Electric power screen cabinet monitoring point shooting method, system and equipment and storage medium

Abstract

The invention discloses an electric power screen cabinet monitoring point shooting method, system and device and a storage medium. The method comprises the steps of obtaining selectable monitoring point data, a global configuration holder absolute position and selectable configuration offset of a standard global screen cabinet configuration picture of a target electric power screen cabinet and a local configuration holder absolute position of a standard local screen cabinet configuration picture; based on the optional configuration offset and global and local configuration holder absolute positions, obtaining a configuration distant view rotation proportion; based on the target monitoring point data, globally configuring the absolute position of the holder to obtain a screen cabinet use picture; obtaining a deviation correction angle based on the rotation proportion of the screen cabinet use picture, the standard global screen cabinet configuration picture and the configuration distant view picture; obtaining a close-shot adjustment angle based on the target monitoring point data, the selectable monitoring point data, the selectable configuration offset and the configuration long-shot image rotation proportion; and obtaining a target monitoring point picture based on the local configuration holder absolute position, the correction angle and the close-range adjustment angle. The shooting reliability of the monitoring point of the electric screen cabinet is improved.

Description

Technical Field

[0001] This invention relates to the field of power distribution cabinet monitoring point photography, and more particularly to a method, system, equipment, and storage medium for power distribution cabinet monitoring point photography. Background Technology

[0002] In power system operation and maintenance, the status monitoring of indicator lights, pressure plates, and other monitoring points (also known as "points of interest") on power control cabinets (such as control cabinets) relies on camera capture and image recognition. Current technology typically establishes a "preset point-monitoring point" correspondence by manually configuring preset camera positions: initially, maintenance personnel manually adjust the camera position and focus, setting the camera status for each monitoring point to the preset position and recording it; during system operation, images captured at the preset positions are directly retrieved, and the monitoring point status is obtained through a recognition algorithm.

[0003] To address the issue of preset position misalignment caused by mechanical attenuation over long-term use, some existing technologies propose periodic or on-demand automatic correction of the preset positions. However, these existing technologies still have significant drawbacks: Firstly, when manually configuring preset positions, the monitoring points in the power distribution cabinet are densely distributed and have similar appearances (e.g., indicator lights are mostly round / square, and pressure plates have uniform styles), making them distinguishable only by the text on stickers near the monitoring points. However, cameras in a production environment often struggle to clearly recognize the text, easily leading to confusion in the "preset position-monitoring point" correspondence. Secondly, whether manual or automatic correction is used, each preset position must be operated individually. The correction process requires interrupting the normal monitoring flow, and the offset data before correction reduces the accuracy of image recognition, affecting the reliability of the system's judgment of the monitoring point status. Summary of the Invention

[0004] This invention provides a method, system, device, and storage medium for capturing images at monitoring points of power distribution cabinets, which can improve the reliability of capturing images at monitoring points of power distribution cabinets.

[0005] This invention discloses a method for capturing images at monitoring points of power distribution cabinets, applied to the controller of a power distribution cabinet monitoring point capturing device. The method includes:

[0006] Identify the target power distribution cabinet and control the camera to capture standard global cabinet configuration images and standard partial cabinet configuration images of the target power distribution cabinet;

[0007] Obtain the optional monitoring point data, the absolute position of the global configuration PTZ and the optional configuration offset of the standard global cabinet configuration image, and obtain the absolute position of the local configuration PTZ of the standard local cabinet configuration image;

[0008] Based on the global configuration gimbal absolute position and the local configuration gimbal absolute position, the configuration field view rotation ratio is obtained;

[0009] Determine the target monitoring point data for the target power cabinet;

[0010] The camera's movement is controlled based on the absolute position of the global configuration PTZ, so that the camera can obtain a picture of the cabinet in use based on the target monitoring point data;

[0011] Based on the image of the cabinet in use and the image of the standard global cabinet configuration, the usage offset is obtained;

[0012] The correction angle is obtained based on the offset and the rotation ratio of the configured distant view.

[0013] Based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration distant view rotation ratio, the close-up adjustment angle is obtained;

[0014] The camera is controlled based on the absolute position of the locally configured gimbal, the correction angle, and the close-up adjustment angle, so that the camera can capture data of the target monitoring point and obtain an image of the target monitoring point.

[0015] In the above scheme, by configuring standard global panel configuration images and standard local panel configuration images for the target power panel cabinet, the rotation ratio of the configuration view image generated by the camera during the global-local adjustment process is calculated by configuring the absolute position of the pan-tilt unit globally and locally. This provides a data foundation for accurately capturing target monitoring point data in the future. At the same time, after obtaining the rotation ratio of the configuration view image, it is not necessary to set a preset point for each monitoring point, which greatly reduces the number of preset points. Furthermore, during subsequent use, the camera acquires images of the power cabinet based on the absolute position of the globally configured PTZ, combines these images with the standard global power cabinet configuration image to obtain the usage offset, and then quickly calculates the correction angle by configuring the rotation ratio of the distant view. This correction angle achieves initial correction, ensuring that the monitoring point is within the global field of view. Based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration distant view rotation ratio, the close-up adjustment angle is obtained. This close-up adjustment angle is used to locate the target monitoring point data. Finally, the camera is controlled to capture images of the target monitoring point based on the local configuration of the PTZ absolute position, the correction angle, and the close-up adjustment angle. This avoids the problem in existing technologies where preset points are offset due to mechanical attenuation, requiring periodic or manual correction that affects normal use, thus improving the reliability of the camera capturing images of the power cabinet monitoring points.

