Power equipment video monitoring method and monitoring equipment for digital power system
By analyzing the grayscale distribution and shape variation values of the video frame images monitored by power equipment and dynamically adjusting the scaling factor, the problem of low high-definition video transmission efficiency in digital power systems is solved, and efficient video data compression and monitoring is achieved.
Patent Information
- Application Number
- CN202411067636.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-06
AI Technical Summary
In digital power systems, the transmission of high-definition video surveillance data occupies a large network bandwidth and electrical energy, and traditional video compression algorithms cannot effectively adapt to the changes in images in different frames, resulting in low quality and low transmission efficiency of surveillance video.
By analyzing the difference in grayscale distribution, shape variation values and electromagnetic interference coefficients of frame images, dynamically adjust the independent scaling factor of each frame image, and data processing is performed in combination with video compression algorithms to eliminate electromagnetic interference and optimize transmission.
It improves the transmission efficiency of video surveillance data of power equipment, distinguishes electromagnetic interference from real abnormalities, reduces bandwidth resource occupation and power consumption, and improves the quality of monitoring data.
Smart Images

Figure CN118590623B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of video monitoring of electric power equipment, and in particular to a video monitoring method and monitoring equipment for electric power equipment oriented to a digital electric power system. Background Art
[0002] At present, the coverage of power grids is expanding, the span of transmission lines is increasing, and the power grid structure is becoming more complex and decentralized. As a result, the operation and maintenance of the power system as a whole is becoming more difficult, and the reliability of power supply is facing severe challenges. Especially for power equipment in remote areas, the cost of manual inspection is high. Usually, based on the digital power system, monitoring equipment is deployed on edge power equipment to achieve remote monitoring of power equipment.
[0003] In order to accurately obtain the operating status of power equipment, network cameras usually have high resolutions. However, since the transmission of high-definition video requires a large network bandwidth and consumes more electricity, further processing of video data is required. In video transmission, a video scaling factor is usually set to mainly enlarge or reduce the size of the video image. In traditional video compression processing, a unified scaling factor is used. Since the image changes of different frames are different, the use of a unified scaling factor cannot be effectively applied to the specific analysis of each frame, resulting in lower monitoring video quality, which may occupy a large bandwidth resource and low transmission efficiency. Summary of the invention
[0004] In order to solve the above technical problems, the purpose of this application is to provide a video monitoring method and monitoring equipment for power equipment in a digital power system. The technical solutions adopted are as follows:
[0005] In a first aspect, an embodiment of the present application provides a method for video monitoring of electric power equipment in a digital electric power system, the method comprising the following steps:
[0006] S1, obtaining each frame image of the power equipment monitoring video in the digital power system;
[0007] S2, obtaining the device operation mutation coefficient of the current frame image according to the grayscale distribution difference between the current frame image and the frame image before it in the local time;
[0008] S3, obtaining the connected domains in the current frame image, and obtaining the shape variation value of the current frame image according to the shape features of all the connected domains;
[0009] S4, obtaining a standard outline of the power equipment; extracting outline information of the power equipment in the current frame image; obtaining an electromagnetic interference coefficient of the current frame image according to the difference between the outline information of the power equipment in the current frame image and the standard outline and the shape variation value;
[0010] S5, obtaining an independent scaling factor of the current frame image according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image;
[0011] S6, scaling the size of the power equipment monitoring video according to the independent scaling factors of all frame images and transmitting it to the digital power system.
[0012] Furthermore, obtaining the device operation mutation coefficient of the current frame image according to the grayscale distribution difference between the current frame image and the frame image in the previous local time includes:
[0013] Obtain a preset number of frame images before the current frame image as local contrast data of the current frame; calculate the difference between the grayscale co-occurrence matrix of the current frame image and each frame image in its local contrast data, and record it as the inter-frame deviation value of each frame image in the local contrast data of the current frame image;
[0014] The equipment operation mutation coefficient is obtained according to the inter-frame deviation value and grayscale distribution difference between the current frame image and all frame images in its local comparison data.
[0015] Furthermore, the method for calculating the equipment operation mutation coefficient includes: recording the equipment operation mutation coefficient of the current frame image as A, ,in, represents the inter-frame deviation value of the j-th frame image in the local contrast data of the current frame, W represents the number of frame images in the local contrast data of the current frame image, , They respectively represent the current frame image and the information entropy of the j-th frame image in the local contrast data of the current frame image.
