Electric power tower fitting identification control method and related device

Abstract

The embodiment of the invention discloses an electric power tower fitting identification control method and a related device, and the method comprises the steps: carrying out the photographing of a target electric power tower through a pan-tilt camera according to a first photographing parameter, and obtaining a first image; electric power tower fitting multi-scale target identification is carried out on the first image through a target electric power tower fitting identification model, k electric power tower fittings are obtained, and each electric power tower fitting corresponds to one scale parameter; determining a target working parameter corresponding to the pan-tilt module and a second shooting parameter of the pan-tilt camera according to the scale parameter of the target first electric power tower fitting; the target first electric power tower fitting is one electric power tower fitting in the k electric power tower fittings; and controlling the pan-tilt module to work according to the target working parameter, and controlling the pan-tilt camera to shoot the target first electric power tower fitting according to the second shooting parameter to obtain a second image so as to improve the screen-to-body ratio of the target first electric power tower fitting in the second image.

Description

Technical Field

[0001] The present application relates to the field of image processing technology or the field of electric power technology, and in particular to a method for identifying and controlling electric power tower hardware and related devices. Background Art

[0002] In actual applications, there are many types of power pole tower hardware with different uses, such as various wire clamps for installing conductors; various hanging rings for forming insulator strings; various crimping tubes for connecting conductors; various types of spacers on repairing split conductors, various types of wire pulling hardware for power poles, etc. Power pole tower hardware is related to the safety of conductors or poles. Even if one is damaged, it may cause line failure. However, power pole tower hardware is often high above the ground, and maintenance is relatively inconvenient. Therefore, how to perform accurate image recognition of power pole tower hardware to improve the maintenance efficiency of power pole tower hardware needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide a power pole tower hardware identification and control method and related devices, which perform accurate image recognition of power pole tower hardware to improve the efficiency of the maintenance and upkeep of power pole tower hardware.

[0004] In a first aspect, an embodiment of the present application provides a method for identifying and controlling power pole tower hardware, which is applied to an electronic device, wherein the electronic device is communicatively connected to a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the method includes:

[0005] The target power pole tower is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image;

[0006] The target power pole tower hardware recognition model is used to perform multi-scale target recognition of power pole tower hardware on the first image to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer;

[0007] Determine the target working parameter corresponding to the pan / tilt module and the second shooting parameter of the pan / tilt camera according to the scale parameter of the target first power pole tower fitting; the target first power pole tower fitting is one of the k power pole tower fittings;

[0008] The gimbal module is controlled to operate with the target operating parameters, and the gimbal camera is controlled to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

[0009] In a second aspect, an embodiment of the present application provides a power pole tower hardware identification control device, which is applied to an electronic device, wherein the electronic device is communicatively connected to a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the device includes: a shooting unit, an identification unit, a determination unit, and a control unit, wherein:

[0010] The shooting unit is used to shoot the target power pole tower with the pan-tilt camera using the first shooting parameter to obtain a first image;

[0011] The recognition unit is used to perform multi-scale target recognition of power pole tower hardware on the first image through a target power pole tower hardware recognition model to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer;

[0012] The determination unit is used to determine the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the scale parameters of the target first power pole tower hardware; the target first power pole tower hardware is one of the k power pole tower hardware;

[0013] The control unit is used to control the pan-tilt module to operate with the target operating parameters, and to control the pan-tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0017] The implementation of the embodiments of the present application has the following beneficial effects:

[0018] It can be seen that the power pole tower hardware identification control method and related devices described in the embodiments of the present application are applied to an electronic device, wherein the electronic device is communicatively connected to a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the target power pole is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image; multi-scale target recognition of power pole tower hardware is performed on the first image through a target power pole tower hardware recognition model to obtain k power pole tower hardware, and each power pole tower hardware corresponds to a scale parameter; k is a positive integer; according to the scale parameter of the target first power pole tower hardware, the target working parameter corresponding to the pan-tilt module and the second shooting parameter of the pan-tilt camera are determined; the target first power pole tower hardware is one of the k power pole tower hardware. Tower fittings; controlling the pan / tilt module to work with the target working parameters, and controlling the pan / tilt camera to shoot the target first power tower fittings with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power tower fittings in the second image. On the one hand, the target power tower fittings recognition model can be used to realize multi-scale target recognition of power tower fittings based on the image of the target power tower, so as to obtain the power tower fittings required by the user. On the other hand, the working parameters and shooting parameters of the pan / tilt module can be dynamically adjusted based on the scale parameters of the power tower fittings, so as to increase the screen-occupancy ratio of the power tower fittings. In this way, accurate image recognition of the power tower fittings can be realized, so as to improve the care and maintenance efficiency of the power tower fittings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a flow chart of a method for identifying and controlling power tower hardware provided in an embodiment of the present application;

[0021] Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0022] Figure 3 is a structural schematic diagram of another electronic device provided in an embodiment of the present application;

[0023] Figure 4 It is a block diagram of the functional units of a power pole tower hardware identification and control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] In an embodiment of the present application, the electronic device may include at least one of the following: an aerial device (for example, a manned aerial device or an unmanned aerial device (UAV)), a mobile phone, a server, etc., which are not limited here.

