An AI recognition-based power operation environment monitoring system, method and device

Abstract

The embodiment of the application relates to an AI recognition-based power operation environment monitoring system, method and equipment, the system comprising a data acquisition unit, a distance calculation unit and a pre-warning prompting unit. The AI recognition-based power operation environment monitoring system acquires three-dimensional data of power operation in real time based on the data acquisition unit, calculates the spatial distance between power equipment and the human body according to the three-dimensional data through the distance calculation unit, and finally judges whether the spatial distance exceeds the distance threshold value to issue a pre-warning through the pre-warning prompting unit, so as to realize the monitoring of the power operation environment. This monitoring mode does not need manual participation, has fast response timeliness, can also discover the hidden danger of power operation in time, avoids causing safety accidents, and solves the technical problems that the existing power operation environment monitoring cannot guarantee the response timeliness and the control effectiveness.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, and particularly relates to a power operation environment monitoring system, method and equipment based on AI recognition. BACKGROUND

[0002] The power operation has operation conditions such as large data volume, wide distribution, complex environment and uneven construction personnel level, which brings great control difficulty to power operation environment monitoring. In the power operation environment monitoring process, operation hidden dangers cannot be found or investigated in the first time, causing safety accidents.

[0003] The main function of the existing power operation environment monitoring is post-facto evidence collection, remote monitoring and on-site control are implemented through various conventional monitoring terminals, which need manual real-time monitoring of computer screens and cannot prevent risks. At the same time, with the increase of the number of monitoring terminal devices, the workload of manual verification of power operation environment monitoring mass data increases day by day, and the response timeliness and control effectiveness cannot be guaranteed. SUMMARY

[0004] The embodiments of the present application provide a power operation environment monitoring system, method and equipment based on AI recognition, which are used to solve the technical problem that the existing power operation environment monitoring needs manual checking, and the response timeliness and control effectiveness cannot be guaranteed.

[0005] In order to achieve the above purpose, the embodiments of the present application provide the following technical solutions:

[0006] A power operation environment monitoring system based on AI recognition comprises a data acquisition unit, a distance calculation unit and a warning prompt unit.

[0007] The data acquisition unit is used to collect three-dimensional data of the power operation environment in real time and transmit the three-dimensional data to the distance calculation unit, wherein the three-dimensional data comprises power equipment images and human body posture images.

[0008] The distance calculation unit is used to calculate the spatial distance between the power equipment and the human body according to the three-dimensional data, and send the spatial distance to the warning prompt unit.

[0009] The warning prompt unit is used to judge whether the spatial distance exceeds a distance threshold, and if so, issue a warning prompt.

[0010] Preferably, the distance calculation unit comprises a marking subunit and a calculation subunit.

[0011] The marking subunit is used to mark one positioning point on the power equipment image and mark a plurality of key points on the human body posture image.

[0012] The calculating sub-unit is configured to calculate the distance between each key point and the positioning point to obtain a distance set, and select the smallest distance in the distance set as the spatial distance.

[0013] The positioning point is the position of the power equipment in the power equipment image, and the key point is the position of the human body part in the human body posture image.

[0014] Preferably, the calculating sub-unit obtains the spatial distance by using a spatial distance calculation formula, and the spatial distance calculation formula is as follows:

[0015]

[0016] In the formula, x is the positioning point, x i , and x j are the horizontal coordinate value and the vertical coordinate value of the positioning point in a three-dimensional coordinate system, d' is the spatial distance, d ij is the distance between the horizontal and vertical coordinates of the positioning point relative to any key point in the three-dimensional space, d ik is the distance between the horizontal coordinate of the kth key point and the positioning point, d kj is the distance between the vertical coordinate of the kth key point and the positioning point, K is the set of all key points, D i is the set of horizontal coordinate values of all key points and the positioning point, and D j is the set of vertical coordinate values of all key points and the positioning point.

[0017] Preferably, the marking sub-unit is further configured to obtain the first gray scale and the second gray scale of the same joint node of two adjacent human body posture images in the three-dimensional data, calculate the pixel gray scale difference value according to the first gray scale and the second gray scale, and if the pixel gray scale difference value is not 0, mark the joint node as a key point, so as to complete the marking of the plurality of key points of the human body posture image.

