Personnel distance determination method and device based on data center scenario

Abstract

The present invention belongs to the field of information security technology. The present invention provides a method and device for determining the distance between people in a data room scenario. The method for determining the distance between people in a data room scenario includes: acquiring imaging screen data of multiple people in the data room in real time; determining the number of standard reference objects between the multiple people according to the imaging screen data; and determining the distance between the multiple people according to the number of standard reference objects. The present invention can quickly obtain the distance between multiple people in the data room by analyzing the image content in the video screenshot. When the distance exceeds the threshold, the system will give priority to pushing the alarm information of abnormal behavior to the accompanying person. This prevents information leakage in the data room and protects the accompanying person from being punished.

Description

Technical Field

[0001] The present invention belongs to the field of information security technology, and in particular to the field of software automation testing technology, and specifically to a method and device for determining personnel distance in a data room scenario. Background Art

[0002] Large numbers of servers, storage devices, encryption machines, and industrial computers are running in the data centers of major enterprises. To ensure the security of business test systems, major enterprises have established data security management rules. According to the computer room management regulations, outsiders entering the computer room must submit an entry and exit application by data center personnel, and they must accompany and supervise the entire process during the computer room activities. Unless necessary, outsiders are strictly prohibited from operating equipment in the computer room. If outsiders are required to cooperate with the operation due to personnel and technical conditions, the maintenance operation must be supervised and reviewed throughout the process to prevent the leakage of important information such as data, passwords, and keys. In the daily maintenance of servers, storage, and encryption equipment, there is a high frequency of need for cooperation from manufacturer engineers. During the problem handling process, common problems after entering the computer room are:

[0003] 1. It usually takes a long time to solve complex equipment problems. Due to work or personal reasons, the accompanying person is likely to be too far away from the manufacturer's engineers, and sometimes even out of sight. Being too far away or out of sight may cause the leakage of important information such as device terminal data;

[0004] 2. For abnormal behaviors such as the accompanying person not accompanying and supervising throughout the process, the security management department uses camera recordings for analysis and inspection. The computer room management regulations require that the video recordings in the test computer room be kept for several months. The massive amount of data recorded by the camera seriously affects the efficiency and effect of supervision and inspection;

[0005] 3. When abnormal behavior is discovered through video recording analysis, the accompanying person will be severely punished. Under the existing model, there is no effective real-time reminder mechanism. When abnormal behavior occurs, if timely reminders are given, the accompanying person can promptly discover his or her own problems and stop the abnormal behavior, thus avoiding punishment. Summary of the invention

[0006] The present invention belongs to the field of information security technology. Aiming at the problems in the prior art, the present invention can obtain the distance between the accompanying person and the manufacturer's engineer by analyzing the image content in the video screenshot with only one calculation. When the distance between the two exceeds the threshold, or the two appear in cameras at different points, the system will push the alarm information of abnormal behavior to the accompanying person first, so as to prevent the leakage of information in the data room and to prevent the accompanying person from being punished.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for determining a person's distance in a data center scenario, comprising:

[0009] Real-time acquisition of imaging data of multiple personnel in the data room;

[0010] Determining the number of standard reference objects between the multiple persons according to the imaging picture data;

[0011] The distances between the multiple persons are determined according to the number of standard reference objects.

[0012] In one embodiment, the real-time acquisition of imaging data of multiple persons in a data room includes:

[0013] Numbering multiple cameras in the data room;

[0014] Establishing a mapping relationship between cabinet channels and camera numbers in the data room;

[0015] The positions of the multiple persons are determined according to the mapping relationship to obtain the imaging picture data in real time.

[0016] In one embodiment, determining the number of standard reference objects between the multiple persons according to the imaging picture data includes:

[0017] Establishing index information of a plurality of standard reference objects in the data room;

[0018] The number of standard reference objects between the multiple persons is determined according to the positions and the index information.

[0019] In one embodiment, the method for determining the personnel distance in a data center scenario further includes: preprocessing the imaging picture data, including:

[0020] Performing grayscale processing on the imaging picture data to generate a grayscale image;

[0021] Capturing the grayscale image within a preset time to generate a video screenshot;

[0022] Establishing a convolution kernel of a standard reference object in the video screenshot;

[0023] Calculating the covariance of the convolution kernel;

[0024] Interference images in the video screenshot are eliminated according to the covariance.

