Electric energy metering device detection method based on face recognition

Abstract

The invention discloses an electric energy metering device detection method based on face recognition. The method comprises the following steps: acquiring visual detection data of a plurality of visual angles in a preset area around an electric energy metering device; executing primary face recognition based on the visual detection data, and determining whether to start an equipment self-checking program according to a primary face recognition result; after the equipment self-checking program is started, whether secondary face recognition is executed or not is determined according to an equipment self-checking result; and determining whether to start the auxiliary detection equipment or not according to the secondary face recognition result. Identity verification is carried out through a face recognition technology, and the field detection efficiency and accuracy can be improved; secondary identity verification is added to the specific auxiliary detection device, it is ensured that only authorized personnel can execute operation, abnormal damage of the metering detection device or detected equipment caused by illegal operation or misoperation is prevented, and the safety of field detection is improved.

Description

Technical Field

[0001] This invention relates to the field of electrical energy detection technology, and in particular to a method for detecting electrical energy metering devices based on facial recognition. Background Technology

[0002] An electricity metering device is a measuring instrument based on modern electronic and computer technologies, capable of monitoring the power quality and power consumption in a power system in real time. The testing of electricity metering devices is used to monitor their operational status, which is crucial for ensuring the accuracy and reliability of metering results.

[0003] In existing technologies, the testing of electricity metering devices usually adopts on-site testing methods. By comparing the metering deviation between standard equipment (such as electricity meters or transformers) and the equipment under test under the same operating conditions, the error of the equipment under test is calculated. This method has the following problems: On-site testing usually relies on traditional methods such as keys, passwords or manual inspection, which are complicated to operate, have low testing efficiency, and are prone to misoperation during manual inspection, which can damage the metering device or testing instrument and pose significant safety hazards. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides a method for detecting electricity metering devices based on facial recognition. This method uses facial recognition to provide safety supervision and assistance during the detection process of electricity metering devices, thereby solving the problems of complex operation, low detection efficiency, and poor security in existing electricity metering device detection methods.

[0005] According to one aspect of the present invention, a method for detecting an electricity metering device based on face recognition is provided, comprising: acquiring visual detection data from multiple perspectives within a preset area surrounding the electricity metering device; performing a face recognition based on the visual detection data, and determining whether to initiate a device self-test program based on the result of the first face recognition; after initiating the device self-test program, determining whether to perform a second face recognition based on the result of the device self-test; and determining whether to activate an auxiliary detection device based on the result of the second face recognition; wherein the auxiliary detection device includes: a current auxiliary detection device and / or a temperature auxiliary detection device.

[0006] Optionally, after starting the device self-test program, determining whether to perform secondary face recognition based on the device self-test results includes: determining whether current-assisted detection and / or temperature-assisted detection need to be performed based on the device self-test results; and starting secondary face recognition when at least one of current-assisted detection or temperature-assisted detection needs to be performed.

[0007] Optionally, after starting the device self-test program, determining whether to perform secondary face recognition based on the device self-test result further includes: obtaining the self-test current in the device self-test result, and determining that current-assisted detection needs to be performed when the self-test current is greater than or equal to a preset current value; and / or obtaining the self-test temperature in the device self-test result, and determining that temperature-assisted detection needs to be performed when the self-test temperature exceeds a first preset temperature range.

[0008] Optionally, determining whether to activate the auxiliary detection device based on the secondary face recognition result includes: acquiring a face feature image and operation feature data based on the visual detection data; comparing the face feature image with image data stored in the first authorized database, and comparing the operation feature data with operation data stored in the second authorized database; and determining whether to activate the auxiliary detection device based on the comparison result.

[0009] Optionally, the step of acquiring facial feature images and operation feature data based on the visual detection data includes: decoding video frames of the visual detection data; performing facial recognition based on the decoded video frame images to obtain the facial feature images, and adding corresponding personnel codes and timestamps to single-frame images; cropping the images of personnel who pass facial recognition once to obtain regions of interest; and forming the operation feature data based on the regions of interest of multiple consecutive frames within a preset time period.

[0010] Optionally, the step of performing a face recognition based on the visual detection data and determining whether to start the device self-test program based on the face recognition result includes: acquiring a face feature image based on the visual detection data; comparing the face feature image with image data stored in a third authorized database; and determining whether to start the device self-test program based on the comparison result.

