Method, device and system for detecting internal space of cabinet

Abstract

The embodiment of the present application provides a method, device and system for detecting the internal space of a cabinet, which can be used in the field of artificial intelligence technology. The method includes: determining the type and number of space identification parts in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, each space identification part is set on the outer wall of the target cabinet so that all space identification parts on the target cabinet are included in the corresponding target cabinet image, and different types of space identification parts are used to represent the different space sizes occupied by each electronic device in the target cabinet; according to the preset internal complete space of the target cabinet, the type and number of space identification parts in the target cabinet image, determine the current remaining available space of the target cabinet. The present application can effectively improve the automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet, and can effectively reduce the number and cost of hardware deployment in the process of detecting the internal space of the cabinet.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, in particular to the field of artificial intelligence technology, and specifically to a method, device and system for detecting the internal space of a cabinet. Background Art

[0002] At present, data centers carry a large number of IT equipment to support system operation, such as servers, open storage and network equipment. Combined with the characteristics of cloud environment and distributed architecture, most IT equipment is mainly rack-mounted equipment, deployed in cabinets such as dedicated 19-inch IT cabinets. With the rapid development of IT technology today, IT equipment in data centers has shown an explosive growth trend, which has brought unprecedented challenges to various resource management tasks in data centers. Cabinet space resource management is one of the main tasks of data center management. Operation and maintenance personnel need to fully understand the cabinet space data and trends of the data center to maximize the use of high-cost data center infrastructure.

[0003] At present, data center operation and maintenance personnel mostly record cabinet space resource data manually, and then manually match and calculate the appropriate deployment conditions by combining data such as electrical power and air conditioning cooling capacity. This method has exposed the shortcomings of poor timeliness and accuracy, and also greatly wastes precious human resource costs. In order to replace the manual detection method, the existing cabinet space detection method mostly uses RFID technology or infrared technology to achieve, which requires the deployment of detection devices and gateways and other equipment in the cabinet, and obtains equipment location information through wired or wireless methods to calculate the used and remaining space in the IT cabinet. However, this method requires the deployment of more hardware, and if the data center is large, it will incur a lot of costs.

[0004] That is to say, no matter which of the above cabinet space detection methods is used, it is impossible to simultaneously meet the detection requirements of cabinet space detection such as high efficiency, accuracy, automation, less hardware deployment and low cost. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a method, device and system for detecting the internal space of a cabinet, which can effectively improve the degree of automation, efficiency and accuracy of obtaining the space occupied by each electronic device in the target cabinet, and can effectively reduce the number and cost of hardware deployment in the process of detecting the internal space of the cabinet.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for detecting an internal space of a cabinet, comprising:

[0008] Determine the type and quantity of space identification members in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification members is arranged on the outer wall of the target cabinet so that all of the space identification members on the target cabinet are included in the corresponding target cabinet image, and different types of space identification members are respectively used to represent different space sizes occupied by each electronic device in the target cabinet;

[0009] The current remaining available space of the target cabinet is determined according to the preset complete internal space of the target cabinet and the types and quantities of the space identification components in the target cabinet image.

[0010] Furthermore, the types of the space identification elements are distinguished by different shapes;

[0011] Correspondingly, the method of determining the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method includes:

[0012] Intercepting effective areas corresponding to the space identification elements in the target cabinet image;

[0013] Based on a preset Hough transform method, feature detection is performed on each of the effective areas to obtain the type and quantity of the space identification parts in the target cabinet image corresponding to the target cabinet.

[0014] Furthermore, the determining the type and quantity of the space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method includes:

[0015] Inputting the target cabinet image into a preset image recognition model for identifying space identification components, so that the image recognition model outputs the type and quantity of space identification components in the target cabinet image;

[0016] The image recognition model is pre-trained based on a plurality of historical cabinet images with labels, and the labels are used to indicate the type and quantity of space identification components in the corresponding historical cabinet images.

[0017] Further, the determining the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the type and quantity of the space identification components in the target cabinet image includes:

[0018] Retrieving a pre-stored comparison table of the internal complete space dimensions and identification space of the target cabinet, wherein the identification space comparison table is used to store the correspondence between the type of each space identification component and the occupied cabinet space dimensions;

[0019] Determine the total occupied space size of the target cabinet occupied by the electronic equipment according to the identification element space comparison table and the types and quantities of the space identification elements in the target cabinet image;

[0020] Based on the internal complete space size of the target cabinet and the total occupied space size of the target cabinet occupied by electronic equipment, the current remaining available space of the target cabinet is determined.

[0021] Furthermore, before determining the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on the preset image recognition method, the method further includes:

[0022] Receiving a cabinet image captured by an image acquisition device, wherein the cabinet image includes at least one complete cabinet;

[0023] Acquire a valid image capture area of ​​at least one cabinet from the cabinet image;

[0024] A cabinet is selected as a target cabinet to be detected currently, and a valid image capture area of ​​the target cabinet is determined as a corresponding target cabinet image.

[0025] Furthermore, it also includes:

[0026] The current remaining available space of the target cabinet is visually displayed, and / or the current remaining available space of the target cabinet is sent to the corresponding client device.

[0027] Furthermore, the space identification element is a magnetic sticker.

[0028] In a second aspect, the present application provides a cabinet internal space detection device, comprising:

[0029] An image recognition module, used to determine the type and quantity of space identification members in a target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification members is arranged on an outer wall of the target cabinet so that all of the space identification members on the target cabinet are included in the corresponding target cabinet image, and different types of space identification members are used to represent different space sizes occupied by each electronic device in the target cabinet;

[0030] The space detection module is used to determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the types and quantities of the space identification components in the target cabinet image.

[0031] In a third aspect, the present application provides a cabinet internal space detection system, comprising: a space identification member for being arranged on the outer wall of the target cabinet, at least one image acquisition device, and a cabinet internal space detection device for implementing the cabinet internal space detection method;

[0032] The image acquisition device is arranged within the space where the cabinet is located, and each of the image acquisition devices is used to acquire a cabinet image of at least one cabinet;

[0033] The image acquisition device is communicatively connected to the cabinet internal space detection device, and is used to send the acquired cabinet image of at least one cabinet to the cabinet internal space detection device, so that the cabinet internal space detection device obtains a target cabinet image corresponding to the current target cabinet based on the cabinet image of at least one cabinet.

[0034] In a fourth aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the cabinet internal space detection method when executing the program.

[0035] In a fifth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the cabinet internal space detection method when executed by a processor.