[0025] In one embodiment, determining the distance between the multiple persons according to the number of the standard reference objects includes:

[0026] The distance between the persons is calculated according to the number of the standard reference objects and the length of the standard reference objects.

[0027] In one embodiment, in the method for determining the distance between people in a data room scenario, before acquiring the imaging picture data of multiple people in the data room in real time, the method further includes:

[0028] Acquiring facial data of the plurality of persons using cameras in the data room;

[0029] Determine whether the identities of the multiple persons are legal based on the facial data.

[0030] In one embodiment, the method for determining the personnel distance in a data center scenario further includes:

[0031] When the distance between the multiple persons exceeds a preset threshold, an early warning message is issued.

[0032] In a second aspect, the present invention provides a device for determining a personnel distance based on a data center scenario, comprising:

[0033] A data acquisition module is used to acquire the imaging data of multiple personnel in the data room in real time;

[0034] A quantity determination module, used to determine the quantity of standard reference objects between the multiple persons according to the imaging picture data;

[0035] The distance determination module is used to determine the distance between the multiple persons according to the number of standard reference objects.

[0036] In one embodiment, the data acquisition module includes:

[0037] A camera numbering unit, used for numbering a plurality of cameras in the data room;

[0038] A mapping relationship establishing unit, used to establish a mapping relationship between cabinet channels and camera numbers in the data room;

[0039] The data acquisition unit is used to determine the positions of the multiple persons according to the mapping relationship so as to acquire the imaging picture data in real time.

[0040] In one embodiment, the quantity determination module includes:

[0041] An index information establishing unit, used for establishing index information of a plurality of standard reference objects in the data room;

[0042] A data determination unit is used to determine the number of standard reference objects between the multiple persons according to the positions and the index information.

[0043] In one embodiment, the device for determining the personnel distance in a data center scenario further includes:

[0044] A preprocessing module is used to preprocess the imaging picture data.

[0045] The preprocessing modules include:

[0046] A grayscale image generating unit, used for performing grayscale processing on the imaging picture data to generate a grayscale image;

[0047] A video screenshot generating unit, used for capturing the grayscale image within a preset time to generate a video screenshot;

[0048] A convolution kernel establishing unit, used to establish a convolution kernel of a standard reference object in the video screenshot;

[0049] A covariance calculation unit, used to calculate the covariance of the convolution kernel;

[0050] The interference image removal unit is used to remove the interference image in the video screenshot according to the covariance.

[0051] In one embodiment, the distance determination module is specifically configured to calculate the distance between the persons according to the number of the standard reference objects and the length of the standard reference objects.

[0052] In one embodiment, the device for determining the personnel distance in a data center scenario further includes:

[0053] A facial data acquisition module, used to acquire facial data of the plurality of persons using cameras in the data room;

[0054] An identity determination module is used to determine whether the identities of the multiple persons are legal based on the facial data.

[0055] In one embodiment, the device for determining the personnel distance in a data center scenario further includes:

[0056] The warning information issuing module is used to issue a warning message when the distance between the multiple persons exceeds a preset threshold.

[0057] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of a method for determining personnel distance in a data center scenario are implemented.

[0058] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for determining personnel distance based on a data center scenario.

[0059] From the above description, it can be seen that the method and device for determining the distance between people in the data room scenario provided by the embodiment of the present invention first obtains the imaging picture data of multiple people in the data room in real time; then, determines the number of standard reference objects between multiple people based on the imaging picture data; finally, determines the distance between multiple people based on the number of standard reference objects. The present invention establishes a complete set of methods for confirming the identity of people, detecting the distance between different people, and pushing alarms for abnormal messages based on the video surveillance camera in the test room. While ensuring the accuracy of the distance measurement of people, it pushes the abnormal behavior information of the staff who fail to effectively accompany and supervise the manufacturer. It has the characteristics of prevention and real-time, and the main beneficial effects are:

[0060] 1. The present invention is based on the existing video monitoring system in the test room. It can realize the measurement of the distance between different personnel without adding new monitoring camera equipment, and there is no additional hardware purchase cost;

[0061] 2. The distance measurement algorithm based on the calibration of the camera's internal parameters first requires placing reference objects of specific length, width, and height in the corresponding calibration camera's imaging screen, and completing the calibration of the camera's internal parameters based on the reference objects. After the calibration is completed, when processing specific distance measurement tasks, it is necessary to manually determine the specific positions of different people in the monitoring screen, and use this as a basis to calculate the distance between different people. If the camera position is moved or replaced, it is necessary to rearrange the reference objects for secondary calibration, which is complicated.

