any more, the video analysis efficiency of the converter station is improved, and whether the converter station is abnormal or not is determined in time.
Description
Technical Field
The present application relates to the field of power technologies, and in particular, to a converter station video monitoring method, system, apparatus, computer device, and storage medium.
Background
With the increasing perfection and popularization of power grids, sufficient and reliable power supply becomes the basis of national economic and social development. The converter station is used as an important facility in the power industry, is responsible for the task of power transmission, and directly causes the limitation of regional load if the converter station is attacked and fails, thereby influencing the safety and stability of a power grid and the normal power utilization of users.
In the related art, for the purpose of security protection, a video monitoring system can be arranged in the converter station, video collection is carried out on the area in the converter station, and after the video is collected, the monitoring terminal analyzes and processes the video to determine whether the converter station is safe at present.
However, under the condition that the number of cameras in the converter station is large, video data acquired in a set period is huge and limited by hardware limitations of the monitoring terminal, and the requirement of large-scale video data processing cannot be met, so that the analysis efficiency of the converter station video is low, and the analysis result is delayed.
Disclosure of Invention
In view of the above, it is necessary to provide a converter station video monitoring method, system, device, computer equipment and storage medium capable of improving analysis efficiency.
A converter station video monitoring method is applied to an edge server, and comprises the following steps:
responding to a data distribution request sent by a scheduling server, and determining idle thread information corresponding to the edge server;
sending the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
when the image data is received, obtaining an image analysis result corresponding to the image data, and sending the image analysis result to a monitoring center so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
In one embodiment, the sending the idle thread information to the scheduling server includes:
determining thread demand information corresponding to the data allocation request;
and when the idle thread information is greater than or equal to the thread requirement information, sending the idle thread information to the scheduling server.
In one embodiment, the obtaining, when the image data is received, an image analysis result corresponding to the image data includes:
when the image data is received, acquiring a security verification result corresponding to the image data;
according to the safety verification result, obtaining safety image data which passes data safety inspection from the image data, and registering the safety image data;
and acquiring an image analysis result corresponding to the registered safety image data.
In one embodiment, the method further comprises the following steps:
and according to the safety verification result, when abnormal image data which do not pass the data safety check are determined to exist in the image data, sending prompt information corresponding to the abnormal image data to the scheduling server, and pausing the analysis of the abnormal image data.
In one embodiment, the obtaining of the image analysis result corresponding to the image data includes:
acquiring a face data feature library corresponding to the converter station; the face data feature library comprises user face features associated with the converter station;
acquiring the face features to be compared corresponding to the image data;
and when the matching degree between the face features to be compared and each user face feature in the face data feature library is smaller than a preset similarity threshold, generating illegal user intrusion information as an image analysis result.
In one embodiment, the obtaining of the image analysis result corresponding to the image data includes:
acquiring a license plate database corresponding to the convertor station; the license plate database comprises preset license plate information associated with the converter station;
acquiring license plate information to be compared corresponding to the image data;
and when the license plate information to be compared is not matched with each preset license plate information in the license plate database, generating illegal vehicle intrusion information as an image analysis result.
A converter station video surveillance system, the system comprising:
the edge server is used for responding to a data distribution request sent by the scheduling server, determining idle thread information corresponding to the edge server, and sending the idle thread information to the scheduling server;
the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
the edge server is further used for acquiring an image analysis result corresponding to the image data when the image data is received, and sending the image analysis result to a monitoring center;
and the monitoring center is used for determining whether to generate alarm information aiming at the converter station or not based on the image analysis result.
A converter station video monitoring device is applied to an edge server, and the device comprises:
the idle thread information determining module is used for responding to a data distribution request sent by a scheduling server and determining idle thread information corresponding to the edge server;
an idle thread information sending module, configured to send the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
and the analysis result acquisition module is used for acquiring an image analysis result corresponding to the image data when the image data is received, and sending the image analysis result to a monitoring center so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as claimed in any one of the above when the computer program is executed.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of the preceding claims.