[0036] It can be seen from the above technical scheme that the present application provides a method, device and system for detecting the internal space of a cabinet, the method comprising: determining the type and number of space identification components in a target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification components is arranged on the outer wall of the target cabinet so that all of the space identification components on the target cabinet are included in the corresponding target cabinet image, and different types of space identification components are respectively used to represent different space sizes occupied by each electronic device in the target cabinet; determining the current remaining available space of the target cabinet according to the preset internal complete space of the target cabinet and the type and number of space identification components in the target cabinet image, by arranging on the outer wall of the cabinet each of the space identification components respectively used to represent different space sizes occupied by each electronic device in the target cabinet The system can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet. At the same time, since only the space identification parts are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the process of detecting the internal space of the cabinet. By determining the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the type and number of space identification parts in the target cabinet image, the efficiency and reliability of the internal space detection of the cabinet can be further improved, and then the use of the cabinet can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and the accuracy and timeliness of electronic equipment management can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 It is a schematic diagram of the interaction between the cabinet internal space detection device and other client devices and image acquisition devices in an embodiment of the present application.

[0039] Figure 2 It is a first flow chart of the cabinet internal space detection method in the embodiment of the present application.

[0040] Figure 3 It is a second flow chart of the cabinet internal space detection method in the embodiment of the present application.

[0041] Figure 4 This is a third flow chart of the cabinet internal space detection method in the embodiment of the present application.

[0042] Figure 5 This is a fourth flow chart of the cabinet internal space detection method in the embodiment of the present application.

[0043] Figure 6 This is a fifth flow chart of the cabinet internal space detection method in the embodiment of the present application.

[0044] Figure 7 This is a sixth flow chart of the cabinet internal space detection method in the embodiment of the present application.

[0045] Figure 8 It is a structural schematic diagram of the cabinet internal space detection device in an embodiment of the present application.

[0046] Fig. 9 It is a structural schematic diagram of the cabinet internal space detection system in an embodiment of the present application.

[0047] Fig.10 This is a structural block diagram of a data center cabinet space detection system provided in an application example of this application.

[0048] Fig.11 It is a unit structure diagram within the space identification setting module 1 in the data center cabinet space detection system provided in the application example of the present application.

[0049] Fig.12 It is a unit structure diagram of the environmental preprocessing module 2 in the data center cabinet space detection system provided in the application example of the present application.

[0050] Fig.13 It is a unit structure diagram of the U-position space statistics module 3 in the data center cabinet space detection system provided in the application example of the present application.

[0051] Fig.14 It is a unit structure diagram of the information display module 4 in the data center cabinet space detection system provided in the application example of the present application.

[0052] Fig.15 This is an example diagram of the recognition results of the effective imaging area in the data center cabinet space detection method provided in the application example of the present application.

[0053] Fig.16 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] It should be noted that the cabinet internal space detection method, device and system disclosed in the present application can be used in the fields of artificial intelligence technology and data center operation and maintenance technology, and can also be used in any field other than the fields of artificial intelligence technology and data center operation and maintenance technology. The application field of the cabinet internal space detection method, device and system disclosed in the present application is not limited.

[0056] Existing cabinet space detection methods cannot simultaneously meet the detection requirements of cabinet space detection such as high efficiency, accuracy, automation, less hardware deployment and low cost. The embodiments of the present application respectively provide a cabinet internal space detection method, a cabinet internal space detection device, a cabinet internal space detection system, and an electronic device computer-readable storage medium, which determine the type and number of space identification parts in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification parts is arranged on the outer wall of the target cabinet so that all the space identification parts on the target cabinet are included in the corresponding target cabinet image, and different types of space identification parts are respectively used to represent different space sizes occupied by each electronic device in the target cabinet; according to the preset internal complete space of the target cabinet, the type and number of space identification parts in the target cabinet image, the current remaining available space of the target cabinet is determined, and by setting a space identification part on the outer wall of the cabinet The space identification members are respectively used to represent the different space sizes occupied by the electronic devices in the target cabinet, and the type and number of space identification members in the target cabinet image corresponding to the current target cabinet are determined based on a preset image recognition method. This can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet. At the same time, since only space identification members are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the process of detecting the internal space of the cabinet. By determining the current remaining available space of the target cabinet based on the preset complete internal space of the target cabinet and the type and number of space identification members in the target cabinet image, the efficiency and reliability of the internal space detection of the cabinet can be further improved, and then the use of the cabinet can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and improves the accuracy and timeliness of electronic equipment management.

[0057] In one or more embodiments of the present application, the cabinet or IT cabinet refers to an independent or self-supporting housing for accommodating electrical or electronic equipment. The cabinet is generally equipped with doors, detachable or non-detachable side panels and back panels. The cabinet is an indispensable component of electrical equipment and is the carrier of electrical control equipment. It is generally made of cold-rolled steel plates or alloys. It can provide waterproof, dustproof, anti-electromagnetic interference and other protection for stored equipment. Cabinets are generally divided into server cabinets, network cabinets, console cabinets, etc.

[0058] In one or more embodiments of the present application, the U in the U-space is a unit representing the external dimensions of IT equipment such as servers, and is an abbreviation of unit. The detailed dimensions are determined by the American Electronics Industry Association (EIA). The reason for specifying the size of the server is to keep the server at an appropriate size so that it can be placed on an iron or aluminum rack. There are screw holes on the rack to fix the server so that it can be aligned with the screw holes of the server and then fixed with screws to facilitate the installation of the space required for each server. Among them, 1U is: 4.445cm, and 4U is 4 times of 1U, which is: 4.445×4=17.78cm.

[0059] In one or more embodiments of the present application, the Hough transform method or the Hough transform feature detection method is a feature extraction method used to identify features in an object, such as lines and any other shapes, such as squares, circles, and ellipses. Given an object and the type of shape to be identified, the algorithm performs voting in the parameter space to determine the shape of the object, which is determined by the local maximum in the accumulator space. By using the voting step in the Hough transform algorithm, the parameters of the graphic are found in the complex parameter space, that is, the shape of the edge can be known from the parameters.

[0060] Based on the above content, the present application also provides a cabinet internal space detection device for implementing the cabinet internal space detection method provided in one or more embodiments of the present application, and the cabinet internal space detection device can be a server, see Figure 1The cabinet internal space detection device can communicate and connect with the client device held by the technician and the image acquisition device used to collect the cabinet image of the cabinet by itself or through a third-party server, so as to receive the cabinet internal space detection instructions sent by the client devices corresponding to each operation and maintenance personnel, so that the cabinet internal space detection device executes the cabinet internal space detection method mentioned in one or more embodiments of the present application based on the cabinet internal space detection instructions, and after determining the current remaining available space of the target cabinet according to the preset internal complete space of the target cabinet and the type and number of space identification parts in the target cabinet image, a result notification message used to represent the current remaining available space of the target cabinet is sent to the client device held by the operation and maintenance personnel or is visualized on a preset display screen. The specific method of visualization display can be: the user develops an information display system by himself, establishes a computer room or cabinet model in the display system, synchronizes the complete space of the IT cabinet (mostly 42U) with the occupied space of the electronic equipment in the cabinet calculated by the camera, and displays the used space and remaining space information of the computer room and cabinet in the information display system.

