Autonomous visual sniffing identification method and system for transformer substation instrument

Through the autonomous visual sniffing recognition method, the robot and gimbal position is adjusted using 3D point cloud information and rotation translation matrix, the problem of inefficient instrument data acquisition in the existing technology is solved, and the independent detection and efficient acquisition of instrument equipment are realized. Adapt to complex environments.

CN119049037APending Publication Date: 2024-11-29STATE GRID INTELLIGENCE TECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411138427.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing substation instrument data acquisition method fails to effectively consider the target angle and position, resulting in incomplete image display or too low resolution, low efficiency, and requires cumbersome early configuration work, which is unable to cope with the movement of electrical instrument equipment.

Method used

Adopt the autonomous visual sniffing recognition method, by obtaining the image data of the dashboard, independently planning the path, adjusting the optimal positioning of the robot and gimbal, realizing the autonomous detection and positioning of the dashboard and using 3D point cloud information and rotational translation The matrix performs pose fitting to ensure the integrity and clarity of the image data.

Benefits of technology

It realizes the active discovery and active collection of electrical instrumentation equipment, reduces the preliminary configuration work, can cope with complex and changeable inspection environments, and improves the collection efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119049037A_ABST
    Figure CN119049037A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of substation data acquisition, and provides an autonomous visual sniffing identification method and system for a substation instrument, and the technical scheme is as follows: obtaining image data of an instrument panel at the position of a current sniffing target; according to the obtained image data of the instrument panel at the position of the current to-be-sniffed target, position information and size information of the instrument panel are obtained through detection, and meanwhile attitude information of the instrument panel is obtained; the optimal poses of the robot and the holder are obtained according to the posture information of the instrument panel; calculating the position of the next to-be-sniffed target of the robot based on the position information of the instrument panel and the optimal pose of the robot; the angle and the focal length of the holder are adjusted according to the size information of the instrument panel and the optimal pose of the holder, and the image data of the instrument panel are acquired based on the adjusted holder, so that the problem that the image display is incomplete or the resolution is too low, so that the image cannot be identified and fails is solved. Image data needs to be collected again, and the efficiency is low.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of substation data collection, and in particular relates to a method and system for autonomous visual sniffing recognition of substation instruments. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Substation instruments are key equipment for controlling the safe operation of power grids and play an important role in ensuring the normal operation of power systems. They can monitor and measure various parameters in the power system, such as voltage, current, power, etc., and transmit these data to the control system to help staff adjust relevant parameters in time to prevent failures. In addition, power meters can also monitor the load of the power grid, detect abnormal conditions in time and report them to relevant personnel to avoid further losses.

[0004] At present, the acquisition of substation instrument data is mostly done by obtaining electrical instrument equipment images through inspection robots, and then distinguishing through image recognition algorithms, automatically identifying the instrument type, and then identifying the reading. This method does not take into account the angle of the target and the position in the field of view when acquiring the electrical instrument equipment image, resulting in incomplete image display or too low resolution, which leads to failure to recognize and invalid, and the image data needs to be collected again, resulting in low efficiency. In addition, the existing sniffing method requires a lot of calibration and configuration work in advance. It is necessary to move the robot to a specific position in advance, manually adjust the pan-tilt to a suitable angle, and capture the electrical instrument equipment at this angle. The work is cumbersome and the workload of configuring all instruments is large. The next time the robot works, it moves to the position according to the recorded position information to take pictures. If the electrical instrument equipment moves, this preset position method will not be actively adjusted, and the collected information will be invalid. Summary of the invention

[0005] In order to solve at least one technical problem existing in the above-mentioned background technology, the present invention provides a method and system for autonomous visual sniffing and identification of substation instruments, which can realize autonomous detection and positioning of designated instrument targets, autonomous image acquisition and information ID identification, etc.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a method for autonomous visual sniffing and identification of substation instruments, comprising the following steps:

[0008] Get the image data of the instrument panel at the current sniffing target location;

[0009] Based on the image data of the instrument panel at the current sniffing target's location, the system autonomously plans the path to reach the locations of the targets to be sniffed in sequence, performs posture fitting and gimbal adjustment at each location, and completes the image information collection of all the locations of the targets to be sniffed, including:

[0010] According to the acquired image data of the dashboard at the current position of the sniffing target, the position information and three-dimensional size information of the dashboard are detected, and the posture information of the dashboard is obtained at the same time;

[0011] According to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information, the optimal posture of the robot is obtained by adjustment;

[0012] Based on the position information of the instrument panel and the optimal position of the robot, the position of the next target to be sniffed by the robot is calculated;

[0013] According to the position information of the dashboard and the optimal posture of the robot, the angle and focal length of the gimbal are adjusted, and the image data of the dashboard is obtained based on the adjusted gimbal.

