Plug-and-play intelligent power transmission line video monitoring system

Abstract

The application provides a plug-and-play intelligent power transmission line video monitoring system, comprising a device access terminal and an edge processing terminal; wherein the device access terminal is used for establishing a data connection with external video monitoring devices, acquiring video monitoring data collected by each external video monitoring device, and performing intelligent data correlation and recognition processing according to the acquired video monitoring data, marking the video monitoring data, and transmitting the marked video monitoring data to the edge processing terminal; the edge processing terminal performs power transmission line anomaly recognition and analysis processing on the acquired video monitoring data to obtain power transmission line anomaly monitoring results, and further sends an abnormal alarm information to an upper computer device when the power transmission line anomaly monitoring results are abnormal. The application realizes the plug-and-play of external video monitoring devices, and helps to improve the intelligent level of video monitoring data processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power transmission line video monitoring, and particularly relates to a plug-and-play intelligent power transmission line video monitoring system. BACKGROUND

[0002] With the increasing development of the power system, the safety operation requirements for the power transmission line are higher and higher. For the monitoring of the power transmission line, a video monitoring-based mode is mostly adopted to obtain image monitoring data of the power transmission line and to improve the monitoring effect of the power transmission line by combining with image processing technology.

[0003] At present, if the comprehensive video monitoring is to be performed on a large-scale power transmission line network, a large number of video monitoring devices need to be arranged to collect the video monitoring data of each part of the power transmission line. In the prior art, the video monitoring system for the power transmission line is weak in the management of the video monitoring devices and is low in the intelligent level, so that the cooperation / association level between the video monitoring devices is low. Therefore, when the massive video monitoring data is processed, a large amount of computing power needs to be consumed, so that the video monitoring system for the large-scale power transmission line is more and more large, which is not conducive to the continuous development of the safety monitoring of the power transmission line. SUMMARY

[0004] In view of the above problems, the present application aims to provide a plug-and-play intelligent power transmission line video monitoring system.

[0005] The object of the present application is achieved by the following technical solutions:

[0006] The present application shows a plug-and-play intelligent power transmission line video monitoring system, comprising a device access terminal and an edge processing terminal.

[0007] The device access terminal is configured to establish a data connection with an external video monitoring device, to obtain video monitoring data collected by each external video monitoring device, and to perform intelligent data association recognition processing according to the obtained video monitoring data, to associate and mark the video monitoring data, and to transmit the video monitoring data after the association and marking to the edge processing terminal.

[0008] The edge processing terminal is configured to perform power transmission line anomaly recognition and analysis processing on the obtained video monitoring data, to obtain a power transmission line anomaly monitoring result, and to further send an abnormal alarm information to an upper computer device when the power transmission line anomaly monitoring result is abnormal.

[0009] Preferably, the system further comprises a local management terminal.

[0010] The local management terminal is configured to receive the abnormal alarm information sent by the edge processing terminal, and to send a corresponding alarm signal according to the obtained abnormal alarm information.

[0011] Preferably, the system further comprises a cloud service platform;

[0012] The cloud service platform is configured to acquire the video monitoring data and the transmission line anomaly monitoring result transmitted by the edge processing terminal, integrate the acquired video monitoring data and the transmission line anomaly monitoring result into a visual transmission line monitoring model, and visually display the transmission line monitoring data and the anomaly monitoring result.

[0013] Preferably, the device access terminal comprises an access module, a receiving module, a preprocessing module, an association analysis module, a marking module, and a transmission module; wherein,

[0014] The access module is configured to establish a data connection with the external video monitoring device based on a preset communication protocol;

[0015] The receiving module is configured to receive the video monitoring data collected by the external video monitoring device;

[0016] The preprocessing module is configured to preprocess the acquired video monitoring data, including standardization and filtering processing, to obtain preprocessed video monitoring data;

[0017] The association analysis module is configured to perform association recognition processing on the preprocessed video monitoring data collected by each external video monitoring device, identify the transmission line features in the video monitoring data, and associate the video monitoring data for the same transmission line according to the transmission line features to obtain an association recognition result of each video monitoring data;

[0018] The marking module is configured to mark the corresponding preprocessed video monitoring data according to the association recognition result, so that the preprocessed video monitoring data carries an association identifier corresponding to the transmission line;

[0019] The transmission module is configured to transmit the preprocessed video monitoring data with the association identifier to the edge processing terminal.