[0061] It is understandable that the client device may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0062] In another practical application scenario, the part of the cabinet internal space detection device that performs the cabinet internal space detection can be executed in the server as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor for specific processing of the cabinet internal space detection.

[0063] In a third practical application scenario, the aforementioned cabinet internal space detection device can also be a functional module in the architecture of a management system or platform of the cabinet holding company, etc.

[0064] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0065] The server and the client device may communicate with each other using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocols may include, for example, TCP / IP, UDP / IP, HTTP, HTTPS, etc. Of course, the network protocols may also include, for example, RPC (Remote Procedure Call Protocol) and REST (Representational State Transfer) protocols used on top of the above protocols.

[0066] The details are described in detail through the following embodiments and application examples.

[0067] In order to solve the problem that the existing cabinet space detection methods cannot simultaneously meet the detection requirements of cabinet space detection such as high efficiency, accuracy, automation, less hardware deployment and low cost, the present application provides an embodiment of a cabinet internal space detection method, see Figure 2 The cabinet internal space detection method performed by the cabinet internal space detection device specifically includes the following contents:

[0068] Step 100: Determine the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification components is arranged on the outer wall of the target cabinet so that all of the space identification components on the target cabinet are included in the corresponding target cabinet image, and different types of space identification components are respectively used to represent different space sizes occupied by each electronic device in the target cabinet.

[0069] In step 100, each of the space identification elements is disposed on the outer wall of the target cabinet so that all the space identification elements on the target cabinet are included in the corresponding target cabinet image. The specific description is as follows:

[0070] (1) Each of the space identification members can be set on the upper side, front side, rear side, left side, right side, etc. of the target cabinet, but all of the space identification members need to be set on the same side outer wall so that the image acquisition device can capture all of the space identification members on the target cabinet in one imaging with respect to the side outer wall; in particular, these space identification members can be set on the rear side of the target cabinet, that is, on the rear door, because the rear door is less frequently used, and thus the setting reliability of the space identification members can be effectively improved.

[0071] (2) Each of the space identification members can be dispersedly set on different side outer walls of the target cabinet, but it is necessary to select three or two adjacent outer walls for setting so that the image acquisition device can capture all the space identification members on the target cabinet in one imaging. Although this setting method improves the convenience of setting the space identification members, it is less reliable than the setting method in (1).

[0072] It can be understood that the image acquisition device used to acquire the target cabinet image corresponding to the current target cabinet in step 100 can be an image acquisition device such as a camera. The image acquisition device needs to be in the same area as the target cabinet and be arranged relative to the side outer wall of the target cabinet where the space identification parts are provided. In other words, the image acquisition device needs to be able to acquire all the space identification parts on the target cabinet in one imaging.

[0073] At the same time, in order to further reduce the hardware setting complexity and cost of the cabinet internal space detection process, the original monitoring probes in the indoor space where the cabinet is located can be used to collect the target cabinet image corresponding to the target cabinet, etc.

[0074] In addition, in order to further reduce the hardware setup complexity and cost of the cabinet internal space detection process, the embodiment of the present application can be applied to the situation where one camera collects the image of one cabinet, and can also be applied to the situation where one camera collects multiple cabinets and performs single cabinet cropping, that is, one camera can be used to collect multiple complete cabinets in one image, and then the cabinet internal space detection device will crop the image according to the preset detection degree to obtain the effective image capture area of ​​multiple cabinets, and select a cabinet that needs to be processed currently as the target cabinet, and use the effective image capture area of ​​the cabinet as the target cabinet image. Therefore, the number and position of image acquisition devices such as cameras can be set in the cabinet area according to the equipment parameters of the image acquisition device, the actual cost requirements and the application scenario, so as to further reduce the hardware setup cost of the cabinet internal space detection process and ensure the accuracy of the cabinet internal space detection results.

[0075] Step 200: Determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the types and quantities of space identification components in the target cabinet image.

[0076] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet by setting each space identification member on the outer wall of the cabinet, which is respectively used to represent the different space sizes occupied by each electronic device in the target cabinet, and determining the type and number of space identification members in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method. At the same time, since only space identification members are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the cabinet internal space detection process. By determining the current remaining available space of the target cabinet based on the preset complete internal space of the target cabinet and the type and number of space identification members in the target cabinet image, the efficiency and reliability of the cabinet internal space detection can be further improved, and then the cabinet usage status can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and improves the accuracy and timeliness of electronic equipment management.

[0077] In order to improve the convenience and accuracy of the cabinet internal space detection, in an embodiment of the cabinet internal space detection method provided in the present application, the types of the space identification parts are distinguished by different shapes; see Figure 3 An implementation of step 100 in the cabinet internal space detection method specifically includes the following contents:

[0078] Step 110: intercepting effective areas corresponding to the respective space identification elements in the target cabinet image.

[0079] In an example of step 110, the specific method of intercepting the effective areas corresponding to each of the space identification components in the target cabinet image can be: the cabinet internal space detection device can send the target cabinet image to the client device held by the operation and maintenance personnel, and after the operation and maintenance personnel select the effective areas corresponding to each of the space identification components on their client device, the cabinet internal space detection device receives the result data of the above-mentioned selected effective areas corresponding to each of the space identification components sent by the client device.

[0080] Although the above method can ensure the effectiveness of the effective areas corresponding to each of the space identification components, it still requires manual participation. In order to further improve the efficiency and automation of intercepting the effective areas corresponding to each of the space identification components, in another example of step 110, the specific method of intercepting the effective areas corresponding to each of the space identification components in the target cabinet image can be: since each of the space identification components can be set to a component with a different color from the outer wall of the target cabinet, the cabinet internal space detection device can be based on a preset color distinction method and edge recognition method, by distinguishing the color of the outer wall of the target cabinet and the space identification component, to select and crop the effective area where each space identification component in the target cabinet image is located.

[0081] Step 120: Perform feature detection on each of the effective areas based on a preset Hough transform method to obtain the type and quantity of space identification components in the target cabinet image corresponding to the target cabinet.

