Cabinet state information acquisition method, storage medium and electronic equipment

Abstract

The invention relates to the technical field of cabinet inspection, in particular to a cabinet state information acquisition method, a storage medium and electronic equipment. Comprising the steps of generating primary displacement information between a current position of camera equipment and an initial target acquisition point according to a difference value between a world coordinate corresponding to a central pixel position of each auxiliary positioning paste and a world coordinate corresponding to a preset central position; according to the primary displacement information and the secondary displacement information, the camera device is controlled to move, and image information corresponding to the current position is collected when execution of each piece of displacement information is completed. According to the invention, the abnormal target acquisition point corresponding to the image area where the indicator lamp is shielded is arranged at the position close to the cabinet door of the cabinet, so that camera equipment can get close to the observation hole to shoot a certain part. At the moment, the shielding of honeycomb-shaped metal in the visual field of the camera equipment can be avoided, so that the image information of the shielded indicator light can be acquired more clearly.

Description

Technical Field

[0001] This invention relates to the field of cabinet inspection technology, and in particular to a method for acquiring cabinet status information, a storage medium, and an electronic device. Background Technology

[0002] Rack inspections are a crucial part of data center or server room maintenance, aiming to ensure all hardware is functioning properly, environmental conditions are suitable, and potential problems are identified and resolved promptly. During inspections, it's essential to observe the indicator lights or displays corresponding to each condition (such as temperature and humidity sensor indicator lights and various signal indicator lights on the servers within the rack) to prevent and resolve potential issues, ensuring the stable operation of the data center.

[0003] In existing technologies, the use of automated inspection terminals to automatically inspect equipment in server racks is primarily an intelligent monitoring method that utilizes autonomous navigation, automatic control, and image technology. Current products typically employ an autonomous mobile platform, multi-axis adjustment components, and cameras for image acquisition. The autonomous mobile platform usually has a wheeled, quadrupedal, or track-based base. First, the automated inspection terminal travels along a pre-set route to the vicinity of the server rack via the autonomous mobile platform; then, the camera acquires images of the equipment. To capture as many indicator lights as possible in a single image, the image acquisition position is usually located relatively far from the server rack door. Finally, image recognition technology is used to analyze the equipment status values ​​and indicator light status.

[0004] However, many server racks currently use honeycomb-patterned metal doors instead of transparent glass. In this case, the metal mesh structure of the door significantly obstructs the view, blocking small indicator lights (such as dot-matrix indicator lights) or digital displays in certain locations. Furthermore, the distance between the camera and the door further reduces the image size of the indicator lights, resulting in the camera being unable to capture clear images of some indicator lights. Consequently, image recognition technology cannot be used to analyze the device status values ​​and indicator light status. Summary of the Invention

[0005] To address one of the aforementioned technical problems, the present invention adopts the following technical solution:

[0006] According to one aspect of the present invention, a method for obtaining rack status information is provided, the method comprising the following steps:

[0007] Based on the target cabinet door-closed image captured by the camera equipment in the inspection area, the world coordinates corresponding to the center pixel position of each auxiliary positioning sticker in the target cabinet door-closed image are obtained. One of the auxiliary positioning sticker images includes a QR code, which stores the world coordinates corresponding to the preset center position of each auxiliary positioning sticker, and the secondary displacement information corresponding to two adjacent nodes in the preset camera inspection path. The nodes in the preset camera inspection path include the initial target acquisition point of the camera equipment and the abnormal target acquisition point corresponding to the abnormal area in the initial acquisition image. The lens of the camera equipment located at the abnormal target acquisition point is located at the corresponding observation hole on the cabinet door. The distance between the abnormal target acquisition point and the plane where the cabinet door is located is less than the distance between the initial target acquisition point and the plane where the cabinet door is located. The abnormal target acquisition point is used to acquire a partial status information image of the cabinet. The initial target acquisition point is used to acquire a full status information image of the cabinet. The abnormal area includes the image area where indicator lights are obscured.

[0008] Based on the difference between the world coordinates corresponding to the center pixel position of each auxiliary positioning patch and the world coordinates corresponding to the preset center position, primary displacement information between the current position of the camera device and the initial target acquisition point is generated; the primary displacement information and secondary displacement information are used to determine the adjustment increment of each position adjustment axis in the multi-axis adjustment component corresponding to the camera device;

[0009] Based on the order of the nodes to be reached in the preset camera inspection path according to the primary displacement information and secondary displacement information, the camera equipment is moved sequentially, and the status information map of the corresponding area of ​​the cabinet is collected after each displacement information is executed.

[0010] Furthermore, the abnormal target acquisition points corresponding to the abnormal regions in the initial acquired image are obtained according to the following steps:

[0011] Control the camera equipment at the initial target acquisition point to acquire the open and closed state images of the target cabinet respectively;

[0012] Image region segmentation is performed on the open and closed state images respectively to generate open and closed state binary images; in the binary images, the pixel value of the target image region corresponding to the indicator light is 0, and the pixel value of the background image region is 255.

