Method for identifying equipment state information in cabinet, storage medium and equipment

Abstract

The invention relates to the field of cabinet state identification, in particular to a method for identifying equipment state information in a cabinet, a storage medium and equipment. Comprising the following steps: determining an initial clustering radius R1; the center position coordinates of the observation window are used as iteration coordinates of the mass center, R1 is used as the clustering radius, a clustering algorithm is used for clustering the center position coordinates corresponding to the display parts, and a plurality of ethnic groups are generated; and controlling an acquisition camera in the automatic inspection terminal to sequentially move to the position coordinate of the mass center corresponding to each group to acquire the state information of the equipment in the cabinet. According to the invention, R1 is determined through the distance between the cabinet door and the state display panel in the cabinet and the field angle of the camera, and then clustering is carried out by taking the center position coordinates of each observation window as the selection coordinates of the mass center of the clustering group. In this way, it can be ensured that each cluster obtained through clustering can fall within the image collection range of the collection camera, and therefore the comprehensiveness of image collection is ensured.

Description

Background Art

[0002] Cabinet inspection is an important part of data center or server room maintenance, which aims to ensure that all hardware equipment is operating normally, environmental conditions are suitable, and potential problems are discovered and resolved in a timely manner. During the inspection process, it is necessary to prevent and resolve potential problems by observing the indicator lights or display contents corresponding to each condition (such as the temperature and humidity sensor indicator lights and the various signal indicator lights set on each service in the cabinet) to ensure the stable operation of the data center.

[0003] In the prior art, an automatic inspection terminal is used to automatically inspect the equipment in the cabinet. It is mainly an intelligent monitoring method realized by autonomous navigation, automatic control technology and image technology. At present, products usually use an autonomous mobile platform, a longitudinal lifting device, and a zoom camera to collect images. The autonomous mobile platform is usually a base in the form of wheels, four legs, tracks, etc. First, the automatic inspection terminal travels to the vicinity of the cabinet along the preset route through the autonomous mobile platform; then the longitudinal lifting device adjusts the camera to the height of the equipment in the cabinet; then the camera collects images of the equipment by adjusting the focal length, and finally analyzes the equipment status value and indicator light status through image recognition technology.

[0004] However, many cabinet doors are not made of transparent glass, but honeycomb metal doors. In this case, the cabinet doors will block the line of sight, so that the camera cannot capture clear images through zoom shooting at some preset positions, resulting in the inability to analyze the device status value and indicator light status through image recognition technology. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is:

[0006] According to one aspect of the present invention, a method for identifying device status information in a cabinet is provided, the method comprising the following steps:

[0007] According to the distance L between the cabinet door and the status display panel in the cabinet and the field of view θ of the acquisition camera in the automatic inspection terminal, the initial clustering radius R1 is determined; R1 satisfies the following conditions:

[0008] R1=L×tanθ;

[0009] Obtaining the center position coordinates of each display part in the status display panel and each observation window in the cabinet door; the center position coordinates of each display part and each observation window are located in the same plane coordinate system;

[0010] The center position coordinates of the observation window are taken as the iterative coordinates of the centroid, R1 is the clustering radius, and the center position coordinates corresponding to each display part are clustered using the K-Means clustering algorithm to generate multiple groups;

[0011] Control the collection camera in the automatic inspection terminal to move to the position coordinates of the corresponding centroid of each group in turn to collect the status information of the equipment in the cabinet.

[0012] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for identifying device status information in a cabinet is implemented.

[0013] According to a third aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for identifying device status information in a cabinet when executing the computer program.

[0014] The present invention has at least the following beneficial effects:

[0015] In the present invention, the initial clustering radius is determined by the distance L between the cabinet door and the status display panel in the cabinet and the field of view θ of the acquisition camera in the automatic inspection terminal, and then clustering is performed using the center position coordinates of each observation window as the selection coordinates of the centroid of the cluster group. This ensures that each group obtained by clustering can fall within the image acquisition range of the acquisition camera, thereby ensuring the comprehensiveness of image acquisition.