[0016] Furthermore, the method for obtaining the shape variation value of the current frame image includes:
[0017] Performing connected domain analysis on the current frame image to obtain connected domains; recording each connected domain as a potential interference area;
[0018] For each potential interference area, obtain the minimum bounding rectangle of the potential interference area; calculate the minimum value of the distance between each edge pixel point of the potential interference area and all pixel points on the minimum bounding rectangle, and record it as the shortest edge distance of each edge pixel point; take the average of the shortest edge distances of all edge pixel points of the potential interference area as the minimum bounding distance of each potential interference area;
[0019] The average of the minimum circumscribed distances of all potential interference regions of the current frame image is taken as the shape variation value of the current frame image.
[0020] Further, the electromagnetic interference coefficient of the current frame image is obtained according to the difference between the contour information of the power equipment in the current frame image and the standard contour and the shape variation value, including:
[0021] The semantic segmentation model is used to extract the contour information of the power equipment in the current frame image, which is recorded as the electromagnetic interference contour;
[0022] Obtaining an intersection-and-union ratio between the electromagnetic interference contour and the standard contour, and recording the difference between the intersection-and-union ratio and a value of 1 as a contour difference value of the current frame image;
[0023] According to the contour difference value and shape variation value of the current frame image, the electromagnetic interference coefficient of the current frame image is obtained.
[0024] Furthermore, the method for obtaining the electromagnetic interference coefficient of the current frame image includes:
[0025] If the contour difference value of the current frame image is 0, the electromagnetic interference coefficient of the current frame image is 0; otherwise, the electromagnetic interference coefficient of the current frame image is the ratio of the shape variation value of the current frame image to the contour difference value.
[0026] Further, the independent scaling factor of the current frame image is obtained according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image, including:
[0027] Calculate the scaling adjustment coefficient according to the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image;
[0028] If the scaling adjustment coefficient of the current frame image is less than or equal to the first preset value, the value of the independent scaling factor of the current frame image is 0.2; if the scaling adjustment coefficient of the current frame image is between the first preset value and the second preset value, the value of the independent scaling factor of the current frame image is 0.5; if the scaling adjustment coefficient of the current frame image is greater than or equal to the second preset value, the value of the independent scaling factor of the current frame image is 1; wherein the first preset value is less than the second preset value.
[0029] Further, the scaling adjustment coefficient is calculated by: recording the scaling adjustment coefficient of the current frame image as , ; Wherein, A represents the device operation mutation coefficient of the current frame image, D is the electromagnetic interference coefficient of the current frame, and Norm() is the linear normalization function.
[0030] Furthermore, scaling the power equipment monitoring video according to the independent scaling factors of all frame images and transmitting the video to the digital power system includes:
[0031] The independent scaling factor of the current frame image is substituted into the image scaling function to scale the current frame image; all scaled frame images in the power equipment monitoring video are compressed and transmitted to the digital power system.
[0032] In the second aspect, an embodiment of the present application also provides a video monitoring device for electric power equipment for a digital power system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned methods for video monitoring of electric power equipment for a digital power system are implemented.
[0033] This application has at least the following beneficial effects:
[0034] This application aims at the efficiency problem of the monitoring data of power equipment in the digital power system during the transmission process, analyzes the difference between adjacent frames in the monitoring video data, firstly obtains the equipment operation mutation coefficient according to the frame difference between the single frame image and the image in the local time in the monitoring data, and reflects the abnormal operation of the equipment; further analyzes the connected domain of the single frame image, identifies the interference of the snowflake effect caused by electromagnetic interference on the contour recognition of the power equipment, obtains the shape variation value, and combines the analysis of the detailed contour information of the single frame image to obtain the electromagnetic interference coefficient, reflects the situation of the monitoring equipment being subjected to electromagnetic interference during the operation of the power equipment, and can effectively distinguish electromagnetic interference from real abnormal conditions; finally, combined with the equipment operation mutation coefficient and the electromagnetic interference coefficient, a comprehensive analysis is performed to obtain the independent scaling factor of each frame image, and the video compression algorithm is combined to realize the compression processing of the data. Compared with the traditional algorithm, this application can eliminate electromagnetic interference, set an independent scaling factor for each frame image, and reduce the influence of electromagnetic interference on the independent scaling factor based on the difference between frames and the detailed characteristics of electromagnetic interference, so as to realize the effective compression of the monitoring data of the power equipment and improve the transmission efficiency of the video monitoring data of the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0036] Figure 1 A flowchart of the steps of a method for video monitoring of electric power equipment in a digital electric power system provided by one embodiment of the present application;
[0037] Figure 2 A block diagram for obtaining a device operation mutation coefficient provided in one embodiment of the present application. DETAILED DESCRIPTION
[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0040] The specific scheme of the power equipment video monitoring method and monitoring equipment for a digital power system provided by the present application is described in detail below with reference to the accompanying drawings.