[0016] Further, the step of obtaining the optional monitoring point data, the absolute position of the global configuration PTZ, and the optional configuration offset of the standard global cabinet configuration image, and obtaining the absolute position of the local configuration PTZ of the standard local cabinet configuration image, includes:

[0017] Get the text display cabinet configuration image;

[0018] By using a preset cabinet image recognition model and the text cabinet configuration image, the text monitoring point information of the text cabinet configuration image is obtained;

[0019] The global monitoring point information of the standard global cabinet configuration image is obtained by using the cabinet image recognition model and the standard global cabinet configuration image.

[0020] Based on the text monitoring point information and the global monitoring point information, a text-global monitoring point mapping relationship is obtained;

[0021] The initial monitoring point text is obtained by using the preset screen cabinet text recognition model and the text screen cabinet configuration image;

[0022] Based on the preset cabinet semantic matching model and the initial monitoring point text, the standard monitoring point text is obtained;

[0023] Based on the standard monitoring point text, the text-global monitoring point mapping relationship, and the standard global cabinet configuration image, the optional monitoring point data is obtained.

[0024] In the above solution, by combining text-based cabinet configuration images with cabinet image recognition models, cabinet text recognition models, and cabinet semantic matching models, a text-to-global monitoring point mapping relationship is established to obtain standard monitoring point text. Finally, the optional monitoring point data is determined, ensuring that the optional monitoring point data accurately corresponds to the monitoring points in the business scenario. This solves the problem of the disconnect between monitoring points and power industry terminology in business information in existing technologies and improves the reliability of optional monitoring point data.

[0025] Further, the step of obtaining the optional monitoring point data, the absolute position of the global configuration PTZ, and the optional configuration offset of the standard global cabinet configuration image, and obtaining the absolute position of the local configuration PTZ of the standard local cabinet configuration image, includes:

[0026] Obtain the center point of the standard global cabinet configuration image;

[0027] Obtain the distance between the optional monitoring point data and the center point to obtain the optional configuration offset.

[0028] In the above scheme, the center point of the standard global cabinet configuration image is obtained, and the distance between the optional monitoring point data and the center point is calculated to obtain the optional configuration offset, which provides accurate basic data for subsequent calculations based on the offset.

[0029] Further, the step of obtaining the optional monitoring point data, the absolute position of the global configuration PTZ, and the optional configuration offset of the standard global cabinet configuration image, and obtaining the absolute position of the local configuration PTZ of the standard local cabinet configuration image, includes:

[0030] Select reference monitoring point data from the optional monitoring point data;

[0031] The camera is controlled based on the reference monitoring point data, so that the camera obtains the standard partial cabinet configuration image based on the reference monitoring point data.

[0032] Obtain the current position and zoom information of the camera to obtain the absolute position of the locally configured gimbal.

[0033] In the above solution, reference monitoring point data is selected from the available monitoring point data to control the camera to obtain a standard local panel configuration image, thereby obtaining the absolute position of the local configuration pan-tilt unit. This eliminates the need for repeated manual adjustment of the camera position, reducing manual operation costs and improving configuration efficiency.

[0034] Further, the global configuration gimbal absolute position includes a global horizontal angle and a global vertical angle, and the local configuration gimbal absolute position includes a local horizontal angle and a local vertical angle. The step of obtaining the configuration field view rotation ratio based on the reference configuration offset, the global configuration gimbal absolute position, and the local configuration gimbal absolute position includes:

[0035] The horizontal angle difference is obtained based on the difference between the global horizontal angle and the local horizontal angle;

[0036] The vertical angle difference is obtained based on the difference between the global vertical angle and the local vertical angle;

[0037] Based on the reference monitoring point data, a reference configuration offset is selected from the optional configuration offsets;

[0038] The horizontal ratio is obtained based on the ratio of the horizontal offset of the reference configuration to the horizontal angle difference in the reference configuration offset.

[0039] The vertical ratio is obtained based on the ratio of the vertical offset of the reference configuration to the vertical angle difference in the reference configuration offset.

[0040] Based on the horizontal and vertical proportions, the rotation ratio of the configured distant view is obtained.

[0041] In the above scheme, based on the horizontal angle difference between the global horizontal angle and the local horizontal angle, and the vertical angle difference between the global vertical angle and the local vertical angle, the horizontal and vertical ratios are calculated in combination with the reference configuration offset to obtain the configuration distant view rotation ratio. This provides an accurate basis for the subsequent conversion of offset and angle, avoids errors in the correction and adjustment angle calculations caused by inaccurate ratios, and ensures the accuracy of camera angle adjustment.