[0013] Using the binary image of the open state as a mask for the closed state image, the fill coefficient corresponding to the mask area of ​​each indicator light in the binary image of the open state is obtained; wherein, the fill coefficient Gn corresponding to the mask area of ​​the nth indicator light satisfies the following condition:

[0014] Gn = G z n / G m n ;

[0015] Among them, G z n Let G be the area of ​​the indicator light image region in the closed state diagram, within the mask region of the nth indicator light in the open state binary diagram; m n The image area of ​​the mask region for the nth indicator light in the binary image of the open door state;

[0016] If the fill coefficient of any indicator mask area in the binary image of the open state is less than the fill threshold, then the world coordinates corresponding to the center of the indicator mask area are taken as the coordinates of the first type of abnormal area.

[0017] The coordinates of the center of the observation hole in the equivalent observation plane of the cabinet door that is closest to the coordinates of the first type of anomaly area are taken as the coordinates of the collection point of the first type of anomaly target; the equivalent observation plane of the cabinet door is set parallel to and spaced apart from the cabinet door.

[0018] Furthermore, the abnormal area also includes the false indicator light image area formed by light leakage from scattered light;

[0019] After generating the binary images of the open and closed states, the method also includes:

[0020] The closed state binary image is used as a mask for the open state image. If there is no indicator light image in any indicator light mask area in the closed state binary image, the world coordinates corresponding to the center of the indicator light image closest to the indicator light mask area in the open state image are used as the coordinates of the second type of abnormal area.

[0021] The coordinates of the center of the observation hole that is closest to the coordinates of the second type of anomaly area in the equivalent observation plane of the cabinet door are taken as the coordinates of the collection point corresponding to the second type of anomaly target.

[0022] Furthermore, the QR code also stores the location coordinates of the initial target acquisition point and the abnormal target acquisition point. The method also includes:

[0023] Based on the nearest neighbor algorithm, path planning is performed on the initial target acquisition points and abnormal target acquisition points to generate a preset camera inspection path.

[0024] Furthermore, the QR code also stores a binary image of the cabinet's updated door closing state corresponding to the previous update cycle. The method also includes:

[0025] If an update command is received, the camera device is controlled to acquire the target cabinet door closing image at the initial target acquisition point at the current update time.

[0026] The target rack door-closed image collected at the current update time is processed by image region segmentation to generate an updated door-closed state binary image corresponding to the current update time; in the updated door-closed state binary image corresponding to the current update time, the pixel value of the target image region corresponding to the indicator light is 0, and the pixel value of the background image region is 255.

[0027] The binary image of the updated door-closing state corresponding to the current update time of the cabinet is compared with the binary image of the updated door-closing state corresponding to the previous update cycle. At least one positional image region with pixel differences between the binary image of the updated door-closing state corresponding to the current update time and the binary image of the updated door-closing state corresponding to the previous update cycle is generated.

[0028] The coordinates of the center of the observation hole that is closest to the center coordinates of the image area of ​​position change in the equivalent observation plane of the cabinet door are used as the coordinates of the acquisition point corresponding to the third type of abnormal target.

[0029] Further pixel matching processing includes:

[0030] Align the binary image of the update closing state corresponding to the current update time with the binary image of the update closing state corresponding to the previous update cycle.

[0031] The two images are compared pixel by pixel to generate the image region with positional change; the pixel-by-pixel comparison must meet the following conditions:

[0032]

[0033] Among them, diff (x,y) This is the pixel value obtained by comparing two pixels at pixel coordinates (x, y); imgD (x,y) This refers to the pixel value of the pixel at coordinates (x, y) in the binary image of the updated gate closing state at the current update time; imgS (x,y) This represents the pixel value of the pixel with coordinates (x, y) in the binary image of the updated gated state corresponding to the previous update cycle.

[0034] Furthermore, after generating the coordinates corresponding to the collection points of the third type of abnormal target, the method also includes:

[0035] If the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or the abnormal target acquisition point is greater than the field of view radius of the camera device, then the third type of abnormal target acquisition point will be identified as a new abnormal target acquisition point.

[0036] The field of view radius L of the camera device satisfies the following condition:

[0037] Where H is the distance between the camera lens and the indicator light inside the cabinet according to the equivalent plane, and FOV is the field of view of the camera lens;

[0038] Based on the updated initial target acquisition points and abnormal target acquisition points, a new preset camera inspection path is generated.

[0039] Furthermore, after generating the coordinates corresponding to the collection points of the third type of abnormal target, the method also includes:

[0040] If the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or the abnormal target acquisition point is less than the field of view radius of the camera device, then the third type of abnormal target acquisition point will be deleted.

[0041] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the above-described method for obtaining cabinet status information.

