Instrument information acquisition method and device, equipment, storage medium and program product

Abstract

The invention relates to an instrument information acquisition method and device, equipment, a storage medium and a program product. The method comprises the following steps: collecting an initial instrument image on an instrument in a power system, and obtaining a standard instrument image; the initial instrument image and the standard instrument image are both images containing instruments; acquiring a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and acquiring a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are the same boundary line of the instrument; determining a space rotation angle corresponding to the initial instrument image according to an included angle between each first tangent line and each corresponding second tangent line; and correcting the initial instrument image according to the space rotation angle to obtain a corrected image, and reading instrument information in the corrected image. By adopting the method, the accuracy of the instrument information identified from the accurate correction image can be ensured.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, apparatus, device, storage medium, and program product for acquiring meter information. Background Art

[0002] With the development of power technology, sensors are widely used to collect various production data and environmental information in real time in smart power plants. For example, robots can be used to collect instrument information from at least one instrument in a power plant. This allows the power plant to monitor the operating status of power equipment based on the automated reading of instrument information, effectively preventing power accidents and ensuring the safe and stable operation of the power plant.

[0003] However, the current method for obtaining instrument information has the problem of low accuracy. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, equipment, storage medium and program product for obtaining meter information to address the above technical problems, which can improve the accuracy of the method for obtaining meter information.

[0005] In a first aspect, the present application provides a method for obtaining instrument information, comprising:

[0006] Collecting an initial instrument image on an instrument in the power system and obtaining a standard instrument image; the initial instrument image and the standard instrument image are both images containing the instrument;

[0007] Obtaining a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument;

[0008] determining a spatial rotation angle corresponding to the initial instrument image according to an angle between each of the first tangent lines and the corresponding second tangent lines;

[0009] The initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image, and the instrument information in the corrected image is read.

[0010] In one embodiment, determining the spatial rotation angle corresponding to the initial instrument image according to the angle between each first tangent line and the corresponding second tangent line includes:

[0011] Constructing a rotation angle vector according to the included angles between each of the first tangent lines and the corresponding second tangent lines; the rotation angle vector includes the rotation angle values corresponding to all the included angles;

[0012] The rotation angle vector is input into a preset angle prediction network to perform spatial angle prediction, so as to obtain the spatial rotation angle corresponding to the initial instrument image.

[0013] In one embodiment, inputting the rotation angle vector into a preset angle prediction network to perform spatial angle prediction to obtain the spatial rotation angle corresponding to the initial instrument image includes:

[0014] Inputting the rotation angle vector into the angle prediction network to perform spatial angle prediction, thereby obtaining a plurality of spatial angles corresponding to each of the first tangent lines;

[0015] determining a target spatial angle corresponding to each of the first tangent lines according to a plurality of spatial angles corresponding to each of the first tangent lines;

[0016] The target space angles corresponding to all first tangent lines are fused to obtain the space rotation angle corresponding to the initial instrument image.

[0017] In one embodiment, correcting the initial instrument image according to the spatial rotation angle to obtain a corrected image includes:

[0018] The position of each pixel in the initial instrument image is transformed according to the spatial rotation angle to obtain the corrected image.

[0019] In one embodiment, reading the instrument information in the calibration image includes:

[0020] Identifying the center of gravity position of the instrument and the end position of the pointer of the instrument in the correction image, and constructing a connecting line between the center of gravity position and the end position;

[0021] The pointer direction is determined according to the connection line, and the instrument information is determined according to the pointer direction.

[0022] In one embodiment, the method further comprises:

[0023] identifying a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image;

[0024] Taking the center point as the origin, constructing a plane rectangular coordinate system, and determining a plurality of rays in each quadrant of the plane rectangular coordinate system;

[0025] The intersection points of the rays and the first boundary line are determined as the first boundary points.

[0026] In a second aspect, the present application further provides a device for acquiring instrument information, comprising:

[0027] An acquisition module, configured to acquire an initial instrument image on an instrument in the power system and obtain a standard instrument image; both the initial instrument image and the standard instrument image are images containing the instrument;

[0028] an acquisition module, configured to acquire a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and to acquire a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument;

[0029] a determination module, configured to determine a spatial rotation angle corresponding to the initial instrument image according to an angle between each of the first tangent lines and the corresponding second tangent lines;

[0030] The correction module is used to correct the initial instrument image according to the spatial rotation angle to obtain a corrected image, and read the instrument information in the corrected image.

[0031] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in any one of the embodiments of the first aspect when executing the computer program.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method in any one of the embodiments of the first aspect.

[0033] In a fifth aspect, the present application further provides a computer program product, comprising a computer program that, when executed by a processor, implements the steps of the method in any one of the embodiments of the first aspect.