[0062] 3. When calculating the distance between different people, the present invention only needs to process one grayscale image per second. Since the effective screenshot area and floor gap information are preprocessed in advance in the environmental preprocessing module, the calculation steps involve only simple accumulation and comparison, and the processing and push of abnormal behavior information can be completed in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 The method for determining the distance between people in a data center scenario according to an embodiment of the present invention is shown in FIG. Figure 1 ;

[0065] Figure 2 is a flow chart of step 100 in an embodiment of the present invention;

[0066] Figure 3is a flow chart of step 200 in an embodiment of the present invention;

[0067] Figure 4 The method for determining the distance between people in a data center scenario according to an embodiment of the present invention is shown in FIG. Figure 2 ;

[0068] Figure 5 is a flow chart of step 400 in an embodiment of the present invention;

[0069] Figure 6 is a flow chart of step 300 in an embodiment of the present invention;

[0070] Figure 7 The method for determining the distance between people in a data center scenario according to an embodiment of the present invention is shown in FIG. Figure 3 ;

[0071] Figure 8 The method for determining the distance between people in a data center scenario according to an embodiment of the present invention is shown in FIG. Figure 4 ;

[0072] Fig. 9 It is a structural block diagram of a device for determining a personnel distance based on a data center scenario in a specific application example of the present invention;

[0073] Fig.10 It is a structural block diagram of a personnel identification module in a specific application example of the present invention;

[0074] Fig.11 It is a block diagram of the environment preprocessing module element in a specific application example of the present invention;

[0075] Fig.12 It is a structural block diagram of a distance detection module in a specific application example of the present invention;

[0076] Fig.13 It is a structural block diagram of an alarm module in a specific application example of the present invention;

[0077] Fig.14 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0079] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. 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 code.

[0080] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatuses.

[0081] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0082] The embodiment of the present invention provides a specific implementation method of a method for determining a person's distance in a data center scenario, see Figure 1 , the method specifically includes the following contents:

[0083] Step 100: Acquire imaging data of multiple persons in a data room in real time.

[0084] In a typical scenario, there are usually two people in the data room, one is the equipment maintenance engineer (usually an external person from the company to which the data room belongs), and the other is an internal accompanying person from the company to which the data room belongs. The accompanying person is responsible for informing the equipment maintenance engineer of the specific equipment failure and for supervising whether there is any data leakage. There are generally multiple cabinet channels in the data room, and each cabinet channel is equipped with at least one camera, which takes pictures of the corresponding cabinet channel. In addition, cameras should also be installed in the corners of the room to ensure that there are no blind spots in the data room and 360-degree all-round monitoring.

[0085] Step 200: Determine the number of standard reference objects between the multiple persons according to the imaging picture data.

[0086] There are two situations in step 200: The first situation: when multiple people are within the acquisition range of the same camera, it is only necessary to calculate the number of standard reference objects between the multiple people in the imaging picture data. Specifically, the standard reference objects can be identified based on the color difference between the standard reference objects and the surrounding objects. For example, the number of floors between multiple people can be counted because the color difference between the gaps between the floors and the floors is different.

[0087] In the second case, when multiple persons are within the collection range of different cameras, this situation generally means that the distance between multiple persons is greater than the preset threshold, and an early warning message should be issued to the accompanying persons. However, there are exceptions, such as when the accompanying persons or equipment maintenance engineers are blocked by the cabinet. At this time, it is necessary to consider the imaging data collected by different cameras comprehensively, and determine the positions of the persons in the imaging data collected by different cameras according to the predetermined camera numbers, so as to count the number of standard reference objects between multiple persons. The specific method refers to the first case and will not be repeated here.

