A method, device and computer-readable storage medium for monitoring transmission line images

Abstract

The present application relates to the field of artificial intelligence technology and provides a method for monitoring images of power transmission lines, comprising the following steps: the first sub-process of the control module obtains each monitoring image captured by the first camera and the received second camera; the first sub-process performs fusion processing on each of the monitoring images to obtain a first image to be identified; wherein the main process monitors the exposure parameter of the first camera in real time and determines whether the ambient light applicable to the exposure parameter changes; when the illuminance value corresponding to the applicable ambient light changes and is less than the illuminance threshold, the clarity of the second image to be identified is obtained; if the clarity of the second image to be identified does not meet the requirements and there is no room for parameter adjustment, the number of enabled second cameras is adjusted. Based on this, the clarity of the image to be identified in a low-light environment can be improved and energy consumption can be saved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and device for monitoring transmission line images, and a computer-readable storage medium. Background Art

[0002] With the development of smart grid technology, transmission line monitoring systems are playing an increasingly important role in ensuring the safe operation of power grids. These systems typically consist of on-site transmission line monitoring devices and control platforms. Transmission line monitoring devices are essential for ensuring the safe and efficient operation of power grids. These devices come in a variety of types and can monitor the status of transmission lines and the surrounding environment in real time, promptly identifying and warning of potential safety hazards. Existing monitoring systems...

[0003] Among them, the transmission line image monitoring device collects image information of the transmission line and the surrounding environment and identifies safety hazards based on the images, and issues early warnings to the control platform or alarms through on-site equipment. It usually adopts a 24-hour uninterrupted monitoring method, so it is often necessary to use multiple cameras for image collection to achieve real-time monitoring during the day and night.

[0004] In the existing technology, monitoring image collection is achieved by timing the activation of low-light cameras at night. However, the timing activation method is difficult to adapt to changes in ambient light in different geographical locations and seasonal climates, resulting in insufficient clarity of monitoring images and untimely identification of safety hazards. Summary of the Invention

[0005] In order to solve the above technical problems, embodiments of the present application provide a transmission line image monitoring method, a transmission line image monitoring device, and a computer storage medium.

[0006] Specifically, the transmission line image monitoring method provided in the embodiment of the present application is applied to a transmission line image monitoring device, the device including a control module and an image acquisition module, wherein the image acquisition module includes a first camera and at least one second camera, the first camera is used to acquire images within the entire monitoring period, and the second camera is in a closed state by default, and the method includes the steps of: a first sub-process of the control module acquires each monitoring image acquired by the first camera and the received second camera; wherein the first sub-process is created by the main process in the control module after controlling the opening and closing of each second camera according to the exposure parameter of the first camera; the first sub-process The process performs fusion processing on each of the monitoring images to obtain a first image to be identified; and identifies the first image to be identified based on a security identification model to obtain a security identification result; wherein the main process controls the opening and closing of each of the second cameras according to the exposure parameters of the first camera, including: real-time monitoring of the exposure parameters of the first camera, and determining whether the ambient light applicable to the exposure parameters changes; when the illuminance value corresponding to the applicable ambient light changes and is less than the illuminance threshold, obtaining the clarity of the second image to be identified; when the clarity of the second image to be identified does not meet the requirements and there is no parameter adjustment space, adjusting the number of opened second cameras.

[0007] Based on the above technical solution, the main process can control the number of second cameras that are turned on according to changes in ambient light. In this way, in a low-light environment, the monitoring images collected by the first camera and the second camera can be fused and processed to obtain an image to be identified with a clarity that meets the requirements, so as to ensure the accuracy of security identification and help reduce the energy consumption of the monitoring device. Furthermore, the main process obtains the dynamic changes in ambient light according to the changes in the exposure parameters of the first camera, and can obtain the changes in ambient light more timely, and accurately control the opening and closing status of the second camera based on the judgment of the changes in ambient light. In addition, when it is determined that the ambient light has changed, the main process gives priority to ensuring the clarity of the image to be identified by adjusting the parameters of the cameras that have been turned on, which not only reduces energy consumption but also saves process resources.