[0014] As an implementation mode, the method of adjusting and obtaining the best posture of the robot and the gimbal according to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information includes:

[0015] Get the 3D point cloud information within the bounding box of the target to be detected;

[0016] Obtain the corresponding point pairs between the three-dimensional size information and the 3D point cloud information, construct a rotation and translation matrix based on the corresponding point pairs, and use the rotation and translation matrix to transform the 3D point cloud information to the coordinate system of the three-dimensional size information, and estimate the error function between the transformed 3D point cloud information and the 3D size information. If the error function value is greater than the set threshold, iterate the above operation until the given error requirement is met to obtain the optimal posture of the robot and the gimbal.

[0017] As an implementation mode, adjusting the angle and focal length of the gimbal according to the position information of the instrument panel and the optimal posture of the robot includes: recording the posture information of the optimal posture of the gimbal as [x, y, z, roll, yaw, pitch];

[0018] Among them, x, y, and z are the spatial positions of the instrument panel relative to the robot's center coordinate system, and roll, yaw, and pitch are the posture information of the gimbal relative to the robot's center coordinate system;

[0019] According to x, y, and z, the distance information between the instrument panel and the robot is obtained, and the focal length setting is obtained by looking up the table according to the distance information, and the image is captured based on the focal length;

[0020] The angle of the gimbal relative to the robot's center coordinate system is obtained based on roll, yaw, and pitch. The gimbal angle is adjusted based on the angle to ensure that the instrument panel is in the center of the camera's field of view, and images are collected based on the adjusted gimbal.

[0021] As an implementation manner, the target bounding box to be detected is obtained based on target detection using a YOLOv5 model.

[0022] As an embodiment, the method also includes, after acquiring image data of the instrument panel based on the adjusted pan-tilt head, acquiring the ID information of the instrument, and determining the ID attribute of the instrument, wherein the ID information represents the category of the identified meter, including a voltmeter, an ammeter, and an SF6 meter.

[0023] As an implementation method, after obtaining the image data of the dashboard at the location of the current sniffing target, it also includes preprocessing the image data of the dashboard, including using the synchronous pulse emission characteristics of PCNN to detect isolated noise points, and using mathematical morphology operations to filter out the noise points in the image of the dashboard. At the same time, the contrast of the image of the dashboard is enhanced using a timing matrix to obtain a processed target image.

[0024] A second aspect of the present invention provides a substation instrument autonomous visual sniffing identification system, comprising:

[0025] An image acquisition module is configured to acquire image data of a dashboard at a location of a current sniffing target;

[0026] The autonomous visual sniffing recognition module is configured to autonomously plan a path based on the image data of the instrument panel at the current sniffing target's location, arrive at the location of the target to be sniffed in sequence, perform posture fitting and gimbal adjustment at each location, until the image information collection of all the locations of the target to be sniffed is completed, specifically including:

[0027] According to the acquired image data of the dashboard at the current position of the sniffing target, the position information and three-dimensional size information of the dashboard are detected, and the posture information of the dashboard is obtained at the same time;

[0028] According to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information, the optimal posture of the robot is obtained by adjustment;

[0029] Based on the position information of the instrument panel and the optimal position of the robot, the position of the next target to be sniffed by the robot is calculated;

[0030] According to the position information of the dashboard and the optimal posture of the robot, the angle and focal length of the gimbal are adjusted, and the image data of the dashboard is obtained based on the adjusted gimbal.

[0031] A third aspect of the present invention provides a computer-readable storage medium.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned method for autonomous visual sniffing and identification of substation instruments.

[0033] A fourth aspect of the present invention provides a computer device.

[0034] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the above-mentioned method for autonomous visual sniffing and identification of substation instruments are implemented.

[0035] A fifth aspect of the present invention provides a program product, which is a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps in the above-mentioned method for autonomous visual sniffing and identification of substation meters.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention uses autonomous visual sniffing and recognition technology to autonomously plan a path based on the image data of the instrument panel at the position of the current sniffing target, arrives at the positions of the targets to be sniffed in turn, performs posture fitting and pan / tilt adjustment at each position, thereby completing the image information collection of all the positions of the targets to be sniffed, realizing active discovery and active collection of electrical instrument equipment, solving the problem of traditional inspection methods using preset positions, getting rid of tedious and complicated preliminary configuration work, being able to cope with complex and changeable inspection environments, having strong adaptability and simple configuration.