[0034] The above-mentioned method, device, equipment, storage medium and program product for acquiring meter information collect an initial meter image on a meter in a power system and acquire a standard meter image; the initial meter image and the standard meter image are both images containing the meter; the first tangent of each first boundary point on the first boundary line of the meter in the initial meter image is acquired, and the second tangent of each second boundary point on the second boundary line of the meter in the standard meter image is acquired; the first boundary line and the second boundary line are both the same boundary line of the meter; the spatial rotation angle corresponding to the initial meter image is determined based on the angle between each first tangent and the corresponding second tangent; the initial meter image is corrected based on the spatial rotation angle to obtain a corrected image, and the meter information in the corrected image is read. The embodiment of the present application can accurately determine the spatial rotation angle through the first tangent corresponding to the first boundary line of the initial meter image and the second tangent corresponding to the second boundary line of the standard meter image, and correct the initial meter image based on the spatial rotation angle to obtain an accurate corrected image, thereby ensuring the accuracy of the meter information identified from the accurate corrected image. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A diagram showing an application environment of a method for obtaining instrument information in one embodiment;

[0037] Figure 2 1 is a flow chart of a method for obtaining instrument information in one embodiment;

[0038] Figure 3 is a flow chart of a method for acquiring instrument information in another embodiment;

[0039] Figure 4 1 is a schematic flow chart of a spatial angle prediction step in one embodiment;

[0040] Figure 5 Schematic diagram of a flow chart of a method for acquiring instrument information in an optional embodiment;

[0041] Figure 6 FIG. 4 is a structural block diagram of a device for acquiring instrument information in an embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0044] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0045] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] Smart power plants are a significant milestone in the power industry's journey toward modernization and intelligent development. They deeply integrate information technology with traditional power generation technologies, revolutionizing power plant operations and management. This revolutionary model for power plant operations and management can be leveraged through cutting-edge technologies such as big data, cloud computing, the Internet of Things (IoT), and artificial intelligence (AI). It seamlessly connects all aspects of a power plant's production, monitoring, management, and maintenance, forming a highly integrated, intelligent, and collaborative ecosystem. With the advancement of power technology, sensors and the IoT are widely used to collect and transmit various production data and environmental information in smart power plants in real time. This data and environmental information, processed and analyzed by cloud computing platforms, not only provides a scientific basis for power plant decision-making but also drives automation and intelligent development of the entire production process. By deeply mining these data and environmental information through big data algorithms and AI models, power plants can accurately predict equipment status, optimize operational strategies, reduce energy consumption and emissions, and significantly improve energy efficiency and environmental performance.

[0047] Smart power plants can utilize 3D visualization technology to present the complex structure and operating status of power plants in an intuitive and vivid manner, enabling operators to quickly grasp the overall situation and respond promptly to various abnormal situations. For example, in terms of power plant safety, smart power plants can use robots to conduct inspections of the power plant and collect instrument information from at least one instrument in the power plant. This allows the power plant to monitor the operating status of power equipment based on the automatically read instrument information, thereby automatically identifying potential risks and taking preemptive measures to effectively avoid power accidents and ensure the safe and stable operation of the power plant.

[0048] However, due to differences in the robot's shooting angles, there are often errors in the robot's reading of instrument information. Therefore, the current method for obtaining instrument information has the problem of low accuracy.

[0049] After the above introduction to the background technology of the method for obtaining instrument information provided by the embodiment of the present application, the implementation environment involved in the method for obtaining instrument information provided by the embodiment of the present application will be briefly described below. The method for obtaining instrument information provided by the embodiment of the present application can be applied to robots in power plants. The robot may include but is not limited to a robotic arm, an image acquisition component, a processing component, etc., wherein the robotic arm, the image acquisition component and the processing component are all connected, and the robotic arm is used to control the robot to move in various directions in the power plant to adjust the image acquisition angle of the image acquisition component; the image acquisition component is used to acquire instrument images in the power plant; and the processing component is used to process and analyze the acquired instrument images to obtain instrument information in the instrument images. The robot may be a patrol robot of a power plant, and the image acquisition component may include a camera.

[0050] Among them, the processing component can be Figure 1The computer device shown, which can be a terminal or a server, includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, while the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, with wireless communication being achieved via Wi-Fi, mobile cellular networks, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for acquiring instrument information. The display unit of the computer device is used to produce a visual display and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0051] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0052] In one embodiment, Figure 2 As shown, a method for obtaining instrument information is provided, which is described by taking the method applied to a robot as an example, and includes the following steps:

[0053] S201, collecting an initial instrument image on an instrument in a power system, and obtaining a standard instrument image; the initial instrument image and the standard instrument image are both images containing instruments.

[0054] Among them, the power system refers to the system where the power plant is located, the instrument refers to at least one instrument in the power plant, the initial instrument image is the instrument image captured by the image acquisition component in the robot, and the standard instrument image is the instrument image obtained by shooting directly facing the instrument, that is, the shooting direction of the standard instrument image is perpendicular to the surface where the instrument dial is located. It should be noted that the initial instrument image and the standard instrument image are both images containing the same instrument.

[0055] In an embodiment of the present application, after controlling the robotic arm to move to a preset position, the robot can use the image acquisition component to capture an initial meter image of a meter in the power system. Optionally, after capturing the initial meter image of the meter in the power system, the robot can preprocess the initial meter image, thereby enabling subsequent steps S202-S204 to be executed based on the preprocessed initial meter image. Preprocessing methods may include, but are not limited to, filtering using a smoothing filter and wavelet noise reduction, and are used to remove noise from the initial meter image.

[0056] Smoothing filters weaken or eliminate high-frequency components in an image. These high-frequency components typically correspond to areas with large grayscale value variations, such as image edges. By filtering out these high-frequency components, smoothing filters can reduce local grayscale fluctuations, resulting in a smoother image. Wavelet denoising uses the wavelet transform to decompose the image signal into different scales or frequencies, then removes the wavelet coefficients that represent noise, retains and enhances the wavelet coefficients that represent the signal, and finally reconstructs the denoised image signal. Smoothing filters and wavelet denoising each have their own unique roles and effects in image processing. Specifically, smoothing filters are primarily used for tasks such as image smoothing, noise removal, and detail removal, while wavelet denoising leverages the multi-resolution, decorrelation, and basis selection flexibility of the wavelet transform to effectively remove noise while preserving image detail.