[0042] According to a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for obtaining cabinet status information.

[0043] This invention has at least one of the following beneficial effects:

[0044] In this invention, the abnormal target acquisition point corresponding to the image area where the indicator light is obscured is positioned near the cabinet door. This allows the lens of the camera device located at the abnormal target acquisition point to be positioned at the corresponding observation hole on the cabinet door. In other words, the camera device can approach the observation hole to capture a specific area. This avoids obstruction from the honeycomb-shaped metal in the camera's field of view, allowing for clearer acquisition of the image information of the obscured indicator light. This enables subsequent identification of the cabinet's relevant status information through the visible light display information of the indicator light.

[0045] Simultaneously, this invention employs multiple auxiliary positioning stickers affixed to the cabinet door to locate the initial target acquisition point for each camera inspection. This ensures that the position of the initial acquisition point for each subsequent inspection is identical to the initial acquisition point set during the initial preparation phase, thereby guaranteeing that the viewing angle range of each captured image is the same as the previously specified viewing angle range. Furthermore, since the positions of the equipment within the cabinet generally do not change frequently, the positions of indicator lights that might experience obstruction during initial acquisition point photography remain stable. Therefore, the initial target acquisition point and abnormal target acquisition points can be used to form a preset camera inspection path, and the corresponding displacement information can be stored in a QR code. The initial target acquisition point is used to capture a full-view image of the cabinet's status information, while the abnormal target acquisition point is used to obtain a partial image of local status information. Whenever the camera performs an inspection, the initial target acquisition point can be directly located based on the information in the QR code, and the camera can move and take pictures according to the preset camera inspection path, thus clearly and comprehensively capturing the image information of each status indicator light in the cabinet.

[0046] In addition, in this invention, the secondary displacement information is directly stored in the QR code. Thus, during subsequent inspections, the displacement adjustment system corresponding to the camera device can directly adjust the corresponding position adjustment axis according to each level of displacement information to complete the traversal of the entire inspection path. There is no need to calculate the displacement information during inspection, thereby improving inspection efficiency. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating a method for obtaining rack status information provided in an embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of the working scenario of the camera device during the inspection of the cabinet, provided in an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the area where a false indicator light image appears, provided in an embodiment of the present invention.

[0051] Figure 4 This is a working diagram showing the cabinet status information of the inspection robot during inspection, provided in an embodiment of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] As one possible embodiment of the present invention, such as Figure 1 As shown, a method for obtaining rack status information is provided, which includes the following steps:

[0054] S100: Based on the target rack door-closed image currently captured by camera device 1, obtain the world coordinates corresponding to the center pixel position of each auxiliary positioning patch in the target rack door-closed image. Camera device 1 can refer to... Figure 2 Camera device 1.

[0055] One of the auxiliary positioning stickers includes a QR code in its image. The QR code stores the world coordinates corresponding to the preset center position of each auxiliary positioning sticker, and the secondary displacement information corresponding to any two adjacent nodes in the preset camera inspection path. The nodes in the preset camera inspection path include the initial target acquisition point of camera device 1 and the abnormal target acquisition point corresponding to the abnormal area in the initial acquisition image. The lens of camera device 1 located at the abnormal target acquisition point is located at the corresponding observation hole on the cabinet door. Specifically, the QR code also stores the position coordinates corresponding to the initial target acquisition point and the abnormal target acquisition point. Based on the nearest neighbor algorithm, path planning can be performed on the initial target acquisition point and the abnormal target acquisition point to generate the preset camera inspection path, which is the shortest running path.

[0056] In this embodiment, terms such as primary displacement information, secondary displacement information, initial target acquisition point, initial acquisition image, and abnormal target acquisition point are used. To more clearly explain their meanings in this embodiment, the following explanations are provided:

[0057] Both primary and secondary displacement information are displacement information used to control the adjustment variation of each position adjustment axis in the multi-axis adjustment assembly. Each element is a displacement increment (i.e., the adjustment increment of the corresponding position adjustment axis) in the prior art. Taking a three-axis adjustment assembly as an example, if a displacement information is (ΔX, ΔY, ΔZ), then ΔX represents the distance ΔX the X-axis moves from the current position along a preset positive direction. Similarly, the Y-axis and Z-axis move ΔY and ΔZ distances from the current position along their respective preset positive directions. In this embodiment, an initial inspection docking point (i.e., an initial target acquisition point) for camera device 1 is set in front of each cabinet. However, due to the positioning error of the moving platform of the inspection device, it is possible that its docking position is not the preset initial inspection docking point. Therefore, in this embodiment, the primary displacement information is used to adjust camera device 1 from any inaccurate docking point to the position corresponding to the initial target acquisition point. When camera device 1 is at the initial target acquisition point, it can acquire a complete image of the cabinet's status information.