[0042] Further, the use of offset includes using horizontal offset and using vertical offset, and the determination of the correction angle based on the used offset and the configured perspective view rotation ratio includes:

[0043] Obtain the ratio of the horizontal offset to the horizontal ratio to get the corrected horizontal angle;

[0044] Obtain the ratio of the vertical offset to the vertical ratio to get the corrected vertical angle;

[0045] The correction angle is obtained based on the correction horizontal angle and the correction vertical angle.

[0046] In the above solution, by using the ratio of the offset to the horizontal and vertical ratios in the configuration of the distant view rotation ratio, the horizontal and vertical correction angles are obtained, and then the correction angle is determined, so as to achieve precise correction of camera offset, solve the problem of inaccurate offset correction in the prior art, and ensure that the camera can return to the accurate shooting position.

[0047] Further, obtaining the near-field adjustment angle based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configured distant view rotation ratio includes:

[0048] Obtain the monitoring point-offset mapping relationship between the optional monitoring point data and the optional configuration offset;

[0049] Based on the monitoring point-offset mapping relationship and the target monitoring point data, the target configuration offset is obtained from the optional configuration offset;

[0050] Obtain the ratio of the target configuration horizontal offset to the horizontal ratio in the target configuration offset to get the near-view horizontal adjustment angle;

[0051] Obtain the ratio of the target configuration vertical offset to the vertical ratio in the target configuration offset to get the near-field vertical adjustment angle;

[0052] The close-up adjustment angle is obtained based on the close-up horizontal adjustment angle and the close-up vertical adjustment angle.

[0053] In the above scheme, the target configuration offset is obtained based on the monitoring point-offset mapping relationship, and the close-up adjustment angle is calculated by combining the configuration distant view rotation ratio, so as to achieve accurate positioning and adjustment of the target monitoring point. There is no need to set adjustment parameters for each target monitoring point data separately, and the accuracy and efficiency of target monitoring point shooting are also improved.

[0054] Another embodiment of the present invention provides a power cabinet monitoring point imaging system, including a power cabinet monitoring point imaging device and a controller, wherein the power cabinet monitoring point imaging device is connected to the controller, and the power cabinet monitoring point imaging device includes:

[0055] The first control module is used to determine the target power cabinet and control the camera to capture standard global cabinet configuration images and standard partial cabinet configuration images of the target power cabinet;

[0056] The acquisition module is used to acquire the optional monitoring point data, the absolute position of the global configuration PTZ and the optional configuration offset of the standard global cabinet configuration image, and to acquire the absolute position of the local configuration PTZ of the standard local cabinet configuration image.

[0057] The rotation ratio module is used to obtain the rotation ratio of the configured distant view based on the global configuration gimbal absolute position and the local configuration gimbal absolute position.

[0058] The monitoring point determination module is used to determine the target monitoring point data of the target power cabinet;

[0059] The second control module is used to control the movement of the camera based on the absolute position of the global configuration PTZ, so that the camera can obtain a picture of the cabinet in use based on the target monitoring point data;

[0060] The offset module is used to obtain the usage offset based on the image of the cabinet in use and the image of the standard global cabinet configuration.

[0061] The correction angle module is used to obtain the correction angle based on the used offset and the configured distant view rotation ratio;

[0062] The close-up adjustment angle module is used to obtain the close-up adjustment angle based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration distant view rotation ratio;

[0063] The monitoring point shooting module is used to control the camera based on the absolute position of the local configuration gimbal, the correction angle, and the close-up adjustment angle, so that the camera can capture the target monitoring point data and obtain the target monitoring point image.

[0064] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the power panel cabinet monitoring point shooting method of the present invention.

[0065] Another embodiment of the present invention also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the power cabinet monitoring point shooting method of the present invention. Attached Figure Description

[0066] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0067] Figure 1 This is a flowchart illustrating a method for capturing images at monitoring points of a power distribution cabinet, as provided in an embodiment of the present invention.

[0068] Figure 2 This is a schematic diagram of the structure of a power cabinet monitoring point shooting system provided in an embodiment of the present invention. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0071] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0072] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0073] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0074] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0075] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0076] See Figure 1 To improve the reliability of power distribution cabinet monitoring point imaging, an embodiment of the present invention provides a power distribution cabinet monitoring point imaging method, applied to the controller of the power distribution cabinet monitoring point imaging device, the method comprising:

[0077] Step S1: Identify the target power distribution cabinet and control the camera to capture standard global cabinet configuration images and standard partial cabinet configuration images of the target power distribution cabinet;

[0078] Step S2: Obtain the optional monitoring point data, the absolute position of the global configuration PTZ and the optional configuration offset of the standard global cabinet configuration image, and obtain the absolute position of the local configuration PTZ of the standard local cabinet configuration image;

[0079] Step S3: Based on the global configuration gimbal absolute position and the local configuration gimbal absolute position, obtain the configuration field view rotation ratio;

[0080] Step S4: Determine the target monitoring point data for the target power cabinet;

[0081] Step S5: Control the movement of the camera based on the absolute position of the PTZ camera in the global configuration so that the camera can obtain images of the cabinet based on the target monitoring point data;

[0082] Step S6: Based on the image of the cabinet in use and the standard global cabinet configuration image, obtain the usage offset;

[0083] Step S7: Based on the offset and the rotation ratio of the distant view, obtain the correction angle;

[0084] Step S8: Based on the target monitoring point data, optional monitoring point data, optional configuration offset, and configuration of the distant view rotation ratio, obtain the near-view adjustment angle;

[0085] Step S9: Control the camera based on the absolute position of the local configuration gimbal, the correction angle, and the close-up adjustment angle so that the camera can capture data of the target monitoring point and obtain an image of the target monitoring point.