[0008] In one implementation, the exposure parameter is adaptively adjusted by a built-in program of the first camera according to ambient light.

[0009] Based on this, the main process uses the built-in photosensitivity system of the first camera to capture changes in ambient light, making full use of existing resources and saving device costs.

[0010] In one embodiment, determining whether the ambient light applicable to the exposure parameters has changed includes: determining the ambient light applicable to the exposure parameters based on a correspondence file between the exposure parameters and the ambient light, and comparing the ambient light with the ambient light determined last time to determine whether the ambient light has changed; wherein the correspondence is determined based on a configuration file provided by the first camera manufacturer, or generated based on historical data analysis.

[0011] In one embodiment, the clarity generation of the second image to be identified includes: a second sub-process identifies key elements in the second image to be identified based on an image recognition model, matches the identified key element information based on standard element information to determine the baseline clarity of the second image to be identified, and when the baseline clarity of the second image to be identified meets the preset requirements, performs security identification on the second image to be identified based on the security identification model, corrects the baseline clarity according to the security identification result, and obtains the clarity of the second image to be identified.

[0012] Based on this technical solution, the second sub-process determines the clarity of the second image to be identified during the security recognition process, allowing the main process to directly obtain the clarity of the second image to be identified without additional calculations, thereby improving system processing efficiency. Furthermore, the second sub-process uses the recognition results of the security recognition model to correct the baseline clarity, improving the accuracy of the clarity judgment of the second image to be identified.

[0013] In one implementation, adjusting the number of second cameras turned on includes: controlling the turning on or pre-closing of some second cameras according to the changing trend of the ambient light; fusing the monitoring images captured by the first camera and the adjusted second cameras to obtain a third image to be identified; determining whether the clarity of the third image to be identified meets the requirements; if it does not meet the requirements and there is no room for parameter adjustment, increasing the number of second cameras turned on or pre-closed.

[0014] Based on the above technical solution, the main process gradually controls the number of second cameras turned on, and combines parameter adjustment to finally determine the number of second cameras turned on, which can minimize the change of the second camera status, ensure the full utilization of camera resources, and avoid frequent opening and closing of the second camera.

[0015] In one embodiment, the fusing processing of each of the monitoring images to obtain the first image to be identified includes: determining the difference in system time between each of the second cameras and the first camera; based on the difference, obtaining monitoring images collected at the same time from each of the second cameras and the first camera; and fusing the obtained monitoring images based on a fusion algorithm to obtain the first image to be identified.

[0016] In one embodiment, the method further includes: if the clarity of the third image to be identified does not meet the requirements and there is room for parameter adjustment, analyzing defects in the third image to be identified and adjusting the exposure parameters of each of the second cameras according to the defect type.

[0017] Based on the above technical solution, the parameters of the second camera are adjusted according to the defects in the third recognition image, so that the parameters can be adjusted quickly and accurately.

[0018] Based on the same inventive concept, an embodiment of the present application also provides a transmission line image monitoring device, which includes a control module and an image acquisition module, wherein the image acquisition module includes a first camera and at least one second camera, the first camera is used to collect images within the entire monitoring period, the second camera is in a closed state by default, and the control module is used to implement the method provided in the above embodiment.

[0019] In one embodiment, the monitoring device is fixedly mounted on a tower.

[0020] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the above method when executed by a processor.

[0021] In summary, the embodiments of the present application include at least the following beneficial technical effects:

[0022] 1. Realize 24-hour real-time monitoring based on the first camera, and automatically control the opening of the second camera in low-light conditions to improve the clarity of the image to be identified, thereby ensuring the accuracy of security identification, making it easier for back-end management personnel to understand the on-site situation and improving user experience.

[0023] 2. Detect changes in ambient light based on the exposure parameter adjustments of the first camera, making full use of existing resources and accurately assisting the first camera.

[0024] 3. With the first camera as the main camera and the second camera as the auxiliary camera, the clarity of the image to be recognized is guaranteed by adjusting the parameters first to save energy consumption of the device, avoid frequent activation of the second camera, and extend the life of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings that constitute a part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application.

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.

[0027] Figure 1A A schematic structural diagram of a power transmission line image monitoring system provided in an embodiment of the present application is shown.