In response to a data allocation request sent by a scheduling server, the edge server may determine idle thread information corresponding to the edge server and send the idle thread information to the scheduling server, and then the scheduling server may determine a target edge server from the edge servers based on the idle thread information sent by the edge servers and send image data corresponding to the converter station to be monitored to the target edge server. In this embodiment, by processing image data in a plurality of extensible edge servers, while image analysis is performed by effectively utilizing computing resources of the edge servers, processing of image data in the monitoring process of the converter station is not limited by hardware of the monitoring terminal any more, so that the analysis efficiency of the video of the converter station is improved, and whether the converter station is abnormal or not is determined in time.
Drawings
Fig. 1 is an application environment diagram of a converter station video monitoring method in an embodiment;
FIG. 2 is a schematic flow chart of a method for monitoring a video of a converter station according to an embodiment;
FIG. 3 is a block diagram of a converter station video surveillance system according to an embodiment;
fig. 4 is a block diagram of a structure of a video monitoring apparatus of a converter station in an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The video monitoring method for the converter station can be applied to the application environment shown in fig. 1. In the application environment, a scheduling server 101, an edge server 102 and a monitoring center 103 may be included. The dispatch server 101 and the edge server 102 may communicate with each other through a network, and the edge server 102 and the monitoring center 103 may communicate with each other through a network. The edge server 102 may be a plurality of edge servers. The scheduling server 101 and the edge server 102 may be implemented by separate servers or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a method for monitoring a video of a converter station is provided, which is illustrated by applying the method to the edge server 102 in fig. 1, and may include the following steps:
As an example, the data allocation request may be a scheduling server requesting allocation of pending data to an edge server to process image data by the edge server.
The idle thread information may be information corresponding to an available thread of the edge server currently in an idle state, for example, a number corresponding to the idle thread or a data amount that can be processed by the idle thread.
In a specific implementation, after acquiring image data to be processed, the scheduling server may send a data allocation request to the plurality of edge servers, and inquire whether the edge servers can perform data processing currently. When receiving a data allocation request of the scheduling server, the edge server may determine idle thread information corresponding to the edge server in response to the data allocation request, where the idle thread information may be current idle thread information of the edge server or idle thread information predicted for a preset time in the future.
The scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to the converter station to be monitored to the target edge server.
As an example, a converter station may refer to a station established in a hvdc transmission system to perform conversion from ac power to dc power or vice versa and meet the requirements of a power system for safety, stability and power quality; the corresponding image data of the converter station may be image data reflecting the surroundings of the converter station, such as surveillance video data. Specifically, for example, a plurality of image acquisition modules for acquiring image data may be arranged within a preset range of the converter station, for example, monitoring equipment is deployed within the preset range of the converter station, and the monitoring equipment acquires the image data in the converter station. The image acquisition module can upload the image data to the scheduling server after acquiring the image data.
In practical application, after the edge server obtains the idle thread information, the edge server may send the idle thread information to the scheduling server. After receiving the idle thread information sent from the plurality of edge servers, the scheduling server may determine, from the plurality of edge servers, a target edge server for which the idle thread information satisfies the thread screening condition based on the idle thread information corresponding to each of the plurality of edge servers, for example, may sort the plurality of idle thread information, and determine, according to a result of the sorting, one or a preset number of edge servers corresponding to the largest processable data amount or the largest number of idle threads as the target edge server. After determining the target edge server, the scheduling server may send image data corresponding to the converter station to the edge server.
As an example, the image analysis result may be an analysis result that determines whether an abnormal condition exists at the converter station.
The monitoring center may be a platform or a server for monitoring the converter station.
When the edge server receives the image data, it can be determined that the scheduling server determines the current edge server as the target edge server, and the edge server can analyze the received image data, acquire an image analysis result corresponding to the image data, and send the currently obtained image analysis result to the monitoring center. After receiving the image analysis result, the monitoring center may determine whether to generate warning information for the converter station according to the image analysis result, for example, if it is determined that there is an obvious abnormality in the converter station based on the image analysis result, the monitoring center may send warning information to a terminal of a related administrator, where the warning information may indicate that there is an abnormality in the converter station and a specific abnormality in the converter station.
In this embodiment, in response to a data allocation request sent by a scheduling server, an edge server may determine idle thread information corresponding to the edge server and send the idle thread information to the scheduling server, and then the scheduling server may determine a target edge server from a plurality of edge servers and send image data corresponding to a converter station to be monitored to the target edge server based on the idle thread information sent by the plurality of edge servers. In this embodiment, by processing image data in a plurality of extensible edge servers, while image analysis is performed by effectively utilizing computing resources of the edge servers, processing of image data in the monitoring process of the converter station is not limited by hardware of the monitoring terminal any more, so that the analysis efficiency of the video of the converter station is improved, and whether the converter station is abnormal or not is determined in time.