[0011] Optionally, after the auxiliary detection device is started, the face recognition-based power metering device detection method further includes: acquiring the electrical parameters of the power metering device and the current auxiliary detection device; issuing an electrical parameter abnormality warning when the electrical parameters are greater than a preset electrical parameter threshold, and controlling the current auxiliary detection device and the power metering device to shut down; and / or acquiring first operation detection data of the current auxiliary detection stage, determining whether there is improper operation based on the first operation detection data, and issuing an operation abnormality warning when improper operation is found.

[0012] Optionally, after the auxiliary detection device is started, the detection method further includes: acquiring the measured temperature value of the power metering device, issuing a temperature abnormality warning when the measured temperature value exceeds a second preset temperature range, and controlling the auxiliary temperature detection device and the power metering device to shut down; and / or acquiring the second operation detection data of the temperature auxiliary detection stage, determining whether there is any improper operation based on the second operation detection data, and issuing an operation abnormality warning when improper operation is found.

[0013] Optionally, the preset area is established based on the metrology and testing interaction area; the multiple perspectives include at least: a first perspective facing the metrology and testing interaction area and a second perspective away from the metrology and testing interaction area.

[0014] Optionally, the method for detecting an energy metering device based on face recognition further includes: modifying the authorization database of the primary face recognition and the secondary face recognition based on host computer software; and / or storing and displaying at least one of the visual detection data, the device self-test result, the primary face recognition result, and the secondary face recognition result based on the host computer software; wherein the host computer software is set on a local end and / or a remote end.

[0015] Based on the above technical features, the present invention has the following technical effects: Firstly, it improves detection efficiency and intelligence. By collecting visual detection data from the electricity metering device testing site and combining it with facial recognition technology, identity verification can be completed quickly and efficiently, achieving contactless identity verification. This improves detection efficiency while reducing contact points and lowering the risk of disease transmission. Secondly, it improves operational safety. By introducing two facial recognition steps, a second identity verification is added to the start-up control of the auxiliary testing equipment. This ensures that only authorized personnel can operate the electricity metering device, and the auxiliary testing equipment is started only after the personnel's identity verification is correct. This effectively prevents unauthorized access, illegal operation, or misoperation from causing abnormal damage to the metering testing device or the tested equipment, thereby improving the safety of on-site testing and providing a reliable basis for operational safety and accident tracing.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for detecting an energy metering device based on face recognition, provided in an embodiment of the present invention; Figure 2 A flowchart of another method for detecting an energy metering device based on face recognition provided in an embodiment of the present invention; Figure 3 A flowchart illustrating a high-current detection method for an energy metering device based on face recognition, provided as an embodiment of the present invention; Figure 4 This is a flowchart of a high and low temperature auxiliary detection method for an energy metering device based on face recognition, provided as an embodiment of the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] Figure 1 This is a flowchart illustrating a face recognition-based method for detecting electricity metering devices, provided as an embodiment of the present invention. This embodiment is applicable to on-site detection scenarios for electricity metering devices. Figure 1 As shown, the method for detecting an electricity metering device based on facial recognition includes: S1: Acquire visual detection data from multiple perspectives within a preset area surrounding the power metering device.

[0022] The preset area can be understood as a specific area of ​​interest pre-defined by software or hardware before the image acquisition system (such as a camera or webcam) begins capturing images or video streams. Optionally, the preset area is established based on the metering and testing interaction area. Multiple perspectives include at least a first perspective facing the metering and testing interaction area and a second perspective away from it. The metering and testing interaction area can be understood as the area where operators perform metering, testing, wiring, and other operations. Typically, the metering and testing interaction area includes, but is not limited to, display panels, meter boxes, and distribution cabinets.

[0023] Visual inspection data can be understood as images or video streams containing human faces and information related to the operation of electricity metering devices, captured by a camera or webcam. In this embodiment, visual inspection data includes at least static images and dynamic images.

[0024] Specifically, multiple acquisition devices (such as cameras or webcams) can be set up at different angles within the metrology and testing interaction area. When an operator enters the metrology and testing interaction area, the acquisition devices (such as cameras or webcams) automatically acquire images or video streams as visual inspection data.