[0028] Figure 1B A flow chart of a power transmission line image monitoring method provided in an embodiment of the present application is shown.

[0029] Figure 2 A flow chart of a method for a main process to create a first sub-process in an embodiment of the present application is shown.

[0030] Figure 3 A flow chart of a method for adjusting the number of enabled second cameras by a main process in an embodiment of the present application is shown.

[0031] Figure 4 A flow chart of a method for fusing monitoring images in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0032] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0033] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, and "first", "second" and various numerical numbers are only distinctions for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0034] The features, structures, or characteristics of this application may be combined in any suitable manner in one or more embodiments. In the various embodiments of this application, the order of the sequence numbers of the processes does not necessarily indicate the order of execution. The order of execution of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation of the embodiments of this application.

[0035] Some optional features in the embodiments of the present application can be implemented independently in some scenarios without relying on other features to solve corresponding technical problems and achieve corresponding effects. They can also be combined with other features in some scenarios according to needs.

[0036] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments of this application, unless otherwise specified and there is no logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0037] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0038] Please refer to Figure 1A , Figure 1A A power transmission line image monitoring system provided in an embodiment of the present application is shown, including a power transmission line image monitoring device 11 and a monitoring server 12 .

[0039] The transmission line image monitoring device 11 is installed at the site of the monitored transmission line and is used to collect image information of the monitored transmission line and the surrounding environment. For example, it is fixedly installed on a tower to ensure the stability of the collected image. The transmission line image monitoring device 11 includes a control module 111, an image acquisition module 112, a power supply module 113, and a communication module 114. The image acquisition module 112 includes a first camera 112a and at least one second camera 112b. The first camera 112a is a main camera with a higher resolution requirement and is used to collect images during the entire monitoring period. The second camera 112b is an auxiliary camera with a lower resolution requirement and is used to assist the first camera 112a in image acquisition in low-light environments. The second camera 112b is in an off state by default and is controlled by the control module 111.

[0040] The power supply module 113 includes a solar panel, a battery, and a power control module, and is used to power the image acquisition module 112 and the control module 111. The communication module 114 includes a GPS positioning module and a master station communication module, and is used to obtain location information and communicate with the monitoring server 12.

[0041] Control module 111 is used to control and manage other modules, identify and analyze monitoring images collected by image acquisition module 112, and send notifications to monitoring server 12 via communication module 114 when a safety hazard is identified, prompting backend management personnel to investigate the safety hazard. Backend management personnel can also send monitoring instructions to control module 111 through monitoring server 12 to request real-time monitoring images and analysis results.

[0042] Please refer to the Figure 1B , Figure 1B The power transmission line image monitoring method provided in an embodiment of the present application is illustrated, specifically comprising the following steps:

[0043] S101: A first sub-process obtains monitoring images captured by a first camera and received by a second camera.

[0044] In practice, after the main process in control module 111 controls the activation and deactivation of the second camera based on the exposure parameters of the first camera, it creates a first sub-process and synchronizes information about the currently activated second camera to the first sub-process. The currently activated second camera and the first camera are used to capture monitoring images at different exposure levels, i.e., the exposure parameters are different.

[0045] It is worth noting that the control of the second camera's activation and deactivation mentioned in the embodiments of this application includes the control of the activation and deactivation of any second camera. In other words, when the activation and deactivation status of any second camera controlled by the main process changes, a child process is created to implement security monitoring of the power transmission line based on all currently activated second cameras and the first camera.

[0046] S102: The first sub-process performs fusion processing on each monitoring image to obtain a first image to be identified.

[0047] In a specific example, performing fusion processing on each monitoring image specifically includes:

[0048] First, multiple images of the transmission line site under different exposure settings can be collected based on the first camera and each second camera, including normal exposure, overexposure and underexposure images, among which the images collected by the first camera are normal exposure images.

[0049] Then, image alignment is performed. Because the shooting angles of each camera may be slightly different, the captured images need to be aligned to ensure that they are accurately matched when fused.