[0028] The following is a detailed description of the embodiments of the present application.

[0029] See also Figure 1 , Figure 1 It is a flow chart of a method for identifying and controlling hardware of a power pole tower provided by an embodiment of the present application. As shown in the figure, it is applied to an electronic device, the electronic device is connected to a pan-tilt camera for communication, and the pan-tilt camera includes a pan-tilt module; the method for identifying and controlling hardware of a power pole tower includes:

[0030] 101. Use the pan-tilt camera to shoot a target power pole tower with a first shooting parameter to obtain a first image.

[0031] The first shooting parameter may include at least one of the following: sensitivity, exposure, shooting mode, shooting time, focal length, etc., which are not limited here.

[0032] In the specific implementation, Figure 2As shown, the electronic device can be connected to the gimbal camera in communication, and the gimbal camera includes a gimbal module. For example, the electronic device can be a drone, and the drone is equipped with a gimbal camera. For example, the gimbal module of the gimbal camera can adjust the shooting angle and ensure the stability of the photo. The drone and the gimbal camera can be integrated or can be separated.

[0033] In a specific implementation, the target power pole tower can be photographed by a gimbal camera with a first shooting parameter to obtain a first image. In this way, a corresponding image of the target power pole tower can be obtained. Since the target power pole tower is equipped with many power pole tower hardware, the power pole tower hardware can be identified based on the image.

[0034] Optionally, before the above step 101, the following steps may also be included:

[0035] Determining a second distance between the pan / tilt camera and a preset position of the target power pole tower;

[0036] determining initial shooting parameters corresponding to the second distance;

[0037] Get target environment parameters;

[0038] Determining a second adjustment parameter corresponding to the target environmental parameter;

[0039] The initial shooting parameters are adjusted according to the second adjustment parameters to obtain the first shooting parameters.

[0040] The preset position may be preset or set by system default.

[0041] The initial shooting parameters may include at least one of the following: sensitivity, exposure, shooting mode, shooting time, focal length, etc., which are not limited here.

[0042] The environmental parameters may include at least one of the following: weather, ambient brightness, air density, direction, air humidity, temperature, atmospheric pressure, etc., which are not limited here.

[0043] In a specific implementation, the gimbal camera can be equipped with a binocular camera, and the binocular camera can be used to realize the ranging function, thereby determining the second distance between the gimbal camera and the preset position of the target power pole tower, and pre-store the mapping relationship between the preset distance and the shooting parameters, and then determine the initial shooting parameters corresponding to the second distance based on the mapping relationship. In this way, the shooting parameters corresponding to the distance can be obtained.

[0044] Next, the target environmental parameters can be obtained, as well as the mapping relationship between the preset environmental parameters and the adjustment parameters that are pre-stored. Then, the second adjustment parameters corresponding to the target environmental parameters can be determined based on the mapping relationship, and the initial shooting parameters are adjusted according to the second adjustment parameters to obtain the first shooting parameters. The adjustment parameters can adjust part or all of the shooting parameters in the initial shooting parameters. Therefore, not only can the shooting parameters corresponding to the distance be obtained, but the shooting parameters can also be adjusted so that the final shooting parameter depth conforms to the actual environment, which helps to improve the shooting effect and ensure the recognition accuracy of the power pole tower hardware.

[0045] 102. Perform multi-scale target recognition of power pole tower hardware on the first image using a target power pole tower hardware recognition model to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer.

[0046] In the embodiment of the present application, the target power pole hardware identification model can be preset or the system defaults. For example, the target power pole hardware identification model can be a deep learning model or a neural network model or an artificial intelligence model, etc., which is not limited here. For example, the target power pole hardware identification model can be at least one of the following: a convolutional neural network model, a fully connected neural network model, a recurrent neural network model, etc., which is not limited here.

[0047] Among them, the target power pole tower hardware identification model can be used to achieve at least one of the following functions: identifying the type of power pole tower hardware, whether it is in the power pole tower hardware, the model of the power pole tower hardware, the scale parameters of the power pole tower hardware, the probability that the power pole tower hardware belongs to a certain type of hardware, the fault type of the power pole tower hardware, the failure probability of the power pole tower hardware, the cleanliness of the power pole tower hardware, etc., without limitation here.