[0038] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0040] Figure 1 This is a flow chart of a method for autonomous visual sniffing and identification of substation instruments provided by an embodiment of the present invention;

[0041] Figure 2 This is an analysis diagram of the visual sniffing technology provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0044] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0045] At present, the acquisition of substation instrument data is mostly done by obtaining electrical instrument equipment images through inspection robots, and then distinguishing through image recognition algorithms, automatically identifying the instrument type, and then identifying the readings. This method does not take into account the angle of the target and the position in the field of view when acquiring the electrical instrument equipment image, resulting in incomplete image display or too low resolution, which leads to failure to recognize and the need to collect image data again, resulting in low efficiency. In addition, the existing sniffing method requires a lot of calibration and configuration work in advance. It is necessary to move the robot to a specific position in advance, manually adjust the pan-tilt to a suitable angle, and capture the electrical instrument equipment at this angle. The work is cumbersome and the workload of configuring all instruments is large. The next time the robot works, it moves to the position according to the recorded position information to take pictures. If the electrical instrument equipment moves, this preset position method will not be actively adjusted, and the collected information will be invalid.

[0046] The present invention provides an autonomous visual sniffing and identification method for substation instruments. Through the autonomous visual sniffing and identification technology, active discovery and active collection of electrical instrument equipment are realized, which solves the problem of traditional inspection method using preset positions, gets rid of the tedious and complicated preliminary configuration work, can cope with complex and changeable inspection environments, has strong adaptability and simple configuration.

[0047] Embodiment 1

[0048] like Figure 1 As shown, this embodiment provides a substation instrument autonomous visual sniffing identification method, including the following steps:

[0049] Step 1: Obtain the image data of the dashboard at the current sniffing target location;

[0050] Step 2: Preprocess the image data of the instrument panel to obtain preprocessed image data;

[0051] Step 3: Based on the image data of the instrument panel at the current sniffing target's location, the path is autonomously planned to reach the locations of the targets to be sniffed in sequence, and posture fitting and gimbal adjustment are performed at each location until the image information collection of all the locations of the targets to be sniffed is completed;

[0052] Step 4: Obtain the ID information and ID attributes of the instrument based on the collected image information.

[0053] The present invention can automatically identify dashboard targets, automatically adjust the target angle and position in the field of view when acquiring images of electrical instrument equipment, automatically complete data collection, and extract information to solve the problem of incomplete image display or too low resolution resulting in recognition failure, requiring image data to be collected again, resulting in low efficiency.

[0054] Mines and tunnels are typical application scenarios for visual sniffing. Attached to a quadruped robot, without configuration information, autonomous sniffing technology can achieve autonomous detection and positioning of designated targets (such as instruments), autonomous image acquisition, and information ID recognition.

[0055] This embodiment uses a circular dial as a typical sniffing target, and the task objective is to achieve the extraction of a clear dial image.

[0056] The logic and technology modules implemented in typical application scenarios of visual sniffing technology are as follows: Figure 1 As shown. It includes target detection technology, autonomous path planning technology, posture fitting technology and pan-tilt control technology. In an unknown environment, the target detection technology obtains the position of the sniffing target, and the quadruped robot autonomously plans the path according to the position, and arrives at the sniffing positions A, B, and C in turn, performs posture fitting and pan-tilt adjustment, until the image information of the sniffing target is collected, the sniffing state is jumped out, and the patrol is continued.

[0057] In step 2, the image data of the dashboard is preprocessed, specifically including:

[0058] The target image of the instrument panel is obtained, the synchronous pulse emission characteristics of PCNN are used to detect isolated noise points, and the noise points in the image of the instrument panel are filtered out using mathematical morphology operations. At the same time, the contrast of the image of the instrument panel is enhanced using a timing matrix to obtain a processed target image.

[0059] like Figure 2 As shown, in step 2, based on the image data of the instrument panel at the current sniffing target position, the path is autonomously planned to reach the positions of the targets to be sniffed in sequence, and posture fitting and gimbal adjustment are performed at each position until the image information collection of all the positions of the targets to be sniffed is completed, which specifically includes the following steps:

[0060] Step 201: Sniffing target identification

[0061] According to the acquired image data of the dashboard at the current position of the sniffing target, the position information and size information of the dashboard are detected;

[0062] In this embodiment, the image data of the dashboard at the current position of the target to be sniffed is obtained, and the position information and three-dimensional size information of the dashboard are detected, specifically including:

[0063] Detect and segment objects based on 2D images to obtain pixel coordinates and estimate their approximate posture.

[0064] In this embodiment, the YOLOv5 model is selected for target detection, and the object to be identified is represented in the form of a rectangular bounding box.