[0088] Step 300: Determine the distance between the multiple persons according to the number of standard reference objects.

[0089] It is understandable that after counting the number of standard reference objects and knowing the specifications (length, width and height) of the standard reference objects, the distance between multiple people can be calculated by multiplying the number of standard reference objects by their specifications.

[0090] From the above description, it can be seen that the method for determining the distance between people in the data room scenario provided by the embodiment of the present invention first obtains the imaging picture data of multiple people in the data room in real time; then, determines the number of standard reference objects between multiple people based on the imaging picture data; finally, determines the distance between multiple people based on the number of standard reference objects. The present invention establishes a complete set of methods for confirming the identity of people, detecting the distance between different people, and pushing alarms for abnormal messages based on the video surveillance camera in the test room. While ensuring the accuracy of the distance measurement of people, it pushes the abnormal behavior information of the staff who fail to effectively accompany and supervise the manufacturer, which has the characteristics of prevention and real-time.

[0091] In one embodiment, see Figure 2 , step 100 further comprises:

[0092] Step 101: numbering multiple cameras in the data room to determine camera numbers;

[0093] Step 102: Establishing a mapping relationship between cabinet channels and camera numbers in the data room;

[0094] In step 101 and step 102, the monitoring point cameras are numbered corresponding to each cabinet channel, and a mapping table between each cabinet channel and camera point information is established.

[0095] Step 103: Determine the positions of the multiple persons according to the mapping relationship to obtain the imaging picture data in real time.

[0096] Specifically, the positions of the multiple persons are determined according to the mapping relationship in step 102, and the cameras corresponding to the positions are called to photograph the multiple persons in real time to obtain imaging picture data.

[0097] In one embodiment, see Figure 3 , step 200 further comprises:

[0098] Step 201: Establishing index information of a plurality of standard reference objects in the data room;

[0099] Step 202: Determine the number of standard reference objects between the multiple persons according to the positions and the index information.

[0100] In step 201 and step 202, since there are interference objects between adjacent standard reference objects, there are differences in the grayscale pixel values ​​of the two objects, and the accumulated values ​​of the two objects will show regular differences in the X direction and the Y direction. According to the differences in the accumulated pixel values, the array indexes of the positions where the floor gaps appear in the X direction and the Y direction are recorded respectively, and the floor gap position data index of the corresponding channel and the data information of the accumulated pixel values ​​in the X and Y directions are added to the mapping table between the cabinet channel and the camera point information; then, based on the personnel position data index information and the floor gap position data index information, the number of times N of interference objects appearing between the standard reference objects in the X direction and the Y direction at the positions where multiple personnel appear is counted, and N-1 is the number of floors between the personnel.

[0101] In one embodiment, see Figure 4 , the method for determining the personnel distance in the data center scenario also includes:

[0102] Step 400: pre-processing the imaging picture data;

[0103] It is understandable that the enterprise information security management department uses camera recordings for analysis and inspection. The computer room management regulations require that the video recordings of the test computer room be kept for several months (at least 3 months). The massive amount of data recorded by the camera seriously affects the efficiency and effect of supervision and inspection, so it is necessary to pre-process the imaging picture data.

[0104] Further, see Figure 5 , step 400 comprises:

[0105] Step 401: grayscale processing is performed on the imaging picture data to generate a grayscale image;

[0106] Generally, the video surveillance image of the camera is an RGB three-channel color image. In order to reduce the amount of calculation and improve the operation speed, the RGB image is grayed and the original RGB color image is converted into a single-channel grayscale image.

[0107] Step 402: capturing the grayscale image within a preset time to generate a video screenshot;

[0108] Step 403: establishing a convolution kernel of a standard reference object in the video screenshot;

[0109] Step 404: Calculate the covariance of the convolution kernel;

[0110] Step 405: Eliminate interference images in the video screenshot according to the covariance.

[0111] In steps 402 to 405, in order to eliminate the interference of other image information outside the area of ​​interest, it is necessary to construct convolution kernels for the standard reference object and the interfering objects between them respectively. At the same time, in order to ensure the accuracy of the convolution kernel information, it is necessary to sample the image information of two different areas to construct multiple convolution kernels. Finally, the accuracy of the convolution kernel information is further improved by averaging.