[0057] In addition, the robot can also pre-acquire standard instrument images on instruments in the power system. Optionally, the robot can obtain standard instrument images from a database; or, the robot can also control the movement of the robotic arm to adjust the shooting direction of the image acquisition component located on the robotic arm to a direction perpendicular to the surface where the instrument dial is located, and then collect standard instrument images through the image acquisition component after adjusting the direction. Of course, the embodiment of the present application does not limit the specific implementation method of obtaining standard instrument images.

[0058] S202, obtaining a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument.

[0059] The first boundary line refers to the boundary line of the instrument in the initial instrument image, the first boundary point refers to at least two boundary points on the first boundary line, and the first tangent line refers to the tangent of the first boundary line constructed at the first boundary point. The second boundary line refers to the boundary line of the instrument in the standard instrument image, the second boundary point refers to at least two boundary points on the second boundary line, and the second tangent line refers to the tangent of the second boundary line constructed at the second boundary point. It should be noted that the first boundary line and the second boundary line are the same boundary line of the instrument.

[0060] In an embodiment of the present application, a processing component in the robot can determine each first boundary point on a first boundary line of an instrument in an initial instrument image, and construct a first tangent to the first boundary line at each first boundary point. Furthermore, the robot can determine each second boundary point on a second boundary line of an instrument in a standard instrument image, and construct a second tangent to the second boundary line at each second boundary point. Of course, in an embodiment of the present application, there is no limitation on the order in which the first tangents and the second tangents are constructed.

[0061] S203 : Determine a spatial rotation angle corresponding to the initial instrument image according to the included angle between each first tangent line and the corresponding second tangent line.

[0062] In an embodiment of the present application, the processing component in the robot can determine the second tangent corresponding to each first tangent, and determine the angle between each first tangent and the corresponding second tangent. Thus, the spatial rotation angle corresponding to the initial instrument image can be determined based on the angle between each first tangent and the corresponding second tangent. Optionally, the processing component in the robot can directly determine the spatial rotation angle corresponding to the initial instrument image based on the angle between each first tangent and the corresponding second tangent; or, the processing component in the robot can first determine the rotation angle vector based on the angle between each first tangent and the corresponding second tangent, and then determine the spatial rotation angle corresponding to the initial instrument image based on the rotation angle vector. The spatial rotation angle refers to the angle required to spatially rotate the initial instrument image, and the spatial rotation angle can include at least the rotation values of the three axes x, y, and z.

[0063] S204: Correct the initial instrument image according to the spatial rotation angle to obtain a corrected image, and read the instrument information in the corrected image.

[0064] In an embodiment of the present application, the processing component in the robot can use image processing software to correct or restore the initial instrument image according to the spatial rotation angle to obtain a corrected image. The image processing software can be any one of Photoshop, GIMP or OpenCV. For example, Photoshop can simulate the inverse process of three-dimensional rotation through functions such as "Free Transform" or "Distort", combined with operations such as rotation, scaling and tilt, to adjust the initial instrument image to the main view angle to obtain a corrected image. Alternatively, the matrix operations and transformation functions of OpenCV can be used to construct the inverse matrix of the three-dimensional rotation matrix, and the inverse matrix of the three-dimensional rotation matrix is applied to the initial instrument image to obtain a corrected image, thereby achieving three-dimensional rotation restoration. Afterwards, the robot can read the instrument information from the corrected image. The corrected image refers to the corrected initial instrument image, and the instrument information may include but is not limited to information such as instrument readings.

[0065] In the above-mentioned method for acquiring meter information, an initial meter image on a meter in a power system is collected, and a standard meter image is acquired; both the initial meter image and the standard meter image are images containing the meter; a first tangent of each first boundary point on the first boundary line of the meter in the initial meter image is acquired, and a second tangent of each second boundary point on the second boundary line of the meter in the standard meter image is acquired; the first boundary line and the second boundary line are both the same boundary line of the meter; the spatial rotation angle corresponding to the initial meter image is determined based on the angle between each first tangent and the corresponding second tangent; the initial meter image is corrected based on the spatial rotation angle to obtain a corrected image, and the meter information in the corrected image is read. The embodiment of the present application can accurately determine the spatial rotation angle through the first tangent corresponding to the first boundary line of the initial meter image and the second tangent corresponding to the second boundary line of the standard meter image, and correct the initial meter image based on the spatial rotation angle to obtain an accurate corrected image, thereby ensuring the accuracy of the meter information identified from the accurate corrected image.

[0066] In one embodiment, a method for determining each first boundary point is provided, that is, before "obtaining the first tangent line of each first boundary point on the first boundary line of the instrument in the initial instrument image" in S202, as follows Figure 3 As shown, the above-mentioned method for obtaining instrument information also includes:

[0067] S205 , identifying a first boundary line of the instrument and a center point of the area where the instrument is located in the initial instrument image.

[0068] In this embodiment of the present application, the robot can use a pre-trained first graph neural network model to identify the first boundary line of the instrument and the center point of the area where the instrument is located in the initial instrument image, thereby obtaining the specific location of the first boundary line of the instrument and the specific location of the center point of the area where the instrument is located. Of course, this embodiment of the present application does not limit the model structure of the first graph neural network model.