[0086] In the above scheme, by configuring standard global panel configuration images and standard local panel configuration images for the target power panel cabinet, the rotation ratio of the configuration view image generated by the camera during the global-local adjustment process is calculated by configuring the absolute position of the pan-tilt unit globally and locally. This provides a data foundation for accurately capturing target monitoring point data in the future. At the same time, after obtaining the rotation ratio of the configuration view image, it is not necessary to set a preset point for each monitoring point, which greatly reduces the number of preset points. Furthermore, during subsequent use, the camera acquires images of the power cabinet based on the absolute position of the globally configured PTZ, combines these images with the standard global power cabinet configuration image to obtain the usage offset, and then quickly calculates the correction angle by configuring the rotation ratio of the distant view. This correction angle achieves initial correction, ensuring that the monitoring point is within the global field of view. Based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration distant view rotation ratio, the close-up adjustment angle is obtained. This close-up adjustment angle is used to locate the target monitoring point data. Finally, the camera is controlled to capture images of the target monitoring point based on the local configuration of the PTZ absolute position, the correction angle, and the close-up adjustment angle. This avoids the problem in existing technologies where preset points are offset due to mechanical attenuation, requiring periodic or manual correction that affects normal use, thus improving the reliability of the camera capturing images of the power cabinet monitoring points.

[0087] In another embodiment, obtaining the optional monitoring point data, the absolute position of the global configuration PTZ, and the optional configuration offset of the standard global cabinet configuration image, and obtaining the absolute position of the local configuration PTZ of the standard local cabinet configuration image, includes:

[0088] Get the text display cabinet configuration image;

[0089] By using a preset cabinet image recognition model and the text cabinet configuration image, the text monitoring point information of the text cabinet configuration image is obtained;

[0090] The global monitoring point information of the standard global cabinet configuration image is obtained by using the cabinet image recognition model and the standard global cabinet configuration image.

[0091] Based on the text monitoring point information and the global monitoring point information, a text-global monitoring point mapping relationship is obtained;

[0092] The initial monitoring point text is obtained by using the preset screen cabinet text recognition model and the text screen cabinet configuration image;

[0093] Based on the preset cabinet semantic matching model and the initial monitoring point text, the standard monitoring point text is obtained;

[0094] Based on the standard monitoring point text, the text-global monitoring point mapping relationship, and the standard global cabinet configuration image, the optional monitoring point data is obtained.

[0095] It should be noted that, in order to capture more images and freely switch between capturing global or partial images, the camera is usually placed at a relatively far distance from the target power distribution cabinet. This makes it difficult to clearly capture the text content of the stickers near various monitoring points (or points of interest) on the target power distribution cabinet. Therefore, a close-range shooting device, such as a mobile device, can be controlled to capture the front content of the target power distribution cabinet to obtain a text cabinet configuration image. The text cabinet configuration image should clearly show the text content of the stickers near the monitoring points.

[0096] Furthermore, the camera is positioned so that the center of the target power distribution cabinet is in the center of the camera's view, allowing for a complete view of the cabinet, including the top and bottom of the cabinet. The focus is then adjusted so that the top and bottom of the cabinet are at the top and bottom of the camera's field of view, respectively. The absolute position of the pan-tilt unit (PTZ) is acquired and saved as a global configuration, containing position information (including vertical and horizontal angles), zoom information (including zoom range), and the current focal length (as the global configuration focal length). An image is then captured and saved as a standard global cabinet configuration image.

[0097] The text-based cabinet configuration image is then input into a preset cabinet image recognition model to obtain the text monitoring point information, including the monitoring point location and type. Similarly, the standard global cabinet configuration image is input into the same model to obtain the global monitoring point information, including the monitoring point location and type. It is understood that the cabinet image recognition model uses existing image recognition models, such as Convolutional Neural Networks (CNNs). Based on the monitoring point location and type, the text monitoring point information and global monitoring point information are associated to obtain a text-to-global monitoring point mapping relationship. Furthermore, to improve accuracy, the text-to-global monitoring point mapping relationship can be manually selected. The text-based cabinet configuration image is then input into a preset cabinet text recognition model to extract all the text from the image, obtaining the initial monitoring point text. It is understood that the cabinet text recognition model uses existing text recognition models, such as OCR models. The initial monitoring point text is input into a pre-set cabinet semantic matching model to obtain standard monitoring point text. This model is a pre-trained power industry semantic relevance model, which can utilize existing semantic matching models, such as the DSSM model trained on power industry semantics from the business system. This updates the initial monitoring point text with professional and standardized power industry terminology for monitoring points, avoiding accuracy drops caused by different naming conventions. Furthermore, to further improve matching accuracy, manual review and matching can be performed, associating the initial monitoring point text with the power industry terminology of professional monitoring points in the business system. Then, based on the text-global monitoring point mapping relationship, the standard monitoring point text can be mapped to the standard global cabinet configuration image to obtain the text for each monitoring point. Combining this with the original monitoring point locations and types on the standard global cabinet configuration image, optional monitoring point data is obtained. Furthermore, for monitoring points with long physical distances, the standard monitoring point text can be manually associated with the corresponding monitoring point in the standard global cabinet configuration image for accuracy reasons, obtaining the optional monitoring point data. The above operations resolved the issue of unclear text in the standard global cabinet configuration images; and the cabinet semantic matching model resolved the disconnect between monitoring points and business systems.