[0041] See also Figure 1 , which shows a flowchart of a method for video monitoring of electric power equipment in a digital electric power system provided by an embodiment of the present application, the method comprising the following steps:
[0042] S1, obtaining each frame image of the power equipment monitoring video in the digital power system.
[0043] A specific implementation scenario of the embodiment of the present application is the compression and transmission scenario of the monitoring video of power equipment in a digital power system; the digital power system mainly refers to a system that uses digital technology to monitor, operate and manage the power equipment in the power system, wherein the monitoring of the power equipment is the basis for the system to obtain data. Therefore, this solution obtains the monitoring video data of a single power device through a digital power system, and sets the acquisition frame rate of the monitoring device to 30FPS. This solution aims to perform monitoring data analysis at the data acquisition end and realize effective compression of the monitoring data.
[0044] The resolution of power equipment monitoring video is usually high, so the monitoring data of edge power equipment generally occupies a large transmission bandwidth during transmission, resulting in a certain amount of resource waste. Power equipment is usually in a static state during operation. If no abnormal situation occurs, the image difference between adjacent frames is small, and the outline of the power equipment is clear. It does not require too high a resolution to occupy storage resources, and a smaller scaling factor can be set; when an abnormal situation of power equipment failure occurs, it is usually necessary to identify the abnormal part, so a higher resolution is required, and a larger scaling factor is required to retain the equipment data details. This embodiment sets an independent scaling factor for each frame image based on the grayscale change difference information of adjacent images and the power equipment recognition accuracy.
[0045] S2, obtaining the device operation mutation coefficient of the current frame image according to the grayscale distribution difference between the current frame image and the frame image before it in the local time.
[0046] During the operation of power equipment, the power equipment is basically stationary and basically located in the center of the monitoring screen. There will not be a large difference between adjacent frames of monitoring data. At this time, a smaller zoom factor can be used. When the equipment is operating abnormally, such as smoke, fire, discharge arc, etc., it will cause a large difference in the screen of the power equipment in a local time. At this time, the equipment is operating abnormally. At this time, the original resolution of the monitoring equipment should be used for transmission to retain more detailed information.
[0047] In order to measure the difference information of the current frame in the monitoring data of the power equipment operation process, it is necessary to divide the local time range and obtain the image of W frames before the current frame image as the local comparison data of the current frame. This scheme sets W=60. It should be noted that if the current frame is in the initial stage of acquisition, that is, when the amount of data is less than W, the image of the current frame is used for filling. First, based on the grayscale difference between the current frame and each frame image in its local comparison data, the inter-frame deviation value is calculated, specifically:
[0048] The difference between the gray level co-occurrence matrix of the current frame image and each frame image in its local contrast data is calculated, and recorded as the inter-frame deviation value of each frame image in the local contrast data of the current frame image.
[0049] It should be noted that the difference between the two matrices represents a difference measure between the two matrices. As an embodiment of the present application, the L1 norm is used for calculation, and the calculation formula of the inter-frame deviation value is: ,in, Indicates the inter-frame deviation value of the j-th frame image in the local contrast data of the current frame, Represents the gray level co-occurrence matrix of the j-th frame image in the local contrast data, Represents the gray-level co-occurrence matrix of the current frame image, Representation calculation L1 norm of the difference matrix. As another embodiment of the present application, KL divergence may be used to calculate the difference between gray level co-occurrence matrices.