[0069] Furthermore, the robot can render the instrument area boundary at a preset first pixel value as the first boundary line of the instrument, and / or render the area outside the instrument in the initial instrument image at a second preset pixel value. Since the instrument panel is typically a standard circle or ellipse, changes in the instrument area boundary typically represent changes in the observation angle. Therefore, representing the instrument panel boundary with the first preset pixel value facilitates subsequent rotation analysis. By rendering the area outside the instrument panel at the second preset pixel value, this area outside the instrument panel can be prevented from affecting subsequent analysis.

[0070] S206 , using the center point as the origin, constructing a plane rectangular coordinate system, and determining a plurality of rays in each quadrant of the plane rectangular coordinate system.

[0071] In an embodiment of the present application, the robot can mark the center point of the instrument and use the center point as the origin of the plane rectangular coordinate system to construct a plane rectangular coordinate system. The center point of the instrument usually corresponds to the center of a circular instrument panel. Thus, the robot can use the center point of the instrument as the endpoint of a ray to construct multiple rays that bisect each quadrant in the plane rectangular coordinate system. For example, the robot can use the center point of the instrument as the endpoint to evenly divide the range of 90° angles in each quadrant of the plane rectangular coordinate system into a preset number of angles, and construct multiple rays based on the center point of the instrument and the side of each angle.

[0072] S207: Determine the intersection points of each ray and the first boundary line as each first boundary point.

[0073] In the embodiment of the present application, the robot can determine the intersection of each ray and the first boundary line, and determine the intersection of each ray and the first boundary line as each first boundary point.

[0074] Furthermore, it should be noted that the method for determining each second boundary point for a standard instrument image is similar to the method for determining each first boundary point described above. For example, the robot can identify the second boundary line of the instrument in the standard instrument image and the center of gravity of the standard instrument image. Thus, using the center of gravity of the standard instrument image as the origin, a plane rectangular coordinate system is constructed, and multiple rays are determined for each quadrant of the plane rectangular coordinate system. Subsequently, rays are used to evenly divide the 90° angle range in each quadrant into a predetermined number of angles, and the intersection of each ray with the second boundary line is determined as each second boundary point.

[0075] In this embodiment, the first boundary line of the instrument in the initial instrument image and the center point of the area where the instrument is located can be identified, and the center point can be used as the origin to construct a plane rectangular coordinate system, and multiple rays in each quadrant of the plane rectangular coordinate system can be determined. Thus, the intersection points of each ray with the first boundary line can be determined as each first boundary point, and the first boundary line and each first boundary point can be accurately determined.

[0076] In one embodiment, a method for determining the spatial rotation angle is provided, namely, "determining the spatial rotation angle corresponding to the initial instrument image according to the angle between each first tangent line and the corresponding second tangent line" in the above S203. Figure 4 As shown, including:

[0077] S301 : Constructing a rotation angle vector according to the included angles between each first tangent line and the corresponding second tangent line; the rotation angle vector includes the rotation angle values corresponding to all the included angles.

[0078] Among them, the rotation angle vector contains the rotation angle values corresponding to all angles.

[0079] In an embodiment of the present application, the robot can number each first tangent in the initial instrument image and each second tangent in the standard instrument image. For example, the positive direction of the horizontal axis can be selected as the starting position for numbering, and each ray can be sequentially numbered in a clockwise direction. The tangents corresponding to the rays are constructed with the same number, so that the tangents with the same number can be determined as corresponding tangents. Since changes in the boundaries of the captured image usually cause changes in the angles of the tangents at the corresponding positions of the boundaries, the degree of refinement of the processing can be ensured by finely dividing each quadrant. Furthermore, by constructing rays, it is easy to make the tangents at the same position in the standard instrument image correspond to the tangents in the initial instrument image, and then the corresponding tangents can be analyzed one by one.

[0080] Thus, for each corresponding first tangent and second tangent, the robot can determine the angle between each first tangent and each corresponding second tangent, normalize the value of each angle to obtain a normalized angle, and then use the value of the normalized angle as the value of each dimension in the rotation angle vector. In this way, the rotation angle vector can be constructed. For example, the angle value can be normalized to between 0 and 1, and the normalized angle value can be used as the value of the corresponding dimension in the rotation angle vector based on the tangent number.

[0081] S302: Input the rotation angle vector into a preset angle prediction network to perform spatial angle prediction, and obtain the spatial rotation angle corresponding to the initial instrument image.

[0082] In an embodiment of the present application, the robot can input the rotation angle vector into a preset angle prediction network to perform spatial angle prediction, and obtain the spatial rotation angle corresponding to the initial instrument image. The angle prediction network can be any neural network model. Of course, the embodiment of the present application is not limited to the angle prediction network. Optionally, the robot can input the rotation angle vector into a preset angle prediction network to perform spatial angle prediction, and obtain the spatial rotation angle corresponding to the initial instrument image; or, the preset angle prediction network can include sub-networks corresponding to the three axes x, y and z respectively. Based on this, the robot can also input the rotation angle vector into the three sub-networks in the preset angle prediction network to perform spatial angle prediction respectively, and obtain the rotation values of the three axes x, y and z respectively corresponding to the initial instrument image.