[0098] In another embodiment, obtaining the optional monitoring point data, the absolute position of the global configuration PTZ, and the optional configuration offset of the standard global cabinet configuration image, and obtaining the absolute position of the local configuration PTZ of the standard local cabinet configuration image, includes:

[0099] Obtain the center point of the standard global cabinet configuration image;

[0100] Obtain the distance between the optional monitoring point data and the center point to obtain the optional configuration offset.

[0101] It should be noted that the center point is obtained by calculating the coordinates of the center point based on the resolution of the standard global cabinet configuration image: Obtain the resolution of the standard global cabinet configuration image (e.g., 1920×1080), and calculate the coordinates of the center point of the image based on the resolution (center point X coordinate = resolution width / 2, center point Y coordinate = resolution height / 2). Optional monitoring point data includes the coordinates of each optional monitoring point. The offset (Δx = x1 - x2, Δy = y1 - y2) of each monitoring point coordinate (x2, y2) in the optional monitoring point data from the center point (x1, y1) is calculated as the optional configuration offset, forming an association list of optional monitoring point data and optional configuration offsets.

[0102] In another embodiment, obtaining the optional monitoring point data, the absolute position of the global configuration PTZ, and the optional configuration offset of the standard global cabinet configuration image, and obtaining the absolute position of the local configuration PTZ of the standard local cabinet configuration image, includes:

[0103] Select reference monitoring point data from the optional monitoring point data;

[0104] The camera is controlled based on the reference monitoring point data, so that the camera obtains the standard partial cabinet configuration image based on the reference monitoring point data.

[0105] Obtain the current position and zoom information of the camera to obtain the absolute position of the locally configured gimbal.

[0106] It should be noted that when selecting reference monitoring point data from the optional monitoring point data, typically, for ease of measurement, calculation, and adjustment, the monitoring point with the largest area is selected as the reference monitoring point data. The camera is then aimed at the reference monitoring point data and magnified to the required level of observation, generally to the extent that the entire camera frame is magnified, to obtain the standard local screen cabinet configuration image. The current absolute position of the gimbal is then obtained as the local configuration gimbal absolute position, which includes position information (including horizontal and vertical angles) and zoom information (including zoom range), and may also include the current focal length (as the local configuration focal length).

[0107] Furthermore, to further improve accuracy, camera lens distortion can also be taken into consideration, since camera distortion may cause image distortion. Therefore, the existing geometric fitting algorithm is used to calculate the correction formula to ensure the accuracy of coordinate calculation and position adjustment: (1) Since the power cabinet is a cuboid, the sides of the power cabinet are straight lines and are on a plane. It can be independent of the absolute size line constraint. The principle is that after correct distortion removal, the four sides of the rectangle "should be straight lines". Hundreds or thousands of edge sampling points in multiple frames are used to fit the straight lines and the distortion parameters are optimized in reverse to straighten the "curved lines". (2) Place the outer frame of the power supply cabinet in the corner of the camera's field of view as much as possible; (3) Drive the camera to move slowly, at a speed that does not produce obvious motion blur; (4) Use the pre-trained YOLO algorithm to identify the target power supply cabinet and process the captured image; (5) The YOLO algorithm outputs multiple power supply cabinet detection boxes; (6) Find the power supply cabinet detection box with the largest area to prevent multiple power supply cabinets from being in the same scene, and select the largest power supply cabinet as the correction material: 6.1: Use the existing shoelace method to calculate the area of ​​each power supply cabinet detection box. Where Area is the area of ​​the power distribution cabinet detection frame, n is the number of vertices of the detection frame, (x i ,y i Let (x, y) represent the x and y coordinates of the i-th vertex of the power distribution cabinet detection frame in the image pixel coordinate system. i+1 ,y i+1 ) represents the x and y coordinates of the (i+1)th vertex of the power supply cabinet detection box in the image pixel coordinate system; 6.2 Find the largest power supply cabinet detection box by sorting. (7) Calculate the center point coordinates and rotation angle of the rectangle of the largest power supply cabinet detection box using the existing minimum bounding algorithm in OpenCV. (8) Obtain the four vertices of the rectangle, accurately locate the vertices of the screen cabinet rectangle, and select the vertex coordinates with the minimum x+y to the upper left, the maximum x+y to the lower right, the minimum xy to the upper right, and the maximum xy to the lower left; (9) Compare the coordinates of the four points with the coordinates in the current frame, select the closest coordinates and save them, and the minimum x'-x+y'-y; (10) To improve the accuracy of calculating the vertex subpixel coordinates: 10.1 Use the existing OpenCVimread(image,0) to read the grayscale image; 10.2 Set the search window (5,5) to search within a 5-pixel range around the corner point; 10.3 Set the zero zone to (-1,-1) to indicate that the center area is not excluded; 10.4 Set the maximum number of iterations to 30; 10.5 Set the accuracy threshold to 0.01 pixels; 10.6 Take the current corner point as the center and cut out a small area of ​​the grayscale image as a local window; 10.7 Use the existing OpenCV cornerSubPix function to calculate the vertex subpixel; (11) Continuously move the camera until the result converges.