[0050] If the current frame is an abnormal device operation frame, the monitoring screen of the device will undergo a large difference change, resulting in a large change in the grayscale of the current frame and the frame image in the local comparison data, and the inter-frame deviation value calculated thereby is large.
[0051] Furthermore, the equipment operation mutation coefficient is obtained by the difference between the inter-frame deviation value and the grayscale distribution of the single-frame image in the current frame and the local contrast data. The specific calculation is:
[0052]
[0053] Among them, A represents the device operation mutation coefficient of the current frame image, represents the inter-frame deviation value of the j-th frame image in the local contrast data of the current frame, W represents the number of frame images in the local contrast data of the current frame image, and They respectively represent the information entropy of the current frame image and the j-th frame image in the local contrast data of the current frame image. The calculation of image information entropy is a well-known technology and will not be repeated in this solution.
[0054] If the device is operating abnormally at the sampling moment of the current frame, the grayscale difference between the current frame image and the frame image in the local comparison data is large, which makes the difference between the inter-frame deviation value and the information entropy large, and the value of the device operation mutation coefficient of the current frame is large. On the contrary, if the current frame is a frame image of the normal operation of the device, since the device is in a static state, the difference between the current frame and the frame image in the local comparison data is small, and the value of the device operation mutation coefficient is small.
[0055] The block diagram for obtaining the equipment operation mutation coefficient is as follows: Figure 2 shown.
[0056] S3, obtaining connected domains in the current frame image, and obtaining shape variation values of the current frame image according to shape features of all connected domains.
[0057] The edge power equipment monitored by the digital power system is basically an important node in power transmission, responsible for the power transmission and diversion of the entire place. Therefore, there is strong electromagnetic interference in the local space of this type of power equipment. When the electromagnetic interference is strong, the setting will affect the monitoring screen to generate electromagnetic noise, thereby producing a snowflake effect. However, at this time, the power equipment is still processing the normal operation status, but the picture changes due to external interference. If only the equipment operation mutation coefficient is used to measure the equipment's operating status at this time, it will no longer be accurate, and further analysis is required based on the content details of the frame image.
[0058] In order to further measure the variation and interference of the current frame image, the current frame image is firstly subjected to a connected domain analysis to obtain each connected domain; each connected domain is recorded as a potential interference region; and all the potential interference regions in the current frame image are combined into a potential interference region set.
[0059] The set of potential interference areas obtained includes the real interference area and the area of the power equipment. When the power equipment is running, it is susceptible to electromagnetic interference and produces a snowflake effect, that is, a random bright spot area appears on the monitoring frame image. The shape of the bright spot has irregular characteristics, which interferes with the monitoring of the power equipment and makes the current frame image different from the frame image in the local comparison data. This leads to a deviation in the reflection of the equipment operation mutation coefficient. Therefore, the shape of the potential interference area is analyzed:
[0060] For each potential interference area, obtain the minimum bounding rectangle of the potential interference area; calculate the minimum value of the distance between each edge pixel point of the potential interference area and all pixel points on the minimum bounding rectangle, and record it as the shortest edge distance of each edge pixel point; take the average of the shortest edge distances of all edge pixel points of the potential interference area as the minimum bounding distance of each potential interference area;
[0061] The average of the minimum circumscribed distances of all potential interference regions of the current frame image is taken as the shape variation value of the current frame image.
[0062] If the current frame image is affected by electromagnetic interference and produces a snowflake effect or is caused by real abnormal conditions such as smoke, there will be more potential interference areas. Since the shape of the random bright spots formed by the snowflake effect is irregular, the distance from the edge pixel point to the minimum circumscribed rectangle in a single potential interference area is far, and the shape variation value of the current frame is large.
[0063] S4, obtaining the standard outline of the power equipment; extracting the outline information of the power equipment in the current frame image; obtaining the electromagnetic interference coefficient of the current frame image according to the difference between the outline information of the power equipment in the current frame image and the standard outline and the shape variation value.