[0065] Step 202: Sniffing target pose estimation

[0066] Acquire the attitude information of the instrument panel. In this embodiment, the attitude information of the instrument panel is the direction of the instrument panel. The optimal posture of the robot and the gimbal can be obtained according to the attitude information of the instrument panel.

[0067] In this embodiment, obtaining the optimal posture of the robot and the gimbal according to the posture information of the instrument panel includes:

[0068] Obtain the 3D dimension information of the marked instrument equipment according to the 3D drawing, and obtain the 3D point cloud information within the rectangular bounding box according to the above-mentioned rectangular bounding box;

[0069] The ICP (Iterative Closest Point) method is used to obtain the corresponding point pairs between the 3D size information and the 3D point cloud information. A rotation and translation matrix is ​​constructed based on the corresponding point pairs. The 3D point cloud information is transformed into the coordinate system of the 3D size information using the obtained matrix. The error function between the transformed 3D point cloud information and the 3D size information is estimated. If the error function value is greater than the threshold, the above operation is iterated until the given error requirement is met to obtain the optimal position and posture of the robot and the gimbal.

[0070] Step 203: Autonomous Path Planning and Robot Control

[0071] Based on the position information of the instrument panel and the optimal posture of the robot, the position of the next target to be sniffed by the robot is calculated, for example, the detection points A, B, and C are obtained, and the robot is controlled to reach positions A, B, and C to continue the sniffing function.

[0072] Step 204: PTZ Control

[0073] According to the size information of the instrument panel and the optimal position of the gimbal, adjust the angle and focal length of the gimbal. According to the target posture estimation in step 202, the posture information of the instrument panel is known, which is [x, y, z, roll, yaw, pitch] at this time, where xyz is the spatial position relative to the robot center coordinate system, and roll yaw pitch is the posture information relative to the robot center coordinate system. According to xyz, the distance information of the instrument panel from the robot is obtained, and the focal length setting is obtained by looking up the table according to the distance information to obtain a clear image. According to the roll yaw pitch, adjust the angle of the gimbal to ensure that the instrument panel is in the center of the camera field of view and obtain an accurate image.

[0074] Step 3: Get the ID information of the instrument and determine the ID attribute of the instrument.

[0075] In this embodiment, high-definition instrument panel information is collected, and the ID information of the instrument is obtained based on the high-definition image information. The ID information indicates the type of the identified meter, whether it is a voltmeter, an ammeter or an SF6 meter. At the same time, the existing table calculation reading model is applied to read the reading, and the final result is eg: ammeter: 15a.

[0076] Through the above solution, active discovery and collection of electrical instrument equipment are realized, which solves the traditional inspection method of using preset positions and gets rid of the tedious and complicated preliminary configuration work. It can cope with complex and changeable inspection environments, has strong adaptability and simple configuration.

[0077] Embodiment 2

[0078] This embodiment provides a substation instrument autonomous visual sniffing recognition system, including:

[0079] An image acquisition module is configured to acquire image data of a dashboard at a location of a current sniffing target;

[0080] The autonomous visual sniffing recognition module is configured to autonomously plan a path based on the image data of the instrument panel at the current sniffing target's location, arrive at the location of the target to be sniffed in sequence, perform posture fitting and gimbal adjustment at each location, until the image information collection of all the locations of the target to be sniffed is completed, specifically including:

[0081] According to the acquired image data of the dashboard at the current position of the sniffing target, the position information and three-dimensional size information of the dashboard are detected, and the posture information of the dashboard is obtained at the same time;

[0082] According to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information, the optimal posture of the robot is obtained by adjustment;

[0083] Based on the position information of the instrument panel and the optimal position of the robot, the position of the next target to be sniffed by the robot is calculated;

[0084] According to the position information of the dashboard and the optimal posture of the robot, the angle and focal length of the gimbal are adjusted, and the image data of the dashboard is obtained based on the adjusted gimbal.

[0085] Embodiment 3

[0086] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the above-mentioned method for autonomous visual sniffing and identification of substation meters are implemented.

[0087] Embodiment 4

[0088] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the above-described method for autonomous visual sniffing and identification of substation instruments are implemented.

[0089] Embodiment 5

[0090] This embodiment provides a program product, which is a computer program product, including a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method for autonomous visual sniffing and identification of substation meters are implemented.