[0048] In a specific implementation, a large number of images of power pole tower hardware can be obtained, and features of these images of power pole tower hardware can be extracted to obtain image features. The image features are input into the initial power pole tower hardware recognition model for training. When the initial power pole tower hardware recognition model meets the preset conditions, the target power pole tower hardware recognition model is obtained. The preset conditions can be preset or system default. For example, the preset condition can be to reach a preset number of training times, and for another example, the preset condition can be to reach a preset model accuracy. The preset number of training times and the preset model accuracy can both be preset or system default.

[0049] The image features may include at least one of the following: feature points, feature vectors, feature values, the color of power pole tower fittings, the shape of power pole tower fittings, etc., which are not limited here.

[0050] In a specific implementation, the target power pole hardware recognition model can be used to perform multi-scale target recognition of power pole hardware on the first image to obtain k power pole hardware, each of which corresponds to a scale parameter; k is a positive integer. The scale parameter reflects the size of the target power pole hardware in the first image to a certain extent.

[0051] Optionally, the above step 102, performing multi-scale target recognition of power pole tower hardware on the first image by using the target power pole tower hardware recognition model to obtain k power pole tower hardware, may include the following steps:

[0052] Acquiring initial model parameters of the target power tower hardware identification model;

[0053] Determining a second screen-occupying ratio of the target power pole tower in the first image;

[0054] Determining a first adjustment parameter corresponding to the second screen-occupancy ratio;

[0055] Acquire first attribute information of the target power pole tower;

[0056] Determine a target power tower hardware distribution parameter corresponding to the first attribute information;

[0057] Determine a first fine-tuning parameter corresponding to the target power tower hardware distribution parameter;

[0058] Adjust the initial model parameters according to the first adjustment parameters and the first fine-tuning parameters to obtain target model parameters;

[0059] The target power pole tower hardware identification model is used to perform multi-scale target recognition of power pole tower hardware on the first image with the target model parameters to obtain the k power pole tower hardware.

[0060] The first attribute information of the target power pole tower may include at least one of the following: the model of the power pole tower, the number of the power pole tower, the coordinate position of the power pole tower, the function of the power pole tower, etc., which are not limited here.

[0061] In a specific implementation, different power pole tower hardware identification models may correspond to different model parameters. The model parameters are used to determine the model capability, identification accuracy, identification efficiency, etc. of the power pole tower hardware identification model, which are not limited here.

[0062] In the embodiment of the present application, the initial model parameters of the target power pole tower hardware identification model can be obtained, and the initial model parameters can be preset or system default. It is also possible to determine the second screen ratio of the target power pole tower in the first image based on the first image, that is, the ratio between the area of ​​the target power pole tower in the first image and the entire area of ​​the first image, and use the ratio as the second screen ratio.

[0063] In a specific implementation, since different screen-occupancy ratios may correspond to different adjustment parameters, the mapping relationship between the preset screen-occupancy ratio and the adjustment parameter may be pre-stored, that is, the first adjustment parameter corresponding to the second screen-occupancy ratio may be determined based on the mapping relationship, and the first attribute information of the target power tower may be obtained. Since different power towers are equipped with different power tower hardware, that is, the distribution of power tower hardware is different, the mapping relationship between the preset attribute information and the power tower hardware distribution parameter may be pre-stored, and the target power tower hardware distribution parameter corresponding to the first attribute information may be determined based on the mapping relationship, and the mapping relationship between the preset power tower hardware distribution parameter and the fine-tuning parameter may be pre-stored. Then, the first fine-tuning parameter corresponding to the target power tower hardware distribution parameter may be determined based on the mapping relationship, and then the initial model parameter may be adjusted according to the first adjustment parameter and the first fine-tuning parameter to obtain the target model parameter, that is, the target model parameter=(1+first adjustment parameter =The number of)*(1+first fine-tuning parameters)*initial model parameters, that is, the target power pole tower hardware recognition model can be used to perform multi-scale target recognition of power pole tower hardware on the first image with the target model parameters to obtain k power pole tower hardware. In this way, on the one hand, since the screen-occupancy ratio of the power pole tower will also affect the model recognition accuracy to a certain extent, the initial model parameters can be adjusted based on the screen-occupancy ratio of the power pole tower. On the other hand, considering the characteristics of the power pole tower itself (the first attribute information), it determines the distribution density, distribution position, and distribution area of ​​the power pole tower hardware to a certain extent. Then, the power pole tower hardware distribution parameters corresponding to the characteristics of the power pole tower itself can be determined, and the model parameters can be dynamically fine-tuned based on the power pole tower hardware distribution parameters, so that the depth of the model recognition capability matches the distribution of the power pole tower hardware, and the recognition accuracy of the power pole tower hardware distribution area is guaranteed, thereby guiding the target power pole tower hardware recognition model to have regional key recognition capabilities, and further ensuring the recognition accuracy of the power pole tower hardware.