[0025] It should be noted that after receiving the visual inspection data provided by the acquisition device, the visual inspection data can be preprocessed first, and a timestamp and device identifier can be added to the visual inspection data. The timestamp can be used to associate the operation record of the power metering device, and the device identifier can be understood as the code of the acquisition device, which is used for data management and traceability.

[0026] S2: Perform a face recognition based on visual detection data, and determine whether to start the device self-test program based on the face recognition result.

[0027] In this context, a single facial recognition scan can be understood as the initial identity verification performed upon the operator's arrival at the electricity metering device's testing site. In this embodiment, a facial (frontal or side profile) image can be extracted from visual inspection data using a facial recognition module, and identity verification is performed through image comparison. The device self-test procedure can be understood as a program used to obtain the operating status of the electricity metering device and / or the execution status of the testing procedures.

[0028] Specifically, facial recognition technology is used to extract the operator's face (front or side view) image from the visual detection data. This face image is then compared with the face image of an authorized person at the electricity metering device. If the face verification passes (i.e., the face image matches the face image of any authorized person at the electricity metering device), the current operator is determined to be an authorized person at the electricity metering device, and the device's self-test program is initiated to obtain the operating status and testing specifications of the electricity metering device. If the face verification fails (i.e., the face image does not match the face images of any authorized persons at the electricity metering device), the current operator is determined to be an unauthorized person at the electricity metering device, the electricity metering device is kept powered off, the operator is refused operation, and relevant information about the operation is recorded (including but not limited to: unauthorized personnel image, unauthorized operation time, and number of operation attempts).

[0029] S3: After starting the device self-test program, determine whether to perform secondary face recognition based on the device self-test results.

[0030] Secondary facial recognition can be understood as performing a second identity verification through facial recognition technology.

[0031] Optionally, after initiating the device self-test program, the system determines whether to perform secondary face recognition based on the self-test results. This includes: determining whether current-assisted detection and / or temperature-assisted detection are required based on the self-test results; and initiating secondary face recognition if at least one of current-assisted detection or temperature-assisted detection is required. Current-assisted detection can be understood as a performance testing step for high-current devices in the energy metering device; temperature-assisted detection can be understood as a performance testing step for the energy metering device under specific temperature conditions.

[0032] Specifically, when the equipment self-test results show that the current device under test is a high-current device, or when performance testing under specific temperature conditions needs to be performed, facial recognition technology is used to perform a second identity verification for the operator.

[0033] S4: Determine whether to activate the auxiliary detection equipment based on the results of the secondary face recognition.

[0034] The auxiliary testing equipment can be understood as equipment that assists in the testing of electricity metering performance in specific testing scenarios (including but not limited to: testing high-current equipment or using high and low temperature auxiliary equipment to test the impact of temperature conditions on equipment). Optionally, the auxiliary testing equipment of the present invention includes, but is not limited to: current auxiliary testing equipment and / or temperature auxiliary testing equipment. The current auxiliary testing equipment is used to assist in testing the performance of high-current equipment such as electricity meters / terminals in the electricity metering device; the temperature auxiliary testing equipment is used to apply specific temperature conditions (including but not limited to: low temperature conditions, medium temperature conditions, and high temperature conditions) during the performance testing process of the electricity metering device.

[0035] In embodiments of the present invention, the current-assisted detection device and the temperature-assisted detection device can be integrated into the power metering device, and the current-assisted detection device, the temperature-assisted detection device, and other auxiliary detection devices can be started or stopped by relay switching.

[0036] Specifically, if the secondary facial verification passes, indicating the operator is an authorized auxiliary detection personnel, the corresponding auxiliary detection equipment (such as current auxiliary detection equipment or temperature auxiliary detection equipment) is activated, allowing the operator to proceed with the next detection operation. If the secondary facial verification fails, indicating the operator is not an authorized auxiliary detection personnel, the auxiliary detection equipment (such as current auxiliary detection equipment or temperature auxiliary detection equipment) remains powered off, preventing the operator from performing the operation, and recording the relevant information for this operation. For example, if the current auxiliary detection equipment needs to be activated after the secondary facial verification passes, the operating status of the relay in the current auxiliary detection equipment is checked. If the relay is not connected, the current auxiliary detection equipment is activated by switching the relay's on / off state. Similarly, if the temperature auxiliary detection equipment needs to be activated after the secondary facial verification passes, the operating status of the relay in the temperature auxiliary detection equipment is checked. If the relay is not connected, the temperature auxiliary detection equipment is activated by switching the relay's on / off state.