[0108] In another embodiment, the global configuration gimbal absolute position includes a global horizontal angle and a global vertical angle, and the local configuration gimbal absolute position includes a local horizontal angle and a local vertical angle. The step of obtaining the configuration field view rotation ratio based on the reference configuration offset, the global configuration gimbal absolute position, and the local configuration gimbal absolute position includes:

[0109] The horizontal angle difference is obtained based on the difference between the global horizontal angle and the local horizontal angle;

[0110] The vertical angle difference is obtained based on the difference between the global vertical angle and the local vertical angle;

[0111] Based on the reference monitoring point data, a reference configuration offset is selected from the optional configuration offsets;

[0112] The horizontal ratio is obtained based on the ratio of the horizontal offset of the reference configuration to the horizontal angle difference in the reference configuration offset.

[0113] The vertical ratio is obtained based on the ratio of the vertical offset of the reference configuration to the vertical angle difference in the reference configuration offset.

[0114] Based on the horizontal and vertical proportions, the rotation ratio of the configured distant view is obtained.

[0115] It should be noted that the difference between the global horizontal angle and the local horizontal angle is calculated to obtain the horizontal angle difference (Δθ_h), and the difference between the global vertical angle and the local vertical angle is calculated to obtain the vertical angle difference (Δθ_v). Simultaneously, the ratio of the reference configuration offset to the angle difference is calculated: the horizontal ratio is the ratio of the reference configuration horizontal offset to the horizontal angle difference = Δx / Δθ_h; the vertical ratio is the ratio of the reference configuration vertical offset to the vertical angle difference = Δy / Δθ_v, where (Δx, Δy) represent the reference configuration offset corresponding to the reference monitoring point data in the optional monitoring point data. Based on the horizontal and vertical ratios, the rotation ratio of the configuration distant view is obtained.

[0116] In another embodiment, the use of offset includes using horizontal offset and using vertical offset, and the determination of the correction angle based on the used offset and the configured perspective view rotation ratio includes:

[0117] Obtain the ratio of the horizontal offset to the horizontal ratio to get the corrected horizontal angle;

[0118] Obtain the ratio of the vertical offset to the vertical ratio to get the corrected vertical angle;

[0119] The correction angle is obtained based on the correction horizontal angle and the correction vertical angle.

[0120] It should be noted that, after determining the detection points that need to be photographed in the target power cabinet, and using them as target monitoring point data, the camera is controlled to move to the absolute position of the global configuration pan-tilt unit so that the camera can capture images of the cabinet in use. The images of the cabinet in use and the standard global cabinet configuration images are compared. Existing image matching methods, such as the SIFT feature point matching algorithm, can be used to calculate the displacement deviation between the two images, obtaining the usage offset: the usage horizontal offset Δx' and usage vertical offset Δy' of the cabinet in use image relative to the standard global cabinet configuration image. Then, based on the rotation ratio of the configuration view and the usage offset, the vertical and horizontal angles (i.e., correction angles) that the camera needs to correct are calculated: the horizontal correction angle (Δθ_h' = Δx' / horizontal ratio) and the vertical correction angle (Δθ_v' = Δy' / vertical ratio) are calculated based on the horizontal and vertical ratios of the configuration view rotation ratio. The camera pan-tilt unit is then controlled to rotate the corresponding angles to complete the initial correction of the global field of view, thereby ensuring that the field of view of the cabinet in use image is consistent with the standard global cabinet configuration image during the configuration phase, and that the monitoring points have not moved out of the frame.

[0121] In another embodiment, obtaining the near-field adjustment angle based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration distant view rotation ratio includes:

[0122] Obtain the monitoring point-offset mapping relationship between the optional monitoring point data and the optional configuration offset;

[0123] Based on the monitoring point-offset mapping relationship and the target monitoring point data, the target configuration offset is obtained from the optional configuration offset;

[0124] Obtain the ratio of the target configuration horizontal offset to the horizontal ratio in the target configuration offset to get the near-view horizontal adjustment angle;

[0125] Obtain the ratio of the target configuration vertical offset to the vertical ratio in the target configuration offset to get the near-field vertical adjustment angle;

[0126] The close-up adjustment angle is obtained based on the close-up horizontal adjustment angle and the close-up vertical adjustment angle.