[0058] Then, due to the presence of areas where indicator lights are obscured or false indicator light images (area 3) in the overall status information map of the cabinet, these areas are all abnormal areas. The collection points of the local status information map corresponding to these areas are the abnormal target collection points. Multiple abnormal target collection points can form part of the preset camera inspection path. The secondary displacement information is used to control the movement of each axis in the multi-axis adjustment component, thereby moving the camera device 1 from the current abnormal target collection point to the next abnormal target collection point, so as to complete the collection of the local status information map of the cabinet at each abnormal target collection point.

[0059] Before proceeding to this step, some preparatory work needs to be done, which may include the following:

[0060] Multiple auxiliary positioning stickers are affixed to each rack door. For example, three rectangular auxiliary positioning stickers can be selected and affixed to the upper left, lower left, and upper right corners of the rack to provide positioning assistance. These auxiliary positioning stickers, distributed across multiple corners of the shooting area, provide a global reference frame for the entire scene. The positional relationship of these markers clearly defines the scene's coordinate system (e.g., origin, X-axis, Y-axis), making it easier to calculate the absolute position of the target object. For example, in this invention, the upper left auxiliary positioning sticker can be set as the coordinate origin, the line connecting the centers of the upper left and upper right auxiliary positioning stickers is the X-axis, the line connecting the centers of the upper left and lower left auxiliary positioning stickers is the Y-axis, and the line perpendicular to the XY plane is the Z-axis. This determines the world coordinates of each location point, and the specific coordinate values ​​or displacement information can be stored in a QR code as needed.

[0061] An initial target acquisition point is determined, which is also a fixed inspection point. Typically, when camera device 1 is at this location, it can capture images of all indicator lights in the cabinet; that is, at the initial target acquisition point, a complete image of the cabinet's status information can be acquired. However, due to the limitations of this shooting position, some indicator lights may be obstructed, preventing the acquisition of a complete image of that indicator light. Alternatively, due to the multiple diffuse reflections of light from the metal cabinet door and the outer walls of the equipment inside the cabinet, some light may leak out from the honeycomb observation holes where there are no indicator lights, thus forming false indicator light images in that area when camera device 1 images the image. The image areas corresponding to the above two situations are considered abnormal areas in this embodiment.

[0062] Specifically, the abnormal target acquisition points corresponding to the abnormal areas where indicator lights are obscured in the initial acquired image are obtained according to the following steps:

[0063] S101: Control camera device 1 to acquire the open and closed state images of the target cabinet at the initial target acquisition point.

[0064] In this step, keep the position of camera device 1 unchanged and take images of the cabinet with the door open and closed. Additionally, to more comprehensively identify all abnormal areas, all indicator lights in the cabinet can be set to active status.

[0065] S102: Perform image region segmentation processing on the open and closed state images respectively to generate open and closed state binary images. In the binary images, the pixel value of the target image region corresponding to the indicator light is 0, and the pixel value of the background image region is 255.

[0066] In this step, because the color and shape of the indicator lights in the cabinet differ significantly from the rest of the background (such as the outer wall panel of the equipment and the mesh cabinet door), image region segmentation can be used to better segment the binary image composed of the indicator lights and the other background. In this embodiment, the target image region corresponding to the indicator light includes the entire indicator light (e.g., ...). Figure 2 The green circular indicator light 21) and the digital display section of the display screen (such as...) Figure 2 The image area corresponding to the red number 22 on the display screen.

[0067] S103: Use the binary image of the open state as a mask for the closed state image, and obtain the fill coefficient corresponding to the mask area of ​​each indicator light in the binary image of the open state. The fill coefficient Gn corresponding to the mask area of ​​the nth indicator light satisfies the following condition:

[0068] Gn = G z n / G m n .

[0069] Among them, G z n Let G be the area of ​​the indicator light image region in the closed state diagram, within the mask region of the nth indicator light in the binary image of the open state. m n The area of ​​the mask region for the nth indicator light in the binary image of the open door state.

[0070] S104: If the fill coefficient of any indicator light mask area in the binary image of the open state is less than the fill threshold, then the world coordinates corresponding to the center of the indicator light mask area are taken as the coordinates of the first type of abnormal area.

[0071] In this embodiment, the first type of abnormal area mainly refers to the abnormality caused by the cabinet door obstructing some small point light sources and screen display numbers, thus preventing the acquisition of all indicator light images. Since the point light sources and screen display numbers in this embodiment are all relatively small indicator lights, even though the mesh wall of the cabinet door is thin, the proportion of obstruction of the aforementioned types of indicator lights is still relatively large. Therefore, the abnormal area caused by the obstruction is determined based on the fill factor.

[0072] S105: Take the coordinates of the center of the observation hole in the equivalent observation plane of the cabinet door that is closest to the coordinates of the first type of abnormal area as the coordinates of the collection point of the first type of abnormal target.