[0050] Then, they are selectively fused based on the strengths of each image: the normally exposed image is used to preserve the main details of the scene, the overexposed image is used to capture details in the highlights, and the underexposed image is used to capture details in the shadows.

[0051] Finally, a fusion algorithm may be used to fuse these fusion objects, wherein the fusion algorithm includes stack averaging, median blending, Laplacian pyramid fusion, etc., to smoothly transition between different exposure areas and reduce artificial traces.

[0052] Preferably, after fusion, further adjustments can be made, such as contrast, brightness, saturation, etc., to make the final image natural and balanced.

[0053] Based on the above fusion processing, the first image to be recognized has a higher definition, which not only improves the accuracy of subsequent image recognition, but also facilitates the review of back-end management personnel.

[0054] S103: The first sub-process identifies the first image to be identified based on the security identification model to obtain a security identification result.

[0055] In one implementation, the safety identification model is a pre-built AI (artificial intelligence) model based on deep learning algorithms, such as convolutional neural networks (CNN), recurrent neural networks (RNN), and generative adversarial networks (GAN). It can identify the type and location of risk elements in the input monitoring image and output a safety identification result that includes the name and location of the risk element. Risk elements include, but are not limited to, safety hazards such as foreign objects in wires, smoke, fire points, and cranes, tower cranes, excavators, and other large construction machinery.

[0056] Based on the above method, by fusing the monitoring images at different exposure levels captured by the first camera and the turned-on second camera to obtain a first image to be identified with higher detail clarity, the accuracy of image recognition can be improved, and a clearer monitoring screen can be presented to the back-end management personnel so that the back-end management personnel can confirm the security identification results based on the first image to be identified.

[0057] It's worth noting that in the embodiments of this application, the first sub-process continuously performs real-time analysis based on the monitoring images captured by the first camera. When an anomaly is detected, further analysis is performed in conjunction with the monitoring images captured by the second camera, triggering the execution of step S102. This allows for 24 / 7 real-time monitoring of the transmission line, while also optimizing the monitoring images captured by the first camera with the monitoring images captured by the second camera to improve clarity and further confirm risk identification to increase risk identification accuracy.

[0058] In implementation, the first sub-process may also trigger the execution of step S102 after receiving an instruction sent by the back-end manager through the monitoring server 12 to satisfy the back-end manager's need for real-time acquisition of on-site conditions. In addition, the first sub-process may also periodically trigger the execution of step S102.

[0059] In the above step S101, the method for the main process to create the first sub-process can be referred to Figure 2 The method is executed by the main process in the control module 111, and includes the main process's control process of each second camera, specifically including the following steps:

[0060] S210: Monitor the exposure parameters of the first camera in real time.

[0061] Specifically, in the embodiment of the present application, the first camera 112a is the main camera, which remains turned on during the entire monitoring period and collects on-site images in real time. The first camera 112a has a photosensitive element and a built-in automatic dimming program, which can automatically adjust the exposure parameters according to the ambient light.

[0062] The control module 111 can create a main process for monitoring the automatic dimming program of the first camera. When the automatic dimming program modifies the exposure parameters, the modified exposure parameters are read. In implementation, the modified exposure parameters can be obtained by building a trigger into the automatic dimming program, or by reading the exposure parameters through an interface to obtain the exposure parameters.

[0063] S220: Determine whether the ambient light to which the exposure parameter is applicable has changed.

[0064] Specifically, when the main process obtains the modified exposure parameters, it can determine the ambient light suitable for the current exposure parameters based on the corresponding relationship between the exposure parameters and the ambient light, and compare it with the previously determined ambient light to determine whether the ambient light has changed. In one example, the corresponding relationship between the exposure parameters and the ambient light is determined based on a configuration file provided by the first camera manufacturer.

[0065] In another example, the correspondence between the exposure parameter and the ambient light is generated based on historical data analysis, that is, the ambient light is obtained with the help of the built-in photosensitive element of the first lens or the second lens, and the exposure parameter of the first camera is read accordingly, thereby generating a correspondence between the two. In this example, the exposure parameter of the first camera can be automatically adjusted or obtained by adjustment by the main process.