[0112] After selecting the valid screenshot area, the image content in the corresponding area only contains valid floor information. Through the convolution kernel, the selected valid screenshot area is correlated from top to bottom and from left to right. The correlation assessment is calculated by covariance. If the covariance of the pixel area is positive, it means that the processing area is an interference and the pixel value is retained without processing. If the covariance is negative, it means that the processing area is a floor and the corresponding pixel value is set to 0.

[0113] In one embodiment, see Figure 6 , step 300 further comprises:

[0114] Step 301: Calculate the distance between the persons according to the number of the standard reference objects and the length of the standard reference objects.

[0115] In one embodiment, see Figure 7 Before step 100, the method for determining the personnel distance in the data center scenario further includes:

[0116] Step 500: Acquire facial data of the plurality of persons using a camera in the data room;

[0117] Step 600: Determine whether the identities of the multiple persons are legal based on the facial data.

[0118] In the above two steps, the purpose is to confirm the identity information of the person entering the data room before entering the data room. Since the ICBC official employee who is the accompanying person has reserved facial information in the facial recognition database, and the outsider has no reserved facial information, the identity of the person entering the test room can be determined by whether there is reserved information; according to the room management regulations, the accompanying outsider entering the test room to operate the terminal must apply for entry into the room. According to the identified personnel information, if an outsider enters the room, it will be checked whether the person has an application for entry into the room submitted by the accompanying person during the time period when the person enters the test room. If there is no application, it will trigger the push of alarm information, and the abnormal information will be pushed to the on-duty personnel of the security center, and archived for processing.

[0119] In one embodiment, see Figure 8 , the method for determining the personnel distance in the data center scenario also includes:

[0120] Step 700: When the distance between the multiple persons exceeds a preset threshold, a warning message is issued.

[0121] It is understandable that when the distance between multiple persons is greater than a preset threshold, a warning message should be sent to the accompanying persons, informing them of the risk of data leakage and the possibility of punishment, and that they should return to the preset range as soon as possible to monitor the maintenance engineer.

[0122] In summary, the present invention is based on the existing video surveillance system in the computer room, corresponds to each cabinet channel, and performs number processing on the camera, obtains a video screenshot of each video point every second, and establishes image content coordinate indexes in the horizontal and vertical directions based on the floor content and the gap between the floors. Compared with the traditional calibration algorithm based on the internal parameters of the camera, by analyzing the image content in the video screenshot, only one calculation is required to obtain the distance between the accompanying person and the manufacturer's engineer. When the distance between the two exceeds the threshold, or the two appear in the cameras at different points, the system will give priority to pushing the alarm information of abnormal behavior to the accompanying person. If the abnormal behavior has not stopped after an interval of ten seconds, the system will push the abnormal behavior alarm information of the accompanying person to the security center service personnel for easy archiving and inspection.

[0123] To further illustrate the present solution, the present invention also provides a specific application example of a personnel distance determination device based on a data center scenario, which specifically includes the following contents.

[0124] In this specific application example, the standard reference object is the floor in the data center, and the interference object is the gap between the floors.

[0125] Fig. 9 This is a structural block diagram of a device for determining the distance between people in a data center scenario in this specific application example. Fig. 9As shown, the device includes a face recognition module 1, an environment preprocessing module 2, a distance detection module 3, and an alarm module 4. The execution order of each module is:

[0126] Face recognition module 1: Use the face recognition project of the camera to determine the identity of the person entering the test room and whether the person entering the room is compliant.

[0127] Environmental preprocessing module 2: Corresponding to each cabinet channel, the cameras at the monitoring points are numbered and the corresponding relationship between the cameras and the cabinet channels in the test room is established. The influence of redundant information on the subsequent analysis and calculation of the distance between two people is eliminated by selecting multiple pairs of monitoring areas. The accumulated information of the pixels in the horizontal and vertical directions of the floor area is calculated using the image information selected by the frame, and used as the prior value of the corresponding channel for subsequent analysis and calculation.