[0064] Optionally, the above step of obtaining the initial model parameters of the target power tower hardware identification model may include the following steps:

[0065] Obtaining second attribute information of the power tower hardware that needs to be identified;

[0066] The initial model parameters of the target power pole tower hardware identification model are acquired according to the second attribute information.

[0067] In the embodiment of the present application, the second attribute information of the power pole tower hardware that needs to be identified may include at least one of the following: the model of the power pole tower hardware, the appearance of the power pole tower hardware, the size of the power pole tower hardware, the color of the power pole tower hardware, the material of the power pole tower hardware, the setting location of the power pole tower hardware, the purpose or function of the power pole tower hardware, etc., which is not limited here.

[0068] In a specific implementation, the second attribute information of the power pole tower fittings to be identified can be obtained, and the mapping relationship between the preset attribute information and the initial model parameters of the target power pole tower fittings identification model can be pre-stored. Then, the initial model parameters of the target power pole tower fittings identification model corresponding to the second attribute information can be determined based on the mapping relationship. In this way, the power pole tower fittings to be identified can be accurately identified based on user needs, thereby further improving the identification accuracy of the specified power pole tower fittings.

[0069] 103. Determine target working parameters corresponding to the pan / tilt module and second shooting parameters of the pan / tilt camera according to scale parameters of a target first power pole tower fitting; the target first power pole tower fitting is one of the k power pole tower fittings.

[0070] In the embodiment of the present application, the second shooting parameter may include at least one of the following: sensitivity, exposure, shooting mode, shooting time, focal length, etc., which are not limited here.

[0071] Among them, the target operating parameters corresponding to the gimbal module may include at least one of the following: rotation rate, rotation angle, driving force, driving direction, working current, working voltage, working power, etc., which are not limited here.

[0072] In the embodiment of the present application, taking the target first power pole tower fitting as an example, the target first power pole tower fitting is one of the k power pole tower fittings, then the target working parameters corresponding to the pan-tilt module and the second shooting parameters of the pan-tilt camera can be determined according to the scale parameters of the target first power pole tower fitting, and then, the pan-tilt module can be adjusted to shoot the target first power pole tower fitting, and the shooting parameters can be adjusted based on the relative position relationship between the pan-tilt camera and the target first power pole tower fitting, so that the shooting parameter depth conforms to the actual situation, thereby ensuring that the target first power pole tower fitting has a sufficient screen-occupying ratio, which can not only ensure the recognition accuracy of the target first power pole tower fitting, but also facilitate user viewing and improve user experience.

[0073] Optionally, the above step 103, determining the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the dimensional parameters of the target first power pole tower hardware, may include the following steps:

[0074] Acquire a first relative angle between the pan / tilt camera and the target first power pole tower hardware through the first image;

[0075] Determine the target operating parameter corresponding to the pan / tilt module according to the first relative angle, wherein the target operating parameter is used to adjust the first relative angle to a preset relative angle range;

[0076] Determine a first screen-occupying ratio of the target first power pole tower hardware in the first image according to the scale parameter of the target first power pole tower hardware;

[0077] Determine a first distance between the pan / tilt camera and the target first power pole tower hardware;

[0078] Determining a reference screen ratio corresponding to the first distance;

[0079] Determining a first deviation between the first screen-occupancy ratio and the reference screen-occupancy ratio;

[0080] Determining a target optimization parameter corresponding to the first deviation;

[0081] The first shooting parameter is optimized according to the target optimization parameter to obtain the second shooting parameter.

[0082] The preset relative angle range may be preset or a system default. Being within the preset relative angle range may be understood as being directly facing the camera for shooting.

[0083] In an embodiment of the present application, a first relative angle between the pan-tilt camera and the target first power pole tower hardware can be obtained through a first image, and the target operating parameters corresponding to the pan-tilt module can be determined based on the first relative angle. The target operating parameters are used to adjust the first relative angle to a preset relative angle range. For example, the target angle difference between the first relative angle and the middle value of the preset relative angle range can be determined, and the target operating parameters corresponding to the first relative angle are determined according to the mapping relationship between the preset angle difference and the operating parameters.