[0082] In step 120, a specific example of feature detection of each of the valid areas based on a preset Hough transform method is as follows: if the types of the above-mentioned space identification parts are distinguished by shape, such as square identification parts, circular identification parts and triangular identification parts, then the cabinet internal space detection device can use the Hough transform feature to detect whether there are squares in each valid area in the statistical screen one by one, and summarize and save the number of squares in the valid area of ​​a single cabinet; the cabinet internal space detection device can use the Hough transform feature to detect the number of straight lines in each valid area in the statistical screen one by one. If the number of straight lines is three, the figure in the statistical area is determined to be a triangle, and the number of triangles in the valid area of ​​a single cabinet is summarized and saved; the cabinet internal space detection device can use the Hough transform feature to detect the number of circles in each valid area in the statistical screen one by one, and summarize and save the number of circles in the valid area of ​​a single cabinet.

[0083] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application, if the type of the space identification parts are distinguished by different shapes, can perform feature detection on each of the effective areas based on the preset Hough transform method to obtain the type and quantity of the space identification parts in the target cabinet image corresponding to the target cabinet, thereby effectively improving the convenience and accuracy of the cabinet internal space detection, and at the same time further improving the efficiency of the cabinet internal space detection.

[0084] In order to further improve the automation and intelligence of the cabinet internal space detection, an embodiment of the cabinet internal space detection method provided in the present application is as follows: Figure 4 Another implementation of step 100 in the cabinet internal space detection method specifically includes the following contents:

[0085] Step 130: Input the target cabinet image into a preset image recognition model for identifying space identification components, so that the image recognition model outputs the type and quantity of space identification components in the target cabinet image; wherein the image recognition model is pre-trained based on multiple historical cabinet images with labels, and the labels are used to represent the type and quantity of space identification components in the corresponding historical cabinet images.

[0086] In step 130, the image recognition model may adopt an existing machine learning model capable of image recognition, such as a convolutional neural network (CNN) or a classic image recognition model (Densenet), and may be pre-trained in the following manner:

[0087] First, a plurality of historical cabinet images with labels are obtained, wherein the labels are used to indicate the type and quantity of space identification components in the corresponding historical cabinet images;

[0088] Then, these labeled historical cabinet images are divided into a training set and a validation set, and the training set is used to perform offline training on the convolutional neural network (CNN) to obtain an initial image recognition model for identifying space identification parts.

[0089] The validation set is then used to verify and adjust the initial image recognition model, and finally an image recognition model that can be used online to identify spatial identification parts is formed.

[0090] It can be understood that when the type of the spatial identification parts is not distinguished by different shapes, only the image recognition model used to identify the spatial identification parts can be used to identify the type and quantity of the spatial identification parts. When the type of the spatial identification parts is distinguished by different shapes, the Hough transform method and / or the image recognition model can be used to identify the type and quantity of the spatial identification parts.

[0091] When the Hough transform method and the image recognition model are selected to identify the type and quantity of the space identification parts, the recognition results of the type and quantity of the space identification parts of the Hough transform method and the image recognition model can be compared to see if they are the same. If they are the same, the recognition results are directly output or displayed in the preset device; if they are not the same, a notification message for informing the client device of the operation and maintenance personnel that the recognition results of the type and quantity of the space identification parts are different can be sent, and the image acquisition device can be controlled to re-acquire the image of the target cabinet, and the effective image interception area of ​​the entire cabinet is performed on the image to generate the target cabinet image of the target cabinet, and then the Hough transform method and / or the image recognition model are selected again to identify the type and quantity of the space identification parts, until the recognition results of the type and quantity of the space identification parts of the Hough transform method and the image recognition model are the same or the preset number of cycles are reached. Then, the recognition accuracy and effectiveness of the type and quantity of the space identification parts in the target cabinet image can be further improved, thereby providing a more accurate data basis for the detection of the internal space of the cabinet, so as to improve the detection accuracy of the internal space of the cabinet.

[0092] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application can input the target cabinet image into a preset image recognition model for identifying space identification parts, regardless of the form in which the space identification parts are distinguished, so that the image recognition model outputs the type and quantity of space identification parts in the target cabinet image, thereby effectively improving the efficiency and accuracy of the cabinet internal space detection, and can further improve the degree of automation and intelligence of the cabinet internal space detection.

[0093] In order to further improve the convenience and accuracy of determining the current remaining available space of the target cabinet, an embodiment of the cabinet internal space detection method provided in the present application is as follows: Figure 5 , step 200 in the cabinet internal space detection method specifically includes the following contents:

[0094] Step 210: Retrieve a pre-stored comparison table of the internal complete space dimensions and identification component space of the target cabinet, wherein the identification component space comparison table is used to store the correspondence between the type of each of the space identification components and the occupied cabinet space dimensions.

[0095] Step 220: Determine the total occupied space size of the target cabinet occupied by electronic equipment based on the identification element space comparison table and the types and quantities of the space identification elements in the target cabinet image.

[0096] Step 230: Determine the current remaining available space of the target cabinet based on the internal complete space size of the target cabinet and the total occupied space size of the target cabinet occupied by electronic equipment.

[0097] Specifically, assuming that a total of four servers are deployed in the cabinet, there should be four magnetic sheets in the space identification area. The effective imaging area is from area 1 to area 4. The Hough transform feature detection is used to calculate the shapes of the magnetic sheets contained in the four areas. There is a circular magnetic sheet in area 1, a square magnetic sheet in area 2, a triangular magnetic sheet in area 3, and a circular magnetic sheet in area 4. According to the square corresponding to 1U, the triangle corresponding to 2U, and the circle corresponding to 4U, the calculation shows that the usable space in the cabinet is 4U+1U+2U+4U=11U. Since the cabinet used is a standard cabinet, the available space is 42U. Subtracting the used space, the remaining space of the cabinet is 42U-11U=31U.

[0098] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application, by calling the pre-stored internal complete space size and identification space comparison table of the target cabinet, wherein the identification space comparison table is used to store the correspondence between the type of each space identification part and the occupied cabinet space size, can effectively improve the efficiency of determining the current remaining available space of the target cabinet, and can further improve the convenience and accuracy of determining the current remaining available space of the target cabinet.

[0099] In order to further reduce the hardware setting cost of the cabinet internal space detection process, an embodiment of the cabinet internal space detection method provided in the present application is shown in FIG. Figure 6 , the cabinet internal space detection method further specifically includes the following contents before step 100:

[0100] Step 010: Receive a cabinet image captured by an image acquisition device, wherein the cabinet image includes at least one complete cabinet.

[0101] Step 020: Acquire a valid image capture area of ​​at least one cabinet from the cabinet image.

[0102] Step 030: Select a cabinet as the target cabinet to be detected currently, and determine the effective image capture area of ​​the target cabinet as the corresponding target cabinet image.