[0020] Preferably, the access module further comprises:

[0021] When the external video monitoring device accesses the system for the first time, a local routing protocol is transmitted to the external video monitoring device, so that the external video monitoring device can form a wireless local area network with other external video monitoring devices according to the local routing protocol, and the collected video monitoring data is transmitted to the device access terminal by direct transmission or multi-hop indirect transmission through the wireless local area network.

[0022] Preferably, the edge processing terminal comprises an extraction module, an anomaly analysis module, a control module, and an alarm module; wherein,

[0023] The extraction module is configured to extract the video monitoring data according to a preset rule;

[0024] The abnormality analysis module is configured to analyze the power transmission line based on the extracted video monitoring data to obtain a power transmission line abnormality analysis result.

[0025] The control module is configured to control the extraction module to further call other video monitoring data associated with the power transmission line with the abnormality and transmit the data to the abnormality analysis module for further abnormality analysis when the power transmission line abnormality analysis result is abnormal; and control the extraction module to ignore other video monitoring data associated with the power transmission line and not called and control the alarm module to issue an abnormality alarm information corresponding to the abnormality analysis result when more than N abnormality analysis results are abnormal based on the video monitoring data associated with the same power transmission line.

[0026] The alarm module is configured to issue the abnormality alarm information to the upper computer device.

[0027] Preferably, in the abnormality analysis module, the power transmission line abnormality analysis based on the extracted video monitoring data comprises:

[0028] The trained power transmission line abnormality analysis model is used to analyze and process the obtained video monitoring data to obtain a power transmission line abnormality analysis result; wherein the power transmission line abnormality analysis model is built based on a CNN convolutional neural network, the collected video monitoring data is input into the power transmission line abnormality analysis model, the video monitoring data is extracted by the power transmission line abnormality analysis model in multiple dimensions, and the abnormality is identified based on the obtained multi-dimensional feature information, and the classifier is combined to finally output the power transmission line abnormality analysis result; wherein the power transmission line abnormality analysis result includes normal and abnormal; the abnormal result includes different types of abnormal results such as cover, fire, and bird damage.

[0029] The present application has the advantages that the present application provides a plug-and-play intelligent power transmission line video monitoring system, a plurality of external video monitoring devices in a local range are connected to a terminal, the video monitoring data obtained by the external video monitoring devices is collected by the device access terminal, the video monitoring data for monitoring the same area / section of the power transmission line is associated and identified, and the video monitoring data is marked with an associated mark corresponding to different power transmission lines, which helps to associate the video monitoring data based on the power transmission line for targeted monitoring under different conditions such as video shooting angle and shooting position, realizes the plug-and-play of the external video monitoring device, and improves the data management level. At the same time, the video monitoring data is centrally processed based on the edge processing terminal, the abnormal situation of the power transmission line is intelligently monitored, which helps to improve the monitoring effect of the power transmission line monitoring and improve the intelligent level of the video monitoring data processing. BRIEF DESCRIPTION OF DRAWINGS

[0030] The application is further described by using the accompanying drawings, but the embodiments in the drawings do not constitute any limitation to the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the following drawings.

[0031] Figure 1 A framework structure diagram of a plug-and-play intelligent power transmission line video monitoring system shown in an embodiment of the application is shown in the figure.

[0032] Figure 2 For Figure 1 A framework structure diagram of a device access terminal in the embodiment is shown in the figure. DETAILED DESCRIPTION

[0033] The application is further described in combination with the following application scenarios.

[0034] Referring to Figure 1 which shows a plug-and-play intelligent power transmission line video monitoring system, including a device access terminal and an edge processing terminal.

[0035] The device access terminal is configured to establish a data connection with external video monitoring devices, acquire video monitoring data collected by the external video monitoring devices, and perform intelligent data association and recognition processing according to the acquired video monitoring data, associate and mark the video monitoring data, and transmit the video monitoring data with the association marks to the edge processing terminal.