[0084] Of course, since the scale parameter reflects the size to a certain extent, the first screen-occupancy ratio of the target first power pole tower hardware in the first image can be determined according to the scale parameter of the target first power pole tower hardware, and the first distance between the gimbal camera and the target first power pole tower hardware can also be determined. The mapping relationship between the preset distance and the screen-occupancy ratio can also be pre-stored, and then, based on the mapping relationship, a reference screen-occupancy ratio corresponding to the first distance can be determined, and a first deviation between the first screen-occupancy ratio and the reference screen-occupancy ratio can be determined, the first deviation = (first screen-occupancy ratio-reference screen-occupancy ratio) / reference screen-occupancy ratio. The mapping relationship between the preset deviation and the optimization parameter can also be pre-stored, and then, based on the mapping relationship, a reference screen-occupancy ratio corresponding to the first distance can be determined. The system determines the target optimization parameter corresponding to the first deviation degree, and optimizes the first shooting parameter based on the target optimization parameter to obtain the second shooting parameter. In this way, not only can the working parameters corresponding to the gimbal module be dynamically adapted based on the relative angle between the gimbal camera and the target first power pole tower hardware, but the first shooting parameter can also be dynamically optimized based on the scale parameters of the target first power pole tower hardware and the distance analysis of the deviation between the current screen ratio and the ideal screen ratio, so that the final shooting parameter depth meets the screen ratio requirements and the actual position relationship between the gimbal camera and the target first power pole tower hardware. Therefore, accurate image recognition of the power pole tower hardware can be further realized to improve the care and maintenance efficiency of the power pole tower hardware.

[0085] 104. Control the pan / tilt module to operate with the target operating parameters, and control the pan / tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

[0086] In a specific implementation, the gimbal module can be controlled to work with target working parameters, and the gimbal camera can be controlled to shoot the target first power pole tower hardware with second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image. In this way, the working parameters and shooting parameters of the gimbal module can be dynamically adjusted based on the scale parameters of the power pole tower hardware to increase the screen-occupancy ratio of the power pole tower hardware. In this way, accurate image recognition of the power pole tower hardware can be achieved to improve the care and maintenance efficiency of the power pole tower hardware.

[0087] To give an example, the AI ​​model of power pole tower hardware can be obtained through computer deep learning, and the problem of recognition accuracy of targets with different screen ratios can be solved. As a result, small-scale targets can be found in wide-angle pictures, and the gimbal module can be driven to rotate quickly and over a large range and zoom to a rough magnification. Conversely, large-scale targets can be found in the picture of the zoom camera, and the gimbal module and zoom lens can be driven to make small adjustments in a small range. In this way, accurate shooting angles and target screen ratios can be achieved.

[0088] It can be seen that the power pole tower hardware identification control method described in the embodiment of the present application is applied to an electronic device, which is communicatively connected to a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the target power pole tower is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image; multi-scale target recognition of power pole tower hardware is performed on the first image through a target power pole tower hardware recognition model to obtain k power pole tower hardware, and each power pole tower hardware corresponds to a scale parameter; k is a positive integer; according to the scale parameter of the target first power pole tower hardware, the target working parameter corresponding to the pan-tilt module and the second shooting parameter of the pan-tilt camera are determined; the target first power pole tower hardware is a power pole tower among the k power pole tower hardware. Hardware; controlling the pan / tilt module to work with the target working parameters, and controlling the pan / tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image. On the one hand, the target power pole tower hardware recognition model can be used to realize multi-scale target recognition of power pole tower hardware for the image based on the target power pole to obtain the power pole tower hardware required by the user. On the other hand, the working parameters and shooting parameters of the pan / tilt module can be dynamically adjusted based on the scale parameters of the power pole tower hardware to increase the screen-occupancy ratio of the power pole tower hardware. In this way, accurate image recognition of power pole tower hardware can be realized to improve the care and maintenance efficiency of power pole tower hardware.

[0089] In accordance with the above embodiment, please refer to Figure 3 , Figure 3 : is a structural diagram of another electronic device provided in an embodiment of the present application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. In the embodiment of the present application, the electronic device is connected to a gimbal camera for communication, and the gimbal camera includes a gimbal module; the program includes instructions for executing the following steps:

[0090] The target power pole tower is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image;

[0091] The target power pole tower hardware recognition model is used to perform multi-scale target recognition of power pole tower hardware on the first image to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer;

[0092] Determine the target working parameter corresponding to the pan / tilt module and the second shooting parameter of the pan / tilt camera according to the scale parameter of the target first power pole tower fitting; the target first power pole tower fitting is one of the k power pole tower fittings;

[0093] The gimbal module is controlled to operate with the target operating parameters, and the gimbal camera is controlled to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

[0094] Optionally, in determining the target operating parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the dimensional parameters of the target first power pole tower hardware, the program includes instructions for executing the following steps:

[0095] Acquire a first relative angle between the pan / tilt camera and the target first power pole tower hardware through the first image;

[0096] Determine the target operating parameter corresponding to the pan / tilt module according to the first relative angle, wherein the target operating parameter is used to adjust the first relative angle to a preset relative angle range;

[0097] Determine a first screen-occupying ratio of the target first power pole tower hardware in the first image according to the scale parameter of the target first power pole tower hardware;

[0098] Determine a first distance between the pan / tilt camera and the target first power pole tower hardware;

[0099] Determining a reference screen ratio corresponding to the first distance;

[0100] Determining a first deviation between the first screen-occupancy ratio and the reference screen-occupancy ratio;

[0101] Determining a target optimization parameter corresponding to the first deviation;

[0102] The first shooting parameter is optimized according to the target optimization parameter to obtain the second shooting parameter.