[0018] Preferably, the marking sub-unit is further configured to mark the joint node as a key point if the pixel gray scale difference value is 0.

[0019] The application further provides a monitoring method of an AI recognition-based power operation environment monitoring system, including the following steps:

[0020] Real-time acquisition of three-dimensional data of a power operation environment, wherein the three-dimensional data includes a power equipment image and a human body posture image;

[0021] Calculation of the spatial distance between the power equipment and the human body according to the three-dimensional data;

[0022] If the spatial distance exceeds a distance threshold, a pre-warning prompt is issued.

[0023] Preferably, the spatial distance between the power equipment and the human body is calculated according to the three-dimensional data, comprising:

[0024] A positioning point is marked on the power equipment image, and a plurality of key points are marked on the human body posture image;

[0025] The spatial distance is calculated according to the positioning point and the key points by using a spatial distance calculation formula, wherein the spatial distance calculation formula is:

[0026]

[0027] In the formula, x is the positioning point, x i and x j are the horizontal coordinate value and the vertical coordinate value of the positioning point in the three-dimensional space coordinate system, d' is the spatial distance, d ij is the distance between the horizontal and vertical coordinates of the positioning point relative to any key point in the three-dimensional space, d ik is the distance between the horizontal coordinate of the kth key point and the positioning point, d kj is the distance between the vertical coordinate of the kth key point and the positioning point, K is the set of all key points, D i is the set of horizontal coordinate values of all key points connected to the positioning point, and D j is the set of vertical coordinate values of all key points connected to the positioning point.

[0028] Preferably, the content of marking a plurality of key points on the human body posture image comprises:

[0029] The first gray scale and the second gray scale of the same joint node of the adjacent two human body posture images in the three-dimensional data are obtained;

[0030] The pixel gray scale difference value is calculated according to the first gray scale and the second gray scale;

[0031] If the pixel gray scale difference value is not 0, the joint node is marked as a key point, so as to complete the marking of a plurality of key points on the human body posture image.

[0032] The application also provides a power operation environment monitoring device, comprising a camera device, wherein a control module is arranged on the camera device, and the control module is used to execute the monitoring method of the AI recognition-based power operation environment monitoring system.

[0033] The application also provides a terminal device, comprising a processor and a memory;

[0034] The memory is used to store program codes and transmit the program codes to the processor.

[0035] The processor is configured to execute the monitoring method of the AI recognition-based power operation environment monitoring system according to the instructions in the program code.

[0036] From the above technical solutions, the embodiments of the present application have the following advantages:

[0037] The AI recognition-based power operation environment monitoring system comprises a data acquisition unit, a distance calculation unit and a warning prompt unit. The data acquisition unit is configured to acquire three-dimensional data of a power operation environment in real time and transmit the three-dimensional data to the distance calculation unit. The three-dimensional data comprises power equipment images and human posture images. The distance calculation unit is configured to calculate a spatial distance between the power equipment and the human body according to the three-dimensional data and transmit the spatial distance to the warning prompt unit. The warning prompt unit is configured to determine whether the spatial distance exceeds a distance threshold. If the spatial distance exceeds the distance threshold, a warning prompt is issued. The AI recognition-based power operation environment monitoring system acquires three-dimensional data of a power operation in real time based on the data acquisition unit, calculates a spatial distance between the power equipment and the human body according to the three-dimensional data through the distance calculation unit, and finally determines whether the spatial distance exceeds a distance threshold to issue a warning through the warning prompt unit, thereby monitoring the power operation environment. This monitoring method does not require human participation, has a fast response time, can timely discover hidden dangers of the power operation, avoids causing safety accidents, and solves the technical problem that the existing power operation environment monitoring cannot guarantee the response timeliness and the effectiveness of management and control. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0039] Figure 1 The AI recognition-based power operation environment monitoring system described in the embodiments of the present application is shown in the framework diagram.

[0040] Figure 2 The steps of the monitoring method of the AI recognition-based power operation environment monitoring system described in the embodiments of the present application are shown in the step flowchart. DETAILED DESCRIPTION

[0041] In order to make the inventive purposes, features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the following described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0042] Therefore, the embodiments of the present application provide an AI recognition-based power operation environment monitoring system, method and device, which are used to solve the technical problems that the existing power operation environment monitoring cannot guarantee the response timeliness and the control effectiveness.