[0016] In addition, during the clustering process, it is required that the center position coordinates of each observation window be used as the selection coordinates of the centroid of the cluster group, and the centroids finally determined are all at the center of each observation window. Therefore, when controlling the acquisition camera to move to the centroid position to collect the status information of the equipment in the cabinet, it can be ensured that the camera is in an unobstructed observation window to avoid the cabinet door blocking the camera's field of view. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flowchart of a method for identifying device status information in a cabinet provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] Exemplarily, if there are descriptions in the form of "S100, ...; S200, ...; S300, ...;" and the like in this embodiment, it only provides an exemplary feasible execution order, not a necessary execution order. For example, the above description only indicates that step S100, step S200 and step S300 can be executed sequentially, but they do not have to be executed sequentially. A technician in the relevant technical field can determine the actual and feasible execution order according to the function and internal logic of each step. For example, step S200, step S300 and step S100 can be executed in sequence, or after executing step S100, steps S200 and S300 can be executed in parallel, or other feasible execution orders; at the same time, the description of "S100, ...; S200, ...; S300, ...;" does not limit the complete method to have only these three steps. A technician in the relevant technical field can determine whether to add other reasonable steps before and after any step according to actual needs.

[0021] In the description of the specification of this application and the attached claims, if the relevant descriptions of common processing functions such as "max(...)", "min(...)", "avg(...)" are used, if a targeted explanation is given in the text, it should be understood in accordance with the targeted explanation. If there is no targeted explanation, technicians in the relevant technical field should connect them with the relevant technical terms of computer science and technology. For example, "max()" is a maximum value determination function, "min()" is a minimum value determination function, "avg()" is an average value determination function, etc.

[0022] Furthermore, in the description of this application specification and the attached claims, if there are mathematical symbols without corresponding explanations, technicians in the relevant technical field should make corresponding interpretations based on the context and the feasibility of the technical solution. If there are differences in understanding, they can be understood in accordance with the "National Standard GB 3102.11-1993". For example, "⊥" means vertical, "A∪B" means the union of A and B, and "log a x" represents the logarithm of x with base a, etc.

[0023] As a possible embodiment of the present invention, Figure 1 As shown, a method for identifying device status information in a cabinet is also provided, the method comprising the following steps:

[0024] S100: Determine an initial clustering radius R1 according to a distance L between a cabinet door and a status display panel in the cabinet and a field of view angle θ of a collection camera in an automatic inspection terminal.

[0025] Specifically, the display part may include an indicator light and a display screen. Usually, multiple servers or other devices may be placed in a cabinet, and indicator lights and display screens may be used on these devices to display corresponding information. In addition, since multiple servers or other devices are placed in different positions in the cabinet, and the positions of the display parts in different types of servers or other devices are different. Usually, there may be a group of multiple centrally distributed indicator lights, which are distributed vertically according to the level. In addition, there may also be scattered indicator lights or display screens in other positions.

[0026] The automatic inspection terminal also includes: a mobile platform and a three-axis slide rail control component. The acquisition camera is connected to the mobile platform through the three-axis slide rail control component. The mobile platform is a wheeled mobile platform with laser SLAM navigation. Therefore, combined with the laser SLAM precise navigation of the autonomous mobile platform and the control of the precise positioning of the three-axis slide rail control component and the touch switch to assist in fine-tuning the distance, the mesh hole position of the cabinet door can be accurately positioned; so that the camera can accurately focus on the equipment at close range and collect clear images through the mesh hole.

[0027] In this embodiment, by combining technical means such as a wheeled autonomous mobile platform, a three-axis slide rail control component, camera control, and an image recognition algorithm, the automatic inspection terminal can automatically inspect the equipment in the cabinet and identify the device name, device value, and indicator light status through the observation port of the honeycomb metal cabinet door without opening the cabinet door.

[0028] The mobile platform in this embodiment: needs to have a certain load-bearing capacity and stability, and can be as close to the cabinet door as possible. The existing four-legged base has insufficient load-bearing capacity; the slide rail base is not flexible enough, the construction conditions of the bridge frame on the top of the machine room are relatively limited, and the line cannot be flexibly planned; so in this embodiment, a wheeled robot that can turn on the spot with laser SLAM navigation is adopted. The robot also has the characteristics of large load, accurate positioning, flexible construction, and flexible line planning, which meets the technical requirements of the base for the use scenario in this embodiment. Therefore, the present invention selects a wheeled base with laser SLAM navigation as an autonomous mobile base, as the base of the automatic inspection terminal and equipped with an automated displacement device (i.e., a three-axis slide rail control component) and a camera (i.e., a collection camera). During the inspection process, the base (i.e., the mobile platform) is first autonomously moved to 5-10 cm in front of the cabinet, and the wheeled base with laser SLAM navigation can ensure that the positioning error is within ±1 cm. It provides an accurate basic operating position for the subsequent control of the camera to move and collect image materials.