[0073] Since the coordinates corresponding to the ultimately determined abnormal target acquisition point are used to determine the position of camera device 1, in order to ensure that camera device 1 can get close enough to take pictures at that position without interfering with the cabinet door, the equivalent observation plane of the cabinet door needs to be set parallel and spaced to the cabinet door. Therefore, the coordinates corresponding to the abnormal target acquisition point in this invention can be the point reached by controlling the center position of the lens of camera device 1.

[0074] In addition, abnormal areas also include areas with false indicator light images formed by light leakage from scattered light, such as... Figure 3 The fake indicator light image area 3 in the image.

[0075] After generating the binary images of the open and closed states, the method for obtaining abnormal target collection points also includes:

[0076] S111: Use the closed state binary image as a mask for the open state image. If there is no indicator light image in any indicator light mask area in the closed state binary image, then the world coordinates corresponding to the center of the indicator light image closest to the indicator light mask area in the open state image will be used as the coordinates of the second type of abnormal region.

[0077] S112: Take the coordinates of the center of the observation hole in the equivalent observation plane of the cabinet door that is closest to the coordinates of the second type of anomaly area as the coordinates of the collection point of the second type of anomaly target.

[0078] For the false indicator light image region 3 formed by light leakage from the scattered light, the false indicator light image caused by this light leakage observation hole will only exist in the binary image of the closed state. Therefore, if there is no indicator light image in any indicator light mask region of the closed state binary image, then that location can be identified as the false indicator light image region 3. False indicator light images are usually formed due to multiple diffuse reflections or even the mixing of light diffraction and scattering phenomena caused by the light emitted from the real indicator light. Therefore, the false indicator light image will only appear in the area close to the real indicator light. Thus, the world coordinates corresponding to the center of the indicator light image closest to the indicator light mask region in the open state image are taken as the coordinates of the second type of abnormal region.

[0079] S200: Based on the difference between the world coordinates corresponding to the center pixel position of each auxiliary positioning patch and the world coordinates corresponding to the preset center position, primary displacement information between the current position of camera device 1 and the initial target acquisition point is generated. The primary displacement information and secondary displacement information are used to determine the adjustment increment of each position adjustment axis in the multi-axis adjustment component corresponding to camera device 1.

[0080] When camera device 1 acquires a full view of the cabinet door's status at its current position, it can use computer vision algorithms (such as edge detection or template matching) to detect the position of the auxiliary positioning stickers and extract the center pixel coordinates of each auxiliary positioning sticker. Then, through a camera projection model (usually a pinhole camera model), the pixel coordinates are converted into real-world coordinates via inverse projection.

[0081] After obtaining the world coordinates corresponding to the center position of each auxiliary positioning patch at the current position, the adjustment increment of each adjustment axis can be determined based on the average difference between the world coordinates corresponding to the center pixel position of each auxiliary positioning patch and the world coordinates corresponding to the preset center position.

[0082] If there are 3 auxiliary positioning stickers, the adjustment increment ΔX in the X-axis direction satisfies the following condition: ΔX=(X1-X2) / ... target +X2-X2 target +X3-X3 target ) / 3, where X1 target X2 target X3 target X1, X2, and X3 are the world coordinates corresponding to the preset center positions of the three auxiliary positioning patches, respectively. X1, X2, and X3 are the world coordinates corresponding to the center pixel positions of the three auxiliary positioning patches in the currently acquired image.

[0083] S300: Based on the order of the nodes to be reached in the preset camera inspection path according to the primary displacement information and secondary displacement information, the camera device 1 is controlled to move sequentially, and the status information map of the corresponding area of ​​the cabinet is collected after each displacement information is executed.

[0084] In this embodiment, by setting the abnormal target acquisition point corresponding to the image area where the indicator light is obscured, near the cabinet door, the lens of camera device 1 located at the abnormal target acquisition point can be positioned at the corresponding observation hole on the cabinet door. That is, camera device 1 can approach the observation hole to capture a specific area. At this time, since the honeycomb-shaped metal obstruction in the field of view of camera device 1 is avoided, the image information of the obscured indicator light can be obtained more clearly, so that the relevant status information of the cabinet can be identified subsequently through the visible light display information of the indicator light.

[0085] In this embodiment, multiple auxiliary positioning stickers are affixed to the cabinet door to locate the initial target acquisition point for each inspection of camera device 1. This ensures that the position of the initial acquisition point for each subsequent inspection is exactly the same as the initial acquisition point set in the initial preparation stage, thus guaranteeing that the viewing angle range of each image captured during subsequent inspections is the same as the previously specified viewing angle range. Since the positions of the equipment in the cabinet generally do not change frequently, the positions of indicator lights that might be obstructed during initial acquisition point photography remain stable. Therefore, the initial target acquisition point and abnormal target acquisition point can be used to form a preset camera inspection path, and the corresponding displacement information can be stored in a QR code. The initial target acquisition point is used to capture a full-view image of the cabinet's status information, while the abnormal target acquisition point is used to obtain a partial image of local status information. Whenever camera device 1 performs an inspection, it can directly locate the initial target acquisition point based on the information in the QR code and move to take pictures according to the preset camera inspection path, thereby clearly and comprehensively capturing the image information of each status indicator light in the cabinet.