In one embodiment, the sending the idle thread information to the scheduling server may include:
determining thread demand information corresponding to the data allocation request; and when the idle thread information is greater than or equal to the thread requirement information, sending the idle thread information to the scheduling server.
As an example, the thread demand information may be the amount of thread resource demand that the dispatch server needs to invoke from the corresponding edge server.
In a specific implementation, the scheduling server may generate a data allocation request carrying the thread requirement information, and send the data allocation request to each edge server. After receiving the data allocation request, the edge server may read the data allocation request and determine corresponding thread requirement information.
Specifically, the scheduling server may distribute a uniform data allocation request to the plurality of edge servers, that is, may request to invoke the same thread resource of the plurality of edge servers; or, the thread demand information may be 0.6m and the thread demand information may be 0.4m, where the thread demand information may be allocated in proportion, for example, the total thread resource demand of the scheduling server is m, and the ratio of the thread resource total amounts corresponding to the edge server a and the edge server b is 3: 2.
After the thread demand information is obtained, current idle thread information of the edge server may be further obtained, and for example, the corresponding idle thread information may be determined according to the total amount of thread resources corresponding to the edge server and the amount of thread resources currently occupied.
After obtaining the idle thread information, the edge server may determine whether the idle thread information is greater than or equal to the thread requirement information. When the idle thread information is greater than or equal to the thread requirement information, it can be determined that the edge server has residual thread resources available for the scheduling server, and then the idle thread information can be sent to the scheduling server under the condition of meeting the thread resource requirement of the edge server. When the idle thread information is smaller than the thread requirement information, the idle thread information may not be sent to the scheduling server.
In this embodiment, the thread requirement information corresponding to the data allocation request may be determined, and when the idle thread information corresponding to the edge server is greater than or equal to the thread requirement information, the idle thread information is sent to the scheduling server, so that when the scheduling server selects the edge server as the data receiver, the edge server whose thread resources meet the requirement may be preferentially selected, and a problem that a large amount of data is accumulated at the edge server to cause downtime is avoided.
In one embodiment, the obtaining an image analysis result corresponding to the image data when the image data is received may include:
when the image data is received, acquiring a security verification result corresponding to the image data; according to the safety verification result, obtaining safety image data which passes data safety inspection from the image data, and registering the safety image data; and acquiring an image analysis result corresponding to the registered safety image data.
As an example, the security check may include at least one of: virus scanning, white list scanning and security authentication.
In practical application, when the edge server receives image data, the edge server may perform data security check on the image data, and obtain a corresponding security verification result, and further may obtain, according to the security verification result, security image data that passes the data security check from the received image data, and register the security image data, where the registered information may include at least one of an image identifier, an image acquisition time, and an image acquisition location corresponding to the security image data.
After the image registration is completed, an image analysis result corresponding to the registered security image data may be acquired.
In this embodiment, when the image data is received, a security verification result corresponding to the image data may be obtained, the security image data that passes data security check may be obtained from the image data according to the security verification result, and after the security image data is registered, an image analysis result corresponding to the registered security image data may be obtained, which may ensure security in an image data analysis process.
In one embodiment, the method may further comprise the steps of:
and according to the safety verification result, when abnormal image data which do not pass the data safety check are determined to exist in the image data, sending prompt information corresponding to the abnormal image data to the scheduling server, and pausing the analysis of the abnormal image data.
As an example, the prompt information may be information characterizing that the image data has an abnormality, which may include information such as an image identifier corresponding to the abnormal image data, and a reason for the abnormality.
After the security verification result is obtained, whether abnormal image data which fails in the data security check exists in the image data can be judged according to the security verification result. And when determining that abnormal image data which does not pass the data security check exists in the image data, sending prompt information corresponding to the abnormal image data to the scheduling server, and suspending analysis of the abnormal image data.
In this embodiment, when it is determined that there is abnormal image data that fails in the data security check in the image data, the edge server may send a prompt message corresponding to the abnormal image data to the scheduling server, and suspend analyzing the abnormal image data, so as to avoid poisoning caused by the abnormal image data in the image data analysis process, and improve the security and reliability of the edge server.