[0064] The cases with large shape variation values are divided into real abnormal situations and electromagnetic interference situations. In order to prevent the influence of electromagnetic interference on the judgment of abnormal situations, it is necessary to distinguish them according to the degree of deformation of the contour of the power equipment; in the frame image with snowflake effect caused by electromagnetic interference, the contour of the power equipment will be affected by the random bright spot area, resulting in a small deviation; at the same time, when the equipment is abnormal, such as smoke and fire, it will affect the contour recognition of the power equipment in the current frame, resulting in a large deviation of the contour of the power equipment in the current frame. Therefore, the contour of the power equipment in the frame image is extracted and compared with the standard contour of the power equipment, which can quantify the interference of electromagnetic interference on the contour recognition of the power equipment, and then analyze the degree of electromagnetic interference in combination with the shape variation value.
[0065] Specifically, a semantic segmentation model is used to extract the contour information of the power equipment in the current frame image, which is recorded as the electromagnetic interference contour;
[0066] Obtaining a standard profile of the power equipment under normal conditions through a digital power system; obtaining an intersection-and-combination ratio of the electromagnetic interference profile and the standard profile, and recording the difference between the intersection-and-combination ratio and a value of 1 as a profile difference value of the current frame image;
[0067] If the contour difference value of the current frame image is 0, the electromagnetic interference coefficient of the current frame image is 0; otherwise, the electromagnetic interference coefficient of the current frame image is the ratio of the shape variation value of the current frame image to the contour difference value.
[0068] In this embodiment, the current frame image is subjected to binary classification extraction through U2Net semantic segmentation. The power equipment is generally located in the center of the picture. At this time, the contour information of the power equipment in the current frame is obtained, and the absolute value of the difference between the intersection and union ratio of the two contours and 1 is taken as the contour difference value E. U2Net semantic segmentation and calculation of the intersection and union ratio are well-known technologies and will not be repeated here; then the electromagnetic interference coefficient of the current frame is , E represents the difference between the outline of the power equipment in the current frame and the standard outline; C represents the shape variation value of the current frame image. In particular, if the difference value E is zero, there is no electromagnetic interference, and the electromagnetic interference coefficient D of the current frame is set to 0.
[0069] If the current frame is an interference frame with a snowflake effect, although the snowflake interference causes the contour of the collected power equipment to differ from the standard contour, the overall difference is small, and the shape variation value is large, indicating the influence of snowflake interference, and the value of the electromagnetic interference coefficient is large. On the contrary, if the current frame is a frame with abnormal operation, since the background environment of the collected power equipment is basically a horizontal and vertical strip shape, the deviation between the edge pixel points in the potential interference area and the minimum circumscribed rectangle is small, and the shape variation value is small. When the current frame power equipment contour deviates greatly from the standard contour, it is explained that it is affected by abnormal conditions such as smoke and fire, and the value of the electromagnetic interference coefficient is small.
[0070] S5, obtaining an independent scaling factor of the current frame image according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image.
[0071] Based on the above analysis, the shape variation of the power equipment caused by electromagnetic interference during the operation of the power equipment can be obtained. During the transmission of power equipment monitoring data, when the equipment is abnormal, in order to analyze the abnormal situation according to the image, the current frame needs to be transmitted with a higher resolution. On the contrary, if the current frame image is only the difference caused by electromagnetic interference, no interpretation is required, and a lower resolution can be used for transmission. In order to ensure the transmission efficiency of the monitoring data, it is necessary to adjust the scaling factor of each frame image based on the equipment operation mutation coefficient and the electromagnetic interference coefficient, so as to achieve efficient transmission of the monitoring data.
[0072] Specifically, the scaling adjustment coefficient of the current frame image ; where A represents the device operation mutation coefficient of the current frame, D is the electromagnetic interference coefficient of the current frame, and Norm() is a linear normalization function.
[0073] If the current frame is a frame of abnormal operation of a real power device, at this time, the difference between the current frame and the frame image in the local comparison data is large, and the value of the device operation mutation coefficient is large. At the same time, since the background environment of the power device is basically a scene with horizontal and vertical lines such as lines or load-bearing frames, when the device has an abnormality, the contour of the power device in the current frame is quite different from the standard contour. At this time, the value of the electromagnetic interference coefficient is small, and finally the value of the scaling adjustment coefficient is large, and the current frame needs to be transmitted at a higher resolution.