[0086] During long-term use, hardware maintenance and inspection of the equipment in the server rack are inevitable. Therefore, after manual maintenance and repositioning the equipment, slight displacement of the equipment's location may occur. In this case, indicator lights may malfunction, such as being obstructed or displaying false indicator images. Therefore, it is necessary to update the coordinates of the abnormal target data collection points.

[0087] In another embodiment of the present invention, the QR code also stores a binary image of the updated door-closing state corresponding to the previous update cycle of the cabinet, and the cabinet status information acquisition method further includes:

[0088] S400: If an update command is received, control camera device 1 to acquire the target cabinet door closing image at the initial target acquisition point at the current update time.

[0089] The update command in this step can be an update command triggered according to a preset cycle, or an update command triggered manually.

[0090] S500: Performs image region segmentation processing on the target rack door-closed image acquired at the current update time, generating an updated door-closed state binary image corresponding to the current update time. In the updated door-closed state binary image corresponding to the current update time, the pixel value of the target image region corresponding to the indicator light is 0, and the pixel value of the background image region is 255.

[0091] S600: Perform pixel comparison processing on the binary image of the updated door-closing state corresponding to the current update time of the cabinet and the binary image of the updated door-closing state corresponding to the previous update cycle, and generate at least one positional image region where there is a pixel difference between the binary image of the updated door-closing state corresponding to the current update time and the binary image of the updated door-closing state corresponding to the previous update cycle.

[0092] Specifically, pixel comparison processing includes:

[0093] S601: Align the binary image of the update closing state corresponding to the current update time with the binary image of the update closing state corresponding to the previous update cycle.

[0094] S602: Compare the two images pixel by pixel to generate the image region with positional change. The pixel-by-pixel comparison must meet the following conditions:

[0095]

[0096] Among them, diff (x,y) This is the pixel value obtained by comparing two pixels at pixel coordinates (x, y). (x,y) This represents the pixel value of the pixel at coordinates (x, y) in the binary image of the updated gated state at the current update time. (x,y) This represents the pixel value of the pixel with coordinates (x, y) in the binary image of the updated gated state corresponding to the previous update cycle.

[0097] S700: The coordinates of the center of the observation hole that is closest to the center coordinates of the image area of ​​position change in the equivalent observation plane of the cabinet door are used as the coordinates of the acquisition point corresponding to the third type of abnormal target.

[0098] In this embodiment, the currently acquired updated gate-closing state binary image is compared with the updated gate-closing state binary image acquired in the previous update cycle. Specifically, if the pixel value of the currently acquired updated gate-closing state binary image is the same as the pixel value at the corresponding position in the updated gate-closing state binary image acquired in the previous update cycle, the comparison result is 255; if they are different, the comparison result is 0. In this embodiment, the image region with a pixel value of 0 can be determined as the position-changed image region.

[0099] After pixel comparison processing, locations with different pixel values ​​before and after device movement are identified as abnormal areas. For example, an image area that was an indicator light area before movement but becomes a background area after movement, or vice versa. These image areas with positional changes are generally distributed within the range of the device's movement. That is, the coordinates of the third-type abnormal target acquisition points corresponding to these image areas can delineate the area where the device's position has changed. Within this movement area, new abnormal situations may arise due to indicator light obstruction, or new false indicator light images may appear due to light leakage. Therefore, close observation of this area is necessary. Specifically, by using these image areas with positional changes to form third-type abnormal target acquisition points as new abnormal target acquisition points, camera device 1 can be controlled to closely observe these points to obtain multiple clearer local images of the localized change location.

[0100] Furthermore, after generating the coordinates corresponding to the collection points of the third type of abnormal target, the method also includes:

[0101] S810: If the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or the abnormal target acquisition point is greater than the field of view radius of camera device 1, then the third type of abnormal target acquisition point is determined as a new abnormal target acquisition point.

[0102] The field of view radius L of camera device 1 satisfies the following condition:

[0103] Where H is the distance between the lens of camera device 1 and the indicator light inside the cabinet according to the equivalent plane, and FOV is the field of view of the lens of camera device 1.

[0104] S900: Generates a new preset camera inspection path based on the updated initial target acquisition points and abnormal target acquisition points.

[0105] S820: If the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or the abnormal target acquisition point is less than the field of view radius of camera device 1, then the third type of abnormal target acquisition point will be deleted.

[0106] After determining the area where the equipment moved using the coordinates of the third type of anomaly target acquisition point, it is necessary to conduct close-up observation of this location area because the anomaly area may change before and after the movement.

