Power cabinet button operation method, device, electronic device and readable storage medium

Abstract

The present invention provides a method, device, electronic device and readable storage medium for operating buttons of an electric cabinet, which relate to the field of electric robot technology. By collecting images in the operation panel area and performing data processing on the collected image information, the positional relationship information between the operating device and each button is obtained. Then, based on the positional relationship information, the operating device is controlled to generate a displacement that matches the controlled button in the control instruction, so as to realize orderly operation of the buttons. The method has the advantages of high accuracy and high speed that the existing button operation methods do not have.

Description

Technical Field

[0001] The present application relates to the technical field of electric robots, and in particular to a method and device for operating buttons of an electric cabinet, an electronic device, and a readable storage medium. Background Art

[0002] As a critical component of the power grid, the safe and stable operation of substations is of paramount importance. Substation switchrooms involve identifying and operating power equipment status. Current identification and operation methods mostly rely on manual judgment and operation, which poses significant safety risks.

[0003] With the advancement of robotic automation technology, operating robots have begun to enter power station switch rooms to replace workers in performing various tasks, thereby reducing workers' labor intensity and reducing the risks of manual operation. However, the existing power cabinet operation panels are complex and diverse, and the buttons are of different sizes and shapes. As a result, it is difficult for existing robots to accurately identify the position of the buttons on the power cabinet operation panel and correctly perform the corresponding button operations. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to overcome the problem that existing robots find it difficult to accurately identify the button positions on the power cabinet operation panel and correctly perform corresponding button operations, and provide a power cabinet button operation method, device, electronic device and readable storage medium.

[0005] In order to achieve the above-mentioned purpose, the present invention provides a method for operating buttons of an electric cabinet, which is applied to an electric robot, wherein the electric robot includes an operating device, and the method includes: moving to the front of a designated cabinet according to a navigation path; adjusting the operating device to a set posture state; collecting an image of an operating panel of the cabinet, wherein the operating panel is provided with multiple buttons; performing data processing on the collected image information to obtain positional relationship information between the operating device and each button; and controlling the operating device to perform corresponding operations on the buttons according to the positional relationship information.

[0006] Optionally, data processing of the collected image information to obtain positional relationship information between the operating device and each of the buttons includes the following steps: feature matching of the operating panel image with a preset template to obtain feature matching information; calculating the center position information of the operating panel image based on the feature matching information; dividing the operating panel image into area images matching the preset template based on the center position information; position matching of the area image with the preset template and the operating panel image to obtain button position information; and obtaining positional relationship information between the operating device and each of the buttons based on the button position information.

[0007] Optionally, calculating the center position information of the operation panel image based on feature matching information includes the following steps: calculating the average coordinates of points on the preset template that match the operation panel image to obtain a first set point; obtaining a second set point based on the first set point, wherein the second set point is obtained by homographically transforming the first set point to a corresponding point in the operation panel image; and obtaining the center position information based on the second set point and a fixed distance parameter value. Optionally, performing feature matching between the operation panel image and the preset template to obtain feature matching information also includes the following steps: calculating the minimum distance parameter for feature descriptors of matched point pairs; and performing angle and distance screening on feature point pairs by adjusting the distance parameter until the number of screened point pairs is greater than a first set value and the proportion of identical point pairs is less than a second set value, wherein the distance parameter is an integer multiple of the minimum distance parameter.

[0008] Optionally, the angle screening includes the following steps: calculating the slope between the pixel coordinates of the matched point pairs; obtaining a characteristic slope value, which is the slope value with the most identical slopes; and performing angle screening by filtering out feature point pairs outside the slope range, where the slope range is the slope value ± a preset slope threshold.

[0009] Optionally, the distance screening includes the following steps: calculating the pixel distance of the feature point pairs after angle screening; obtaining the feature pixel distance, which is the distance value with the largest number of identical pixel distances; and performing distance screening by filtering out the feature point pairs outside the pixel distance range, where the pixel distance range is the feature pixel distance ± a preset pixel distance threshold.

[0010] Optionally, after controlling the operating device to perform corresponding operations on the keys according to the position relationship information, the following steps are also included: returning the recognition result and the operation result image; controlling the operating device to return to the initial position; and returning to the starting point according to the navigation path.