[0127] It should be noted that there is a monitoring point-offset mapping relationship between the optional monitoring point data and the optional configuration offset. Therefore, the target configuration offset (Δx_target, Δy_target) corresponding to the target monitoring point data is retrieved from the mapping relationship of the optional configuration offset. Based on the configuration of the distant view rotation ratio, the near-view horizontal adjustment angle of the target monitoring point data is calculated, i.e., the horizontal rotation angle Δθ_h_target = Δx_target / horizontal ratio, and the near-view vertical adjustment angle, i.e., the vertical rotation angle Δθ_v_target = Δy_target / vertical ratio. The camera pan-tilt unit is then controlled to rotate by the corresponding angle so that the target monitoring point data is aligned with the center of the image.

[0128] like Figure 2 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided;

[0129] One embodiment of the present invention provides a power distribution cabinet monitoring point imaging system, including a power distribution cabinet monitoring point imaging device and a controller. The power distribution cabinet monitoring point imaging device is connected to the controller, and the power distribution cabinet monitoring point imaging device includes:

[0130] The first control module is used to determine the target power cabinet and control the camera to capture standard global cabinet configuration images and standard partial cabinet configuration images of the target power cabinet;

[0131] The acquisition module is used to acquire the optional monitoring point data, the absolute position of the global configuration PTZ and the optional configuration offset of the standard global cabinet configuration image, and to acquire the absolute position of the local configuration PTZ of the standard local cabinet configuration image.

[0132] The rotation ratio module is used to obtain the rotation ratio of the configured distant view based on the global configuration gimbal absolute position and the local configuration gimbal absolute position.

[0133] The monitoring point determination module is used to determine the target monitoring point data of the target power cabinet;

[0134] The second control module is used to control the movement of the camera based on the absolute position of the global configuration PTZ, so that the camera can obtain a picture of the cabinet in use based on the target monitoring point data;

[0135] The offset module is used to obtain the usage offset based on the image of the cabinet in use and the image of the standard global cabinet configuration.

[0136] The correction angle module is used to obtain the correction angle based on the used offset and the configured distant view rotation ratio;

[0137] The close-up adjustment angle module is used to obtain the close-up adjustment angle based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration distant view rotation ratio;

[0138] The monitoring point shooting module is used to control the camera based on the absolute position of the local configuration gimbal, the correction angle, and the close-up adjustment angle, so that the camera can capture the target monitoring point data and obtain the target monitoring point image.

[0139] It is understood that the above system embodiments correspond to the method embodiments of the present invention, and can realize the method for capturing images of power cabinet monitoring points provided by any of the above method embodiments of the present invention.

[0140] It should be noted that the system embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0141] Based on the above-described embodiment of the power cabinet monitoring point shooting method, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power cabinet monitoring point shooting method of any embodiment of the present invention.

[0142] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0143] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0144] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0145] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the power cabinet monitoring point shooting method described in any of the above-described method embodiments of the present invention.

[0146] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0147] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A power panel monitoring point shooting method, characterized in that, The application is applied to a controller of a power screen cabinet monitoring point shooting device, and the method comprises the following steps: determining a target power screen cabinet, and controlling a camera to shoot a standard global screen cabinet configuration picture and a standard local screen cabinet configuration picture of the target power screen cabinet; obtaining optional monitoring point data, a global configuration cloud platform absolute position and an optional configuration offset of the standard global screen cabinet configuration picture, and obtaining a local configuration cloud platform absolute position of the standard local screen cabinet configuration picture; obtaining a configuration long shot picture rotation ratio based on the optional configuration offset, the global configuration cloud platform absolute position and the local configuration cloud platform absolute position; determining target monitoring point data of the target power screen cabinet; controlling movement of the camera based on the global configuration cloud platform absolute position, so that the camera obtains a screen cabinet use picture based on the target monitoring point data; obtaining a use offset based on the screen cabinet use picture and the standard global screen cabinet configuration picture; obtaining a correction angle based on the use offset and the configuration long shot picture rotation ratio; obtaining a close shot adjustment angle based on the target monitoring point data, the optional monitoring point data, the optional configuration offset and the configuration long shot picture rotation ratio; controlling the camera based on the local configuration cloud platform absolute position, the correction angle and the close shot adjustment angle, so that the camera shoots the target monitoring point data to obtain a target monitoring point picture.

2. The method of claim 1, wherein, The method for obtaining the optional monitoring point data, the global configuration cloud platform absolute position and the optional configuration offset of the standard global screen cabinet configuration picture, and obtaining the local configuration cloud platform absolute position of the standard local screen cabinet configuration picture, comprises the following steps: obtaining a text screen cabinet configuration picture; obtaining text monitoring point information of the text screen cabinet configuration picture by using a preset screen cabinet picture recognition model and the text screen cabinet configuration picture; obtaining global monitoring point information of the standard global screen cabinet configuration picture by using the screen cabinet picture recognition model and the standard global screen cabinet configuration picture; obtaining a text-global monitoring point mapping relationship based on the text monitoring point information and the global monitoring point information; obtaining initial monitoring point text by using a preset screen cabinet text recognition model and the text screen cabinet configuration picture; obtaining standard monitoring point text based on a preset screen cabinet semantic matching model and the initial monitoring point text; obtaining the optional monitoring point data based on the standard monitoring point text, the text-global monitoring point mapping relationship and the standard global screen cabinet configuration picture.