[0103] Optionally, in the aspect of performing multi-scale target recognition of power pole tower hardware on the first image by using the target power pole tower hardware recognition model to obtain k power pole tower hardware, the above program includes instructions for executing the following steps:

[0104] Acquiring initial model parameters of the target power tower hardware identification model;

[0105] Determining a second screen-occupying ratio of the target power pole tower in the first image;

[0106] Determining a first adjustment parameter corresponding to the second screen-occupancy ratio;

[0107] Acquire first attribute information of the target power pole tower;

[0108] Determine a target power tower hardware distribution parameter corresponding to the first attribute information;

[0109] Determine a first fine-tuning parameter corresponding to the target power tower hardware distribution parameter;

[0110] Adjust the initial model parameters according to the first adjustment parameters and the first fine-tuning parameters to obtain target model parameters;

[0111] The target power pole tower hardware identification model is used to perform multi-scale target recognition of power pole tower hardware on the first image with the target model parameters to obtain the k power pole tower hardware.

[0112] Optionally, in the aspect of obtaining the initial model parameters of the target power pole tower hardware identification model, the above program includes instructions for executing the following steps:

[0113] Obtaining second attribute information of the power tower hardware that needs to be identified;

[0114] The initial model parameters of the target power pole tower hardware identification model are acquired according to the second attribute information.

[0115] Optionally, the program further includes instructions for executing the following steps:

[0116] Determining a second distance between the pan / tilt camera and a preset position of the target power pole tower;

[0117] determining initial shooting parameters corresponding to the second distance;

[0118] Get target environment parameters;

[0119] Determining a second adjustment parameter corresponding to the target environmental parameter;

[0120] The initial shooting parameters are adjusted according to the second adjustment parameters to obtain the first shooting parameters.

[0121] It can be seen that the electronic device described in the embodiment of the present application is communicatively connected to a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the target power pole tower is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image; the first image is subjected to multi-scale target recognition of power pole tower hardware by a target power pole tower hardware recognition model to obtain k power pole tower hardware, and each power pole tower hardware corresponds to a scale parameter; k is a positive integer; the target working parameter corresponding to the pan-tilt module and the second shooting parameter of the pan-tilt camera are determined according to the scale parameter of the target first power pole tower hardware; the target first power pole tower hardware is one of the k power pole tower hardware; the pan-tilt camera is controlled The pan-tilt module operates with the target working parameters, and controls the pan-tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to improve the screen-occupancy ratio of the target first power pole tower hardware in the second image. On the one hand, the target power pole tower hardware recognition model can be used to realize multi-scale target recognition of power pole tower hardware for the image based on the target power pole to obtain the power pole tower hardware required by the user. On the other hand, the working parameters and shooting parameters of the pan-tilt module can be dynamically adjusted based on the scale parameters of the power pole tower hardware to improve the screen-occupancy ratio of the power pole tower hardware. In this way, accurate image recognition of the power pole tower hardware can be realized to improve the care and maintenance efficiency of the power pole tower hardware.

[0122] Figure 4 This is a functional unit composition block diagram of a power pole hardware identification control device 400 involved in an embodiment of the present application. The power pole hardware identification control device 400 is applied to an electronic device, the electronic device is connected to a pan-tilt camera for communication, the pan-tilt camera includes a pan-tilt module; the power pole hardware identification control device 400 includes: a shooting unit 401, an identification unit 402, a determination unit 403 and a control unit 404, wherein:

[0123] The shooting unit 401 is used to shoot the target power pole tower with the pan-tilt camera using the first shooting parameter to obtain a first image;

[0124] The recognition unit 402 is used to perform multi-scale target recognition of power pole tower hardware on the first image through a target power pole tower hardware recognition model to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer;

[0125] The determining unit 403 is used to determine the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the scale parameters of the target first power pole tower fitting; the target first power pole tower fitting is one of the k power pole tower fittings;

[0126] The control unit 404 is used to control the pan-tilt module to operate with the target operating parameters, and control the pan-tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

[0127] Optionally, in determining the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the scale parameters of the target first power pole tower hardware, the determining unit 403 is specifically used for:

[0128] Acquire a first relative angle between the pan / tilt camera and the target first power pole tower hardware through the first image;

[0129] Determine the target operating parameter corresponding to the pan / tilt module according to the first relative angle, wherein the target operating parameter is used to adjust the first relative angle to a preset relative angle range;

[0130] Determine a first screen-occupying ratio of the target first power pole tower hardware in the first image according to the scale parameter of the target first power pole tower hardware;

[0131] Determine a first distance between the pan / tilt camera and the target first power pole tower hardware;

[0132] Determining a reference screen ratio corresponding to the first distance;

[0133] Determining a first deviation between the first screen-occupancy ratio and the reference screen-occupancy ratio;

[0134] Determining a target optimization parameter corresponding to the first deviation;

[0135] The first shooting parameter is optimized according to the target optimization parameter to obtain the second shooting parameter.