[0083] In this embodiment, the three-dimensional rotation of the instrument screen is estimated by constructing two-dimensional tangents and comparing the angles of each tangent. The rotation changes in the three-dimensional space are estimated in a two-dimensional manner. Therefore, the rotation angles of each of the x, y and z axes can be calculated through a preset angle prediction network, so that the initial instrument image can be corrected subsequently through the three-dimensional rotation angle, thereby ensuring the correction accuracy.

[0084] In one embodiment, a method for implementing spatial angle prediction is provided, namely, the above-mentioned step S302 of "inputting the rotation angle vector into a preset angle prediction network to perform spatial angle prediction to obtain the spatial rotation angle corresponding to the initial instrument image" includes:

[0085] The rotation angle vector is input into the angle prediction network to perform spatial angle prediction, and multiple spatial angles corresponding to each first tangent are obtained.

[0086] According to the multiple spatial angles corresponding to the first tangent lines, a target spatial angle corresponding to each first tangent line is determined.

[0087] The target space angles corresponding to all first tangents are fused to obtain the space rotation angle corresponding to the initial instrument image.

[0088] In an embodiment of the present application, for each first tangent, the robot can input the rotation angle vector into a preset angle prediction network to perform spatial angle prediction, and obtain multiple spatial angles corresponding to each first tangent. Thus, the robot can determine the target spatial angle corresponding to each first tangent based on the multiple spatial angles corresponding to each first tangent. Among them, for each first tangent, optionally, the robot can filter out the target spatial angle corresponding to the first tangent from the multiple spatial angles corresponding to the first tangent; or, the robot can also fuse the multiple spatial angles corresponding to the first tangent to obtain the target spatial angle corresponding to the first tangent. Afterwards, the robot can fuse the target spatial angles corresponding to all first tangents to obtain the spatial rotation angle corresponding to the initial instrument image. Among them, the fusion processing method may include but is not limited to fusion methods such as weighted fusion.

[0089] In this embodiment, the rotation angle vector can be input into the angle prediction network for spatial angle prediction, resulting in multiple spatial angles corresponding to each first tangent. Based on these multiple spatial angles, the target spatial angle corresponding to each first tangent can be accurately determined. Consequently, the target spatial angles corresponding to all first tangents can be fused to accurately determine the spatial rotation angle corresponding to the initial instrument image.

[0090] In one embodiment, a method for correcting the initial instrument image is provided, namely, the step of “correcting the initial instrument image according to the spatial rotation angle to obtain a corrected image” in S204, including:

[0091] According to the spatial rotation angle, the position of each pixel in the initial instrument image is transformed to obtain a corrected image.

[0092] In an embodiment of the present application, the robot can transform the position and / or pixel value of each pixel point in the instrument area in the initial instrument image according to the spatial rotation angle, that is, a corrected image corresponding to the instrument area in the initial instrument image.

[0093] In this embodiment, the position of each pixel in the initial instrument image can be accurately transformed according to the spatial rotation angle to obtain an accurate corrected image.

[0094] In one embodiment, a method for reading instrument information is provided, namely, the step of “reading instrument information in the correction image” in S204, including:

[0095] The center of gravity position of the instrument and the end position of the pointer of the instrument in the correction image are identified, and a connecting line between the center of gravity position and the end position is constructed.

[0096] The pointer direction is determined according to the connecting line, and the instrument information is determined according to the pointer direction.

[0097] In an embodiment of the present application, the robot can use a pre-trained second graph neural network model to identify the end position of the instrument pointer in the correction image and the center of gravity position of the correction image. Based on a pre-set identification model, the robot can mark the end position of the instrument pointer in the correction image and the center of gravity position of the correction image. Thereafter, based on the end position of the instrument pointer and the center of gravity position of the correction image, a line is constructed between the center of gravity position (i.e., the starting end position) and the end position of the correction image. The second graph neural network model and the identification model can both be any type of neural network model. Of course, the embodiment of the present application does not limit the identification model.

[0098] Thus, the robot can determine the pointing vector based on the line connecting the center of gravity of the calibration image and the end position, and determine the pointing direction of the pointer corresponding to the pointing vector. Furthermore, the robot can determine the instrument reading in the calibration image based on the pointing direction of the pointer.

[0099] In this embodiment, the pointer of the calibration image can be identified, and the direction of the pointer can be determined by the positions of the head and tail ends of the pointer. Accurate instrument readings can be obtained by combining with the original scale of the original instrument.

[0100] In an optional embodiment, if Figure 5 As shown, a method for obtaining instrument information is provided, which is applied to a robot and includes:

[0101] S401, collecting an initial instrument image on an instrument in a power system and obtaining a standard instrument image; both the initial instrument image and the standard instrument image are images containing instruments;

[0102] S402, identifying a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image;

[0103] S403, constructing a plane rectangular coordinate system with the center point as the origin, and determining multiple rays in each quadrant of the plane rectangular coordinate system;

[0104] S404, determining the intersection points of each ray and the first boundary line as each first boundary point;

[0105] S405, obtaining a first tangent line of each first boundary point, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument;

[0106] S406, constructing a rotation angle vector based on the included angles between each first tangent line and the corresponding second tangent line; the rotation angle vector includes the rotation angle values corresponding to all included angles;

[0107] S407, inputting the rotation angle vector into an angle prediction network to perform spatial angle prediction, and obtaining multiple spatial angles corresponding to each first tangent line;

[0108] S408, determining a target spatial angle corresponding to each first tangent line based on the multiple spatial angles corresponding to each first tangent line;

[0109] S409, performing fusion processing on the target spatial angles corresponding to all first tangent lines to obtain the spatial rotation angle corresponding to the initial instrument image;

[0110] S410, transforming the position of each pixel in the initial instrument image according to the spatial rotation angle to obtain a corrected image;

[0111] S411, identifying the center of gravity position of the instrument and the end position of the pointer of the instrument in the calibration image, and constructing a connecting line between the center of gravity position and the end position;

[0112] S412: Determine the pointer direction according to the connection line, and determine the instrument information according to the pointer direction.