[0037] Therefore, the technical solution of this invention uses facial recognition to conduct safety supervision and assist in the testing process of electricity metering devices, solving the problems of complex operation, low testing efficiency, and poor security of existing electricity metering device testing methods. By collecting visual testing data at the testing site of the electricity metering device and combining it with facial recognition technology, identity verification can be completed quickly and efficiently, achieving contactless identity verification, which can improve testing efficiency, reduce contact points, and reduce the risk of disease transmission. By introducing two facial recognition steps, a second identity verification is added to the start control of the auxiliary testing equipment, ensuring that only authorized personnel can operate the electricity metering device, and the auxiliary testing equipment is started only after the personnel's identity verification is correct. This effectively prevents unauthorized access, illegal operation, or misoperation from causing abnormal damage to the metering testing device or the tested equipment, improving the safety of on-site testing, and providing a reliable basis for operational safety and accident tracing.

[0038] In some optional embodiments, the device self-test results can obtain the operating status of the power metering device during the testing process. Based on this, the above step S3 specifically includes: obtaining the self-test current in the device self-test results, and determining that current-assisted detection needs to be performed when the self-test current is greater than or equal to a preset current value; and / or, obtaining the self-test temperature in the device self-test results, and determining that temperature-assisted detection needs to be performed when the self-test temperature exceeds a first preset temperature range.

[0039] The self-test current can be understood as the maximum or average current flowing through the current detection circuit of the energy metering device during the detection process. The self-test temperature can be understood as the highest or average temperature inside the energy metering device during the detection process.

[0040] In this embodiment, the preset current value and the first preset temperature range are set based on the detection specifications of the power metering device, and their specific values ​​are not limited.

[0041] Specifically, if the self-test current is greater than or equal to the preset current value, the device under test is determined to be a high-current device. Before initiating current-assisted detection, the operator undergoes a second identity verification using facial recognition technology. If the self-test temperature exceeds the first preset temperature range, performance testing under specific temperature conditions is required. Before initiating temperature-assisted detection, the operator undergoes a second identity verification using facial recognition technology. If the self-test current is less than the preset current value and the self-test temperature is within the first preset temperature range, the current testing procedure is determined to be a routine procedure, and no second identity verification is required. The operator can then conduct on-site testing of the electricity metering device within the authorized scope.

[0042] In some alternative embodiments, the device self-test results can obtain the execution status of the testing procedure. Based on this, step S3 above specifically includes: obtaining the current execution status of the testing procedure displayed in the device self-test results; when the current execution status of the testing procedure is high current testing, determining that current-assisted testing needs to be performed; and / or, when the current execution status of the testing procedure is high and low temperature equipment testing, determining that temperature-assisted testing needs to be performed.

[0043] Therefore, the technical solution of the present invention improves the detection efficiency of the electricity metering device by adaptively adjusting the identity verification strategy after obtaining the operating status or detection procedure execution status of the electricity metering device.

[0044] Figure 2 A flowchart illustrating another method for detecting an electricity metering device based on face recognition, provided in an embodiment of the present invention, is shown below. Figure 1 Based on the illustrated embodiment, a specific implementation of a secondary face recognition technology is shown as an example. See also... Figure 2 As shown, in step S4 above, determining whether to activate the auxiliary detection device based on the secondary face recognition result specifically includes the following steps: S401: Obtain facial feature images and operational feature data based on visual inspection data.

[0045] In this context, the facial feature image can be understood as an image that can represent the identity information of the operator. This facial feature image contains at least the pixel coordinates of five key points: the eyes, the tip of the nose, and the two corners of the mouth, which facilitates facial pose estimation and data space alignment.

[0046] Operational characteristic data can be understood as dynamic data that characterizes the operator's work process.

[0047] S402: Compare the facial feature image with the image data stored in the first authorized database, and compare the operation feature data with the operation data stored in the second authorized database.