[0066] It is understandable that the exposure parameter value corresponding to a certain ambient light may be a range of values. Therefore, when the exposure parameter changes, the applicable ambient light may remain unchanged. Therefore, when the exposure parameter changes, it is also necessary to determine whether the ambient light has changed.

[0067] In this embodiment, whether the ambient light has changed can be determined based on the relationship between the illuminance values corresponding to the current ambient light and the previous ambient light. Furthermore, when it is determined that the current ambient light has changed, subsequent operations can also be determined based on the relationship between the current illuminance value and the illuminance threshold.

[0068] Among them, the illumination threshold is determined according to the clarity of the image captured by the first camera. For example, the first camera continuously captures images under ambient light with continuously changing illumination values, and the clarity analysis of the images captured under each ambient light is performed to determine the range of ambient light illumination values corresponding to the images whose clarity meets the monitoring requirements, and then determine the illumination threshold. When the illumination value of the ambient light is less than the illumination threshold, the clarity of the image captured by the first camera does not meet the requirements. When the illumination value is greater than or equal to the illumination threshold, it meets the requirements.

[0069] When the relationship between the illuminance value corresponding to the applicable ambient light and the illuminance threshold changes from less than to greater than or equal to, execute step S231; when the illuminance value corresponding to the applicable ambient light changes and is less than the illuminance threshold, execute step S232; when the ambient light does not change or the illuminance value remains greater than or equal to the illuminance threshold, return to execute step S210.

[0070] S231, turn off all second cameras.

[0071] When the relationship between the illuminance value and the illuminance threshold changes from less than to greater than or equal to, it means that the ambient light becomes brighter, and at this brightness, the monitoring image captured by the first camera meets the requirements. Therefore, all second cameras can be turned off to reduce the energy consumption of the transmission line image monitoring device 11.

[0072] S232: Obtain the clarity of the second image to be recognized.

[0073] Among them, the second image to be identified refers to the sub-process currently performing security monitoring (hereinafter referred to as the second sub-process) based on the monitoring images captured by the first camera and the received second camera, and the fusion processing method is the same as that of the first image to be identified.

[0074] When the illuminance value corresponding to the applicable ambient light changes and is less than the illuminance threshold, it indicates that the current ambient light has dimmed, which may cause the clarity of the second image to be recognized to fail to meet the requirements. Therefore, it is necessary to further determine whether a new second camera needs to be turned on to improve the clarity of the image to be recognized.

[0075] It is worth noting that the main process can obtain the clarity of the second image to be identified from the second sub-process. Specifically, the process of the second sub-process performing security identification based on the second image to be identified includes first identifying key elements in the second image to be identified based on the image recognition model, matching the identified key element information based on the standard element information to determine the baseline clarity of the second image to be identified, and if the baseline clarity of the second image to be identified meets the preset requirements, performing security identification on the second image to be identified based on the security identification model, correcting the baseline clarity based on the security identification results to obtain the clarity of the second image to be identified, and storing the clarity of the second image to be identified, so that the main process can obtain the clarity of the second image to be identified by accessing the storage. If the baseline clarity of the second image to be identified does not meet the preset requirements, the second sub-process directly stores the baseline clarity as the clarity of the second image to be identified, directly determines that the current on-site environment is abnormal, and issues an alarm to the monitoring server 12.

[0076] It is worth noting that the task types handled by each sub-process created by the main thread in the embodiment of the present application are the same, and the only difference is that there is a difference in the second camera used.

[0077] Among them, the image recognition model is pre-trained based on the image recognition algorithm and historical images to be recognized. The input layer is the image to be recognized, and the output content includes the total number of key elements contained in the image to be recognized, the type of key elements, the position coordinates and the corresponding detail features. Correspondingly, the standard element information includes the required number of key elements, the type of each key element, the position coordinates and the corresponding detail features.

[0078] It is understandable that since the monitored ranges of the monitored transmission lines are different and the on-site environments are also different, the standard element information needs to be set according to the actual conditions of the monitored environment. For example, relatively static elements such as conductors, insulators, hardware, and buildings and mountains in the environment can be marked as key elements, and the standard element information is the information corresponding to all pre-marked key elements.