[0107] In steps S810, S900, and S820, the third type of abnormal target acquisition points are further filtered based on whether the field of view of the camera device 1 at the existing initial target acquisition point or abnormal target acquisition point can cover the image area with position change. Specifically, if the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or abnormal target acquisition point is greater than the field of view radius of the camera device 1, then the third type of abnormal target acquisition point is determined as a new abnormal target acquisition point; otherwise, the third type of abnormal target acquisition point is deleted. Therefore, if an existing close-up shooting point can cover the new abnormal area, no new abnormal target acquisition point is added for that abnormal area; if an existing close-up shooting point cannot cover the new abnormal area, then a new abnormal target acquisition point is added for that abnormal area. This reduces the number of repeated shots of the same abnormal local area in the images acquired during subsequent inspections.

[0108] Furthermore, since the equipment racks within the cabinet are generally fixed, minor displacements caused by manual maintenance will only occur in the horizontal direction. In this case, to further reduce the number of repeated images of the same abnormal local area, the following method can be used to determine the third type of abnormal target acquisition point from multiple position-change image areas generated by the S600.

[0109] The specific steps are as follows:

[0110] Based on the maximum spacing D between the center positions of multiple position-changing image regions max And L, determine the number W of the third type of abnormal target collection points. W satisfies the following condition:

[0111] Divide the line connecting the center positions of the two farthest moving image regions into W-1 segments, and use the endpoint of each segment as the displacement target acquisition point.

[0112] The coordinates of the center of the observation hole in the equivalent observation plane of the cabinet door that is closest to the coordinates of the displacement target acquisition point are used as the coordinates of the acquisition point corresponding to the third type of abnormal target.

[0113] Slight horizontal misalignment (e.g., about 1-2 cm) can cause the indicator light position to shift from its original position. After pixel comparison processing, this results in a relatively dense array of horizontally arranged positional change image areas within the displacement region. If each positional change image area is identified as a third-type anomalous target acquisition point, it will inevitably lead to an overly dense concentration of anomalous target acquisition points, resulting in repeated image acquisition of the same area. In this embodiment, a large field of view radius L is used to evenly divide the maximum displacement distance of the entire offset interval, and the endpoints of each segment are used as displacement target acquisition points. This not only significantly reduces the number of anomalous target acquisition points but also ensures that the distance between any two adjacent third-type anomalous target acquisition points does not exceed the field of view radius L of camera device 1, thereby guaranteeing the comprehensiveness of image acquisition for the positional change area.

[0114] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0115] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0116] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0117] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuits,” “modules,” or “systems.”

[0118] An electronic device according to this embodiment of the invention. The electronic device is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the invention.

[0119] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0120] The memory stores program code that can be executed by a processor, causing the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of the present invention.

[0121] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0122] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0123] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0124] The electronic device can also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules can 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.

[0125] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0126] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0127] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0128] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0129] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0130] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0131] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0132] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0133] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for obtaining rack status information, characterized in that, The method includes the following steps: Based on the target cabinet door closing image collected by the camera equipment in the inspection area, the world coordinates corresponding to the center pixel position of each auxiliary positioning sticker in the target cabinet door closing image are obtained; one of the auxiliary positioning sticker images includes a QR code, which stores the world coordinates corresponding to the preset center position of each auxiliary positioning sticker, and the secondary displacement information corresponding to two adjacent nodes in the preset camera inspection path. The nodes in the preset camera inspection path include the initial target acquisition point of the camera device and the abnormal target acquisition point corresponding to the abnormal area in the initial acquired image. The lens of the camera device located at the abnormal target acquisition point is positioned at the corresponding observation hole on the cabinet door. The distance between the abnormal target acquisition point and the plane where the cabinet door is located is less than the distance between the initial target acquisition point and the plane where the cabinet door is located. The abnormal target acquisition point is used to acquire a partial status information image of the cabinet. The initial target acquisition point is used to acquire a full status information image of the cabinet. The abnormal area includes the image area where indicator lights are obscured. Based on the difference between the world coordinates corresponding to the center pixel position of each auxiliary positioning patch and the world coordinates corresponding to the preset center position, the primary displacement information between the current position of the camera device and the initial target acquisition point is generated. The primary displacement information and secondary displacement information are used to determine the adjustment increment of each position adjustment axis in the multi-axis adjustment assembly corresponding to the camera device. Based on the order of the nodes to be reached in the preset camera inspection path according to the primary displacement information and secondary displacement information, the camera equipment is controlled to move sequentially, and the status information map of the corresponding area of ​​the cabinet is collected after each displacement information is executed.