[0048] The first authorized database can be understood as a database that stores facial images of authorized personnel who assist in detection.

[0049] The second authorized database can be understood as a database that stores the standardized operating procedures for wiring, debugging, and testing during the use of auxiliary testing equipment.

[0050] S403: Determine whether to activate the auxiliary testing equipment based on the comparison results.

[0051] Specifically, during the secondary face recognition process, facial feature image extraction and operation behavior feature extraction are performed based on the visual detection data collected in the interaction area of ​​the auxiliary detection device. The extracted facial feature image is compared with the image data stored in the first authorized database, and the extracted operation feature data is compared with the operation data stored in the second authorized database. If the facial feature image matches any image data stored in the first authorized database, and the operation feature data matches any operation data stored in the second authorized database, the secondary identity verification is deemed successful, and there is no improper operation behavior; the auxiliary detection device is then activated. If the facial feature image does not match any image data stored in the first authorized database, or if the operation feature data does not match any operation data stored in the second authorized database, the verification is deemed unsuccessful, and the auxiliary detection device is not activated.

[0052] Optionally, facial feature images and operation feature data are obtained based on visual detection data, including: decoding video frames of the visual detection data; performing facial recognition based on the decoded video frame images to obtain facial feature images, and adding corresponding personnel codes and timestamps to single frame images; cropping the images of personnel who pass facial recognition once to obtain regions of interest; and forming operation feature data based on regions of interest from multiple consecutive frames within a preset time period.

[0053] Personnel coding can be understood as codes used to identify different individuals in a dynamic environment. The region of interest can be understood as the interaction area for different operational behaviors (such as wiring, debugging, meter testing, etc.). The preset time is established based on the timestamps of the start and end actions of the operation.

[0054] Specifically, a face recognition model can be trained using faces viewed from different angles (yaw, pitch, roll) and under different occlusions (masks, glasses, helmets). Decoded video frame images are then imported into the trained model for face recognition. Affine transformations are performed based on key points (e.g., 5 points) to output standardized facial feature images. Images are cropped based on standardized operational behaviors of electricity metering devices (e.g., meter reading, equipment debugging, opening the electrical box, meter testing, etc.), capturing key postures during the operation to obtain images of different interactive regions (i.e., regions of interest). Based on timestamps, the regions of interest from multiple consecutive frames within a preset time period are stacked into a single data volume, and the corresponding operational feature data is output.

[0055] Optionally, a face recognition is performed based on visual detection data, and a device self-test procedure is initiated based on the face recognition result, including: acquiring a face feature image based on visual detection data; comparing the face feature image with image data stored in a third-party authorized database, and initiating a device self-test procedure based on the comparison result.

[0056] Among them, the facial feature image can be understood as an image that can represent the identity information of the operator. This facial feature image contains at least the pixel coordinates of five key points: the eyes, the tip of the nose, and the two corners of the mouth, facilitating facial pose estimation and data spatial alignment. The third authorization database can be understood as a database storing facial images of authorized personnel for the electricity metering device.

[0057] Specifically, during a face recognition operation, facial feature image extraction is performed based on visual detection data collected within a preset area around the electricity metering device. The extracted facial feature image is then compared with image data stored in a third-party authorized database. If the facial feature image obtained from a face recognition operation matches any image data stored in the third-party authorized database, the identity verification is deemed successful, and the device self-test program is initiated. If the facial feature image obtained from a face recognition operation does not match any of the image data stored in the third-party authorized database, the identity verification is deemed unsuccessful, and the operator is prohibited from operating the electricity metering device.

[0058] Therefore, the technical solution of the present invention improves the security and operational standardization of equipment in specific testing scenarios by setting up different authorized personnel databases and differentiating the authorization permissions for different devices.

[0059] Figure 3 This is a flowchart illustrating a high-current detection method for an electricity metering device based on face recognition, provided in an embodiment of the present invention. Figure 1 Based on the illustrated embodiment, an anomaly detection strategy during the high-current detection phase is presented. See also... Figure 3 As shown, the detection method specifically includes the following steps: S1: Acquire visual detection data from multiple perspectives within a preset area surrounding the power metering device.

[0060] S2: Perform a face recognition based on visual detection data, and determine whether to start the device self-test program based on the face recognition result.