[0074] Due to possible slight differences during the monitoring process of power devices, the normalized values of the obtained scaling adjustment coefficients still differ between adjacent frames, which is not conducive to the compressed transmission of power device monitoring data. Therefore, it is necessary to quantize the scaling adjustment coefficient to obtain an independent scaling factor for each frame image.
[0075]
[0076] Among them, represents the independent scaling factor of the current frame image. If when, a is the first preset value. In this embodiment, a = 0.5 indicates that the overall change difference of the current frame is small, so the image is reduced to 0.2 times the original resolution of the monitoring data; is the second preset value, a < b, b = 0.7. If when, it indicates that there may be slight differences in the current frame. To ensure the picture quality, the image is reduced to 0.5 times the original resolution of the monitoring data. If when, it indicates that the operation of the power device in the current frame has an abnormality. To accurately measure the abnormal state, the current frame needs to be transmitted at the original size, that is, the independent scaling factor is 1 and no scaling is performed.
[0077] S6. Scale the power device monitoring video according to the independent scaling factors of all frame images and transmit it to the digital power system.
[0078] Through the above steps, the independent scaling factor corresponding to each frame image in the monitoring data of the power device operation state can be obtained, and thus the monitoring data is scaled according to the scaling factor of each frame image.
[0079] Specifically, substitute the independent scaling factor of the current frame image into the image scaling function to scale the current frame image; compress all the scaled frame images in the power device monitoring video and transmit them to the digital power system.
[0080] In this embodiment, the scaling method is to use the cv.resize() image scaling function in OpenCV to change the image size. The scaled monitoring data is compressed using the video compression algorithm H.265, and the compressed video data is transmitted to the digital power system server using the network module at the edge device end, thereby reducing the transmission bandwidth while realizing video monitoring of power equipment. Among them, the OpenCV library and H.265 are well-known technologies and will not be described in detail in this solution.
[0081] Finally, according to the independent scaling factor of the video frame, the picture is scaled and the video is compressed. Every hour, the video data stored in the memory is uploaded to the digital power system through the wired network transmission interface and the network cable.
[0082] Based on the same inventive concept as the above method, an embodiment of the present application also provides a video monitoring device for electric power equipment for a digital power system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of the video monitoring method for electric power equipment for a digital power system are implemented in any one of the above-mentioned video monitoring methods for electric power equipment for a digital power system.
[0083] Through the above description of the implementation method in combination with the accompanying drawings, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0084] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.
Claims
1. A method for video monitoring of electric power equipment for a digital electric power system, characterized in that: The method comprises the following steps: S1, obtaining each frame image of the power equipment monitoring video in the digital power system; S2, obtaining the device operation mutation coefficient of the current frame image according to the grayscale distribution difference between the current frame image and the frame image before it in the local time; S3, obtaining the connected domains in the current frame image, and obtaining the shape variation value of the current frame image according to the shape features of all the connected domains; S4, obtaining a standard outline of the power equipment; extracting outline information of the power equipment in the current frame image; obtaining an electromagnetic interference coefficient of the current frame image according to the difference between the outline information of the power equipment in the current frame image and the standard outline and the shape variation value; S5, obtaining an independent scaling factor of the current frame image according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image; When it is determined that the device is abnormal according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image, a large scaling adjustment coefficient is used to transmit the current frame with a high resolution; when it is determined that the device is not abnormal according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image, a small scaling adjustment coefficient is used to transmit the current frame with a low resolution; S6, scaling the size of the power equipment monitoring video according to the independent scaling factors of all frame images and transmitting it to the digital power system.
2. The method for video monitoring of electric power equipment for a digital electric power system according to claim 1, characterized in that: The obtaining of the device operation mutation coefficient of the current frame image according to the grayscale distribution difference between the current frame image and the frame image in the previous local time includes: Obtain a preset number of frame images before the current frame image as local contrast data of the current frame; calculate the difference between the grayscale co-occurrence matrix of the current frame image and each frame image in its local contrast data, and record it as the inter-frame deviation value of each frame image in the local contrast data of the current frame image; The equipment operation mutation coefficient is obtained according to the inter-frame deviation value and grayscale distribution difference between the current frame image and all frame images in its local comparison data.