In one embodiment, the obtaining of the image analysis result corresponding to the image data includes:
acquiring a face data feature library corresponding to the converter station; acquiring the face features to be compared corresponding to the image data; and when the matching degree between the face features to be compared and each user face feature in the face data feature library is smaller than a preset similarity threshold, generating illegal user intrusion information as an image analysis result.
The face data feature library can comprise user face features related to the converter station; the facial features of the user associated with the converter station may include facial features corresponding to personnel or resident personnel within the converter station. Specifically, face images corresponding to multiple workers in the converter station can be obtained in advance, feature extraction can be performed on the face images of the workers to obtain user face features, and then the face data feature library can be constructed by adopting the user face features corresponding to the multiple workers.
After the image data is obtained, the edge server can perform face detection on the obtained image data to determine whether a face image exists in the image data, and if the face image is not detected, it can be determined that no person enters the converter station at present and the face image is sent to the monitoring center as an image analysis result.
If the face image is detected, the edge server may extract a face region from the image data, and perform face recognition based on the face region. Specifically, the face features to be compared can be obtained from the face region corresponding to the image data. Before the face features to be compared are obtained, the image data may be preprocessed, for example, the obtained image data may be converted into a grayscale image, the grayscale image may be subjected to contrast stretching enhancement, then, the grayscale image after the contrast stretching enhancement may be smoothed by using a median filter, and the grayscale image after the smoothing processing may be subjected to moving average binarization processing. After the preprocessing is finished, the face features to be compared can be obtained from the preprocessed image data.
After the face features to be compared are obtained, the face features to be compared can be compared with a plurality of user face features in the face data feature library one by one, and the similarity between the face features to be compared and the user face features is determined.
When the matching degree between the face features to be compared and one of the user face features is greater than a preset similarity threshold value, for example, greater than 98% of the preset similarity threshold value, it can be determined that the person appearing in the image data is a converter station worker, and information entered by a legal person is generated as a corresponding image analysis result.
When the matching degree between the face features to be compared and the face features of each user in the face data feature library is smaller than a preset similarity threshold, the person appearing in the image data can be determined as an illegal user, and then illegal user intrusion information can be generated and used as an image analysis result. When the monitoring center receives the intrusion information of the illegal user, corresponding warning information can be generated, for example, the warning information can include at least one of an intrusion place, intrusion time and a face image corresponding to an illegal person.
In another example, the method for recognizing a human face may also be applied to a process of recognizing secure image data, and specifically may include the following steps: acquiring a face data feature library corresponding to the converter station; acquiring the face features to be compared corresponding to the safety image data; and when the matching degree between the face features to be compared corresponding to the safety image data and the face features of each user in the face data feature database is smaller than a preset similarity threshold, generating illegal user intrusion information as an image analysis result corresponding to the safety image data. The face recognition process of the security image data is similar to the face recognition process of the image data, and is not described herein again.
In the embodiment, the face features to be compared corresponding to the image data can be obtained, when the matching degree between the face features to be compared and each user face feature in the face data feature library is smaller than a preset similarity threshold value, illegal user intrusion information is generated and used as an image analysis result, whether illegal personnel intrude into the converter station or not can be automatically identified, the person does not need to be relied on for watching and identifying, and the identification efficiency of the illegal personnel entering the converter station is effectively improved.
In one embodiment, the obtaining of the image analysis result corresponding to the image data includes:
acquiring a license plate database corresponding to the convertor station; acquiring license plate information to be compared corresponding to the image data; and when the license plate information to be compared is not matched with each preset license plate information in the license plate database, generating illegal vehicle intrusion information as an image analysis result.
The license plate database can comprise preset license plate information related to the converter station; the preset license plate information associated with the converter station may include a license plate number registered in advance in the converter station, for example, a license plate number corresponding to a vehicle used by a worker or a license plate number corresponding to another working vehicle, or a license plate number corresponding to a vehicle entering or exiting the converter station more than a preset number of times may be used as the preset license plate information. In practical application, a plurality of pieces of preset license plate information can be obtained in advance, and a license plate database is constructed.
After receiving the image data, vehicle identification may be performed based on the image data.