[0011] Correspondingly, the present invention also provides a power cabinet button operation device, comprising the following modules: a navigation module, the navigation module is configured to move to the front of a designated cabinet according to a navigation path; an adjustment module, the adjustment device is configured to adjust the operating device to a set posture state; an acquisition module, the acquisition module is configured to acquire an image of an operating panel, and the operating panel is provided with multiple buttons; a data processing module, the data processing module is configured to perform data processing on the acquired image information to obtain positional relationship information between the operating device and each of the buttons; an operation module, the operation module is configured to control the operating device to perform corresponding operations on the buttons according to the positional relationship information.

[0012] Accordingly, the present invention provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the power cabinet key operation method.

[0013] Accordingly, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the power cabinet key operation method.

[0014] Beneficial effects of the present invention:

[0015] The power cabinet button operation method, device, electronic device and readable storage medium of the embodiments of the present invention collect images in the operation panel area and perform data processing on the collected image information to obtain positional relationship information between the operating device and each button. The operating device is then controlled to generate a displacement that matches the controlled button in the control instruction based on the positional relationship information to achieve orderly operation of the buttons. The method and device have the advantages of high accuracy and high speed that existing button operation methods do not have. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments of the present application.

[0017] Figure 1 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention;

[0018] Figure 2 A schematic structural diagram of a robot provided in one embodiment of the present invention;

[0019] Figure 3 A schematic structural diagram of a power cabinet provided in one embodiment of the present invention;

[0020] Figure 4 A schematic diagram of a flow chart of a method for operating a power cabinet key according to an embodiment of the present invention;

[0021] Figure 5 A schematic diagram of a process for processing collected image information according to an embodiment of the present invention;

[0022] Figure 6 A schematic diagram of a process for filtering feature matching information provided by an embodiment of the present invention;

[0023] Figure 7 This is a device block diagram of a key operation device for a power cabinet provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0025] Similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0026] Please refer to Figure 1 , which is a schematic diagram of the structure of an electronic device 100 provided in one embodiment of the present invention. The electronic device 100 includes: one or more processors 120 and one or more memories 104 storing instructions executable by the processors 120. The processors 120 are configured to execute the power cabinet key operation method provided in the following embodiments of this application.

[0027] The processor 120 can be a gateway, a smart terminal, or a device including a central processing unit (CPU), a graphics processing unit (GPU), or other forms of processing units with data processing capabilities and / or instruction execution capabilities. It can process data from other components in the electronic device 100 and control other components in the electronic device 100 to perform desired functions.

[0028] The memory 104 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 120 may execute the program instructions to implement the power cabinet key operation method described below. Various applications and various data may also be stored in the computer-readable storage medium, such as various data used and / or generated by the application.

[0029] In one embodiment, Figure 1 The electronic device 100 may further include an input device 106, an output device 108, and a data acquisition device 110, which are interconnected via a bus system 112 and / or other forms of connection mechanisms (not shown). Figure 1 The components and structures of the electronic device 100 shown are merely exemplary and non-limiting. The electronic device 100 may also have other components and structures as needed.

[0030] The input device 106 can be a device used by a user to input instructions, and can include one or more of a keyboard, a mouse, a microphone, and a touch screen. The output device 108 can output various information (e.g., images or sounds) to the outside (e.g., a user), and can include one or more of a display, a speaker, etc. The data acquisition device 110 can capture images of an object and store the captured images in the memory 104 for use by other components. For example, the data acquisition device 110 can be a camera.

[0031] In one embodiment, the various components in the example electronic device 100 for implementing the power cabinet key operation method of an embodiment of the present invention can be integrated or dispersed, such as integrating the processor 120, memory 104, input device 106 and output device 108 into one, while separating the data acquisition device 110.

[0032] In one embodiment, the electronic device 100 used to implement the power cabinet key operation method of the embodiment of the present invention may be a robot 1 equipped with an operating device 11 and an image acquisition device 12. Figure 2 、 Figure 3 The image acquisition device 12 may be a camera with a video or photo recording function, such as an RGBD depth camera. The operating device 11 may be an end-point key operation tool connected to the robotic arm 13. By adjusting the robotic arm 13 to change the position of the end-point key operation tool, the corresponding operation of the button 22 on the operation panel 21 of the cabinet 2 can be completed.

[0033] Please refer to Figure 4 , is a flow chart of a method for operating a power cabinet key according to an embodiment of the present invention, as shown in FIG. Figure 4 As shown, the method can be executed by the robot 1, including the following steps S310 to S340.

[0034] Step S310: Move to the designated cabinet according to the navigation path.