[0113] In the above-mentioned method for acquiring meter information, an initial meter image on a meter in a power system is collected, and a standard meter image is acquired; both the initial meter image and the standard meter image are images containing the meter; a first tangent of each first boundary point on the first boundary line of the meter in the initial meter image is acquired, and a second tangent of each second boundary point on the second boundary line of the meter in the standard meter image is acquired; the first boundary line and the second boundary line are both the same boundary line of the meter; the spatial rotation angle corresponding to the initial meter image is determined based on the angle between each first tangent and the corresponding second tangent; the initial meter image is corrected based on the spatial rotation angle to obtain a corrected image, and the meter information in the corrected image is read. The embodiment of the present application can accurately determine the spatial rotation angle through the first tangent corresponding to the first boundary line of the initial meter image and the second tangent corresponding to the second boundary line of the standard meter image, and correct the initial meter image based on the spatial rotation angle to obtain an accurate corrected image, thereby ensuring the accuracy of the meter information identified from the accurate corrected image.

[0114] Based on the above embodiments, it can be seen that the embodiments of the present application can first identify the instrument area in the initial instrument image and construct a coordinate system based on the center point of the area. Specifically, the origin of the coordinate system is the center point, and the center point is usually the center of the instrument dial. Secondly, the positions of the first boundary points corresponding to the intersection of the ray that bisects each quadrant in the initial instrument image and the instrument area boundary can be determined, and the positions of the second boundary points corresponding to the intersection of the same ray in the same quadrant of the standard circular instrument area in the standard instrument image and the circular instrument boundary can be determined. Afterwards, the first tangent of each first boundary point is compared with the second tangent of each second boundary point to obtain the spatial rotation angle corresponding to the initial instrument image, so that the initial instrument image can be corrected according to the spatial rotation angle to obtain an accurate corrected image, and further, the accuracy of the instrument readings identified from the accurate corrected image can be guaranteed.

[0115] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0116] Based on the same inventive concept, embodiments of the present application also provide an apparatus for acquiring instrument information for implementing the aforementioned method for acquiring instrument information. The solution provided by this apparatus is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the apparatus for acquiring instrument information provided below can be found in the aforementioned method for acquiring instrument information, and will not be further elaborated here.

[0117] In an exemplary embodiment, Figure 6 As shown, a device for acquiring instrument information is provided, including: a collection module 31, an acquisition module 32, a determination module 33 and a correction module 34, wherein:

[0118] The acquisition module 31 is used to acquire initial instrument images on instruments in the power system and obtain standard instrument images; both the initial instrument image and the standard instrument image are images containing instruments.

[0119] The acquisition module 32 is used to obtain the first tangent line of each first boundary point on the first boundary line of the instrument in the initial instrument image, and to obtain the second tangent line of each second boundary point on the second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument.

[0120] The determination module 33 is configured to determine the spatial rotation angle corresponding to the initial instrument image according to the angles between the first tangent lines and the corresponding second tangent lines.

[0121] The correction module 34 is used to correct the initial instrument image according to the spatial rotation angle to obtain a corrected image, and read the instrument information in the corrected image.

[0122] In one embodiment, the determination module 33 includes:

[0123] A rotation angle vector construction unit is used to construct a rotation angle vector according to the included angles between each first tangent line and each corresponding second tangent line; the rotation angle vector includes the rotation angle values corresponding to all included angles;

[0124] The prediction unit is used to input the rotation angle vector into a preset angle prediction network to perform spatial angle prediction and obtain the spatial rotation angle corresponding to the initial instrument image.

[0125] In one embodiment, the prediction unit is specifically configured to:

[0126] The rotation angle vector is input into the angle prediction network to perform spatial angle prediction, and multiple spatial angles corresponding to each first tangent are obtained;

[0127] Determining a target spatial angle corresponding to each first tangent line according to a plurality of spatial angles corresponding to each first tangent line;

[0128] The target space angles corresponding to all first tangents are fused to obtain the space rotation angle corresponding to the initial instrument image.

[0129] In one embodiment, the correction module 34 includes:

[0130] The transformation unit is used to transform the position of each pixel in the initial instrument image according to the spatial rotation angle to obtain a corrected image.

[0131] In one embodiment, the correction module 34 includes:

[0132] A line construction unit is used to identify the center of gravity position of the instrument and the end position of the pointer of the instrument in the correction image, and to construct a line between the center of gravity position and the end position;

[0133] The instrument information determining unit is used to determine the pointer direction according to the connection line, and determine the instrument information according to the pointer direction.

[0134] In one embodiment, the device for obtaining the instrument information further includes:

[0135] a recognition module, configured to recognize a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image;

[0136] A construction module is used to construct a plane rectangular coordinate system with the center point as the origin, and determine multiple rays in each quadrant of the plane rectangular coordinate system;

[0137] The first boundary point determination module is used to determine the intersection points of each ray and the first boundary line as each first boundary point.