[0036] The edge processing terminal performs power transmission line anomaly recognition and analysis processing on the acquired video monitoring data, and obtains power transmission line anomaly monitoring results. When the power transmission line anomaly monitoring results are abnormal, the edge processing terminal further sends an abnormal alarm message to an upper computer device.

[0037] The above-mentioned embodiments of the application propose a plug-and-play intelligent power transmission line video monitoring system. After a plurality of external video monitoring devices in a local area are connected to the device access terminal, the device access terminal collects video monitoring data acquired by the external video monitoring devices, and associates and recognizes video monitoring data for monitoring the same area / section of the power transmission line, and attaches association marks corresponding to different power transmission lines to the video monitoring data, which helps to associate the video monitoring data based on the power transmission line for targeted monitoring under different conditions such as video shooting angle and shooting position, realizes plug-and-play of the external video monitoring device, and improves data management level. At the same time, the edge processing terminal centrally processes the video monitoring data, intelligently monitors abnormal conditions of the power transmission line, helps to improve the monitoring effect of the power transmission line monitoring, and improves the intelligent level of video monitoring data processing.

[0038] Preferably, the system further includes a local management terminal.

[0039] The local management terminal is configured to receive the abnormal alarm information issued by the edge processing terminal, and issue a corresponding alarm signal according to the obtained abnormal alarm information.

[0040] When the local management terminal receives the abnormal alarm information related to the power transmission line, the power transmission line that generates the abnormality can be identified and alarmed, so that the local management personnel can make timely operation and maintenance scheduling for the abnormal power transmission line, and the reliability of the power transmission line safety monitoring can be improved.

[0041] Preferably, the system further comprises a cloud service platform;

[0042] The cloud service platform is configured to obtain the video monitoring data and the power transmission line abnormality monitoring result transmitted by the edge processing terminal, integrate the obtained video monitoring data and the power transmission line abnormality monitoring result into a visual power transmission line monitoring model, and visually display the power transmission line monitoring data and the abnormality monitoring result.

[0043] By building the cloud service platform, the video monitoring data and the abnormality analysis result related to the power transmission line are further comprehensively stored and managed and further called, which is helpful to improve the data management level and the utilization rate of data resources.

[0044] Preferably, referring to Figure 2 The device access terminal comprises an access module, a receiving module, a preprocessing module, an association analysis module, a marking module and a transmission module; wherein,

[0045] The access module is configured to establish a data connection with an external video monitoring device based on a preset communication protocol;

[0046] The receiving module is configured to receive video monitoring data collected by the external video monitoring device;

[0047] The preprocessing module is configured to preprocess the obtained video monitoring data, including standardization and filtering processing, to obtain preprocessed video monitoring data;

[0048] The association analysis module is configured to perform association recognition processing on the preprocessed video monitoring data collected by each external video monitoring device, recognize the power transmission line features in the video monitoring data, and associate the video monitoring data for the same power transmission line according to the power transmission line features, to obtain an association recognition result of each video monitoring data;

[0049] The marking module is configured to mark the corresponding preprocessed video monitoring data according to the association recognition result, so that the preprocessed video monitoring data carries an association identifier corresponding to the power transmission line;

[0050] The transmission module is configured to transmit the preprocessed video monitoring data with the association identifier to the edge processing terminal.

[0051] Preferably, the preset communication protocol includes HTTP protocol, MQTT protocol, IEEE1451.0 / IEEE1451.5 standard protocol, Bluetooth communication protocol, Zigbee communication protocol, etc.

[0052] In one scenario, in order to identify the power transmission lines with similar appearance and form, the power transmission line equipment (such as power transmission lines, power transmission line towers, transformers, insulators, etc.) in the power transmission line that needs to be monitored is identified in advance, and one or more identification signs (such as digital signs, signs with letters and numbers, etc.) with power transmission line position segment related marks are set on the power transmission line equipment in advance as power transmission line features for subsequent identification of the corresponding identification based on video monitoring data.

[0053] In one scenario, the setting of the identification on the power transmission line equipment is based on positioning information, that is, all power transmission line equipment at the same position are marked with the marks corresponding to the positioning information, such as AR343, so that all power transmission line equipment within a certain range have the same marked sign.