[0035] Specifically, an indoor map of the switchroom and navigation points for each power cabinet 2 are pre-established. When executing a task, the robot 1 receives a command to move to a specific power cabinet and follows the navigation path generated by the command to move to the designated power cabinet where the operation is to be performed. The command to move to the designated power cabinet may be issued by a staff member via a remote control. In other embodiments, the command to move to the designated power cabinet may be pre-set and transmitted to a host computer, from which the robot 1 directly receives the command.

[0036] Step S320: Adjust the operating device to a set posture state.

[0037] When the posture state is set such that the robot 1 can manipulate the entire operation panel 2 , the image acquisition device 12 acquires the image of the operation panel of the cabinet 2 and the optimal posture state of the operation device 11 for operating the buttons.

[0038] For example, the robotic arm 13 can be controlled to move to a preset position so that the image acquisition device 12 on the robotic arm 13 collects image information of the first specified object in the first area, and the image information is processed to obtain the posture information of the robot body, the end operation device 11 and the power cabinet 2 respectively. According to the posture information, the robot body and the operation device 11 are adjusted to the optimal posture state so that the image of the operation panel area can be more accurately captured, thereby more accurately obtaining the position relationship information of the operation device 11 and each button 22.

[0039] The first designated object is a QR code located on the power cabinet, and the first area is the area where the QR code is located. Data processing of the captured QR code image and adjustment of the operating device 11 to the set posture state based on the data processing results adopt existing technology, and its principles and algorithms are not further described here.

[0040] In one embodiment, before adjusting the operating device 11 to the set posture state, the cabinet interval name of the power cabinet is identified to confirm whether the current cabinet is consistent with the cabinet to be operated under the current task, so as to determine whether the current task can continue to be executed.

[0041] For example, OCR optical character recognition technology can be used to identify the cabinet compartment name. If the recognition result is consistent with the cabinet compartment name under the current task, the subsequent steps will continue to be executed. Otherwise, the task will be terminated and reported to the background system.

[0042] Step S330: Acquire an image of the operation panel of the cabinet, where a plurality of buttons are provided on the operation panel.

[0043] For example, the robotic arm 13 can be controlled to move to a preset position, so that the image acquisition device 12 on the robotic arm 13 can capture image information of a second designated object within a second area. The second designated object is an operation panel 21 provided on the power cabinet, and the second area is the area where the operation panel 21 is located.

[0044] Step S340: performing data processing on the collected image information to obtain positional relationship information between the operating device and each of the buttons.

[0045] The specific steps of performing data processing on the collected image information to obtain the positional relationship information between the operating device 11 and each button 22 will be described in detail below.

[0046] Step S350: controlling the operating device to perform corresponding operations on the keys according to the position relationship information.

[0047] For example, after obtaining the positional relationship information between the operating device 11 and each button 22, the robot 1 receives a control instruction for orderly operation of the corresponding button 22 located on the operating panel 21, and controls the operating device 11 to generate a displacement matching the controlled button in the control instruction according to the positional relationship information, so as to realize orderly operation of the button 22.

[0048] For another example, after receiving the control instruction and controlling the operating device to perform corresponding operations on the buttons according to the position relationship information, the following steps are also included: returning the recognition result and the operation result image; controlling the operating device 11 to return to the initial position; and the robot 1 returns to the starting point according to the navigation path.

[0049] The above-described power cabinet key operation method, when applied to a robot 1, uses image acquisition device 12 to capture images of the operating panel area and performs data processing on the captured image information to obtain positional relationship information between operating device 12 and each key 22. Based on this positional relationship information, operating device 11 is then controlled to generate a displacement that matches the controlled key in the control instruction, thereby achieving orderly operation of the keys. The power cabinet key operation method provided in this embodiment of the present invention enables robot 1 to accurately identify the position of the keys on the power cabinet operating panel 21 and correctly execute the corresponding key operations.

[0050] When acquiring the positional relationship information between the operating device 11 and each button 22 , an embodiment of the present invention further provides a method for processing the collected image information.

[0051] Please refer to Figure 5 , which is a flow chart of data processing of collected image information in one embodiment of the present invention, including the following steps S3410 to S3450.

[0052] Step S3410: performing feature matching on the operation panel image and a preset template to obtain feature matching information.

[0053] For example, a feature point algorithm is used to extract feature points and feature point descriptors from the image in the preset template and the captured operation panel image. The extracted feature points and feature point descriptors are then matched to obtain matching point pairs. The feature point algorithm uses the SURF feature point algorithm, which has the advantages of high accuracy and fast processing speed.