[0079] It is worth noting that when determining the baseline clarity of the second image to be identified based on the comparison results, it is not required that all key elements be identified. Instead, it is required that at least some key factors be identified and that the relevant information of the identified key elements be accurate. This is to take into account the possibility that some key elements may be obscured. Therefore, the baseline clarity can be corrected based on the security recognition result to obtain the clarity of the second image to be identified. For example, when the security recognition result shows that there is an obstruction on the wire, and when the wire is not identified in the image recognition result, the recognition result is considered normal and does not affect the clarity judgment. However, when the security recognition result shows that it is normal, if the number of unidentified key factors exceeds a threshold, the baseline clarity is lowered to indicate that the clarity of the second image to be identified does not meet the requirements.

[0080] It is worth noting that if no key factors are identified based on the image recognition model, it may be because the monitoring screen is completely blocked or there is an abnormality in the first camera, then it is determined that the baseline clarity does not meet the preset requirements, and the second sub-process will directly send an alarm to the monitoring server.

[0081] S240: Determine whether the clarity of the second image to be recognized meets the requirement.

[0082] In implementation, the clarity of the second image to be recognized can be represented by the recognition accuracy of the key elements. Therefore, whether the clarity of the second image to be recognized meets the requirement can be determined based on the recognition accuracy requirement.

[0083] The main process can use the clarity corresponding to the first second image to be identified after the parameter change read from the storage space according to the time when the exposure parameter changes as the judgment object.

[0084] When the clarity does not meet the requirements, you can further choose to execute step S251 or S252 based on the adjustable conditions of the exposure parameters, including: if there is no parameter adjustment space, execute step S251, otherwise execute step S252; when the analysis result indicates that the clarity meets the requirements, return to step S210 and start the next round of monitoring.

[0085] Specifically, whether there is room for adjustment can be determined based on whether the current exposure parameter range of the first camera and the turned-on second camera has reached the upper limit, or whether the exposure parameter can be further adjusted based on whether the number of adjustments has reached the upper limit.

[0086] S251, adjusting the number of second cameras to be enabled.

[0087] In the embodiment of the present application, the second camera is closed by default, and the main process controls the opening and closing state of each second camera. When it is determined in step S240 that the clarity of the second image to be identified does not meet the requirements and the exposure parameter cannot be adjusted, the main process will choose to change the opening and closing state of the second camera, thereby realizing the control of the number of second cameras opened, which not only saves the energy consumption of the monitoring device, but also reduces the data processing amount of the sub-process. Please refer to Figure 3 In the embodiment of the present application, the method for the main process to adjust the number of enabled second cameras specifically includes:

[0088] S310: Controlling the opening or pre-closing of part of the second camera according to the changing trend of the ambient light.

[0089] During implementation, when the ambient light becomes weak, a second camera is turned on; when the ambient light becomes strong, some of the second cameras are pre-closed, wherein pre-closing means marking the second camera as closed, and in subsequent steps, the image data of these second cameras are not used, but they are not actually closed, so as to avoid affecting the security identification of the second sub-process.

[0090] S320: Perform fusion processing on the monitoring images collected by the first camera and the adjusted second cameras to obtain a third image to be recognized.

[0091] As mentioned above, the adjusted second cameras in this step refer to all second cameras that are currently turned on and not marked as turned off. The main process's fusion processing of each monitoring image is the same as the relevant processing process of the second sub-process described above, and will not be repeated here.

[0092] S330: Determine whether the clarity of the third image to be recognized meets the requirements.

[0093] If the requirements are not met and there is room for parameter adjustment, step S341 is executed. If the requirements are not met and there is no room for parameter adjustment, the process returns to step S310 and continues to increase the number of open or pre-closed items. If the requirements are met, step S342 is executed. It is worth noting that if there is no room for parameter adjustment and the number of open or closed items cannot be increased, it indicates that an abnormal situation has occurred on site or the existing equipment can no longer meet the on-site monitoring requirements. The main process directly reports to the control server 12 to remind the back-end management staff to confirm the actual situation on site.