[0029] The three-axis slide control assembly controls the movement of the camera: Since the camera needs to be controlled to be close to the cabinet door for image capture, the travel of the control mechanism needs to be sufficient to cover the entire cabinet door. The cabinet is usually about 2m high and 40-60cm wide. The method of mounting the camera on the lifting platform cannot meet the needs, so the three-axis slide is used to mount the camera. The three-axis slide is controlled by a servo motor, which can control the camera to slide in three directions: horizontally, vertically, and front and back, and can control the camera movement speed and position with high precision. It provides mechanical control support for image recognition shooting materials.

[0030] Camera shooting: The operation camera uses a high-definition camera. The distance between the cabinet door and the equipment indicator light is usually 5-10cm; the camera is close to the cabinet door and shoots through the mesh plate. Usually, the size of the camera is smaller than the corresponding aperture on the mesh plate, so the camera uses a high-definition camera that can quickly focus within the range of 5-10cm.

[0031] R1 meets the following conditions:

[0032] R1 = L × tanθ.

[0033] Preferably, L can be set as the minimum distance between the cabinet door and the indicator light or screen on the status display panel. Thus, it can be ensured that the acquisition camera can have a larger field of view when shooting, and thus the status of various knowledge devices can be seen more comprehensively.

[0034] Furthermore, after determining the initial clustering radius R1, the method further includes:

[0035] S110: Obtain the radius of the circumscribed circle corresponding to each display part (R w 1. R w 2. …, R w i , …, R w z ), where R w i is the radius of the circumscribed circle corresponding to the i-th display part, i=1, 2, ..., z, and z is the total number of display parts in the status display panel.

[0036] S120: According to (R w 1. R w 2. …, R w i , …, R w z ) and R1, determine the compensation cluster radius R2. R2 satisfies the following conditions:

[0037] R2=L×tanθ-Max(R w 1. Rw 2. …, R w i , …, R w z ).

[0038] In this case, R1 in S300 may be replaced by R2.

[0039] Because in actual scenarios, the indicator light or display screen is not a point on the status display panel, but has a certain display area, such as the indicator light is generally a circular display area, and the display screen is a rectangular display area. Therefore, in order to place the entire display content of the indicator light or display screen into the picture, it is necessary to further reduce the clustering radius. In this embodiment, a circular bounding box (i.e., a circumscribed circle) is generated for each indicator light or display screen, and the radius of the largest circumscribed circle is used as the reduction value of the clustering radius to reduce the distribution range of each group, so that the acquisition camera can cover the edge of each display area in the group when shooting, so as to avoid the problem of incomplete information collection.

[0040] S200: Obtain the center position coordinates of each display part in the status display panel and each observation window in the cabinet door. The center position coordinates of each display part and each observation window are located in the same plane coordinate system.

[0041] In actual scenarios, there is a distance between the status display panel and the cabinet door, and the acquisition camera is usually attached to the cabinet door. Therefore, in order to eliminate the influence of the distance between the status display panel and the cabinet door on the calculation of the distance between each point during clustering, the center position coordinates of each display part and each observation window need to be located in the same plane coordinate system, which is equivalent to placing each coordinate point in the same plane. The plane can be the plane where the status display panel or the cabinet door is located.

[0042] S300: Taking the center position coordinates of the observation window as the iterative coordinates of the centroid and R1 as the clustering radius, the center position coordinates corresponding to each display part are clustered using the K-Means clustering algorithm to generate multiple groups.

[0043] K-Means clustering is a very popular unsupervised learning algorithm used to partition a dataset into K different clusters, where K is the number of clusters pre-specified by the user.

[0044] Then, randomly select K data points as the initial cluster centers (centers of mass). These centers of mass are usually actual points in the data set, which can be randomly selected or selected using some heuristic method. In this embodiment, the center position coordinate points of each observation window are used as the selection points of the center of mass. Then, for each data point in the data set, in this embodiment, the center position coordinate points corresponding to each display part are used as the points to be clustered, and the distances between them and all K centers of mass are calculated (usually using Euclidean distance). Each data point is assigned to the cluster represented by the nearest center of mass, and the distance between the data points in each cluster and the center of mass is less than or equal to R1 or R2.

[0045] The K value in S300 can be determined as follows:

[0046] S301: Determine the K value in the K-Means clustering algorithm according to the number of regions distributed in each display part in the status display panel.