[0091] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0092] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] Those skilled in the art can 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, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0096] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An autonomous visual sniffing and identification method for substation instruments. It is characterized in that The steps include: Get the image data of the instrument panel at the current sniffing target location; Based on the image data of the instrument panel at the current sniffing target's location, the system autonomously plans the path to reach the locations of the targets to be sniffed in sequence, performs posture fitting and gimbal adjustment at each location, and completes the image information collection of all the locations of the targets to be sniffed, including: According to the acquired image data of the dashboard at the current position of the sniffing target, the position information and three-dimensional size information of the dashboard are detected, and the posture information of the dashboard is obtained at the same time; According to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information, the optimal posture of the robot is obtained by adjustment; Based on the position information of the instrument panel and the optimal position of the robot, the position of the next target to be sniffed by the robot is calculated; According to the position information of the dashboard and the optimal posture of the robot, the angle and focal length of the gimbal are adjusted, and the image data of the dashboard is obtained based on the adjusted gimbal.

2. A substation instrument autonomous visual sniffing identification method as claimed in claim 1, It is characterized in that The method of adjusting and obtaining the best posture of the robot and the gimbal according to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information includes: Get the 3D point cloud information within the bounding box of the target to be detected; Obtain the corresponding point pairs between the three-dimensional size information and the 3D point cloud information, construct a rotation and translation matrix based on the corresponding point pairs, and use the rotation and translation matrix to transform the 3D point cloud information to the coordinate system of the three-dimensional size information, and estimate the error function between the transformed 3D point cloud information and the 3D size information. If the error function value is greater than the set threshold, iterate the above operation until the given error requirement is met to obtain the optimal posture of the robot and the gimbal.

3. A substation instrument autonomous visual sniffing identification method as claimed in claim 1, It is characterized in that The adjusting the angle and focal length of the gimbal according to the position information of the instrument panel and the optimal posture of the robot includes: recording the posture information of the optimal posture of the gimbal as [x, y, z, roll, yaw, pitch]; Among them, x, y, and z are the spatial positions of the instrument panel relative to the robot's center coordinate system, and roll, yaw, and pitch are the posture information of the gimbal relative to the robot's center coordinate system; According to x, y, and z, the distance information between the instrument panel and the robot is obtained, and the focal length setting is obtained by looking up the table according to the distance information, and the image is captured based on the focal length; The angle of the gimbal relative to the robot's center coordinate system is obtained based on roll, yaw, and pitch. The gimbal angle is adjusted based on the angle to ensure that the instrument panel is in the center of the camera's field of view, and images are collected based on the adjusted gimbal.

4. A substation instrument autonomous visual sniffing identification method as claimed in claim 2, It is characterized in that The target bounding box to be detected is obtained based on target detection using the YOLOv5 model.

5. A substation instrument autonomous visual sniffing identification method as claimed in claim 1, It is characterized in that The method also includes obtaining the ID information of the instrument after obtaining the image data of the instrument panel based on the adjusted pan-tilt head, and determining the ID attribute of the instrument, wherein the ID information is represented as the category of the identified meter, including a voltmeter, an ammeter and an SF6 meter.

6. A substation instrument autonomous visual sniffing identification method as claimed in claim 1, It is characterized in that After obtaining the image data of the dashboard at the location of the current sniffing target, the image data of the dashboard is also preprocessed, including using the synchronous pulse emission characteristics of PCNN to detect isolated noise points, and using mathematical morphology operations to filter out the noise points in the dashboard image. At the same time, the contrast of the dashboard image is enhanced using a timing matrix to obtain a processed target image.

7. An autonomous visual sniffing and recognition system for substation instruments, It is characterized in that include: An image acquisition module is configured to acquire image data of a dashboard at a location of a current sniffing target; The autonomous visual sniffing recognition module is configured to autonomously plan a path based on the image data of the instrument panel at the current sniffing target's location, arrive at the location of the target to be sniffed in sequence, perform posture fitting and gimbal adjustment at each location, until the image information collection of all the locations of the target to be sniffed is completed, specifically including: According to the acquired image data of the dashboard at the current position of the sniffing target, the position information and three-dimensional size information of the dashboard are detected, and the posture information of the dashboard is obtained at the same time; According to the three-dimensional size information of the instrument panel and the corresponding 3D point cloud information, the optimal posture of the robot is obtained by adjustment; Based on the position information of the instrument panel and the optimal position of the robot, the position of the next target to be sniffed by the robot is calculated; According to the position information of the dashboard and the optimal posture of the robot, the angle and focal length of the gimbal are adjusted, and the image data of the dashboard is obtained based on the adjusted gimbal.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the steps in the autonomous visual sniffing identification method for substation meters as described in any one of claims 1 to 6 are implemented.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the steps in the autonomous visual sniffing and identification method for substation meters as described in any one of claims 1-6 are implemented.

10. A program product, the program product being a computer program product, comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method for autonomous visual sniffing and identification of substation meters as described in any one of claims 1 to 6 are implemented.