Specifically, a license plate database can be obtained, image recognition is performed on the image data, and license plate information to be compared corresponding to the image data is obtained. When license plate information to be compared is obtained, the area where the license plate is located can be located with low locating precision (precision lower than a preset precision threshold) in the image corresponding to the image data, and a first license plate image is obtained. After the license plate image is obtained, a binary image corresponding to the license plate image can be obtained, and the license plate is accurately positioned based on the license plate image (the positioning accuracy is higher than a preset accuracy threshold), so that a second license plate image is obtained. After the second license plate image is obtained, the second license plate image can be segmented into license plate character blocks, the license plate character blocks are identified, and license plate information to be compared is output.
After the license plate information to be compared is obtained, whether the license plate information to be compared is matched with preset license plate information in a license plate database can be determined, for example, if two pieces of license plate information to be compared in the image data are identified, whether each piece of license plate information to be compared is matched with any piece of preset license plate information can be respectively determined. When the license plate information to be compared is matched with one preset license plate information, legal vehicle entering information can be generated and used as an image analysis result. When the license plate information to be compared is not matched with each preset license plate information in the license plate database, entering of illegal vehicles can be determined, and information about the illegal vehicle intrusion can be used as an image analysis result. When the monitoring center receives the illegal vehicle intrusion information, corresponding warning information can be generated, and the warning information can include at least one of an intrusion point, intrusion time and a license plate number.
In another example, the above method for vehicle identification may also be applied to the analysis process of the security image data, and specifically, may include the following steps: acquiring a license plate database corresponding to the convertor station; acquiring license plate information to be compared corresponding to the safety image data; and when the license plate information to be compared corresponding to the safety image data is not matched with each preset license plate information in the license plate database, generating illegal vehicle intrusion information as an image analysis result of the safety image data. The vehicle identification process of the security image data is similar to the vehicle identification process of the image data, and is not described herein again.
In the embodiment, the license plate information to be compared corresponding to the image data can be acquired, when the license plate information to be compared is not matched with each preset license plate information in the license plate database, illegal vehicle intrusion information is generated and is used as an image analysis result, whether illegal vehicles intrude into the converter station or not can be automatically identified, the converter station does not need to depend on personnel for watching and identifying, and the identification efficiency of the illegal vehicles entering the converter station is effectively improved.
In one embodiment, as shown in fig. 3, there is provided a converter station video monitoring system, which may include:
the edge server 301 is configured to determine, in response to a data allocation request sent by a scheduling server, idle thread information corresponding to the edge server, and send the idle thread information to the scheduling server.
In a specific implementation, after acquiring image data to be processed, the scheduling server may send a data allocation request to the plurality of edge servers, and inquire whether the edge servers can perform data processing currently. When receiving a data allocation request from the scheduling server, the edge server may determine idle thread information corresponding to the edge server in response to the data allocation request, and send the idle thread information to the scheduling server.
The scheduling server 302 is configured to determine a target edge server from the multiple edge servers based on idle thread information sent by the multiple edge servers, and send image data corresponding to a converter station to be monitored to the target edge server.
After receiving the idle thread information sent from the plurality of edge servers, the scheduling server may determine, based on the idle thread information corresponding to each of the plurality of edge servers, a target edge server whose idle thread information satisfies the thread screening condition from the plurality of edge servers, for example, may sort the plurality of idle thread information, and determine, according to a result of the sorting, one or a preset number of edge servers that correspond to the largest processable data amount or number of idle threads as the target edge server.
After determining the target edge server, the scheduling server may send image data corresponding to the converter station to the edge server.
The edge server 301 is further configured to, when receiving the image data, obtain an image analysis result corresponding to the image data, and send the image analysis result to a monitoring center.
When the edge server receives the image data, it can be determined that the scheduling server determines the current edge server as the target edge server, and the edge server can analyze the received image data, acquire an image analysis result corresponding to the image data, and send the currently obtained image analysis result to the monitoring center.
The monitoring center 303 is configured to determine whether to generate alarm information for the converter station based on the image analysis result.
After receiving the image analysis result, the monitoring center may determine whether to generate warning information for the converter station according to the image analysis result, for example, if it is determined that there is an obvious abnormality in the converter station based on the image analysis result, the monitoring center may send warning information to a terminal of a related administrator, where the warning information may indicate that there is an abnormality in the converter station and a specific abnormality in the converter station.