[0043] Embodiment one:

[0044] Figure 1 The framework diagram of the AI recognition-based power operation environment monitoring system described in the embodiments of the present application.

[0045] As Figure 1 shown, the embodiments of the present application provide an AI recognition-based power operation environment monitoring system, which comprises a data acquisition unit 10, a distance calculation unit 20 and a pre-warning prompting unit 30.

[0046] In the embodiments of the present application, the data acquisition unit 10 is used to collect three-dimensional data of the power operation environment in real time and transmit the three-dimensional data to the distance calculation unit 20, and the three-dimensional data comprises power equipment images and human body posture images.

[0047] It should be noted that the data acquisition unit 10 is mainly used to collect three-dimensional data of the power operation environment in real time, so as to facilitate the construction of the spatial coordinate system of the power operation environment in the three-dimensional model according to the three-dimensional data of the power operation environment collected in real time, and to lay a foundation for the subsequent calculation of the spatial distance between the power equipment and the power worker. In the present embodiment, the human body posture image refers to the image of the power worker during the working process in the power operation environment. The power equipment image refers to the image of the power equipment in the power operation environment. Among them, taking the human body as the reference object, the power equipment is in a relatively static state, and the human body is in a relatively dynamic state, that is, the human body posture image comprises an image sequence collected according to the human body in the relatively dynamic state.

[0048] In the embodiments of the present application, the distance calculation unit 20 is used to calculate the spatial distance between the power equipment and the human body according to the three-dimensional data, and send the spatial distance to the pre-warning prompting unit 30.

[0049] It should be noted that the distance calculation unit 20 can calculate the spatial distance between the power equipment and the human body in the spatial coordinate system according to the three-dimensional data collected by the data acquisition unit 10.

[0050] In the embodiment of the present application, the early warning prompting unit 30 is configured to determine whether the distance exceeds the distance threshold value, and if the distance exceeds the distance threshold value, an early warning prompt is sent.

[0051] It should be noted that the early warning prompting unit 30 can compare the spatial distance calculated by the distance calculation unit 20 with the distance threshold value, and only when the spatial distance is greater than the distance threshold value, an early warning prompt is sent, so as to monitor the power operation environment. In this embodiment, the AI recognition-based power operation environment monitoring system can respond in time and send an early warning prompt according to the real-time collected three-dimensional data. Compared with the existing data of the power operation environment checked by artificial, the AI recognition-based power operation environment monitoring system does not need human participation, has fast response time, and can also timely find the hidden danger of power operation to avoid causing safety accidents. The distance threshold value can be set according to requirements, which is not limited here.

[0052] The AI recognition-based power operation environment monitoring system provided by the present application comprises a data acquisition unit, a distance calculation unit and an early warning prompting unit. The data acquisition unit is configured to collect three-dimensional data of a power operation environment in real time and transmit the three-dimensional data to the distance calculation unit. The three-dimensional data comprises a power equipment image and a human body posture image. The distance calculation unit is configured to calculate the spatial distance between the power equipment and the human body according to the three-dimensional data and send the spatial distance to the early warning prompting unit. The early warning prompting unit is configured to determine whether the spatial distance exceeds a distance threshold value, and if the spatial distance exceeds the distance threshold value, an early warning prompt is sent. The AI recognition-based power operation environment monitoring system collects three-dimensional data of a power operation in real time based on the data acquisition unit, calculates the spatial distance between the power equipment and the human body according to the three-dimensional data through the distance calculation unit, and finally determines whether the spatial distance exceeds the distance threshold value through the early warning prompting unit to send an early warning, so as to monitor the power operation environment. This monitoring method does not need human participation, has fast response time, can also timely find the hidden danger of power operation to avoid causing safety accidents, and solves the technical problem that the existing power operation environment monitoring exists artificial checking, response timeliness and control effectiveness cannot be guaranteed.

[0053] In an embodiment of the present application, the distance calculation unit 20 comprises a marking subunit and a calculation subunit.

[0054] The marking subunit is configured to mark a positioning point on the power equipment image and mark a plurality of key points on the human body posture image.