[0061] S3: After starting the device self-test program, determine whether to perform secondary face recognition based on the device self-test results.

[0062] S4: Determine whether to activate the auxiliary detection equipment based on the results of the secondary face recognition.

[0063] S501: Starting current auxiliary detection device.

[0064] S502: Obtain the electrical parameters of the power metering device and the current auxiliary detection device. When the electrical parameters exceed the preset electrical parameter threshold, issue an electrical parameter abnormality warning and control the current auxiliary detection device and the power metering device to shut down.

[0065] Typically, electrical parameters include, but are not limited to, current and voltage.

[0066] S503: Acquire the first operation detection data of the current-assisted detection stage, and determine whether there is any improper operation based on the first operation detection data. If improper operation is found, issue an operation abnormality warning.

[0067] The first operational detection data can be understood as data that characterizes the operator's operational behavior during the current-assisted detection phase.

[0068] Specifically, after successful secondary authentication, the current-assisted detection device is activated, enabling operators to perform performance testing on high-current equipment according to procedures. The device monitors the electrical parameters of the power metering device and the current-assisted detection device in real time. If electrical parameters exceed preset thresholds or improper operation is detected, an abnormal warning is issued (e.g., an alarm sound), and the current-assisted detection device and power metering device are shut down. Current and voltage values ​​are recorded in the system's alarm database, and the surrounding personnel hear the alarm, ensuring the safety of on-site testing operations. During the current-assisted detection phase, initial operation detection data is continuously acquired through image analysis of visual detection data. When improper operation is detected, an operational abnormality warning is issued.

[0069] Figure 4 This is a flowchart illustrating a high and low temperature auxiliary detection method for an electricity metering device based on face recognition, provided in an embodiment of the present invention. Figure 1 Based on the illustrated embodiment, an anomaly detection strategy for the high and low temperature auxiliary detection stage is shown. See also Figure 4 As shown, the detection method specifically includes the following steps: S1: Acquire visual detection data from multiple perspectives within a preset area surrounding the power metering device.

[0070] S2: Perform a face recognition based on visual detection data, and determine whether to start the device self-test program based on the face recognition result.

[0071] S3: After starting the device self-test program, determine whether to perform secondary face recognition based on the device self-test results.

[0072] S4: Determine whether to activate the auxiliary detection equipment based on the results of the secondary face recognition.

[0073] S601: Start the temperature auxiliary detection device.

[0074] S602: Obtain the actual temperature value of the power metering device, and when the actual temperature value exceeds the second preset temperature range, issue a temperature abnormality warning and control the temperature auxiliary detection equipment and power metering device to shut down.

[0075] S603: Acquire the second operation detection data of the temperature auxiliary detection stage, and determine whether there is any improper operation based on the second operation detection data. If improper operation is found, issue an operation abnormality warning.

[0076] The second operational detection data can be understood as data that characterizes the operator's operational behavior during the temperature-assisted detection phase.

[0077] Specifically, operators perform performance tests on the electricity metering device under different temperature conditions. Based on the temperature requirements of the operating specifications, operators select different temperature levels, such as those corresponding to low, medium, and high temperatures, and the device automatically performs tests and saves the data. During the high and low temperature auxiliary testing phase, sensors monitor the actual temperature values ​​of the electricity metering device in real time. If the measured temperature value exceeds the second preset temperature range, a temperature anomaly warning is issued, controlling the shutdown of the temperature auxiliary testing equipment and the electricity metering device, and recording the high temperature value and other data in the system alarm database to ensure that the equipment is not damaged due to excessive temperature. During the high and low temperature auxiliary testing phase, second operational testing data is continuously acquired through image analysis of visual inspection data. When improper operation is detected, an operational anomaly warning is issued.

[0078] Optionally, the method for detecting electricity metering devices based on facial recognition also includes: modifying the authorization database for primary and secondary facial recognition based on host computer software; and / or storing and displaying at least one of visual inspection data, device self-inspection results, primary facial recognition results, and secondary facial recognition results based on host computer software; wherein the host computer software is set on a local end and / or a remote end.