In this embodiment, the edge server may determine idle thread information corresponding to the edge server in response to a data allocation request sent by the scheduling server, and send the idle thread information to the scheduling server, the scheduling server may determine a target edge server from the multiple edge servers based on the idle thread information sent by the multiple edge servers, and send image data corresponding to a converter station to be monitored to the target edge server, and when the edge server receives the image data, the edge server may obtain an image analysis result corresponding to the image data, and send the image analysis result to the monitoring center, and the monitoring center determines whether to generate alarm information for the converter station based on the image analysis result. In this embodiment, by processing image data in a plurality of extensible edge servers, while image analysis is performed by effectively utilizing computing resources of the edge servers, processing of image data in the monitoring process of the converter station is not limited by hardware of the monitoring terminal any more, so that the analysis efficiency of the video of the converter station is improved, and whether the converter station is abnormal or not is determined in time.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
In one embodiment, as shown in fig. 4, there is provided a video monitoring apparatus for a converter station, which may be applied to an edge server, the apparatus including:
an idle thread information determining module 401, configured to determine, in response to a data allocation request sent by a scheduling server, idle thread information corresponding to the edge server;
an idle thread information sending module 402, configured to send the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
an analysis result obtaining module 403, configured to obtain, when the image data is received, an image analysis result corresponding to the image data, and send the image analysis result to a monitoring center, so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
In one embodiment, the idle thread information sending module 402 includes:
the thread requirement information acquisition submodule is used for determining thread requirement information corresponding to the data distribution request;
and the thread requirement information comparison submodule is used for sending the idle thread information to the scheduling server when the idle thread information is greater than or equal to the thread requirement information.
In one embodiment, the analysis result obtaining module 403 includes:
the safety verification result acquisition sub-module is used for acquiring a safety verification result corresponding to the image data when the image data is received;
the registration submodule is used for acquiring the security image data which passes the data security check from the image data according to the security verification result and registering the security image data;
and the registered image analysis submodule is used for acquiring an image analysis result corresponding to the registered security image data.
In one embodiment, the analysis result obtaining module 403 further includes:
and the abnormal image data acquisition sub-module is used for sending prompt information corresponding to the abnormal image data to the scheduling server and temporarily stopping analyzing the abnormal image data when the abnormal image data which fails in data security check is determined to exist in the image data according to the security verification result.
In one embodiment, the analysis result obtaining module 403 includes:
the face feature database acquisition sub-module is used for acquiring a face feature database corresponding to the converter station; the face data feature library comprises user face features associated with the converter station;
the face feature extraction submodule to be compared is used for acquiring the face feature to be compared corresponding to the image data;
and the first analysis result acquisition sub-module is used for generating illegal user intrusion information as an image analysis result when the matching degree between the human face features to be compared and each user human face feature in the human face data feature library is smaller than a preset similarity threshold value.
In one embodiment, the analysis result obtaining module 403 includes:
the license plate database acquisition sub-module is used for acquiring a license plate database corresponding to the convertor station; the license plate database comprises preset license plate information associated with the converter station;
the license plate information to be compared acquisition sub-module is used for acquiring license plate information to be compared corresponding to the image data;
and the second analysis result acquisition sub-module is used for generating illegal vehicle intrusion information as an image analysis result when the license plate information to be compared is not matched with each preset license plate information in the license plate database.
For specific limitations of the video monitoring device of the converter station, reference may be made to the above limitations on the video monitoring method of the converter station, and details are not repeated here. All or part of the modules in the video monitoring device of the converter station can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer arrangement is used for storing image data corresponding to the converter stations. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of video surveillance of a converter station.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
responding to a data distribution request sent by a scheduling server, and determining idle thread information corresponding to the edge server;
sending the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
when the image data is received, obtaining an image analysis result corresponding to the image data, and sending the image analysis result to a monitoring center so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
In one embodiment, the steps in the other embodiments described above are also implemented when the computer program is executed by a processor.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
responding to a data distribution request sent by a scheduling server, and determining idle thread information corresponding to the edge server;
sending the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
when the image data is received, obtaining an image analysis result corresponding to the image data, and sending the image analysis result to a monitoring center so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
In one embodiment, the computer program when executed by the processor also performs the steps in the other embodiments described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A converter station video monitoring method is applied to an edge server, and the method comprises the following steps:
responding to a data distribution request sent by a scheduling server, and determining idle thread information corresponding to the edge server;
sending the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
when the image data is received, obtaining an image analysis result corresponding to the image data, and sending the image analysis result to a monitoring center so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
2. The method of claim 1, wherein sending the idle thread information to the dispatch server comprises:
determining thread demand information corresponding to the data allocation request;
and when the idle thread information is greater than or equal to the thread requirement information, sending the idle thread information to the scheduling server.