[0136] Optionally, in the aspect of performing multi-scale target recognition of power pole tower hardware on the first image by using the target power pole tower hardware recognition model to obtain k power pole tower hardware, the recognition unit 402 is specifically used for:

[0137] Acquiring initial model parameters of the target power tower hardware identification model;

[0138] Determining a second screen-occupying ratio of the target power pole tower in the first image;

[0139] Determining a first adjustment parameter corresponding to the second screen-occupancy ratio;

[0140] Acquire first attribute information of the target power pole tower;

[0141] Determine a target power tower hardware distribution parameter corresponding to the first attribute information;

[0142] Determine a first fine-tuning parameter corresponding to the target power tower hardware distribution parameter;

[0143] Adjust the initial model parameters according to the first adjustment parameters and the first fine-tuning parameters to obtain target model parameters;

[0144] The target power pole tower hardware identification model is used to perform multi-scale target recognition of power pole tower hardware on the first image with the target model parameters to obtain the k power pole tower hardware.

[0145] Optionally, in the aspect of obtaining the initial model parameters of the target power tower hardware identification model, the identification unit 402 is specifically used for:

[0146] Obtaining second attribute information of the power tower hardware that needs to be identified;

[0147] The initial model parameters of the target power pole tower hardware identification model are acquired according to the second attribute information.

[0148] Optionally, the power tower hardware identification control device 400 is further specifically used for:

[0149] Determining a second distance between the pan / tilt camera and a preset position of the target power pole tower;

[0150] determining initial shooting parameters corresponding to the second distance;

[0151] Get target environment parameters;

[0152] Determining a second adjustment parameter corresponding to the target environmental parameter;

[0153] The initial shooting parameters are adjusted according to the second adjustment parameters to obtain the first shooting parameters.

[0154] It can be seen that the power pole tower hardware identification control device described in the embodiment of the present application is applied to an electronic device, which is communicatively connected to a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the target power pole tower is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image; the first image is subjected to multi-scale target recognition of power pole tower hardware by a target power pole tower hardware identification model to obtain k power pole tower hardware, and each power pole tower hardware corresponds to a scale parameter; k is a positive integer; the target working parameters corresponding to the pan-tilt module and the second shooting parameters of the pan-tilt camera are determined according to the scale parameters of the target first power pole tower hardware; the target first power pole tower hardware is a power pole tower among the k power pole tower hardware. Hardware; controlling the pan / tilt module to work with the target working parameters, and controlling the pan / tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image. On the one hand, the target power pole tower hardware recognition model can be used to realize multi-scale target recognition of power pole tower hardware for the image based on the target power pole to obtain the power pole tower hardware required by the user. On the other hand, the working parameters and shooting parameters of the pan / tilt module can be dynamically adjusted based on the scale parameters of the power pole tower hardware to increase the screen-occupancy ratio of the power pole tower hardware. In this way, accurate image recognition of power pole tower hardware can be realized to improve the care and maintenance efficiency of power pole tower hardware.

[0155] It can be understood that the functions of each program module of the power tower hardware identification control device of this embodiment can be specifically implemented according to the method in the above method embodiment, and its specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0156] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0157] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0158] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0159] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0160] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0161] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0163] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0164] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0165] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for identifying and controlling power tower hardware, characterized in that: Applied to an electronic device, the electronic device is communicatively connected with a pan-tilt camera, and the pan-tilt camera includes a pan-tilt module; the method includes: The target power pole tower is photographed by the pan-tilt camera with a first shooting parameter to obtain a first image; The target power pole tower hardware recognition model is used to perform multi-scale target recognition of power pole tower hardware on the first image to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer; Determine the target working parameter corresponding to the pan / tilt module and the second shooting parameter of the pan / tilt camera according to the scale parameter of the target first power pole tower fitting; the target first power pole tower fitting is one of the k power pole tower fittings; The gimbal module is controlled to operate with the target operating parameters, and the gimbal camera is controlled to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

2. The method according to claim 1, characterized in that The step of determining the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the scale parameters of the target first power pole tower hardware includes: Acquire a first relative angle between the pan / tilt camera and the target first power pole tower hardware through the first image; Determine the target operating parameter corresponding to the pan / tilt module according to the first relative angle, wherein the target operating parameter is used to adjust the first relative angle to a preset relative angle range; Determine a first screen-occupying ratio of the target first power pole tower hardware in the first image according to the scale parameter of the target first power pole tower hardware; Determine a first distance between the pan / tilt camera and the target first power pole tower hardware; Determining a reference screen ratio corresponding to the first distance; Determining a first deviation between the first screen-occupancy ratio and the reference screen-occupancy ratio; Determining a target optimization parameter corresponding to the first deviation; The first shooting parameter is optimized according to the target optimization parameter to obtain the second shooting parameter.