[0054] In addition, in order to reduce interference from non-key areas in the operation panel, the image in the preset template only includes image information of the key area of the operation panel.

[0055] Step S3420: Calculate the center position information of the operation panel image based on the feature matching information.

[0056] For example, the center position information of the operation panel image can be calculated by the following steps:

[0057] A first set point is obtained by calculating the average coordinates of points on a preset template that match the operation panel image; a second set point is obtained based on the first set point, where the second set point is obtained by performing a homographic transformation on the first set point to convert it to a corresponding point in the operation panel image; and the center position information is obtained based on the second set point and a fixed distance parameter value, where the fixed distance parameter value is the pixel distance from the set point to the center point of the image.

[0058] Step S3430: Segment the operation panel image into regional images matching the preset template according to the center position information.

[0059] For example, the operation panel image to be identified is first padded on all sides, where the width and height of the padded edges are the width and height of the image in the preset template respectively, and then an area of the same size as the image in the preset template is cut out with the center position information of the operation panel image calculated based on the feature matching information as the center.

[0060] Step S3440: performing position matching on the area image, the preset template, and the operation panel image to obtain button position information.

[0061] The coordinate information of each button center point in the preset template is mapped to the regional image using the mapping relationship between the regional image and the preset template, obtaining the two-dimensional coordinates of each button center point in the regional image. Based on the corresponding relationship between the regional image and the operation panel image, the two-dimensional coordinates of each button center point in the regional image are then converted to the operation panel image to obtain the two-dimensional coordinates of each button center point in the operation panel image to be identified. Finally, the depth information corresponding to each button corresponding to these two-dimensional coordinates is obtained using the depth camera, and the position information of each button in the current depth camera coordinate system is calculated, i.e., the button position information.

[0062] Specifically, when the depth information of each button corresponding to the two-dimensional coordinate is obtained by the depth camera and the position of each button in the current depth camera coordinate system is calculated, the specific steps include: using the depth camera to measure the depth d corresponding to each button, and mapping the point of the image space coordinate system to the depth camera coordinate system according to the calibrated depth camera intrinsic parameter K, by the calculation formula:

[0063] X=(x-cx)·fx·d, Y=(y-cy)·fy·d, Z=d;

[0064] Calculate the position information of each button in the current depth camera coordinate system, where the point in the image coordinate system is (x, y), the point in the depth camera coordinate system is (X, Y, Z), fx, fy, cx, and cy are the four parameters in the depth camera intrinsic parameter matrix, which have been determined when the depth camera leaves the factory.

[0065] Step S3450: Obtaining positional relationship information between the operating device and each of the buttons according to the button position information.

[0066] After obtaining the position information of each button, that is, the position information of each button in the current depth camera coordinate system, the directional distance required for the end-user operating device to operate the button can be located based on the calibrated external parameters, that is, the positional relationship information between the operating device and each button. The external parameters refer to the spatial distance between the depth camera and the end-user tool.

[0067] In one embodiment of the present invention, in a method for performing data processing on collected image information to obtain button position information, the center position information of the operation panel image is calculated by performing feature matching between the operation panel image and a preset template to obtain feature matching information; then, based on the center position information, the operation panel image is divided into area images that match the preset template; then, the area image is position-matched with the preset template and the operation panel image to obtain button position information; finally, based on the button position information, the position relationship information between the operating device and each button is obtained. This series of processing steps obtains accurate button position information, so that the robot can perform button operations accurately.

[0068] In one embodiment, in order to more accurately obtain the positional relationship information between the operating device and each button, the step of performing feature matching between the operating panel image and the preset template to obtain feature matching information also includes a step of filtering the feature matching information.

[0069] Please refer to Figure 6 , is a flow chart of filtering feature matching information, specifically including steps S34110 to S34120:

[0070] Step S34110: Calculate the minimum distance parameter between the matched points and the feature descriptor.

[0071] In order to filter the matching results, the minimum distance D between the points in the matching results and the descriptors is first calculated.

[0072] Step S34120: Perform angle screening and distance screening on feature point pairs by adjusting the distance parameter until the number of point pairs screened out is greater than the first set value and the proportion of similar point pairs is less than the second set value, and the distance parameter is an integer multiple of the minimum distance parameter.