[0128] Distance detection module 3: Calculate the distance between the accompanying person and the manufacturer's engineer.

[0129] Alarm module 4: After completing the distance calculation, if the distance between two people exceeds the set threshold, the alarm module 4 is called to push the abnormal alarm information to the accompanying person first, and then push it to the security center staff on duty if there is no abnormal behavior termination action to complete the push processing. The detailed functions and implementation methods of each module are described as follows:

[0130] Fig.10 The structural block diagram of the face recognition module 1 is as follows: Fig.10 As shown, the face recognition module 1 includes a recognition area selection unit 11, a personnel identity determination unit 12, and a computer room application comparison unit 13, wherein:

[0131] Recognition area selection unit 11: used to complete the selection of effective monitoring areas for face recognition of personnel entering the test room. After the recognition area is selected, the facial information of the entering personnel can be quickly recognized;

[0132] Personnel identity determination unit 12: used to confirm the identity information of the person entering the test room. Since the ICBC official employee who is the accompanying person has reserved face information in the face recognition database, and the outsider has no reserved face information, the identity of the person entering the test room can be determined by using the reserved information.

[0133] Computer room application comparison unit 13: According to the management regulations of the three types of computer rooms, an application for entering the computer room is required when accompanying an outsider to enter the test computer room to operate the terminal. According to the personnel information identified by the personnel identity determination unit 22, if an outsider enters the computer room, it is checked whether there is an application for entering the computer room submitted by the accompanying person during the time period when the person enters the test computer room. If there is no application, the push of alarm information will be triggered, and the abnormal information will be pushed to the on-duty personnel of the security center for archiving and processing;

[0134] Fig.11 This is the meta-structure diagram of the environment preprocessing module, such as Fig.11 As shown, the environment preprocessing module 2 includes an image grayscale processing unit 21, an effective area frame selection unit 22, a floor convolution kernel construction unit 23, and a floor information calculation unit 24, wherein:

[0135] Image grayscale processing unit 21: Corresponding to each cabinet channel, the monitoring point camera is numbered and a mapping table of each cabinet channel and camera point information is established. The camera video monitoring image is an RGB three-channel color image. In order to reduce the amount of calculation and improve the operation speed, the RGB image is grayed and the original RGB color image is converted into a single-channel grayscale image;

[0136] Valid area selection unit 22: The camera monitoring imaging picture corresponding to the cabinet channel includes the test cabinet information. The test cabinet information is an interference item for the subsequent step of calculating the distance based on the floor information. In order to eliminate this interference item, the valid screenshot area is determined by pre-selection;

[0137] Floor convolution kernel construction unit 23: In order to eliminate the interference of other image information outside the focus area, it is necessary to construct 15*15 convolution kernels for floor gaps and floor content respectively. To ensure the accuracy of convolution kernel information, it is necessary to sample image information from 2 different areas to construct 20 different 15*15 convolution kernels. The accuracy of convolution kernel information is further improved by averaging.

[0138] Floor information calculation unit 24: After selecting the valid screenshot area, the image content in the corresponding area only contains valid floor information. The floor gap convolution kernel created by the floor convolution kernel construction unit 23 performs correlation calculations on the selected valid screenshot area from top to bottom and from left to right. The correlation assessment is performed through covariance calculation. If the covariance of the 15*15 pixel area is positive, it indicates that the processing area is the floor gap, and the pixel value is retained without processing. If the covariance is negative, it indicates that the processing area is the floor, and the corresponding 15*15 pixel value is set to 0. For example, the height * width of the valid screenshot corresponds to: 480 (pixels) * 720 (pixels). After performing the correlation calculation, the pixels of the grayscale screenshot are superimposed in the X direction (vertical) and Y direction (horizontal), respectively, and two one-dimensional arrays with a size of 720 in the X direction and a size of 480 in the Y direction can be obtained. Since the grayscale pixel value of the gap between adjacent floors is different from the grayscale pixel value of the floor, the accumulated values ​​of the two will show regular differences in the X direction and the Y direction. According to the difference in the accumulated pixel value, the array index of the position where the floor gap appears in the X direction and the Y direction is recorded respectively, and the floor gap position data index of the corresponding channel and the data information of the accumulated pixel value in both directions of X and Y are added to the mapping table of the cabinet channel and the camera point information established in the image grayscale processing unit 21;