[0103] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application, by receiving the cabinet image captured by the image acquisition device, obtains the effective image capture area of ​​at least one cabinet from the cabinet image. It can be applicable to the situation where one camera captures the image of one cabinet, and can also be applicable to the situation where one camera captures multiple cabinets and performs single cabinet cropping. Therefore, the number and position of image acquisition devices such as cameras can be set in the area where the cabinet is located according to the equipment parameters of the image acquisition device, actual cost requirements and application scenarios, thereby further reducing the hardware setting cost of the cabinet internal space detection process and ensuring the accuracy of the cabinet internal space detection results.

[0104] In order to enable the operation and maintenance personnel to quickly and intuitively know the current remaining available space of the target cabinet, an embodiment of the cabinet internal space detection method provided in the present application is as follows: Figure 7 , the cabinet internal space detection method further specifically includes the following contents after step 200:

[0105] Step 300: Visually display the current remaining available space of the target cabinet, and / or send the current remaining available space of the target cabinet to the corresponding client device.

[0106] In step 300, the cabinet internal space detection device can specifically match the camera position (number), the number of occupied U positions of IT equipment in a single cabinet, and the number of remaining U positions in a single cabinet, and transmit them to the U position information display unit through the network. The U position display unit is developed by the data center manager himself or connected with a third-party management system. A 2D or 3D computer room (cabinet) model is established in the display unit. The cabinet number needs to be matched with the corresponding camera and data to ensure that the number of used U positions in a single IT cabinet and the number of remaining U positions in a single IT cabinet are correct, and the cabinet U position data update strategy is set. Information such as the total number of used U positions in the computer room and the total number of remaining U positions can also be displayed.

[0107] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application can enable the operation and maintenance personnel to quickly and intuitively know the current remaining available space of the target cabinet by visually displaying the current remaining available space of the target cabinet, and / or sending the current remaining available space of the target cabinet to the corresponding client device, thereby effectively improving the user experience of the operation and maintenance personnel.

[0108] In order to make the space identification member reusable, in an embodiment of the cabinet internal space detection method provided in the present application, the space identification member in the cabinet internal space detection method is a magnetic sticker.

[0109] For example, square, triangular, and circular shape features are used to match the height of mainstream IT equipment, such as 1U, 2U, and 4U. Set the corresponding space identification parts according to the deployment of the equipment inside the cabinet. After the space identification parts are fixed, the position should not be changed as much as possible. After the IT equipment is put on the shelf, the rear operating space in the cabinet is limited during the subsequent inspection and maintenance process, so the space identification parts are fixed on the rear door of the cabinet. The magnetic stickers are customized as square, triangular, and circular solid devices. The outer frame has a clear shape frame. The color should avoid using black or white, which is the same color as the cabinet. The specific U number is marked on the surface of the magnetic sticker. The area should not be too large or too small. It should be flexibly adjusted according to the actual deployment conditions of the cabinet and adsorbed on the rear door of the cabinet.

[0110] From the above description, it can be seen that the cabinet internal space detection method provided in the embodiment of the present application, by setting the space identification parts as magnetic stickers, makes the space identification parts reusable, and can effectively improve the convenience of setting and replacing the space identification parts, and reduce the setting cost of the space identification parts.

[0111] From the software level, in order to solve the problem that the existing cabinet space detection methods cannot simultaneously meet the detection requirements of cabinet space detection such as high efficiency, accuracy, automation, less hardware deployment and low cost, the present application provides an embodiment of a cabinet internal space detection device for executing all or part of the contents of the cabinet internal space detection method, see Figure 8 The cabinet internal space detection device specifically includes the following contents:

[0112] The image recognition module 10 is used to determine the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification components is arranged on the outer wall of the target cabinet so that all of the space identification components on the target cabinet are included in the corresponding target cabinet image, and different types of space identification components are used to represent different space sizes occupied by each electronic device in the target cabinet.

[0113] The space detection module 20 is used to determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the types and quantities of the space identification components in the target cabinet image.

[0114] The embodiments of the cabinet internal space detection device provided in the present application can be specifically used to execute the processing flow of the embodiments of the cabinet internal space detection method in the above embodiments. Its functions are not repeated here, and reference can be made to the detailed description of the above method embodiments.

[0115] From the above description, it can be seen that the cabinet internal space detection device provided in the embodiment of the present application can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet by setting each space identification member on the outer wall of the cabinet, which is respectively used to represent the different space sizes occupied by each electronic device in the target cabinet, and determining the type and number of space identification members in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method. At the same time, since only space identification members are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the cabinet internal space detection process. By determining the current remaining available space of the target cabinet based on the preset internal complete space of the target cabinet and the type and number of space identification members in the target cabinet image, the efficiency and reliability of the cabinet internal space detection can be further improved, and then the cabinet usage status can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and improves the accuracy and timeliness of electronic equipment management.

[0116] Based on the above-mentioned embodiments of the cabinet internal space detection device, in order to solve the problem that the existing cabinet space detection methods cannot simultaneously meet the detection requirements of cabinet space detection such as high efficiency, accuracy, automation, less hardware deployment and low cost, the present application provides an embodiment of a cabinet internal space detection system including a cabinet internal space detection device, see Fig. 9 The cabinet internal space detection system specifically includes the following contents:

[0117] A space identification member for being arranged on the outer wall of the target cabinet, at least one image acquisition device and a cabinet internal space detection device for implementing the cabinet internal space detection method;

[0118] The image acquisition device is arranged within the space where the cabinet is located, and each of the image acquisition devices is used to acquire a cabinet image of at least one cabinet;

[0119] The image acquisition device is communicatively connected to the cabinet internal space detection device, and is used to send the acquired cabinet image of at least one cabinet to the cabinet internal space detection device, so that the cabinet internal space detection device obtains a target cabinet image corresponding to the current target cabinet based on the cabinet image of at least one cabinet.

[0120] The embodiments of the cabinet internal space detection system provided in the present application can be specifically used to execute the processing flow of the cabinet internal space detection method and / or the embodiments of the cabinet internal space detection device in the above-mentioned embodiments. Its functions are not repeated here, and reference can be made to the detailed description of the above-mentioned cabinet internal space detection method and / or the embodiments of the cabinet internal space detection device.

[0121] From the above description, it can be seen that the cabinet internal space detection system provided in the embodiment of the present application can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet by setting each space identification member on the outer wall of the cabinet, which is respectively used to represent the different space sizes occupied by each electronic device in the target cabinet, and determining the type and number of space identification members in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method. At the same time, since only space identification members are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the cabinet internal space detection process. By determining the current remaining available space of the target cabinet based on the preset internal complete space of the target cabinet and the type and number of space identification members in the target cabinet image, the efficiency and reliability of the cabinet internal space detection can be further improved, and then the cabinet usage status can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and improves the accuracy and timeliness of electronic equipment management.