[0073] Exemplarily, the angle screening and distance screening of point pairs are first performed within the range of twice the minimum distance D. If the number of point pairs finally screened out is less than the first set value L1 or the proportion of identical point pairs exceeds the second set value L2, the angle screening and distance screening of point pairs are increased by a multiple of D until the number of point pairs finally screened out is greater than the first set value L1 and the proportion of identical point pairs is less than the second set value L2.

[0074] According to experimental results, when the first setting value L1 is 10 and the second setting value L2 is 30%, the feature matching information obtained after final filtering can more accurately obtain the positional relationship information between the operating device and each button.

[0075] Exemplarily, when performing angle screening, first calculate the slope between the pixel coordinates of the matched point pairs; obtain the slope value with the most identical slopes, which is the characteristic slope value k; filter out the point pairs outside the range of k±K according to the preset slope threshold K; finally, determine whether the number of remaining point pairs is greater than the first set value L1 and whether the proportion of identical point pairs is less than the second set value L2; if the conditions are not met, choose to increase the multiple of D to perform angle screening of the point pairs until the number of filtered point pairs is greater than the first set value L1 and the proportion of identical point pairs is less than the second set value L2.

[0076] Exemplarily, when performing distance screening, first calculate the pixel distance of the feature point pairs after angle screening; obtain the distance value with the largest number of identical pixel distances as the feature pixel distance dis; filter the matching point pairs according to the preset pixel distance threshold thresholdDis, filter out the point pairs outside the range of dis±thresholdDis, and finally determine whether the number of remaining point pairs is greater than L1 and whether the proportion of similar points is less than L2. If the conditions are not met, choose to increase the multiple of D and re-perform angle and distance screening until the number of screened point pairs is greater than L1 pairs and the proportion of similar point pairs is less than L2.

[0077] By adjusting the distance parameters to perform angle screening and distance screening on the feature point pairs, until the number of resulting screened point pairs is greater than the first set value and the proportion of identical point pairs is less than the second set value, this series of steps enables more accurate acquisition of the positional relationship information between the operating device and each button based on the feature matching information, ultimately achieving more precise control of the operating device to perform button operations.

[0078] Please refer to Figure 7 , which is a structural diagram of a power cabinet key operation device provided by an embodiment of the present invention, the device includes a navigation module 500, an adjustment module 600, a collection module 700, a data processing module 800 and an operation module 900.

[0079] The navigation module 500 is configured to move to the front of a designated cabinet according to the navigation path.

[0080] The adjustment module 600 is configured to adjust the operating device to a set posture state.

[0081] The acquisition module 700 is configured to acquire an image of an operation panel, where a plurality of buttons are provided.

[0082] The data processing module 800 is configured to perform data processing on the collected image information to obtain position relationship information between the operating device and each key.

[0083] The operating module 900 is configured to receive a control instruction and control the operating device to perform corresponding operations on the keys according to the position relationship information.

[0084] The implementation process of the functions and effects of each module in the above device is specifically described in the implementation process of the corresponding steps in the above power cabinet key operation method, which will not be repeated here.

[0085] In several embodiments provided in this application, the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, may be implemented using a dedicated hardware-based system that performs the specified functions or actions, or may be implemented using a combination of dedicated hardware and computer instructions.

[0086] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0087] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A method for operating a power cabinet key, characterized in that: Applied to an electric robot, the electric robot includes an operating device, and the method includes: Move to the designated cabinet according to the navigation path; Adjusting the operating device to a set posture state; Acquiring an image of an operation panel of the cabinet, where a plurality of buttons are provided on the operation panel; Performing data processing on the collected image information to obtain positional relationship information between the operating device and each of the buttons; controlling the operating device to perform corresponding operations on the button according to the position relationship information; The step of processing the collected image information to obtain positional relationship information between the operating device and each of the buttons includes the following steps: Performing feature matching between the operation panel image and a preset template to obtain feature matching information; Calculating the center position information of the operation panel image according to the feature matching information; Segmenting the operation panel image into regional images matching the preset template according to the center position information; Performing position matching of the area image, the preset template, and the operation panel image to obtain button position information; Obtaining positional relationship information between the operating device and each of the buttons according to the button position information; The step of performing position matching between the region image, the preset template, and the operation panel image to obtain the button position information includes: Mapping the coordinate information of the center point of each button in the preset template to the regional image through the mapping relationship between the regional image and the preset template, to obtain the two-dimensional coordinates of the center point of each button in the regional image; According to the correspondence between the region image and the operation panel image, the two-dimensional coordinates of the center point of each key in the region image are converted into the operation panel image to obtain the two-dimensional coordinates of the center point of each key in the operation panel image to be identified; Acquire the depth information of each button corresponding to the two-dimensional coordinates of the center point of each button in the image of the operation panel to be identified through the depth camera, and calculate the position information of each button in the current depth camera coordinate system, that is, the button position information; The step of calculating the center position information of the operation panel image based on the feature matching information includes the following steps: Calculating the average coordinates of points on the preset template that match the operation panel image to obtain a first set point; Obtaining a second set point according to the first set point, wherein the second set point is obtained by performing a homographic transformation on the first set point to a corresponding point in the operation panel image; The center position information is obtained according to the second set point and a fixed distance parameter value.