[0054] In another scenario, the setting of the identification on the power transmission line equipment is to set corresponding identification for different power transmission lines, that is, for different power transmission line equipment, such as a single power transmission line tower, a length of power transmission line, a single insulator, etc., the corresponding equipment ID identification is set for the equipment, so that different power transmission line equipment carries the sign corresponding to the equipment ID.

[0055] In one embodiment, the association analysis module adopts a sign recognition model based on video AI analysis to extract the sign image contained in the video monitoring image, and extracts the mark information contained in the sign according to the obtained sign image, and uses the extracted mark information as the corresponding power transmission line feature. Wherein, the sign recognition model based on video AI analysis can adopt a video analysis model based on Baidu AI or other existing AI video analysis sign recognition model, which is not limited in the present application.

[0056] The above-mentioned embodiment of the present application, after the external video communication device is completely installed locally, then a data connection is established with the external video communication device through the access module, so that the device access terminal can obtain the video monitoring data transmitted by the external video communication device in real time, according to the obtained video monitoring data, the video monitoring data is preprocessed by the preprocessing module, and then the correlation analysis module performs correlation recognition processing according to the picture of the video monitoring data, recognizes the power transmission line features contained in the video monitoring picture, and correlates the video monitoring data containing the same power transmission line features according to the recognized power transmission line features, to obtain the correlation recognition result of the video monitoring data; the marking module marks the video monitoring data according to the correlation recognition result and further transmits the video monitoring data to the edge processing terminal. Through the device access terminal, the power transmission line video monitoring data collected by the external video monitoring device is preprocessed and correlation marked, which can help to intelligently collect the obtained video monitoring data, improve the accurate classification level of large-scale power transmission line video monitoring data, and based on the classification result, the video monitoring data for the same power transmission line is correlated and managed, which lays a foundation for subsequent abnormal analysis and processing of the power transmission line based on the correlated data.

[0057] Among them, based on the device access terminal, the preprocessing of the video monitoring data is completed, and the preprocessed data is transmitted to the edge processing terminal again, which also helps to improve the quality of the data, and lays a foundation for the subsequent accurate intelligent power transmission line anomaly analysis of the edge processing terminal for the preprocessed video monitoring data.

[0058] Among them, for the reason that the arrangement position or angle of the external video monitoring device collecting the power transmission line is limited, etc., the picture of the video monitoring data collected by the external video monitoring device is easily affected by environmental factors (for example, there is a large area of sky as a background area in the image, so that the power transmission line image exists back light, or the picture taken from the power transmission tower is easily affected by the reflection of the ground such as river, water, etc., resulting in the target power transmission line region also appears back light, etc.), which affects the accuracy and reliability of the subsequent correlation analysis based on the video monitoring data. Therefore, the present application also particularly proposes a preprocessing technical scheme for video monitoring data, which can adaptively perform adaptive enhancement processing based on the picture of the video monitoring data to improve the quality of the picture of the video monitoring data.

[0059] Preferably, the preprocessing module pre-processes the obtained video monitoring data, and the pre-processing further comprises:

[0060] The adaptive enhancement processing for the obtained video monitoring data comprises:

[0061] The obtained video monitoring data is represented by using the HSI model, and the brightness value I(x, y) of each pixel point is extracted;

[0062] Divide the image into regions according to the brightness values of each pixel point, and the specific region division method is as follows:

[0063] 1) Compare the brightness value I(x, y) of each pixel point with the preset first backlight brightness threshold Ih1, mark the pixel points with I(x, y) > Ih1 as type A pixel points, and count all type A pixel points into the set

[0064] 2) Select the pixel point (a, b) with the maximum brightness value from the obtained set as the reference point for diffusion detection, including:

[0065] 21) Mark the pixel point (a, b) as a type I pixel point, and take the pixel point (a, b) as the center point and detect the brightness value I(c, d) of other pixel points (c, d) within its 3×3 neighborhood range Area 3×3 (a, b). If there exists I(a, b) - I(c, d) < Is1, where Is1 represents the preset first brightness detection threshold, then mark the pixel point (c, d) as a type I pixel point;