[0122] In order to further illustrate this solution, this application also provides a specific application example of a cabinet internal space detection method based on a data center cabinet space detection system, which can be specifically applied in a data center, and involves the technical field of spatial data detection of IT equipment deployment in cabinets in data centers, which is an intelligent detection technology based on image recognition technology. The application example of this application is a technical method that is completely different from the current mainstream RFID and infrared detection technologies. It does not require excessive deployment of hardware equipment, greatly saves deployment budget costs, and can be deployed in any cabinet in a data center to achieve the purpose of real-time, accurate and automated detection of cabinet space.

[0123] The method in the application example of the present application is to deploy a high-definition camera and space identification elements outside the cabinet, obtain images of space identification elements in a specific area through the camera, and obtain the real-time space status of the cabinet by identifying, analyzing and calculating the space identification elements of various shape features, and transmit the cabinet space status to the information display module through the network for display.

[0124] The application example of this application consists of four parts: space identification setting module, environment preprocessing module, U-position space statistics module and information display module. Image information is obtained by setting a space identification area and a high-definition camera outside the cabinet, and then the image information is preprocessed to determine the overall range of the picture and the range of the space identification, so as to eliminate redundant information and reduce the difficulty of subsequent statistical calculations.

[0125] See also Fig.10The data center cabinet space detection system includes: space identification setting module 1, environment preprocessing module 2, U-position space statistics module 3, information display module 4, and the execution order of each module is as follows:

[0126] 1. Space identification setting module 1: The servers, open storage and network devices in the data center are mostly 1U, 2U and 4U in height. The space identification piece can be a magnetic sticker of a special shape, which is used to be magnetically attached to the metal outer wall of the cabinet and other equipment mentioned in this application; the magnetic sticker can be represented by a square, triangle, circle and other shapes, and the square, triangle and circle can represent 1U equipment, 2U equipment and 4U equipment respectively, and the space identification piece is adsorbed on a fixed position on the cabinet or any position visible to the camera, etc.

[0127] It can be understood that the shape of the magnetic stickers mentioned in the present application is not limited to the above examples, and can be set according to the size type of the electronic equipment in the cabinet. For example, if there are 5 sizes of electronic equipment in the cabinet, different shapes corresponding to the 5 types of electronic equipment need to be set respectively.

[0128] 2. Environmental preprocessing module 2: According to the installation position of the space identification parts, determine the installation and fixing position of the camera, so that the camera's imaging picture can clearly and completely cover the area where the space identification parts need to be paid attention to. After determining the installation position of the camera, through the effective area selection and imaging picture capture, the interference of redundant data information can be eliminated, and the calculation accuracy and speed of the camera can be improved.

[0129] 3. U-position space statistics module 3: Based on the screenshot of the effective video imaging screen, the space identification elements of different shapes and quantities in the effective imaging screen are counted to calculate the total occupied space in the cabinet, and transmitted to the information display module through the network.

[0130] 4. Information display module 4: Users can develop information display systems by themselves, establish computer room or cabinet models in the display system, synchronize the complete space of the IT cabinet (mostly 42U) with the occupied space of the electronic equipment in the cabinet calculated by the camera, and display the used space and remaining space information of the computer room and cabinet in the information display system.

[0131] See also Fig.11 The space identification setting module 1 includes a U-position shape determination unit 11, a cabinet position selection unit 12, and a magnetic sticker fixing unit 13, which are specifically described as follows:

[0132] (1) U-position shape determination unit 11: matches the height of mainstream IT equipment, such as 1U, 2U and 4U, through square, triangle and circular shape features.

[0133] (2) Cabinet position selection unit 12: Corresponding space identification pieces are set according to the deployment of equipment inside the cabinet. After the space identification pieces are fixed, the position is required to be kept as unchanged as possible. After the IT equipment is put on the shelf, the rear operating space in the cabinet is limited during the subsequent inspection and maintenance process. Therefore, the space identification pieces are fixed on the rear door of the cabinet.

[0134] (3) Magnetic sticker fixing unit 13: The magnetic sticker is customized into square, triangular and circular solid devices. The outer frame has a clear shape frame. The color should avoid using black or white, which is the same color as the cabinet. The specific U number is marked on the surface of the magnetic sticker. The area should not be too large or too small and should be flexibly adjusted according to the actual deployment conditions of the cabinet. It is adsorbed on the rear door of the cabinet.

[0135] See also Fig.12 The environment preprocessing module 2 includes: a camera installation position determination unit 21, an effective area selection unit 22 and an effective information interception unit 23, which are specifically described as follows:

[0136] (1) Camera installation position determination unit 21: The camera deployment position is determined according to the deployment position of the space identification parts. The imaging picture should include the complete space identification parts of a single cabinet to ensure that the imaging picture is clear. The camera position (number) should correspond to the cabinet position or number to avoid data acquisition errors in the display system.

[0137] (2) Valid area selection unit 22: To eliminate redundant data information, each spatial identification element is selected in the camera image based on a preset selection rule or manually according to the fixed position of the spatial identification element, and the position coordinate information of each spatial identification element is saved, including the upper left corner position coordinates of the valid image of each spatial identification element and the image length and width.

[0138] (3) Effective information interception unit 23: intercepts the effective imaging area according to the position coordinate information of the effective area image obtained by the effective area selection unit 22. The interception of the effective area image can reduce the difficulty of subsequent statistical calculations and eliminate invalid interference information in the picture.

[0139] See also Fig.13 The U-position space statistics module 3 includes: a square tile number statistics unit 31, a triangle tile number statistics unit 32 and a circular tile number statistics unit 33, which are specifically described as follows:

[0140] (1) Square tile number counting unit 31: corresponding to the effective image interception area of ​​the entire cabinet, using Hough transform features to detect whether there is a square in each effective area in the counting screen one by one, and the number of squares in the effective area of ​​a single cabinet is summarized and saved.

[0141] (2) Triangle tile number counting unit 32: corresponding to the effective image interception area of ​​the entire cabinet, the number of straight lines in each effective area in the picture is counted one by one using Hough transform feature detection. If the number of straight lines is three, the figure in the statistical area is determined to be a triangle, and the number of triangles in the effective area of ​​a single cabinet is summarized and saved.

[0142] (3) Circular tile number counting unit 33: corresponding to the effective image interception area of ​​the entire cabinet, the number of circles in each effective area in the picture is counted one by one using Hough transform feature detection, and the number of circles in the effective area of ​​a single cabinet is summarized and saved.

[0143] See also Fig.14 The information display module 4 includes: a cabinet U position information statistics unit 41 and a cabinet U position information display unit 42, which are specifically described as follows:

[0144] (1) Cabinet U-position information statistics unit 41: Use the effective information interception unit 23 to intercept the effective imaging area, each effective imaging area has only one magnetic attraction piece of a different shape, and corresponding to each effective imaging area, the number of magnetic attraction pieces contained in the area is calculated according to the U-position space statistics module 3.