[0094] In this step, the method of determining whether the clarity of the third image to be identified meets the requirements is the same as the method of determining whether the clarity of the second image to be identified meets the requirements, and the method of determining the clarity of the third image to be identified is the same as the method of determining the clarity of the second image to be identified by the second sub-process. The difference is that the clarity confirmation process of the third image to be identified is executed by the main process.

[0095] S341: Adjust the exposure parameters of each second camera, and return to step S320.

[0096] In one implementation, the main thread adjusting the exposure parameters of each second camera includes analyzing defects in the third image to be identified and adjusting the exposure parameters of each second camera according to the defect type.

[0097] Specifically, since the exposure parameters of the first camera are automatically adjusted according to the ambient light and have a high resolution, it can be used as the adjustment center line to set the exposure parameters of each second camera. In one example, when the defect type in the third image to be identified is that the highlight elements cannot be identified, the exposure parameters of some second cameras are adjusted to increase the exposure. When the defect type is that the key elements in the shadow area cannot be identified, the exposure parameters of some second cameras can be adjusted to reduce the exposure.

[0098] Exposure parameters include, but are not limited to, aperture, shutter speed, exposure compensation, white balance, backlight compensation, and exposure time, and are determined based on the device conditions of the second camera.

[0099] In one example, if the number of second cameras used to generate the third image to be identified is greater than or equal to two, in the process of adjusting the parameters, it is first ensured that the exposure of the image captured by at least one second camera is higher than that of the first camera, and the exposure of the image captured by at least one second camera is lower than that of the first camera. Based on this, images with normal exposure, high exposure and low exposure can be obtained, providing a wider data basis for image fusion processing and improving the quality of image fusion.

[0100] S342, creating a first sub-process for performing safety monitoring of the power transmission line based on the second camera that is currently in the turned-on state, and turning off the second camera that is pre-turned off.

[0101] When the third image to be identified meets the requirements, it indicates that the image acquisition module under the current setting state can be used to acquire clear monitoring images. The main thread creates another sub-process, namely the first sub-process, which is used to perform safety monitoring of the transmission line based on the currently turned on second camera and the first camera. The safety monitoring method of the transmission line by the first sub-process is the same as that of the second sub-process. The difference is that the device for acquiring the image has changed.

[0102] It is understandable that the second sub-process continues to monitor the safety of the power transmission line while the main process adjusts the status and parameters of the second camera. When the first sub-process is started and outputs the first safety identification result, the main process closes the second sub-process. This ensures the continuity of the safety monitoring process.

[0103] In a preferred embodiment, turning off the second camera includes turning off the power to save energy. In another embodiment, turning off the second camera can be setting it to sleep mode, and the specific method can be set according to the configuration supported by the second camera.

[0104] S252: Adjust the exposure parameters of the second camera, and execute step S232 again after the adjustment is completed.

[0105] The process of adjusting the exposure parameters of the second camera in this step can be referred to Figure 3 The relevant steps in the method shown are different in that this step does not involve the control of opening and closing the second camera, which will not be repeated here.

[0106] Based on the above method, the main process controls the opening and closing of the second camera according to the changes in the exposure parameters of the first camera. It can automatically control the opening and closing of the second camera according to the changes in the ambient light, so that the image to be identified with clarity that meets the requirements can be obtained in different lighting environments. It not only ensures the recognition accuracy of the security recognition model, but also reduces the energy consumption of the monitoring device.

[0107] In an embodiment of the present application, a method for fusing the monitoring images to obtain an image to be identified specifically includes:

[0108] S410: Determine a difference in system time between each second camera and the first camera.

[0109] S420: Align the acquisition time of each second camera with that of the first camera based on the difference.

[0110] S430: Acquire monitoring images captured by the first camera and each second camera.

[0111] S440: performing fusion processing on each monitoring image based on a fusion algorithm to obtain an image to be identified.

[0112] By performing time alignment first, it can be ensured that the image acquisition time of each camera is the same, providing accurate basic data for image fusion processing, and avoiding the inability to obtain images captured at the same time due to confusion in the system time of each second camera due to irregular opening and closing.