[0066] 22) Take each newly added type I pixel point as the basis and repeat step 21) until no new type I pixel points appear;

[0067] 23) Count the type I pixel points connected to the pixel point (a, b), mark the connected region as type I region Area1, and count the pixel points included in this type I region into the set

[0068] 24) According to the set Extract the minimum brightness value of each pixel point in the set According to the brightness value I(m, n) of each pixel point (m, n) in the set According to the set Mark the pixel points that meet the conditions as type II pixel points, mark the connected region of type II pixel points as type II region Area2, and count the pixel points included in this type II region into the set And mark the pixel points that are marked as belonging to the set Remove the pixel points from the set Update the set and type I region Area1;

[0069] 25) For the marked type II region Area2, perform brightness adjustment processing on the pixel points (u, v) in the type II region Area2 to obtain the updated type II region Area2, and the brightness adjustment processing function used is:

[0070]

[0071] wherein I'(u, v) represents the luminance value of pixel point (u, v) after the luminance adjustment processing, wherein pixel point (u, v) is in the second-class region Area2, I(u, v) represents the luminance value of pixel point (u, v) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the second-class region Area2. wherein I'(u, v) represents the luminance value of pixel point (u, v) after the luminance adjustment processing, wherein pixel point (u, v) is in the second-class region Area2, I(u, v) represents the luminance value of pixel point (u, v) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the second-class region Area2. wherein I'(u, v) represents the luminance value of pixel point (u, v) after the luminance adjustment processing, wherein pixel point (u, v) is in the second-class region Area2, I(u, v) represents the luminance value of pixel point (u, v) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the second-class region Area2.

[0072] 26) After the luminance adjustment processing of the second-class region is completed, the luminance adjustment processing is further performed on each pixel point (m, n) in the first-class region Area1 to obtain the updated first-class region Area1, wherein the luminance adjustment processing function used is:

[0073]

[0074] wherein I'(m, n) represents the luminance value of pixel point (m, n) after the luminance adjustment processing, wherein pixel point (m, n) is in the first-class region Area1, I(m, n) represents the luminance value of pixel point (m, n) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the first-class region Area1. wherein I'(m, n) represents the luminance value of pixel point (m, n) after the luminance adjustment processing, wherein pixel point (m, n) is in the first-class region Area1, I(m, n) represents the luminance value of pixel point (m, n) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the first-class region Area1. wherein I'(m, n) represents the luminance value of pixel point (m, n) after the luminance adjustment processing, wherein pixel point (m, n) is in the first-class region Area1, I(m, n) represents the luminance value of pixel point (m, n) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the first-class region Area1. near2norArea1 wherein I'(m, n) represents the luminance value of pixel point (m, n) after the luminance adjustment processing, wherein pixel point (m, n) is in the first-class region Area1, I(m, n) represents the luminance value of pixel point (m, n) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the first-class region Area1. Ds1 represents the preset distance threshold, and D near2norArea1 wherein I'(m, n) represents the luminance value of pixel point (m, n) after the luminance adjustment processing, wherein pixel point (m, n) is in the first-class region Area1, I(m, n) represents the luminance value of pixel point (m, n) before the luminance adjustment processing, and Imin represents the minimum luminance value of each pixel point in the first-class region Area1.

[0075] 27) Detecting the set eliminating the pixel points which have been marked as belonging to the set and the set from the set to obtain the updated set and repeating step 2) based on the set until the set is empty.

[0076] 3) When the set is empty, the adaptive enhancement processing of the current video monitoring data is completed to obtain the preprocessed video monitoring data.

[0077] Optionally, the value range of Ih1 is 0.8 to 0.9, and preferably Ih1 = 0.85.

[0078] Optionally, Is1 is in the range of 0.05 to 0.15, preferably Is1 = 0.1.

[0079] Optionally, ω2 is in the range of 0.6 to 1, preferably ω2 = 0.8.

[0080] Optionally, Ds1 is in the range of 10 to the maximum side length DM of the video monitoring image frame, preferably S(Area1) represents the area of the Area1 category, represents the upward rounding operator.