[0047] Correspondingly, the updated coordinate set of the centroid may be determined according to the distribution areas of the display parts determined in S301 in the following manner.

[0048] S302: Using the center position coordinates of each observation window covered by the area where each display part is distributed in the status display panel as the center of mass update coordinates corresponding to each cluster in the K-Means clustering algorithm.

[0049] The K value can be determined by using some existing publicly available methods (such as the elbow rule). Or, according to S301, by observing the general regional distribution of the displayed part, it is possible to manually determine how many classes to divide into. In addition, in order to reduce the amount of calculation, it is necessary to reduce the updated coordinate set of the centroid, which can be specifically operated according to S302.

[0050] In addition, the final centroid of each group in S300 can also be determined as follows:

[0051] S310: After K is determined, clustering is performed on the coordinate set consisting of the center position coordinates of each display part and each observation window using R1 or R2 as the maximum distance between the group member and the centroid to generate multiple groups.

[0052] S320: The center position coordinates of the observation window whose distance from the centroid of each group is less than a first distance threshold Y1 are used as the candidate centroid corresponding to each group. Y1 can be determined according to the actual usage scenario.

[0053] S330: Obtain the sum of the distances between each candidate centroid and the corresponding group member. Where Dj = (D j 1 , D j 2,…,D j u ,…,D j w ), Dj is the distance and set corresponding to the jth group, D j u is the sum of the distances between the uth candidate centroid and the group members in Dj, X u and Y u is the coordinate of the uth centroid to be selected in Dj, X j b and Y j b is the coordinate of the bth group member in the jth group. m is the total number of group members in the jth group.

[0054] S340: The minimum distance and the corresponding candidate centroid are used as the target centroid of the corresponding group.

[0055] In addition, the final coordinates of the centroid can be determined in the manner of S310-S340, that is, the algorithm is allowed to freely determine the coordinates of the centroid (the coordinates of the center position of the display part). Since the mesh on the cabinet door is very dense, the center position coordinates of the observation window near the centroid can be selected to replace the previous centroid. In this case, the amount of calculation during K-Means clustering can be further reduced.

[0056] S400: Control the collection camera in the automatic inspection terminal to move to the position coordinates of the center of mass of each group in turn to collect status information of the equipment in the cabinet.

[0057] Specifically, S400 includes:

[0058] S401: Controlling the acquisition camera in the automatic inspection terminal to move to the position coordinates of the corresponding centroid of each group in turn, and then collecting low-exposure photos or high-exposure photos or videos of the corresponding area.

[0059] Specifically, the automatic inspection terminal also has an image recognition module for performing image recognition and analysis on different types of equipment, different types of indicator lights and their arrangements.

[0060] Typically, different types of equipment in a cabinet usually have multiple indicator lights arranged horizontally or vertically, so one inspection operation needs to control the camera to capture four types of image materials: a low-exposure photo centered on the position coordinates of each center of mass, a high-exposure photo centered on the position coordinates of each center of mass, a video centered on the position coordinates of each center of mass, and a video that slides uniformly from the first preset position in the group to the second preset position.

[0061] High-exposure photos are used to identify text in the image and locate the positions of each device and its indicator light in the image; low-exposure photos are used to identify the status of the indicator light. Combining high-exposure and low-exposure photos can form complete device status information by corresponding the device and indicator light status. When the device indicator light is a strobe type or a carousel type indicator light or LED value, the device status can be identified by continuously analyzing the changes in the indicator light within a period of time in combination with the video. The video of the first preset position in the group sliding at a constant speed to the second preset position is used as supplementary material. Since the indicator light can be observed from multiple angles during the video sliding process, the obscured indicator light in the photo can be supplemented for identification, thereby improving the identification accuracy.

[0062] Therefore, the present invention can complete inspection and data collection without opening the cabinet door during the inspection process of the automatic inspection terminal, thereby improving the safety and efficiency of the operation. By combining a variety of technical means, close-range accurate image acquisition is achieved, and pictures and videos are collected at the same time, and materials with different exposures are collected at the same time to provide support for the image recognition algorithm. Finally, it is possible to recognize various types of status information such as small text, flashing indicator lights, numbers, and carousel information on cabinet equipment.