[0139] Fig.12 It is the structural block diagram of the distance detection module, such as Fig.12 As shown, the distance detection module 3 includes an image grayscale calculation unit 31, a personnel position confirmation unit 32, a floor spacing statistics unit 33, and a personnel distance calculation unit 34, wherein:

[0140] Image grayscale processing unit 31: To ensure the timeliness of calculating the distance between two people, the frequency of analyzing and processing video screenshots is 1 video screenshot per second. Through grayscale processing, the initial RGB three-channel color image is converted into a single-channel grayscale image, which maximizes the speed of calculation;

[0141] Personnel location confirmation unit 32: Although the pixel values ​​of clothing, skin color and other imaging of the personnel entering the test room are different, they are very different from the information on the floor. Based on this, the pixel values ​​of the imaging screenshots containing personnel information in the passageway entering the room are analyzed and calculated. In order to further improve the contrast between personnel information and the floor, the floor convolution kernel constructed by the floor convolution kernel construction unit 23 is used to perform correlation calculations on the personnel area from top to bottom and from left to right. The correlation assessment is calculated by covariance. If the covariance of the 15*15 pixel area is positive, it indicates that the processing area is the floor, and the pixel value is set to 0. If the covariance is negative, it indicates that the processing area is not the floor, and the corresponding 15*15 pixel value is not processed. The calculation method is the same as that of the floor information calculation unit 23. The pixels of the grayscale screenshot are superimposed in the X direction (vertical) and the Y direction (horizontal) respectively, and two one-dimensional arrays with a size of 720 in the X direction and a size of 480 in the Y direction can be obtained. The grayscale pixel values ​​accumulated in the X and Y directions in the mapping table of the cabinet channel and the camera point information established in the floor information calculation unit 23 are compared to confirm the data index information of the position of the person in both the X and Y directions.

[0142] The floor spacing counting unit 33 is based on the personnel position data index information and the floor gap position data index information obtained in the personnel position confirmation unit 32, and uses the number of times N of the floor gaps between the positions of two personnel appearing in the X direction and the Y direction to be counted, where N-1 is the number of floors between the personnel;

[0143] Personnel distance calculation unit 34: The length and width of the floor of the test room are standardized data. After obtaining the actual length information of the length and width of the floor, multiply it by the number of floors N-1 obtained by the floor interval statistics unit 33 to obtain the distance data between personnel;

[0144] Fig.13 This is the structural diagram of the alarm module, such as Fig.13As shown, the alarm module 4 includes an abnormal alarm information stacking unit 41, an alarm information subscription unit 42, and an alarm information pushing unit 43, wherein:

[0145] Abnormal alarm information stacking unit 41: To ensure the real-time transmission of alarm information and to ensure that the alarm information is not lost due to other messages from the surveillance camera, the MQ message queue is used when constructing message transmission. By constructing the MQ message queue, the abnormal alarm information is transmitted to the MQ message queue for processing.

[0146] Alarm information subscription unit 42: To ensure that the abnormal behavior alarm information can be processed in real time after entering the MQ stack, it is necessary to complete the subscription for specific abnormal behavior alarm information at the information receiving end to achieve real-time acquisition of information.

[0147] Alarm information push unit 43: After completing the alarm information subscription, the alarm information of abnormal behavior is pushed to the accompanying person first. If the abnormal behavior has not stopped after ten seconds, the system will push the abnormal behavior alarm information of the accompanying person to the security center service personnel for archiving and inspection.