[0055] The calculating subunit is configured to calculate the distance between each key point and the positioning point to obtain a distance set, and select the smallest distance in the distance set as the spatial distance.

[0056] The positioning point is the position of the power equipment in the power equipment image, and the key point is the position of the human body part in the human body posture image.

[0057] It should be noted that before the distance calculating unit calculates the spatial distance, the position of the power equipment in the power equipment image and the motion point of the human body posture image need to be marked to obtain a positioning point and a plurality of key points. Then, the distance between each key point and the positioning point can be calculated by using a conventional distance formula or a spatial cosine theorem formula to obtain a distance set composed of the distances between all key points and the positioning point, and the smallest distance in the distance set is selected as the spatial distance. For example, if the coordinates of any key point are (a i , a j ), the distance b between the key point and the positioning point is calculated as follows: b is the straight-line distance between the two points, a i , and a j are the horizontal coordinate value and the vertical coordinate value of the key point in the spatial coordinate system, respectively.

[0058] In an embodiment of the present application, the calculating subunit obtains the spatial distance by using a spatial distance calculation formula, which is as follows:

[0059]

[0060] In the formula, x is the positioning point, x i , and x j are the horizontal coordinate value and the vertical coordinate value of the positioning point in the three-dimensional spatial coordinate system, respectively, d' is the spatial distance, d ij is the distance between the horizontal and vertical coordinates of the positioning point in the three-dimensional space relative to any key point, d ik is the distance between the horizontal coordinates of the kth key point and the positioning point, d kj is the distance between the vertical coordinates of the kth key point and the positioning point, K is the set of all key points, D i is the set of the horizontal coordinate values of all key points and the positioning point, and D j is the set of the vertical coordinate values of all key points and the positioning point.

[0061] It should be noted that before the calculation subunit calculates the distance between each key point and the positioning point, each key point is connected with the positioning point to construct a matrix relationship graph between the power equipment and the human body in a space coordinate system constructed by the power equipment image and the human posture image, and the distance between each key point and the positioning point is calculated according to the matrix relationship graph and a space distance calculation formula, and the space distance is obtained from all the distances.

[0062] In an embodiment of the present application, the marking subunit is further configured to obtain a first gray scale and a second gray scale of the same joint node of two adjacent human posture images in the three-dimensional data, calculate a pixel gray scale difference value according to the first gray scale and the second gray scale, and if the pixel gray scale difference value is not 0, mark the joint node as a key point to complete the marking of the plurality of key points on the human posture image; if the pixel gray scale difference value is 0, do not mark the joint node as a key point.

[0063] It should be noted that before the AI recognition-based power operation environment monitoring system marks the human posture image, the human posture image is denoised by using the difference method, and then the gray scale of the human posture image is calculated to track the real-time change of the human posture, that is, to confirm the position of the marked key point. In this embodiment, the key point is also referred to as a motion point of the human body.

[0064] In an embodiment of the present application, the AI recognition-based power operation environment monitoring system calculates the pixel gray scale difference value by using the calculation formula of the pixel gray scale difference absolute value according to the first gray scale and the second gray scale. , wherein G is the pixel gray scale difference value, I0 is the numerical value of the first gray scale, and I 0+1 is the second gray scale value.

[0065] In an embodiment of the present application, the AI recognition-based power operation environment monitoring system takes the positioning point of the relatively stationary power equipment as the center, judges whether the contact between the human body and the power equipment is within a safe distance range by calculating the space distance between the human body and the power equipment, does not need to wear any sensor, and has the characteristics of high convenience and fast identification response compared with inertial identification and optical identification. The AI recognition-based power operation environment monitoring system uses three-dimensional scene structuring technology, image comparison algorithm, human body tracking algorithm and other technologies to monitor the human action information in the power operation environment, realizes risk early warning through analysis, and provides support for sudden situations in the operation site.

[0066] Embodiment two:

[0067] Figure 2 The monitoring method of the AI recognition-based power operation environment monitoring system is described in the embodiment of the present application.

[0068] As Figure 2 shown, the embodiment of the present application also provides a monitoring method of an AI recognition-based power operation environment monitoring system, comprising the following steps:

[0069] S1. Real-time acquisition of three-dimensional data of the power operation environment, the three-dimensional data comprising power equipment images and human body posture images;

[0070] S2. Calculation of the spatial distance between the power equipment and the human body according to the three-dimensional data;

[0071] S3. If the spatial distance exceeds the distance threshold, a pre-warning prompt is issued.