2. The method according to claim 1, characterized in that, The abnormal target acquisition points corresponding to the abnormal regions in the initial acquired image are obtained according to the following steps: The camera device is controlled to acquire the open and closed state images of the target cabinet at the initial target acquisition point. The open and closed state images are segmented into binary images to generate open and closed state images respectively. The pixel value of the target image area corresponding to the indicator light in the binary image is 0, and the pixel value of the background image area is 255. Using the binary image of the open state as a mask for the closed state image, the fill coefficient corresponding to the mask area of ​​each indicator light in the binary image of the open state is obtained; wherein, the fill coefficient Gn corresponding to the mask area of ​​the nth indicator light satisfies the following condition: Gn=G z n / G m n ; Among them, G z n Let G be the area of ​​the indicator light image region in the closed state diagram, within the mask region of the nth indicator light in the open state binary diagram; m n The image area of ​​the mask region for the nth indicator light in the binary image of the open door state; If any indicator light mask area in the binary image of the open state has a fill coefficient less than the fill threshold, then the world coordinates corresponding to the center of the indicator light mask area are taken as the coordinates of the first type of abnormal area. The coordinates of the center of the observation hole in the equivalent observation plane of the cabinet door that is closest to the coordinates of the first type of abnormal area are taken as the coordinates of the collection point of the first type of abnormal target; the equivalent observation plane of the cabinet door is set parallel to and spaced apart from the cabinet door.

3. The method according to claim 2, characterized in that, The abnormal area also includes a false indicator light image area formed by light leakage from scattered light; After generating the binary image of the open state and the binary image of the closed state, the method further includes: The closed state binary image is used as a mask for the open state image. If there is no indicator light image in any indicator light mask area in the closed state binary image, the world coordinates corresponding to the center of the indicator light image closest to the indicator light mask area in the open state image are used as the coordinates of the second type of abnormal area. The coordinates of the center of the observation hole that is closest to the coordinates of the second type of anomaly area in the equivalent observation plane of the cabinet door are taken as the coordinates of the collection point corresponding to the second type of anomaly target.

4. The method according to claim 1, characterized in that, The QR code also stores the location coordinates of the initial target collection point and the abnormal target collection point. The method further includes: Based on the nearest neighbor algorithm, path planning is performed on the initial target acquisition point and abnormal target acquisition point to generate the preset camera inspection path.

5. The method according to claim 4, characterized in that, The QR code also stores a binary image of the cabinet's updated door-closing state corresponding to the previous update cycle, and the method further includes: If an update command is received, the camera device is controlled to acquire the target cabinet door closing image at the initial target acquisition point at the current update time. The target rack door-closed image collected at the current update time is processed by image region segmentation to generate an updated door-closed state binary image corresponding to the current update time; in the updated door-closed state binary image corresponding to the current update time, the pixel value of the target image region corresponding to the indicator light is 0, and the pixel value of the background image region is 255. The binary image of the updated door-closing state corresponding to the current update time of the cabinet is compared with the binary image of the updated door-closing state corresponding to the previous update cycle. At least one positional image region with pixel differences between the binary image of the updated door-closing state corresponding to the current update time and the binary image of the updated door-closing state corresponding to the previous update cycle is generated. The coordinates of the center of the observation hole that is closest to the center coordinates of the image area of ​​position change in the equivalent observation plane of the cabinet door are used as the coordinates of the acquisition point corresponding to the third type of abnormal target.

6. The method according to claim 5, characterized in that, The pixel comparison process includes: Align the binary image of the update closing state corresponding to the current update time with the binary image of the update closing state corresponding to the previous update cycle. The two images are compared pixel by pixel to generate the image region with positional change; the pixel-by-pixel comparison satisfies the following conditions: Among them, diff (x,y) This is the pixel value obtained by comparing two pixels at pixel coordinates (x, y); imgD (x,y) This refers to the pixel value of the pixel at coordinates (x, y) in the binary image of the updated gate closing state at the current update time; imgS (x,y) This represents the pixel value of the pixel with coordinates (x, y) in the binary image of the updated gated state corresponding to the previous update cycle.

7. The method according to claim 5, characterized in that, After generating the coordinates corresponding to the collection points of the third type of abnormal target, the method further includes: If the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or the abnormal target acquisition point is greater than the field of view radius of the camera device, then the third type of abnormal target acquisition point is determined as a new abnormal target acquisition point; The field-of-view radius L of the camera device satisfies the following condition: Where H is the distance between the camera lens and the indicator light inside the cabinet according to the equivalent plane, and FOV is the field of view of the camera lens; Based on the updated initial target acquisition points and abnormal target acquisition points, a new preset camera inspection path is generated.

8. The method according to claim 7, characterized in that, After generating the coordinates corresponding to the collection points of the third type of abnormal target, the method further includes: If the minimum distance between the third type of abnormal target acquisition point and the initial target acquisition point or the abnormal target acquisition point is less than the field of view radius of the camera device, then the third type of abnormal target acquisition point will be deleted.

9. A non-transitory computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a cabinet status information acquisition method as described in any one of claims 1 to 8.

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, it implements a cabinet status information acquisition method as described in any one of claims 1 to 8.

Images