[0063] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0064] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0065] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0066] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0067] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0068] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0069] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0070] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0071] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0072] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0073] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device (e.g., routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. Such communication may be performed through an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0074] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0075] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0076] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0077] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0078] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0079] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0080] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0081] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0082] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for identifying device status information in a cabinet, characterized in that: The method comprises the following steps: According to the distance L between the cabinet door and the status display panel in the cabinet and the field of view θ of the acquisition camera in the automatic inspection terminal, the initial clustering radius R1 is determined; R1 satisfies the following conditions: R1=L×tanθ; Obtaining the center position coordinates of each display part in the status display panel and each observation window in the cabinet door; the center position coordinates of each display part and each observation window are located in the same plane coordinate system; The center position coordinates of the observation window are taken as the iterative coordinates of the centroid, R1 is the clustering radius, and the center position coordinates corresponding to each display part are clustered using the K-Means clustering algorithm to generate multiple groups; The acquisition camera in the automatic inspection terminal is controlled to move to the position coordinates of the center of mass of each group in turn to collect the status information of the equipment in the cabinet.

2. The method according to claim 1, characterized in that After determining the initial clustering radius R1, the method further includes: Get the radius of the circumscribed circle corresponding to each display part (R w 1. R w 2. …, R w i , …, R w z ), where R w i is the radius of the circumscribed circle corresponding to the i-th display part, i=1, 2, ..., z, and z is the total number of display parts in the status display panel; According to (R w 1. R w 2. …, R w i , …, R w z ) and R1, determine the compensation clustering radius R2; R2 satisfies the following conditions: R2=L×tanθ-Max(R w 1、R w 2、…、R w i 、…、R w z ); Obtaining the center position coordinates of each display part in the status display panel and each observation window in the cabinet door; The center position coordinates of the observation window are taken as the iterative coordinates of the centroid, R2 is the clustering radius, and the center position coordinates corresponding to each display part are clustered using the K-Means clustering algorithm to generate multiple groups; The acquisition camera in the automatic inspection terminal is controlled to move to the position coordinates of the center of mass of each group in turn to collect the status information of the equipment in the cabinet.

3. The method according to claim 2, characterized in that The K-Means clustering algorithm is used to cluster the center position coordinates corresponding to each display part, including: The K value in the K-Means clustering algorithm is determined according to the number of regions distributed in each display part in the status display panel.

4. The method according to claim 3, characterized in that The K-Means clustering algorithm is used to cluster the center position coordinates corresponding to each display part, including: The center position coordinates of each observation window covered by the area where each display part is distributed in the status display panel are used as the centroid update coordinates corresponding to each cluster in the K-Means clustering algorithm.

5. The method according to claim 3, characterized in that: The K-Means clustering algorithm is used to cluster the center position coordinates corresponding to each display part to generate multiple groups; including: After K is determined, R1 or R2 is used as the maximum distance between a group member and the centroid, and the coordinate set consisting of the center position coordinates of each display part and each observation window is clustered to generate multiple groups; The center coordinates of the observation window whose distance from the centroid of each group is less than the first distance threshold Y1 are used as the candidate centroid corresponding to each group; Get the sum of the distances between each candidate centroid and the corresponding group member; where Dj = (D j 1 , D j 2 ,…,D j u ,…,D j w ), Dj is the distance and set corresponding to the jth group, D j u is the sum of the distances between the uth candidate centroid and the group members in Dj, X u and Y u is the coordinate of the uth centroid to be selected in Dj, X j b and Y j b is the coordinate of the bth ethnic group member in the jth ethnic group; m is the total number of ethnic group members in the jth ethnic group; The minimum distance and the corresponding candidate centroid are used as the target centroid of the corresponding group.

6. The method according to claim 1, characterized in that The display part includes an indicator light and a display screen.

7. The method according to claim 1, characterized in that The automatic inspection terminal also includes: a mobile platform and a three-axis slide rail control component; The acquisition camera is connected to the mobile platform through a three-axis slide rail control component; the mobile platform is a wheeled mobile platform for laser SLAM navigation.

8. The method according to claim 1, characterized in that Controlling the acquisition camera in the automatic inspection terminal to move to the position coordinates of the centroid corresponding to each group in turn to collect the status information of the equipment in the cabinet, including: The acquisition camera in the automatic inspection terminal is controlled to move to the position coordinates of the corresponding centroid of each group in turn, and then collect low-exposure photos or high-exposure photos or videos of the corresponding area.

9. A non-transitory computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying device status information in a cabinet as claimed in any one of claims 1 to 8 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for identifying device status information in a cabinet as described in any one of claims 1 to 8 is implemented.

Images