2. The power cabinet key operation method according to claim 1, characterized in that: The feature matching of the operation panel image with the preset template to obtain feature matching information further comprises the following steps: Calculate the minimum distance parameter between the matched points and the feature descriptor; The characteristic point pairs are screened by angle and distance by adjusting the distance parameter until the number of screened point pairs is greater than the first set value and the proportion of similar point pairs is less than the second set value, and the distance parameter is an integer multiple of the minimum distance parameter.

3. The power cabinet key operation method according to claim 2, characterized in that: The angle screening comprises the following steps: Calculate the slope between the pixel coordinates of the matched point pairs; Obtaining a characteristic slope value, wherein the characteristic slope value is a slope value having the most identical slopes; Angle screening is performed by filtering out feature point pairs outside a slope range, where the slope range is the slope value ± a preset slope threshold.

4. The power cabinet key operation method according to claim 2, characterized in that: The distance screening comprises the following steps: Calculate the pixel distance of feature point pairs after angle filtering; Obtaining a characteristic pixel distance, wherein the characteristic pixel distance is a distance value having the largest number of identical pixel distances; Distance screening is performed by filtering out feature point pairs outside a pixel distance range, where the pixel distance range is the feature pixel distance ± a preset pixel distance threshold.

5. The power cabinet key operation method according to claim 1, characterized in that: After controlling the operating device to perform corresponding operations on the keys according to the position relationship information, the following steps are also included: returning the recognition result and the operation result image; controlling the operating device to return to the initial position; and returning to the starting point according to the navigation path.

6. A key operation device for a power cabinet, characterized in that: Includes the following modules: A navigation module, wherein the navigation module is configured to move to the front of a designated cabinet according to a navigation path; an adjustment module, wherein the adjustment module is configured to adjust the operating device to a set posture state; An acquisition module configured to acquire an image of an operation panel, wherein the operation panel is provided with a plurality of buttons; a data processing module, the data processing module being configured to perform data processing on the collected image information to obtain positional relationship information between the operating device and each of the buttons; an operating module, the operating module being configured to control the operating device to perform corresponding operations on the keys according to the position relationship information; The step of processing the collected image information to obtain positional relationship information between the operating device and each of the buttons includes the following steps: Performing feature matching between the operation panel image and a preset template to obtain feature matching information; Calculating the center position information of the operation panel image according to the feature matching information; Segmenting the operation panel image into regional images matching the preset template according to the center position information; Performing position matching of the area image, the preset template, and the operation panel image to obtain button position information; Obtaining positional relationship information between the operating device and each of the buttons according to the button position information; The step of performing position matching between the region image, the preset template, and the operation panel image to obtain the button position information includes: Mapping the coordinate information of the center point of each button in the preset template to the regional image through the mapping relationship between the regional image and the preset template, to obtain the two-dimensional coordinates of the center point of each button in the regional image; According to the correspondence between the region image and the operation panel image, the two-dimensional coordinates of the center point of each key in the region image are converted into the operation panel image to obtain the two-dimensional coordinates of the center point of each key in the operation panel image to be identified; Acquire the depth information of each button corresponding to the two-dimensional coordinates of the center point of each button in the image of the operation panel to be identified through the depth camera, and calculate the position information of each button in the current depth camera coordinate system, that is, the button position information; The step of calculating the center position information of the operation panel image based on the feature matching information includes the following steps: Calculating the average coordinates of points on the preset template that match the operation panel image to obtain a first set point; Obtaining a second set point according to the first set point, wherein the second set point is obtained by performing a homographic transformation on the first set point to a corresponding point in the operation panel image; The center position information is obtained according to the second set point and a fixed distance parameter value.

7. An electronic device, characterized in that: The electronic device includes: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the power cabinet key operation method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the power cabinet key operation method according to any one of claims 1 to 5.

Images