3. The method of claim 1, wherein the method further comprises: The method for obtaining the optional monitoring point data, the global configuration cloud platform absolute position and the optional configuration offset of the standard global screen cabinet configuration picture, and obtaining the local configuration cloud platform absolute position of the standard local screen cabinet configuration picture, comprises the following steps: obtaining a center point of the standard global screen cabinet configuration picture; obtaining a distance between the optional monitoring point data and the center point to obtain the optional configuration offset.

4. The method of claim 1, wherein, The method for obtaining the optional monitoring point data, the global configuration cloud platform absolute position and the optional configuration offset of the standard global screen cabinet configuration picture, and obtaining the local configuration cloud platform absolute position of the standard local screen cabinet configuration picture, comprises the following steps: selecting reference monitoring point data from the optional monitoring point data; controlling the camera based on the reference monitoring point data, so that the camera obtains the standard local screen cabinet configuration picture based on the reference monitoring point data; obtaining position information and zoom information of the current camera to obtain the local configuration cloud platform absolute position.

5. The method of claim 4, wherein, The global configuration cloud platform absolute position includes a global horizontal angle and a global vertical angle, the local configuration cloud platform absolute position includes a local horizontal angle and a local vertical angle, and the configuration long shot picture rotation ratio is obtained based on the reference configuration offset, the global configuration cloud platform absolute position and the local configuration cloud platform absolute position, including: obtaining a horizontal angle difference based on a difference between the global horizontal angle and the local horizontal angle; obtaining a vertical angle difference based on a difference between the global vertical angle and the local vertical angle; selecting a reference configuration offset from the selectable configuration offset based on the reference monitoring point data; obtaining a horizontal ratio based on a ratio between a reference configuration horizontal offset in the reference configuration offset and the horizontal angle difference; obtaining a vertical ratio based on a ratio between a reference configuration vertical offset in the reference configuration offset and the vertical angle difference; obtaining the configuration long shot picture rotation ratio based on the horizontal ratio and the vertical ratio.

6. The method of claim 5, wherein, The use offset includes a use horizontal offset and a use vertical offset, and the correction angle is obtained based on the use offset and the configuration long shot picture rotation ratio, including: obtaining a correction horizontal angle by obtaining a ratio between the use horizontal offset and the horizontal ratio; obtaining a correction vertical angle by obtaining a ratio between the use vertical offset and the vertical ratio; obtaining the correction angle based on the correction horizontal angle and the correction vertical angle.

7. The method of claim 5, wherein the method further comprises: The near shot adjustment angle is obtained based on the target monitoring point data, the selectable monitoring point data, the selectable configuration offset and the configuration long shot picture rotation ratio, including: obtaining a monitoring point-offset mapping relationship of the selectable monitoring point data and the selectable configuration offset; obtaining a target configuration offset from the selectable configuration offset based on the monitoring point-offset mapping relationship and the target monitoring point data; obtaining a near shot horizontal adjustment angle by obtaining a ratio between a target configuration horizontal offset in the target configuration offset and the horizontal ratio; obtaining a near shot vertical adjustment angle by obtaining a ratio between a target configuration vertical offset in the target configuration offset and the vertical ratio; obtaining the near shot adjustment angle based on the near shot horizontal adjustment angle and the near shot vertical adjustment angle.

8. A power panel monitoring point shooting system, characterized in that, The power screen cabinet monitoring point shooting device and the controller are connected, and the power screen cabinet monitoring point shooting device includes: A first control module is configured to determine a target power screen cabinet and control a camera to capture a standard global screen cabinet configuration picture and a standard local screen cabinet configuration picture of the target power screen cabinet. The acquisition module is configured to acquire optional monitoring point data of the standard global screen cabinet configuration picture, global configuration cloud absolute position, and optional configuration offset, and to acquire local configuration cloud absolute position of the standard local screen cabinet configuration picture; The rotation proportion module is configured to obtain a configuration long shot picture rotation proportion based on the global configuration cloud absolute position and the local configuration cloud absolute position; The monitoring point determination module is configured to determine target monitoring point data of the target power screen cabinet; The second control module is configured to control movement of the camera based on the global configuration cloud absolute position, so that the camera obtains a screen cabinet use picture based on the target monitoring point data; The use offset module is configured to obtain a use offset based on the screen cabinet use picture and the standard global screen cabinet configuration picture; The correction angle module is configured to obtain a correction angle based on the use offset and the configuration long shot picture rotation proportion; The close shot adjustment angle module is configured to obtain a close shot adjustment angle based on the target monitoring point data, the optional monitoring point data, the optional configuration offset, and the configuration long shot picture rotation proportion; The monitoring point shooting module is configured to control the camera based on the local configuration cloud absolute position, the correction angle, and the close shot adjustment angle, so that the camera shoots the target monitoring point data to obtain a target monitoring point picture.

9. A terminal device, comprising: A computer program product is provided, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the computer program is executed by the processor, a power screen cabinet monitoring point shooting method according to any one of claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer program product includes: A stored computer program, wherein when the computer program is running, the device in which the computer readable storage medium is located is controlled to execute a power screen cabinet monitoring point shooting method according to any one of claims 1-7.

Images