3. The method according to claim 1 or 2, characterized in that: The step of performing multi-scale target recognition of power pole tower hardware on the first image using a target power pole tower hardware recognition model to obtain k power pole tower hardware includes: Acquiring initial model parameters of the target power tower hardware identification model; Determining a second screen-occupying ratio of the target power pole tower in the first image; Determining a first adjustment parameter corresponding to the second screen-occupancy ratio; Acquire first attribute information of the target power pole tower; Determine a target power tower hardware distribution parameter corresponding to the first attribute information; Determine a first fine-tuning parameter corresponding to the target power tower hardware distribution parameter; Adjust the initial model parameters according to the first adjustment parameters and the first fine-tuning parameters to obtain target model parameters; The target power pole tower hardware identification model is used to perform multi-scale target recognition of power pole tower hardware on the first image with the target model parameters to obtain the k power pole tower hardware.

4. The method according to claim 3, characterized in that The obtaining of initial model parameters of the target power tower hardware identification model includes: Obtaining second attribute information of the power tower hardware that needs to be identified; The initial model parameters of the target power pole tower hardware identification model are acquired according to the second attribute information.

5. The method according to claim 1 or 2, characterized in that: The method further comprises: Determining a second distance between the pan / tilt camera and a preset position of the target power pole tower; determining initial shooting parameters corresponding to the second distance; Get target environment parameters; Determining a second adjustment parameter corresponding to the target environmental parameter; The initial shooting parameters are adjusted according to the second adjustment parameters to obtain the first shooting parameters.

6. A power tower hardware identification and control device, characterized in that: Applied to an electronic device, the electronic device is connected to a pan-tilt camera for communication, the pan-tilt camera includes a pan-tilt module; the device includes: a shooting unit, a recognition unit, a determination unit and a control unit, wherein: The shooting unit is used to shoot the target power pole tower with the pan-tilt camera using the first shooting parameter to obtain a first image; The recognition unit is used to perform multi-scale target recognition of power pole tower hardware on the first image through a target power pole tower hardware recognition model to obtain k power pole tower hardware, each power pole tower hardware corresponding to a scale parameter; k is a positive integer; The determination unit is used to determine the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the scale parameters of the target first power pole tower hardware; the target first power pole tower hardware is one of the k power pole tower hardware; The control unit is used to control the pan-tilt module to operate with the target operating parameters, and control the pan-tilt camera to shoot the target first power pole tower hardware with the second shooting parameters to obtain a second image, so as to increase the screen-occupancy ratio of the target first power pole tower hardware in the second image.

7. The device according to claim 6, characterized in that In the aspect of determining the target working parameters corresponding to the pan / tilt module and the second shooting parameters of the pan / tilt camera according to the scale parameters of the target first power pole tower hardware, the determining unit is specifically used for: Acquire a first relative angle between the pan / tilt camera and the target first power pole tower hardware through the first image; Determine the target operating parameter corresponding to the pan / tilt module according to the first relative angle, wherein the target operating parameter is used to adjust the first relative angle to a preset relative angle range; Determine a first screen-occupying ratio of the target first power pole tower hardware in the first image according to the scale parameter of the target first power pole tower hardware; Determine a first distance between the pan / tilt camera and the target first power pole tower hardware; Determining a reference screen ratio corresponding to the first distance; Determining a first deviation between the first screen-occupancy ratio and the reference screen-occupancy ratio; Determining a target optimization parameter corresponding to the first deviation; The first shooting parameter is optimized according to the target optimization parameter to obtain the second shooting parameter.

8. The device according to claim 6 or 7, characterized in that In the aspect of performing multi-scale target recognition of power pole tower hardware on the first image by using the target power pole tower hardware recognition model to obtain k power pole tower hardware, the recognition unit is specifically used for: Acquiring initial model parameters of the target power tower hardware identification model; Determining a second screen-occupying ratio of the target power pole tower in the first image; Determining a first adjustment parameter corresponding to the second screen-occupancy ratio; Acquire first attribute information of the target power pole tower; Determine a target power tower hardware distribution parameter corresponding to the first attribute information; Determine a first fine-tuning parameter corresponding to the target power tower hardware distribution parameter; Adjust the initial model parameters according to the first adjustment parameters and the first fine-tuning parameters to obtain target model parameters; The target power pole tower hardware identification model is used to perform multi-scale target recognition of power pole tower hardware on the first image with the target model parameters to obtain the k power pole tower hardware.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program comprises instructions for executing the steps in the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 5.

Images