[0138] Each module in the aforementioned instrument information acquisition device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0139] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 1 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means. The wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for obtaining instrument information. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0140] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0141] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0142] Collecting initial instrument images on instruments in the power system and obtaining standard instrument images; both the initial instrument image and the standard instrument image are images containing instruments;

[0143] Obtaining a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument;

[0144] Determining a spatial rotation angle corresponding to the initial instrument image according to the angles between each first tangent line and the corresponding second tangent line;

[0145] The initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image, and the instrument information in the corrected image is read.

[0146] In one embodiment, the spatial rotation angle corresponding to the initial instrument image is determined based on the angle between each first tangent line and the corresponding second tangent line. When the processor executes the computer program, the following steps are further implemented:

[0147] Constructing a rotation angle vector based on the included angles between each first tangent line and the corresponding second tangent line; the rotation angle vector includes the rotation angle values corresponding to all included angles;

[0148] The rotation angle vector is input into the preset angle prediction network to perform spatial angle prediction and obtain the spatial rotation angle corresponding to the initial instrument image.

[0149] In one embodiment, the rotation angle vector is input into a preset angle prediction network to perform spatial angle prediction to obtain a spatial rotation angle corresponding to the initial instrument image. When the processor executes the computer program, the following steps are further implemented:

[0150] The rotation angle vector is input into the angle prediction network to perform spatial angle prediction, and multiple spatial angles corresponding to each first tangent are obtained;

[0151] Determining a target spatial angle corresponding to each first tangent line according to a plurality of spatial angles corresponding to each first tangent line;

[0152] The target space angles corresponding to all first tangents are fused to obtain the space rotation angle corresponding to the initial instrument image.

[0153] In one embodiment, the initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image, and the processor further implements the following steps when executing the computer program:

[0154] According to the spatial rotation angle, the position of each pixel in the initial instrument image is transformed to obtain a corrected image.

[0155] In one embodiment, when reading the instrument information in the calibration image, the processor executes the computer program and further implements the following steps:

[0156] Identify the center of gravity position of the instrument and the end position of the pointer of the instrument in the calibration image, and construct a connecting line between the center of gravity position and the end position;

[0157] The pointer direction is determined according to the connecting line, and the instrument information is determined according to the pointer direction.

[0158] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0159] Identifying a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image;

[0160] Taking the center point as the origin, construct a plane rectangular coordinate system and determine multiple rays in each quadrant of the plane rectangular coordinate system;

[0161] The intersection points of each ray and the first boundary line are determined as first boundary points.

[0162] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0163] Collecting initial instrument images on instruments in the power system and obtaining standard instrument images; both the initial instrument image and the standard instrument image are images containing instruments;

[0164] Obtaining a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument;

[0165] Determining a spatial rotation angle corresponding to the initial instrument image according to the angles between each first tangent line and the corresponding second tangent line;

[0166] The initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image, and the instrument information in the corrected image is read.

[0167] In one embodiment, the spatial rotation angle corresponding to the initial instrument image is determined based on the angle between each first tangent line and the corresponding second tangent line. When the computer program is executed by the processor, the following steps are further implemented:

[0168] Constructing a rotation angle vector based on the included angles between each first tangent line and the corresponding second tangent line; the rotation angle vector includes the rotation angle values corresponding to all included angles;

[0169] The rotation angle vector is input into the preset angle prediction network to perform spatial angle prediction and obtain the spatial rotation angle corresponding to the initial instrument image.

[0170] In one embodiment, the rotation angle vector is input into a preset angle prediction network to perform spatial angle prediction to obtain a spatial rotation angle corresponding to the initial instrument image. When the computer program is executed by the processor, the following steps are further implemented:

[0171] The rotation angle vector is input into the angle prediction network to perform spatial angle prediction, and multiple spatial angles corresponding to each first tangent are obtained;

[0172] Determining a target spatial angle corresponding to each first tangent line according to a plurality of spatial angles corresponding to each first tangent line;

[0173] The target space angles corresponding to all first tangents are fused to obtain the space rotation angle corresponding to the initial instrument image.

[0174] In one embodiment, the initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image. When the computer program is executed by the processor, the following steps are further implemented:

[0175] According to the spatial rotation angle, the position of each pixel in the initial instrument image is transformed to obtain a corrected image.

[0176] In one embodiment, the computer program, when executed by a processor, further implements the following steps when reading instrument information in the calibration image:

[0177] Identify the center of gravity position of the instrument and the end position of the pointer of the instrument in the calibration image, and construct a connecting line between the center of gravity position and the end position;

[0178] The pointer direction is determined according to the connecting line, and the instrument information is determined according to the pointer direction.

[0179] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0180] Identifying a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image;

[0181] Taking the center point as the origin, construct a plane rectangular coordinate system and determine multiple rays in each quadrant of the plane rectangular coordinate system;

[0182] The intersection points of each ray and the first boundary line are determined as first boundary points.

[0183] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0184] Collecting initial instrument images on instruments in the power system and obtaining standard instrument images; both the initial instrument image and the standard instrument image are images containing instruments;

[0185] Obtaining a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument;

[0186] Determining a spatial rotation angle corresponding to the initial instrument image according to the angles between each first tangent line and the corresponding second tangent line;

[0187] The initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image, and the instrument information in the corrected image is read.