[0079] Specifically, the host computer software is used to control equipment, interact with data, process data, display data, and store statistical results and data in all testing processes. For example, it collects visual inspection data, enters data into the authorized database, processes facial recognition results, records high current test data and high and low temperature test data, and controls the start-up and shutdown of auxiliary testing equipment.

[0080] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0081] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A face recognition-based electric energy metering device detection method, characterized in that, The method comprises: acquiring visual detection data of multiple perspectives in a preset area around the electric energy metering device; performing a first face recognition based on the visual detection data, and determining whether to start a device self-checking program according to a first face recognition result; after starting the device self-checking program, determining whether to perform a second face recognition according to a device self-checking result; determining whether to start an auxiliary detection device according to a second face recognition result; wherein the auxiliary detection device comprises a current auxiliary detection device and / or a temperature auxiliary detection device.

2. The face recognition-based electric energy metering device detection method according to claim 1, characterized in that, After starting the device self-checking program, the method further comprises: determining whether to perform current auxiliary detection and / or temperature auxiliary detection according to the device self-checking result; when at least one of current auxiliary detection or temperature auxiliary detection is needed, starting the second face recognition. 3.The face recognition based electric energy metering device detection method of claim 2, wherein, After starting the device self-checking program, the method further comprises: acquiring a self-checking current in the device self-checking result, and determining that current auxiliary detection is needed when the self-checking current is greater than or equal to a preset current value; and / or acquiring a self-checking temperature in the device self-checking result, and determining that temperature auxiliary detection is needed when the self-checking temperature is out of a first preset temperature range. 4.The face recognition based electric energy metering device detection method of claim 1, wherein, The method further comprises: acquiring a face feature image and operation feature data based on the visual detection data; comparing the face feature image with image data stored in a first authorized database, and comparing the operation feature data with operation data stored in a second authorized database; determining whether to start the auxiliary detection device according to a comparison result.

5. The face recognition-based electric energy metering device detection method according to claim 4, characterized in that, The method further comprises: video frame decoding the visual detection data; performing face recognition based on the decoded video frame image to acquire the face feature image, and adding corresponding personnel code and time stamp in a single frame image; cropping an image of a personnel who passes the first face recognition to obtain a region of interest; forming the operation feature data based on the region of interest of continuous multiple frame images within a preset time. 6.The face recognition based electric energy metering device detection method of claim 1, wherein, The method further comprises: acquiring a face feature image based on the visual detection data; comparing the face feature image with image data stored in a third authorized database; determining whether to start the device self-checking program according to a comparison result.

7. The face recognition based electric energy metering device detection method according to any one of claims 1-6, characterized in that, After starting the auxiliary detection device, the method further comprises: acquiring an electric parameter of the electric energy metering device and the current auxiliary detection device, issuing an electric parameter abnormality warning when the electric parameter is greater than a preset electric parameter threshold, and controlling the current auxiliary detection device and the electric energy metering device to shut down; and / or The first operation detection data of the current auxiliary detection stage is acquired, and whether there is an operation improper behavior is determined based on the first operation detection data, and an operation abnormality warning is issued when there is an operation improper behavior.

8. The face recognition based electric energy metering device detection method according to any one of claims 1-6, characterized in that, After the auxiliary detection device is started, the detection method further comprises: acquiring a temperature measured value of the electric energy metering device, issuing a temperature abnormality warning when the temperature measured value exceeds a second preset temperature range, and controlling the temperature auxiliary detection device and the electric energy metering device to shut down; and / or, The second operation detection data of the temperature auxiliary detection stage is acquired, and whether there is an operation improper behavior is determined based on the second operation detection data, and an operation abnormality warning is issued when there is an operation improper behavior.

9. The face recognition based electric energy metering device detection method according to any one of claims 1-6, characterized in that, The preset area is established based on a metering detection interaction area; The multiple perspectives at least include a first perspective toward the metering detection interaction area and a second perspective away from the metering detection interaction area.

10. The face recognition based electric energy metering device detection method according to any one of claims 1-6, characterized in that, Further comprising: The authorization database of the first face recognition and the second face recognition is modified based on the host computer software; And / or, At least one of the visual detection data, the device self-checking result, the first face recognition result, and the second face recognition result is stored and displayed based on the host computer software; The host computer software is arranged at a local end and / or a remote end.

Images