[0113] In another embodiment of the present application, the monitoring images captured by each second camera are corrected so that they can be aligned with the monitoring images captured by the first camera. It is understandable that the installation positions of the cameras will be slightly different, so the shooting angles are different. Aligning the monitoring images can ensure the consistency of image superposition during the fusion process. It is worth noting that the first camera and the second camera provided in the embodiment of the present application are both fixedly installed and have a fixed shooting angle. Based on this, the difference between the shooting angles of each second camera and the first camera can be obtained in advance, and the images captured by each second camera can be aligned according to the difference.

[0114] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method.

[0115] Those skilled in the art will appreciate that all or part of the steps in the above-described embodiments can be implemented by instructing related hardware through a program. The program is stored in a storage medium and includes a number of instructions for causing a device (such as a microcontroller or chip) or a processor to execute all or part of the steps in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0116] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A method for monitoring transmission line images, characterized in that: The method is applied to a power transmission line image monitoring device, which includes a control module and an image acquisition module, wherein the image acquisition module includes a first camera and at least one second camera, the first camera is used to acquire images within the entire monitoring period, and the second camera is in a closed state by default. The method includes the following steps: The first sub-process of the control module obtains each monitoring image captured by the first camera and the received second camera; wherein the first sub-process is created by the main process in the control module after controlling the opening and closing of each second camera according to the exposure parameter of the first camera; The first sub-process performs fusion processing on the monitoring images to obtain a first image to be identified; and identifying the first image to be identified based on a security identification model to obtain a security identification result; The main process controls the opening and closing of each second camera according to the exposure parameter of the first camera, including: monitoring the exposure parameters of the first camera in real time, and determining whether the ambient light to which the exposure parameters apply changes; When the illumination value corresponding to the applicable ambient light changes and is less than an illumination threshold, obtaining the clarity of the second image to be recognized; if the clarity of the second image to be recognized does not meet the requirements and there is no room for parameter adjustment, adjusting the number of activated second cameras; the exposure parameter is adaptively adjusted by a built-in program of the first camera based on the ambient light; determining whether the ambient light applicable to the exposure parameter has changed includes: determining the ambient light applicable to the exposure parameter based on the file of the correspondence relationship between the exposure parameter and the ambient light, and comparing it with the previously determined ambient light to determine whether the ambient light has changed; wherein the correspondence relationship is determined based on a configuration file provided by the manufacturer of the first camera or generated based on historical data analysis; generating the clarity of the second image to be recognized includes: a second sub-process identifying key elements in the second image to be recognized based on an image recognition model, matching the identified key element information based on standard element information to determine a baseline clarity of the second image to be recognized, and if the baseline clarity of the second image to be recognized meets preset requirements, performing security recognition on the second image to be recognized based on the security recognition model, and correcting the baseline clarity based on the security recognition result to obtain the clarity of the second image to be recognized.

2. The method according to claim 1, characterized in that The adjusting the number of enabled second cameras includes: According to the changing trend of the ambient light, controlling to open or pre-close part of the second cameras; fusing the monitoring images captured by the first camera and the adjusted second cameras to obtain a third image to be identified; Determine whether the clarity of the third image to be recognized meets the requirements; if it does not meet the requirements and there is no room for parameter adjustment, increase the number of opening or pre-closing the second camera.

3. The method according to claim 2, characterized in that The fusing the monitoring images to obtain the first image to be identified comprises: Determine a difference between the system time of each of the second cameras and the system time of the first camera; Based on the difference, obtaining monitoring images captured at the same time from each of the second cameras and the first camera; The acquired monitoring images are fused based on a fusion algorithm to obtain the first image to be identified.

4. The method according to claim 2, characterized in that The method further includes: if the clarity of the third image to be identified does not meet the requirements and there is room for parameter adjustment, analyzing defects in the third image to be identified and adjusting the exposure parameters of each of the second cameras according to the defect type.

5. A transmission line image monitoring device, characterized in that: The device includes a control module and an image acquisition module, wherein the image acquisition module includes a first camera and at least one second camera, the first camera is used to acquire images within the entire monitoring period, and the second camera is in a closed state by default. The control module is used to implement the method described in any one of claims 1 to 4.

6. The device according to claim 5, characterized in that The device is fixedly installed on the tower.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images