[0072] In S2 of the embodiment of the present application, the calculation of the spatial distance between the power equipment and the human body according to the three-dimensional data comprises:

[0073] marking a positioning point on the power equipment image and marking a plurality of key points on the human body posture image;

[0074] calculating the spatial distance according to the positioning point and the key points by using a spatial distance calculation formula, the spatial distance calculation formula being:

[0075]

[0076] In the formula, x is the positioning point, x i and x j are the horizontal coordinate value and the vertical coordinate value of the positioning point in the three-dimensional space coordinate system respectively, d' is the spatial distance, d ij is the distance between the horizontal and vertical coordinates of the positioning point in the three-dimensional space relative to any key point, d ik is the distance between the horizontal coordinate of the kth key point and the positioning point, d kj is the distance between the vertical coordinate of the kth key point and the positioning point, K is the set of all key points, D i is the set of the horizontal coordinate values of all key points connected with the positioning point, and D j is the set of the vertical coordinate values of all key points connected with the positioning point.

[0077] In S2 of the embodiment of the present application, the content of marking a plurality of key points on the human body posture image comprises:

[0078] acquiring the first gray scale and the second gray scale of the same joint node of the adjacent two human body posture images in the three-dimensional data;

[0079] calculating the pixel gray scale difference according to the first gray scale and the second gray scale;

[0080] If the pixel gray scale difference value is not 0, the node is marked as a key point, so as to complete marking of the key points of the human body posture image.

[0081] It should be noted that the step content of the monitoring method of the AI recognition-based power operation environment monitoring system in Embodiment Two corresponds to the content of the unit in the system in Embodiment One, and thus the step content of the method in Embodiment Two is not repeated.

[0082] Embodiment Three:

[0083] The embodiment of the application provides a power operation environment monitoring device, which comprises a camera device, and a control module is arranged on the camera device, and the control module is used for executing the monitoring method of the AI recognition-based power operation environment monitoring system.

[0084] It should be noted that the step content of the monitoring method of the AI recognition-based power operation environment monitoring system in Embodiment Three has been described in Embodiment Two, and thus the step content of the method in Embodiment Three is not repeated.

[0085] Embodiment Four:

[0086] The embodiment of the application provides a terminal device, which comprises a processor and a memory.

[0087] The memory is used for storing program code and transmitting the program code to the processor.

[0088] The processor is used for executing the monitoring method of the AI recognition-based power operation environment monitoring system according to the instructions in the program code.

[0089] It should be noted that the processor is used for executing the steps in the monitoring method of the AI recognition-based power operation environment monitoring system according to the instructions in the program code. Alternatively, the processor executes the computer program to realize the functions of the modules / units in the above-mentioned system / device embodiments. In this embodiment, the step content of the monitoring method of the AI recognition-based power operation environment monitoring system in Embodiment Four has been described in Embodiment Two, and thus the step content of the method in Embodiment Four is not repeated.

[0090] For example, the computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0091] The terminal device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The terminal device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the terminal device is not limited to the above, and can include more or less components, or combine some components, or different components, for example, the terminal device can also include an input / output device, a network access device, a bus, and the like.