3. The method of claim 1, wherein obtaining the image analysis result corresponding to the image data when the image data is received comprises:
when the image data is received, acquiring a security verification result corresponding to the image data;
according to the safety verification result, obtaining safety image data which passes data safety inspection from the image data, and registering the safety image data;
and acquiring an image analysis result corresponding to the registered safety image data.
4. The method of claim 3, further comprising:
and according to the safety verification result, when abnormal image data which do not pass the data safety check are determined to exist in the image data, sending prompt information corresponding to the abnormal image data to the scheduling server, and pausing the analysis of the abnormal image data.
5. The method of claim 1, wherein obtaining the image analysis result corresponding to the image data comprises:
acquiring a face data feature library corresponding to the converter station; the face data feature library comprises user face features associated with the converter station;
acquiring the face features to be compared corresponding to the image data;
and when the matching degree between the face features to be compared and each user face feature in the face data feature library is smaller than a preset similarity threshold, generating illegal user intrusion information as an image analysis result.
6. The method of claim 1, wherein obtaining the image analysis result corresponding to the image data comprises:
acquiring a license plate database corresponding to the convertor station; the license plate database comprises preset license plate information associated with the converter station;
acquiring license plate information to be compared corresponding to the image data;
and when the license plate information to be compared is not matched with each preset license plate information in the license plate database, generating illegal vehicle intrusion information as an image analysis result.
7. A converter station video surveillance system, the system comprising:
the edge server is used for responding to a data distribution request sent by the scheduling server, determining idle thread information corresponding to the edge server, and sending the idle thread information to the scheduling server;
the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
the edge server is further used for acquiring an image analysis result corresponding to the image data when the image data is received, and sending the image analysis result to a monitoring center;
and the monitoring center is used for determining whether to generate alarm information aiming at the converter station or not based on the image analysis result.
8. A converter station video monitoring apparatus, applied to an edge server, the apparatus comprising:
the idle thread information determining module is used for responding to a data distribution request sent by a scheduling server and determining idle thread information corresponding to the edge server;
an idle thread information sending module, configured to send the idle thread information to the scheduling server; the scheduling server is used for determining a target edge server from the edge servers based on idle thread information sent by the edge servers and sending image data corresponding to a converter station to be monitored to the target edge server;
and the analysis result acquisition module is used for acquiring an image analysis result corresponding to the image data when the image data is received, and sending the image analysis result to a monitoring center so as to trigger the monitoring center to determine whether to generate alarm information for the converter station based on the image analysis result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111251507.0A CN113691783A (en) | 2021-10-27 | 2021-10-27 | Converter station video monitoring method, system, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111251507.0A CN113691783A (en) | 2021-10-27 | 2021-10-27 | Converter station video monitoring method, system, device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113691783A true CN113691783A (en) | 2021-11-23 |
Family
ID=78588194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111251507.0A Pending CN113691783A (en) | 2021-10-27 | 2021-10-27 | Converter station video monitoring method, system, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113691783A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359025A (en) * | 2022-01-10 | 2022-04-15 | 成都智元汇信息技术股份有限公司 | Method for shunting and dispatching picture to center, edge picture recognition box and system |
| CN114708643A (en) * | 2022-06-02 | 2022-07-05 | 杭州智诺科技股份有限公司 | Computing power improving method for edge video analysis device and edge video analysis device |
| CN116389820A (en) * | 2023-03-28 | 2023-07-04 | 北京睿芯通量科技发展有限公司 | Video processing method, video processing device, electronic device and storage medium |