[0145] See also Fig.15 Assuming that there are four servers deployed in the cabinet, there should be four magnetic sheets in the space identification area. The effective imaging area is from area 1 to area 4. The shapes of the magnetic sheets contained in the four areas are calculated using Hough transform feature detection. There is a circular magnetic sheet in area 1, a square magnetic sheet in area 2, a triangular magnetic sheet in area 3, and a circular magnetic sheet in area 4. According to the square corresponding to 1U, the triangle corresponding to 2U, and the circle corresponding to 4U, the calculation shows that the usable space in the cabinet is 4U+1U+2U+4U=11U. Since the cabinet used is a standard cabinet, the available space is 42U. Subtracting the usable space, the remaining space of the cabinet is 42U-11U=31U.

[0146] (2) Cabinet U-position information display unit 42: The camera position (number), the number of occupied U-positions of IT equipment in a single cabinet, and the number of remaining U-positions in a single cabinet are matched and transmitted to the U-position information display unit via the network. The U-position display unit is developed by the data center manager himself or connected with a third-party management system. A 2D or 3D computer room (cabinet) model is established in the display unit. The cabinet number needs to be matched with the corresponding camera and data to ensure that the number of used U-positions of a single IT cabinet and the number of remaining U-positions of a single IT cabinet are correct, and the cabinet U-position data update strategy is set. Information such as the total number of used U-positions and the total number of remaining U-positions in the computer room can also be displayed.

[0147] The application example of this application is a data center cabinet space detection method, which realizes the real-time capacity detection function of the data center IT cabinet through simple hardware, and can be displayed intuitively in the display system. The operation and maintenance personnel can grasp the use of the data center cabinet in real time, which is convenient and fast to carry out the subsequent deployment of IT equipment, and improve the accuracy and timeliness of IT equipment management. The main advantages of the application example of this application are:

[0148] The application example of this application solves the problem of identifying the cabinet space occupied by equipment of different brands and types in the IT cabinet. It uses a high-definition camera to identify the space identification parts in the fixed area of ​​the cabinet, calculates the real-time occupancy information of the cabinet U position, and transmits it to the information display module through the network, so as to quickly and efficiently obtain data on the space resources of the data center.

[0149] Unlike the mainstream RFID and infrared space detection technologies in the industry, which require a lot of software and hardware to realize cabinet space detection, the application example of this application only needs to deploy one high-definition camera for each IT cabinet or multiple IT cabinets to achieve the purpose of real-time detection of cabinet space. One high-definition camera can detect 8-20 IT equipment at different heights. The cost is only one-tenth of the traditional detection technology, which greatly reduces the operation and maintenance cost. It has the characteristics of real-time detection, high accuracy, convenient and flexible deployment and simple operation.

[0150] From the hardware level, in order to solve the problem that the existing cabinet space detection methods cannot simultaneously meet the detection requirements of cabinet space detection such as high efficiency, accuracy, automation, less hardware deployment and low cost, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the cabinet internal space detection method, and the electronic device specifically includes the following contents:

[0151] Fig.16 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.16 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.16 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0152] In one embodiment, the cabinet internal space detection function may be integrated into the central processing unit. The central processing unit may be configured to perform the following control:

[0153] Step 100: Determine the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification components is arranged on the outer wall of the target cabinet so that all of the space identification components on the target cabinet are included in the corresponding target cabinet image, and different types of space identification components are respectively used to represent different space sizes occupied by each electronic device in the target cabinet.

[0154] Step 200: Determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the types and quantities of space identification components in the target cabinet image.

[0155] From the above description, it can be seen that the electronic device provided in the embodiment of the present application can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet by setting each space identification member on the outer wall of the cabinet, which is respectively used to represent the different space sizes occupied by each electronic device in the target cabinet, and determining the type and number of space identification members in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method. At the same time, since only space identification members are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the process of detecting the internal space of the cabinet. By determining the current remaining available space of the target cabinet based on the preset complete internal space of the target cabinet and the type and number of space identification members in the target cabinet image, the efficiency and reliability of the internal space detection of the cabinet can be further improved, and then the use of the cabinet can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and improves the accuracy and timeliness of electronic equipment management.

[0156] In another embodiment, the cabinet internal space detection device can be configured separately from the central processor 9100. For example, the cabinet internal space detection device can be configured as a chip connected to the central processor 9100, and the cabinet internal space detection function is realized through the control of the central processor.

[0157] like Fig.16 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.16 In addition, the electronic device 9600 may also include Fig.16 For components not shown, reference may be made to the prior art.

[0158] like Fig.16As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0159] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0160] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0161] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0162] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0163] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0164] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0165] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the cabinet internal space detection method in the above embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps in the cabinet internal space detection method in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0166] Step 100: Determine the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification components is arranged on the outer wall of the target cabinet so that all of the space identification components on the target cabinet are included in the corresponding target cabinet image, and different types of space identification components are respectively used to represent different space sizes occupied by each electronic device in the target cabinet.

[0167] Step 200: Determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the types and quantities of space identification components in the target cabinet image.

[0168] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application can effectively improve the degree of automation, efficiency and accuracy of knowing the space occupied by each electronic device in the target cabinet by setting each of the space identification parts on the outer wall of the cabinet, which are respectively used to represent the different space sizes occupied by each electronic device in the target cabinet, and determining the type and number of space identification parts in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method. At the same time, since only space identification parts are required on the outer wall of the cabinet, there is no need to set cameras, infrared devices and other equipment in the target cabinet, which can effectively reduce the number and cost of hardware deployment in the process of detecting the internal space of the cabinet. By determining the current remaining available space of the target cabinet based on the preset complete internal space of the target cabinet and the type and number of space identification parts in the target cabinet image, the efficiency and reliability of the internal space detection of the cabinet can be further improved, and then the use of the cabinet can be known in real time, which is convenient for the subsequent convenient and rapid deployment of electronic equipment, and improves the accuracy and timeliness of electronic equipment management.