3. The method for video monitoring of electric power equipment for a digital electric power system according to claim 2, characterized in that: The method for calculating the equipment operation mutation coefficient comprises: recording the equipment operation mutation coefficient of the current frame image as A, ,in, represents the inter-frame deviation value of the j-th frame image in the local contrast data of the current frame, W represents the number of frame images in the local contrast data of the current frame image, , They respectively represent the current frame image and the information entropy of the j-th frame image in the local contrast data of the current frame image.
4. The method for video monitoring of electric power equipment for a digital electric power system according to claim 1, characterized in that: The method for obtaining the shape variation value of the current frame image includes: Performing connected domain analysis on the current frame image to obtain connected domains; recording each connected domain as a potential interference area; For each potential interference area, obtain the minimum bounding rectangle of the potential interference area; calculate the minimum value of the distance between each edge pixel point of the potential interference area and all pixel points on the minimum bounding rectangle, and record it as the shortest edge distance of each edge pixel point; take the average of the shortest edge distances of all edge pixel points of the potential interference area as the minimum bounding distance of each potential interference area; The average of the minimum circumscribed distances of all potential interference regions of the current frame image is taken as the shape variation value of the current frame image.
5. The method for video monitoring of electric power equipment for a digital electric power system according to claim 1, characterized in that: The method of obtaining the electromagnetic interference coefficient of the current frame image according to the difference between the contour information of the electric power equipment in the current frame image and the standard contour and the shape variation value includes: The semantic segmentation model is used to extract the contour information of the power equipment in the current frame image, which is recorded as the electromagnetic interference contour; Obtaining an intersection-and-union ratio between the electromagnetic interference contour and the standard contour, and recording the difference between the intersection-and-union ratio and a value of 1 as a contour difference value of the current frame image; According to the contour difference value and shape variation value of the current frame image, the electromagnetic interference coefficient of the current frame image is obtained.
6. The method for video monitoring of electric power equipment for a digital electric power system according to claim 1, characterized in that: The method for obtaining the electromagnetic interference coefficient of the current frame image includes: If the contour difference value of the current frame image is 0, the electromagnetic interference coefficient of the current frame image is 0; otherwise, the electromagnetic interference coefficient of the current frame image is the ratio of the shape variation value of the current frame image to the contour difference value.
7. The method for video monitoring of electric power equipment for a digital electric power system according to claim 1, characterized in that: The step of obtaining the independent scaling factor of the current frame image according to the values of the device operation mutation coefficient and the electromagnetic interference coefficient of the current frame image includes: Calculate the scaling adjustment coefficient according to the device operation mutation coefficient and electromagnetic interference coefficient of the current frame image; If the scaling adjustment coefficient of the current frame image is less than or equal to the first preset value, the value of the independent scaling factor of the current frame image is 0.2; if the scaling adjustment coefficient of the current frame image is between the first preset value and the second preset value, the value of the independent scaling factor of the current frame image is 0.5; if the scaling adjustment coefficient of the current frame image is greater than or equal to the second preset value, the value of the independent scaling factor of the current frame image is 1; wherein the first preset value is less than the second preset value.
8. The method for video monitoring of electric power equipment for a digital electric power system according to claim 7, characterized in that: The calculation method of the scaling adjustment coefficient is as follows: the scaling adjustment coefficient of the current frame image is recorded as , ; Wherein, A represents the device operation mutation coefficient of the current frame image, D is the electromagnetic interference coefficient of the current frame, and Norm() is the linear normalization function.
9. The method for video monitoring of electric power equipment for a digital electric power system according to claim 1, characterized in that: The method of scaling the power equipment monitoring video according to the independent scaling factors of all frame images and transmitting the video to the digital power system includes: The independent scaling factor of the current frame image is substituted into the image scaling function to scale the current frame image; all scaled frame images in the power equipment monitoring video are compressed and transmitted to the digital power system.
10. A video monitoring device for electric power equipment in a digital electric power system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for video monitoring of electric power equipment for a digital electric power system as described in any one of claims 1 to 9 are implemented.
Citation Information
Patent Citations
System and method for monitoring snow noise of monitor video
CN104539936A
Online transmission line video monitoring system
CN104581049A
Monitor shooting method, device and equipment
CN107333107A
Agricultural information transmission method and device, electronic equipment and storage medium
CN116320321A
Power equipment management method, system and equipment
CN117375246A