| CN116939171A (en) * | 2023-09-19 | 2023-10-24 | 南方电网数字电网研究院有限公司 | Power transmission line monitoring method, device and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279830A (en) * | 2013-05-28 | 2013-09-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Transformer substation or converter station accident handling cloud terminal remote support decision-making method and system |
| CN108600236A (en) * | 2018-04-28 | 2018-09-28 | 张红彬 | Video surveillance network intelligent information safety integrated management system |
| CN109194984A (en) * | 2018-11-09 | 2019-01-11 | 中山大学 | A kind of video frame dispatching method based on edge calculations |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN112463293A (en) * | 2020-11-18 | 2021-03-09 | 之江实验室 | Container-based expandable distributed double-queue dynamic allocation method in edge scene |
| CN113381511A (en) * | 2021-06-02 | 2021-09-10 | 深圳市莱达四维信息科技有限公司 | Online intelligent inspection system of transformer substation |
-
2021
- 2021-10-27 CN CN202111251507.0A patent/CN113691783A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279830A (en) * | 2013-05-28 | 2013-09-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Transformer substation or converter station accident handling cloud terminal remote support decision-making method and system |
| CN108600236A (en) * | 2018-04-28 | 2018-09-28 | 张红彬 | Video surveillance network intelligent information safety integrated management system |
| CN109194984A (en) * | 2018-11-09 | 2019-01-11 | 中山大学 | A kind of video frame dispatching method based on edge calculations |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
| CN112463293A (en) * | 2020-11-18 | 2021-03-09 | 之江实验室 | Container-based expandable distributed double-queue dynamic allocation method in edge scene |
| CN113381511A (en) * | 2021-06-02 | 2021-09-10 | 深圳市莱达四维信息科技有限公司 | Online intelligent inspection system of transformer substation |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359025A (en) * | 2022-01-10 | 2022-04-15 | 成都智元汇信息技术股份有限公司 | Method for shunting and dispatching picture to center, edge picture recognition box and system |
| CN114708643A (en) * | 2022-06-02 | 2022-07-05 | 杭州智诺科技股份有限公司 | Computing power improving method for edge video analysis device and edge video analysis device |
| CN116389820A (en) * | 2023-03-28 | 2023-07-04 | 北京睿芯通量科技发展有限公司 | Video processing method, video processing device, electronic device and storage medium |
| CN116939171A (en) * | 2023-09-19 | 2023-10-24 | 南方电网数字电网研究院有限公司 | Power transmission line monitoring method, device and computer equipment |
| CN116939171B (en) * | 2023-09-19 | 2024-03-26 | 南方电网数字电网研究院有限公司 | Power transmission line monitoring method, device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113691783A (en) | Converter station video monitoring method, system, device and computer equipment | |
| CN109783338B (en) | Recording processing method and device based on service information and computer equipment | |
| CN111222423B (en) | Target identification method and device based on operation area and computer equipment | |
| CN108229260B (en) | Identity information verification method and system | |
| CN109753848B (en) | Method, device and system for executing face recognition processing | |
| CN110557419A (en) | task processing method and device and cloud computing system | |
| CN110751675B (en) | Urban pet activity track monitoring method based on image recognition and related equipment | |
| CN112507314B (en) | Client identity verification method, device, electronic equipment and storage medium | |
| CN114155614B (en) | Method and system for identifying anti-violation behavior of operation site | |
| CN109325548B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN111241938A (en) | Face recognition method and device based on image verification and computer equipment | |
| CN110702240A (en) | Body temperature early warning method and device based on identity recognition | |
| CN111782383A (en) | Task allocation method, server, electronic terminal and computer readable storage medium | |
| CN110995745A (en) | Method and device for separating and identifying illegal machine card of Internet of things | |
| CN116755891A (en) | Event queue processing method and system based on multithreading | |
| CN103559438A (en) | Progress identification method and progress identification system | |
| CN112926491B (en) | User identification method, device, electronic equipment and storage medium | |
| CN115620243B (en) | Pollution source monitoring method and system based on artificial intelligence and cloud platform | |
| CN112235589B (en) | Live network identification method, edge server, computer equipment and storage medium | |
| CN114299476A (en) | Multi-channel monitoring video processing method, system, terminal and storage medium | |
| CN113920471A (en) | Remote monitoring method and device for production waste, computer equipment and storage medium | |
| CN113051981B (en) | Face recognition method and device | |
| CN112883879B (en) | False position identification method, system, electronic equipment and medium | |
| CN110543497A (en) | high-real-time deployment and control solution method and system | |
| CN113051307A (en) | Alarm signal analysis method, equipment, storage medium and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211123 |