[0081] Compared with the traditional processing method of cutting off the high-light position based on the image brightness information (the traditional cutting-off processing method is easy to eliminate the key power line feature information (such as the edge information of the signboard) when eliminating the background interference information of the high-light, which affects the accuracy of the positioning and extraction of the signboard in the subsequent correlation analysis process). The above embodiment of the present application also proposes a technical solution for adaptive enhancement processing of video monitoring data, which can perform adaptive enhancement processing on the glare phenomenon and the light scattering phenomenon (the phenomenon of eroding the edge of the foreground object due to the strong light background) in the video monitoring data frame caused by the strong light background, and eliminate the related negative effects. The preprocessing unit first performs threshold judgment based on the brightness values of the obtained video monitoring data pixels, extracts the strong light pixels in the image, and based on the obtained strong light pixels, proposes a diffusion detection technical solution, which can accurately detect the area (a category of area) affected by the strong light based on the change characteristics of the brightness value. Further considering the negative effects of the brightness change mitigation in special cases, the diffusion detection result may contain the regular foreground area, therefore, the reverse contraction detection is further performed according to the diffusion detection result to accurately extract the foreground area (a category of area) affected by the glare phenomenon and the light scattering phenomenon. Based on the extracted a category of area, the brightness suppression method is used to eliminate the brightness pollution caused by the background light glare phenomenon and the light scattering phenomenon, and accurately improve the display level of the foreground area in the a category of area. For the a category of area, the brightness value of the non-a category of area range is taken as the basis to adaptively adjust the a category of area affected by the strong background light or the reflection light phenomenon, and the brightness of the blurred edge part affected by the glare phenomenon and the light scattering phenomenon is adaptively repaired, which maximally eliminates the influence of the unclear foreground image caused by the strong background light or the reflection light, effectively improves the clarity of the power line area (foreground area) in the video monitoring data frame and the representation level of the key features, and lays a foundation for further correlation analysis and anomaly analysis based on the video monitoring data.

[0082] Preferably, the access module further comprises:

[0083] When the external video monitoring device accesses the system for the first time, a local routing protocol is transmitted to the external video monitoring device, so that the external video monitoring device can form a wireless local area network with other external video monitoring devices according to the local routing protocol, and transmit the collected video monitoring data to the device access terminal through direct transmission or multi-hop indirect transmission through the wireless local area network.

[0084] When the external video monitoring device accesses the system for the first time, a local routing protocol is transmitted to the external video monitoring device, so that the external video monitoring device can form a wireless local area network with other external video monitoring devices according to the local routing protocol, and transmit the collected video monitoring data to the device access terminal through direct transmission or multi-hop indirect transmission through the wireless local area network.

[0085] Preferably, the edge processing terminal comprises an extraction module, an anomaly analysis module, a control module and an alarm module; wherein,

[0086] The extraction module is used to extract video monitoring data according to a preset rule;

[0087] The anomaly analysis module is used to analyze the power transmission line anomaly according to the extracted video monitoring data, and obtain a power transmission line anomaly analysis result;

[0088] The control module is used to control the extraction module to further call other video monitoring data associated with the power transmission line that appears abnormal and transmit the other video monitoring data to the anomaly analysis module for further anomaly analysis processing when the power transmission line anomaly analysis result appears abnormal, and obtain a power transmission line anomaly analysis result corresponding to the other video monitoring data; and control the extraction module to ignore other video monitoring data associated with the power transmission line that is not called when more than N anomaly analysis results are abnormal through video monitoring data analysis of the same power transmission line, and control the alarm module to issue an abnormal alarm information corresponding to the anomaly analysis result;

[0089] The alarm module is used to issue an abnormal alarm information to the upper computer device.