[0092] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0093] The memory can be an internal storage unit of the terminal device, for example, a hard disk or a memory of the terminal device. The memory can also be an external storage device of the terminal device, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Further, the memory can include both the internal storage unit and the external storage device of the terminal device. The memory is used to store computer programs and other programs and data required by the terminal device. The memory can also be used to temporarily store data that has been output or will be output.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0095] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0096] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0097] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0098] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0099] The above embodiments are merely used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent replacements to some technical features. Such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An AI recognition-based power work environment monitoring system, characterized by, The system comprises a data acquisition unit, a distance calculation unit and a pre-warning prompting unit. The data acquisition unit is configured to collect three-dimensional data of the power operation environment in real time and transmit the three-dimensional data to the distance calculation unit, wherein the three-dimensional data comprises power equipment images and human body posture images. The distance calculation unit is configured to calculate the spatial distance between the power equipment and the human body according to the three-dimensional data and send the spatial distance to the pre-warning prompting unit. The pre-warning prompting unit is configured to determine whether the spatial distance exceeds a distance threshold, and if so, issue a pre-warning prompt. The distance calculation unit comprises a marking subunit and a calculation subunit. The marking subunit is configured to mark one positioning point on the power equipment images and mark a plurality of key points on the human body posture images. The calculation subunit is configured to calculate the distance between each key point and the positioning point to obtain a distance set, and select the smallest distance value from the distance set as the spatial distance. The positioning point is the position of the power equipment in the power equipment images, and the key point is the position of the human body part in the human body posture images. The marking subunit is further configured to obtain the first and second gray scales of the same joint node of two adjacent human body posture images in the three-dimensional data, calculate the pixel gray scale difference according to the first and second gray scales, and if the pixel gray scale difference is not 0, mark the joint node as a key point to complete the marking of a plurality of key points on the human body posture images. 2.The AI recognition-based electric power work environment monitoring system of claim 1, wherein The calculation subunit obtains the spatial distance by using a spatial distance calculation formula, wherein the spatial distance calculation formula is: In the formula, x is a positioning point, x i , x j are respectively the horizontal coordinate value and the vertical coordinate value of the positioning point in a three-dimensional space coordinate system, d' is a space distance, d ij is the distance between the horizontal and vertical coordinates of the positioning point relative to any key point, d ik is the distance between the horizontal coordinate of the kth key point and the positioning point, d kj is the distance between the vertical coordinate of the kth key point and the positioning point, K is a set of all key points, D i is a set of horizontal coordinate values of all key points connected with the positioning point, and D j is a set of vertical coordinate values of all key points connected with the positioning point. 3.The AI recognition-based electric power work environment monitoring system of claim 1, wherein If the pixel gray scale difference is 0, the marking subunit does not mark the joint node as a key point.

4. The monitoring method of the AI recognition-based electric power work environment monitoring system according to any one of claims 1 to 3, characterized by, The method comprises the following steps: Real-time acquisition of three-dimensional data of the power operation environment, wherein the three-dimensional data comprises power equipment images and human body posture images; Calculation of the spatial distance between the power equipment and the human body according to the three-dimensional data; If the spatial distance exceeds a distance threshold, issue a pre-warning prompt. 5.The monitoring method of the AI recognition-based electric power work environment monitoring system according to claim 4, characterized by, The calculation of the spatial distance between the power equipment and the human body according to the three-dimensional data comprises: Marking one positioning point on the power equipment images and marking a plurality of key points on the human body posture images; Calculating the spatial distance by using a spatial distance calculation formula according to the positioning point and the key points, wherein the spatial distance calculation formula is: In the formula, x is a positioning point, x i , x j are respectively the horizontal coordinate value and the vertical coordinate value of the positioning point in the three-dimensional space coordinate system, d' is the spatial distance, d ij is the distance between the horizontal and vertical coordinates of the positioning point relative to any key point in the three-dimensional space, d ik is the distance between the horizontal coordinate of the kth key point and the positioning point, d kj is the distance between the vertical coordinate of the kth key point and the positioning point, K is the set of all key points, D i is the set of horizontal coordinate values of all key points connected to the positioning point, and D j is the set of vertical coordinate values of all key points connected to the positioning point. 6.The monitoring method of the AI recognition-based electric power work environment monitoring system according to claim 5, characterized by, The content of marking a plurality of key points on the human body posture images comprises: Obtaining the first and second gray scales of the same joint node of two adjacent human body posture images in the three-dimensional data; Calculating the pixel gray scale difference according to the first and second gray scales; If the pixel gray scale difference is not 0, mark the joint node as a key point to complete the marking of a plurality of key points on the human body posture images.

7. An electric power work environment monitoring device characterized by comprising: The system comprises a camera device, wherein a control module is arranged on the camera device, and the control module is configured to execute the monitoring method of the AI recognition-based power operation environment monitoring system according to any one of claims 4-6.

8. A terminal device, comprising: The system comprises a processor and a memory. The memory is configured to store program code and transmit the program code to the processor. The processor is configured to execute an instruction in the program code to perform the monitoring method of the AI recognition-based power operation environment monitoring system according to any one of claims 4-6.

Images