[0169] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (devices), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0170] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0171] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for detecting the internal space of a cabinet, characterized in that: include: Determine the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification components is arranged on the outer wall of the target cabinet so that all of the space identification components on the target cabinet are included in the target cabinet image collected in the corresponding one-time imaging, and different types of space identification components are respectively used to represent different space sizes occupied by each electronic device in the target cabinet; Determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the types and quantities of space identification components in the target cabinet image; The types of the space identification elements are distinguished by different shapes; Correspondingly, the method of determining the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on a preset image recognition method includes: Intercepting effective areas corresponding to the space identification elements in the target cabinet image; Performing feature detection on each of the effective areas based on a preset Hough transform method to obtain the type and quantity of space identification components in the target cabinet image corresponding to the target cabinet; and / or, Inputting the target cabinet image into a preset image recognition model for identifying space identification components, so that the image recognition model outputs the type and quantity of space identification components in the target cabinet image; The image recognition model is pre-trained based on a plurality of historical cabinet images with labels, wherein the labels are used to indicate the type and quantity of space identification parts in the corresponding historical cabinet images; When the Hough transform method and the image recognition model are selected to identify the type and quantity of spatial identification components, the recognition results of the type and quantity of spatial identification components of the Hough transform method and the image recognition model are compared to see if they are the same. If they are the same, the recognition results are directly output or displayed in a preset device; if they are different, a notification message is sent to the client device of the operation and maintenance personnel to inform them that the recognition results of the type and quantity of spatial identification components are different, or the recognition is performed in a loop until the recognition results of the type and quantity of spatial identification components of the Hough transform method and the image recognition model are the same or the preset number of cycles is reached and then stopped.

2. The method for detecting the internal space of a cabinet according to claim 1, characterized in that: The determining, according to the preset complete internal space of the target cabinet and the types and quantities of the space identification components in the target cabinet image, the current remaining available space of the target cabinet includes: Retrieving a pre-stored comparison table of the internal complete space dimensions and identification space of the target cabinet, wherein the identification space comparison table is used to store the correspondence between the type of each space identification component and the occupied cabinet space dimensions; Determine the total occupied space size of the target cabinet occupied by the electronic equipment according to the identification element space comparison table and the types and quantities of the space identification elements in the target cabinet image; Based on the internal complete space size of the target cabinet and the total occupied space size of the target cabinet occupied by electronic equipment, the current remaining available space of the target cabinet is determined.

3. The method for detecting the internal space of a cabinet according to claim 1, characterized in that: Before determining the type and quantity of space identification components in the target cabinet image corresponding to the current target cabinet based on the preset image recognition method, the method further includes: Receiving a cabinet image captured by an image acquisition device, wherein the cabinet image includes at least one complete cabinet; Acquire a valid image capture area of ​​at least one cabinet from the cabinet image; A cabinet is selected as a target cabinet to be detected currently, and a valid image capture area of ​​the target cabinet is determined as a corresponding target cabinet image.

4. The method for detecting the internal space of a cabinet according to claim 1, characterized in that: Also includes: The current remaining available space of the target cabinet is visually displayed, and / or the current remaining available space of the target cabinet is sent to the corresponding client device.

5. The method for detecting the internal space of a cabinet according to any one of claims 1 to 4, characterized in that: The space identification element is a magnetic sticker.

6. A cabinet internal space detection device, characterized in that: include: An image recognition module, used to determine the type and quantity of space identification elements in a target cabinet image corresponding to the current target cabinet based on a preset image recognition method, wherein each of the space identification elements is arranged on an outer wall of the target cabinet so that all of the space identification elements on the target cabinet are included in the target cabinet image collected in the corresponding primary imaging, and different types of space identification elements are used to represent different space sizes occupied by each electronic device in the target cabinet; A space detection module, used to determine the current remaining available space of the target cabinet according to the preset complete internal space of the target cabinet and the type and quantity of space identification parts in the target cabinet image; The types of the space identification elements are distinguished by different shapes; The image recognition module is specifically used to intercept the effective areas corresponding to each of the space identification parts in the target cabinet image; perform feature detection on each of the effective areas based on a preset Hough transform method to obtain the type and quantity of the space identification parts in the target cabinet image corresponding to the target cabinet; and / or input the target cabinet image into a preset image recognition model for identifying space identification parts, so that the image recognition model outputs the type and quantity of the space identification parts in the target cabinet image; wherein the image recognition model is pre-trained based on a plurality of historical cabinet images with labels, and the labels are used to indicate the type and quantity of the space identification parts in the corresponding historical cabinet image; When the Hough transform method and the image recognition model are selected to identify the type and quantity of spatial identification components, the recognition results of the type and quantity of spatial identification components of the Hough transform method and the image recognition model are compared to see if they are the same. If they are the same, the recognition results are directly output or displayed in a preset device; if they are different, a notification message is sent to the client device of the operation and maintenance personnel to inform them that the recognition results of the type and quantity of spatial identification components are different, or the recognition is performed in a loop until the recognition results of the type and quantity of spatial identification components of the Hough transform method and the image recognition model are the same or the preset number of cycles is reached and then stopped.

7. A cabinet internal space detection system, characterized in that: include: A space identification member for being arranged on the outer wall of the target cabinet, at least one image acquisition device, and a cabinet internal space detection device for implementing the cabinet internal space detection method according to any one of claims 1 to 5; The image acquisition device is arranged within the space where the cabinet is located, and each of the image acquisition devices is used to acquire a cabinet image of at least one cabinet; The image acquisition device is communicatively connected to the cabinet internal space detection device, and is used to send the acquired cabinet image of at least one cabinet to the cabinet internal space detection device, so that the cabinet internal space detection device obtains a target cabinet image corresponding to the current target cabinet according to the cabinet image of at least one cabinet; The types of the space identification elements are distinguished by different shapes; The cabinet internal space detection device is used to intercept the effective areas corresponding to each of the space identification parts in the target cabinet image; perform feature detection on each of the effective areas based on a preset Hough transform method to obtain the type and quantity of space identification parts in the target cabinet image corresponding to the target cabinet; and / or input the target cabinet image into a preset image recognition model for identifying space identification parts, so that the image recognition model outputs the type and quantity of space identification parts in the target cabinet image; wherein the image recognition model is pre-trained based on multiple historical cabinet images with labels, and the labels are used to represent the type and quantity of space identification parts in the corresponding historical cabinet image; When the Hough transform method and the image recognition model are used to identify the type and quantity of the space identification parts, the recognition results of the type and quantity of the space identification parts of the Hough transform method and the image recognition model are compared to see whether they are the same. If they are the same, the recognition results are directly output or displayed in a preset device; If they are not the same, a notification message is sent to the client device of the operation and maintenance personnel to inform them that the recognition results of the type and quantity of the space identification parts are different, or the recognition is performed in a loop until the recognition results of the type and quantity of the space identification parts of the Hough transform method and the image recognition model are the same or the preset number of cycles is reached and then stopped.

8. 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 cabinet internal space detection method according to any one of claims 1 to 5 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the cabinet internal space detection method described in any one of claims 1 to 5 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the cabinet internal space detection method according to any one of claims 1 to 5 is implemented.

Images