[0090] In the edge processing of a large amount of video monitoring data related to power transmission lines, the edge processing terminal can extract the video monitoring data according to the preset rules, and perform power transmission line anomaly analysis based on the extracted video monitoring data. When the power transmission line anomaly analysis result is abnormal, further secondary analysis is performed on other associated video monitoring data (video monitoring data obtained by other devices from different angles and positions for shooting the same power transmission line) of the abnormal power transmission line, and the abnormal analysis results obtained by comprehensively analyzing the multiple associated video monitoring data are used to feed back the abnormal situation of the power transmission line. In one case, when the same power transmission line is analyzed based on two different video monitoring data and both of them show that the line is abnormal, it is determined that the line is abnormal, and other video monitoring data of the line does not need to be analyzed again to reduce the pressure of data processing. In another case, when all the video monitoring data of the same power transmission line are analyzed and no abnormality is found, it is determined that the abnormal analysis result of the power transmission line is normal. In another case, when only one video monitoring data based on the abnormal analysis result of the same power transmission line is abnormal, the situation can be determined as normal or abnormal of the power transmission line according to different construction ideas (the size of the parameter N value is set flexibly according to the actual situation).

[0091] Through the above embodiments, the edge processing terminal performs intelligent abnormal analysis and processing on the obtained power transmission line video monitoring data, and obtains the power transmission line abnormal analysis result corresponding to the video monitoring data. A control mode of a control module is proposed to optimize the extraction, analysis and result output of massive video monitoring data, so that in the process of processing video monitoring data by the edge processing terminal, the reliability can be ensured while effectively reducing the redundancy of data processing, improving the efficiency and intelligent level of data processing, and adapting to the intelligent processing efficiency of a large number of plug-and-play external video monitoring devices in a large-scale power transmission line scenario.

[0092] The host computer device includes a cloud service platform, a local management terminal, and other intelligent management terminals and servers set according to the actual situation.

[0093] Preferably, the abnormal analysis module performs power transmission line anomaly analysis according to the extracted video monitoring data, including:

[0094] The trained power transmission line anomaly analysis model is used to analyze and process the obtained video monitoring data, and the power transmission line anomaly analysis result is obtained; wherein the power transmission line anomaly analysis model is built based on the CNN convolutional neural network, the collected video monitoring data is input into the power transmission line anomaly analysis model, the power transmission line anomaly analysis model is used to extract multi-dimensional features of the video monitoring data, and the multi-dimensional feature information is used for anomaly recognition, and the classifier is combined to finally output the power transmission line anomaly analysis result; wherein the power transmission line anomaly analysis result includes normal and abnormal; the abnormal result includes different types of abnormal results such as cover, fire, bird damage, etc.

[0095] The artificial intelligence-based mode is used for intelligent anomaly analysis of the video monitoring data of the power transmission line, which helps to improve the accuracy and reliability of the anomaly analysis.

[0096] In one scenario, different types of anomaly analysis processing of the power transmission line equipment, such as cover identification, fire identification, bird damage identification, etc., can use the CNN convolutional neural network trained in the prior art to complete the corresponding anomaly analysis processing, so as to obtain the corresponding anomaly analysis result. As for the structure and parameter setting of the specific application network, the present application does not make specific limitation.

[0097] In another scenario, the CNN convolutional neural network used in the anomaly analysis model can also be obtained by training according to the pre-constructed training set (containing video monitoring data under normal conditions or various abnormal conditions, and the corresponding anomaly analysis result mark) and the test set, which is not limited in the present application.

[0098] It should be noted that each functional unit / module in each embodiment of the present application can be integrated in one processing unit / module, or each unit / module can be physically present alone, or two or more units / modules can be integrated in one unit / module. The integrated unit / module can be realized in the form of hardware or software functional unit / module.

[0099] Those skilled in the art can understand that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof. For software implementation, the procedures described herein can be directed to an associated hardware by a computer program. In implementation, the program can be stored in a computer readable medium or transmitted as one or more instructions or code on a computer readable medium. The computer readable medium includes computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. The storage media can be any available media that can be accessed by a computer. The computer readable medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

[0100] Finally, it should be noted that the above embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the protection scope of the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application.