[0188] In one embodiment, the spatial rotation angle corresponding to the initial instrument image is determined based on the angle between each first tangent line and the corresponding second tangent line. When the computer program is executed by the processor, the following steps are further implemented:

[0189] Constructing a rotation angle vector based on the included angles between each first tangent line and the corresponding second tangent line; the rotation angle vector includes the rotation angle values corresponding to all included angles;

[0190] The rotation angle vector is input into the preset angle prediction network to perform spatial angle prediction and obtain the spatial rotation angle corresponding to the initial instrument image.

[0191] In one embodiment, the rotation angle vector is input into a preset angle prediction network to perform spatial angle prediction to obtain a spatial rotation angle corresponding to the initial instrument image. When the computer program is executed by the processor, the following steps are further implemented:

[0192] The rotation angle vector is input into the angle prediction network to perform spatial angle prediction, and multiple spatial angles corresponding to each first tangent are obtained;

[0193] Determining a target spatial angle corresponding to each first tangent line according to a plurality of spatial angles corresponding to each first tangent line;

[0194] The target space angles corresponding to all first tangents are fused to obtain the space rotation angle corresponding to the initial instrument image.

[0195] In one embodiment, the initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image. When the computer program is executed by the processor, the following steps are further implemented:

[0196] According to the spatial rotation angle, the position of each pixel in the initial instrument image is transformed to obtain a corrected image.

[0197] In one embodiment, the computer program, when executed by a processor, further implements the following steps when reading instrument information in the calibration image:

[0198] Identify the center of gravity position of the instrument and the end position of the pointer of the instrument in the calibration image, and construct a connecting line between the center of gravity position and the end position;

[0199] The pointer direction is determined according to the connecting line, and the instrument information is determined according to the pointer direction.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0201] Identifying a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image;

[0202] Taking the center point as the origin, construct a plane rectangular coordinate system and determine multiple rays in each quadrant of the plane rectangular coordinate system;

[0203] The intersection points of each ray and the first boundary line are determined as first boundary points.

[0204] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0205] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0206] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for obtaining instrument information, characterized in that: Applied to a robot, the method comprises: Collecting an initial instrument image on an instrument in the power system and obtaining a standard instrument image; the initial instrument image and the standard instrument image are both images containing the instrument; Obtaining a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and obtaining a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument; determining a spatial rotation angle corresponding to the initial instrument image according to an angle between each of the first tangent lines and the corresponding second tangent lines; The initial instrument image is corrected according to the spatial rotation angle to obtain a corrected image, and the instrument information in the corrected image is read.

2. The method according to claim 1, characterized in that The determining, based on the angles between the first tangent lines and the corresponding second tangent lines, of the spatial rotation angle corresponding to the initial instrument image includes: Constructing a rotation angle vector according to the included angles between each of the first tangent lines and the corresponding second tangent lines; the rotation angle vector includes the rotation angle values corresponding to all the included angles; The rotation angle vector is input into a preset angle prediction network to perform spatial angle prediction, so as to obtain the spatial rotation angle corresponding to the initial instrument image.

3. The method according to claim 2, characterized in that Inputting the rotation angle vector into a preset angle prediction network to perform spatial angle prediction to obtain the spatial rotation angle corresponding to the initial instrument image includes: Inputting the rotation angle vector into the angle prediction network to perform spatial angle prediction, thereby obtaining a plurality of spatial angles corresponding to each of the first tangent lines; determining a target spatial angle corresponding to each of the first tangent lines according to a plurality of spatial angles corresponding to each of the first tangent lines; The target space angles corresponding to all first tangent lines are fused to obtain the space rotation angle corresponding to the initial instrument image.

4. The method according to any one of claims 1 to 3, characterized in that Correcting the initial instrument image according to the spatial rotation angle to obtain a corrected image includes: The position of each pixel in the initial instrument image is transformed according to the spatial rotation angle to obtain the corrected image.

5. The method according to any one of claims 1 to 3, characterized in that The reading of the instrument information in the calibration image includes: Identifying the center of gravity position of the instrument and the end position of the pointer of the instrument in the correction image, and constructing a connecting line between the center of gravity position and the end position; The pointer direction is determined according to the connection line, and the instrument information is determined according to the pointer direction.

6. The method according to any one of claims 1 to 3, characterized in that The method further comprises: identifying a first boundary line of the instrument and a center point of an area where the instrument is located in the initial instrument image; Taking the center point as the origin, constructing a plane rectangular coordinate system, and determining a plurality of rays in each quadrant of the plane rectangular coordinate system; The intersection points of the rays and the first boundary line are determined as the first boundary points.

7. A device for acquiring instrument information, characterized in that: The device comprises: An acquisition module, configured to acquire an initial instrument image on an instrument in the power system and obtain a standard instrument image; both the initial instrument image and the standard instrument image are images containing the instrument; an acquisition module, configured to acquire a first tangent line of each first boundary point on a first boundary line of the instrument in the initial instrument image, and to acquire a second tangent line of each second boundary point on a second boundary line of the instrument in the standard instrument image; the first boundary line and the second boundary line are both the same boundary line of the instrument; a determination module, configured to determine a spatial rotation angle corresponding to the initial instrument image according to an angle between each of the first tangent lines and the corresponding second tangent lines; The correction module is used to correct the initial instrument image according to the spatial rotation angle to obtain a corrected image, and read the instrument information in the corrected image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images