Claims

1. A plug-and-play intelligent power line video monitoring system, characterized in that, The device access terminal and the edge processing terminal are included. The device access terminal is used for establishing a data connection with external video monitoring devices, obtaining video monitoring data collected by each external video monitoring device, and performing intelligent data correlation and recognition processing according to the obtained video monitoring data, marking the video monitoring data, and transmitting the marked video monitoring data to the edge processing terminal. The edge processing terminal performs abnormality identification and analysis processing on the obtained video monitoring data to obtain abnormality monitoring results of the power transmission line, and further sends an abnormal alarm information to an upper computer device when the abnormality monitoring results of the power transmission line are abnormal. The device access terminal includes an access module, a receiving module, a preprocessing module, a correlation analysis module, a marking module, and a transmission module. The access module is used for establishing a data connection with external video monitoring devices based on a preset communication protocol. The receiving module is used for receiving video monitoring data collected by external video monitoring devices. The preprocessing module is used for preprocessing the obtained video monitoring data, including standardization and filtering processing, to obtain preprocessed video monitoring data. The correlation analysis module is used for performing correlation and recognition processing on the preprocessed video monitoring data collected by each external video monitoring device, identifying the characteristics of the power transmission line in the video monitoring data, and correlating the video monitoring data for the same power transmission line according to the characteristics of the power transmission line to obtain correlation and recognition results of each video monitoring data. The marking module is used for marking the corresponding preprocessed video monitoring data according to the correlation and recognition results, so that the preprocessed video monitoring data carries the correlation identifier corresponding to the power transmission line. The transmission module is used for transmitting the preprocessed video monitoring data with the correlation identifier to the edge processing terminal.

2. The plug-and-play intelligent transmission line video monitoring system according to claim 1, wherein, A local management terminal is also included. The local management terminal is used for receiving the abnormal alarm information sent by the edge processing terminal and sending corresponding alarm signals according to the obtained abnormal alarm information.

3. The plug-and-play intelligent transmission line video monitoring system of claim 1, wherein, A cloud service platform is also included. The cloud service platform is used for obtaining video monitoring data and abnormality monitoring results of the power transmission line transmitted by the edge processing terminal, integrating the obtained video monitoring data and abnormality monitoring results of the power transmission line into a visual power transmission line monitoring model, and visually displaying the power transmission line monitoring data and abnormality monitoring results.

4. The plug-and-play intelligent transmission line video monitoring system of claim 1, wherein, The access module further includes: When the external video monitoring device accesses the system for the first time, a local routing protocol is transmitted to the external video monitoring device, so that the external video monitoring device can form a wireless local area network with other external video monitoring devices according to the local routing protocol, and transmit the collected video monitoring data to the device access terminal through direct transmission or multi-hop indirect transmission through the wireless local area network.

5. The plug-and-play intelligent transmission line video monitoring system of claim 1, wherein, The edge processing terminal includes an extraction module, an abnormality analysis module, a control module, and an alarm module. The extraction module is used for extracting video monitoring data according to a preset rule. The abnormality analysis module is used for performing abnormality analysis on the extracted video monitoring data to obtain abnormality analysis results of the power transmission line. The control module is configured to control the extraction module to further call other video monitoring data associated with the power transmission line with the abnormal analysis result and transmit the other video monitoring data to the abnormal analysis module for further abnormal analysis processing when the abnormal analysis result is abnormal; and control the extraction module to ignore other video monitoring data associated with the power transmission line and not to be called, and control the alarm module to issue abnormal alarm information corresponding to the abnormal analysis result when more than N abnormal analysis results are abnormal through analysis of the video monitoring data associated with the same power transmission line. The alarm module is configured to issue the abnormal alarm information to the upper computer device.

6. The plug-and-play intelligent power line video monitoring system according to claim 5, wherein, In the abnormal analysis module, the power transmission line is analyzed according to the extracted video monitoring data, including: The trained power transmission line abnormal analysis model is used to analyze and process the obtained video monitoring data to obtain a power transmission line abnormal analysis result; wherein the power transmission line abnormal analysis model is built based on a CNN convolutional neural network, the collected video monitoring data is input into the power transmission line abnormal analysis model, the video monitoring data is extracted by the power transmission line abnormal analysis model in multiple dimensions, and abnormal identification is performed based on the obtained multi-dimensional feature information, and finally the power transmission line abnormal analysis result is output by combining the classifier; wherein the power transmission line abnormal analysis result includes normal and abnormal; the abnormal result includes different types of abnormal results of cover, fire and bird damage.

Images