[0148] From the above description, it can be seen that the method for determining the personnel distance based on the data room scenario provided by the specific application example of the present invention can easily and quickly retrieve the camera point information corresponding to different cabinet channels and the adjacent camera point information of the cabinet channel by logically numbering the cameras of each channel. When using the video screenshots of the cameras at each point to calculate the distance between the accompanying person and the manufacturer's engineer, because the effective image content is only the floor area in the video, it is necessary to pre-process the imaging pictures of different channels. By determining the effective area of ​​the imaging picture by box selection, the influence of foreign objects such as cabinets in the imaging pictures of different channels can be eliminated. After determining the effective area, the imaging pictures of each numbered camera are gray-scaled, that is, the RGB three-channel imaging pictures are converted into gray-scale images, redundant information is eliminated, and the calculation speed is improved. The grayscale images of each point channel are accumulated horizontally and vertically. Because there are gaps between floor tiles, the accumulated grayscale value of the gap is different from the accumulated value of the rest of the floor content. The difference information is used to count the number of floor tiles between the accompanying person and the manufacturer's engineer. The size of the floor tiles in the test room is 60cm*60cm. The actual distance between the two people can be obtained by the number of floor tiles between them. If the distance exceeds the set threshold, the abnormal alarm information is pushed.

[0149] The devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is an electronic device, and the electronic device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0150] In a typical example, the electronic device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned method for determining the personnel distance in the data center scenario are implemented, and the steps include:

[0151] Step 100: acquiring imaging data of multiple persons in a data room in real time;

[0152] Step 200: Determine the number of standard reference objects between the multiple persons according to the imaging picture data;

[0153] Step 300: Determine the distance between the multiple persons according to the number of standard reference objects.

[0154] Reference below Fig.14 , which shows a schematic structural diagram of an electronic device 600 suitable for implementing an embodiment of the present application.

[0155] like Fig.14 As shown, electronic device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. In RAM 603, various programs and data required for the operation of system 600 are also stored. CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0156] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.

[0157] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for determining the distance between people in a data center scenario are implemented, and the steps include:

[0158] Step 100: acquiring imaging data of multiple persons in a data room in real time;

[0159] Step 200: Determine the number of standard reference objects between the multiple persons according to the imaging picture data;

[0160] Step 300: Determine the distance between the multiple persons according to the number of standard reference objects.

[0161] In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 609 , and / or installed from the removable medium 611 .

[0162] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0163] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0164] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0165] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0166] 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.

[0167] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, commodity or device including the element.

[0168] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0169] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0170] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for determining personnel distance based on a data center scenario, characterized in that: include: Real-time acquisition of imaging data of multiple personnel in the data room; Determining the number of standard reference objects between the multiple persons according to the imaging picture data; Determining the distance between the multiple persons according to the number of standard reference objects; The real-time acquisition of imaging data of multiple persons in a data room includes: Numbering multiple cameras in the data room; Establishing a mapping relationship between cabinet channels and camera numbers in the data room; Determine the positions of the multiple persons according to the mapping relationship to obtain the imaging picture data in real time; The determining the number of standard reference objects between the multiple persons according to the imaging picture data comprises: Establishing index information of a plurality of standard reference objects in the data room; Determine the number of standard reference objects between the multiple persons according to the positions and the index information, specifically: According to the difference in the accumulated pixel values ​​between adjacent standard reference objects, the array indexes of the positions where the floor gaps appear in the X and Y directions are recorded respectively, and the floor gap position data index of the corresponding channel and the data information of the accumulated pixel values ​​in the X and Y directions are added to the mapping table between the cabinet channel and the camera point information; then, based on the personnel position data index information and the floor gap position data index information, the number of interference objects between the standard reference objects in the X and Y directions at the positions where multiple personnel appear is counted, and N-1 is the number of floors between the personnel.

2. The method for determining the personnel distance based on the data center scenario according to claim 1 is characterized in that: Also includes: Preprocessing the imaging picture data includes: Performing grayscale processing on the imaging picture data to generate a grayscale image; Capturing the grayscale image within a preset time to generate a video screenshot; Establishing a convolution kernel of a standard reference object in the video screenshot; Calculating the covariance of the convolution kernel; Interference images in the video screenshot are eliminated according to the covariance.

3. The method for determining the personnel distance in a data center scenario according to claim 1 is characterized in that: The determining the distances between the multiple persons according to the number of the standard reference objects comprises: The distance between the persons is calculated according to the number of the standard reference objects and the length of the standard reference objects.

4. The method for determining the personnel distance in a data center scenario according to claim 1 is characterized in that: Before the real-time acquisition of imaging picture data of multiple persons in the data room, the method further includes: Acquiring facial data of the plurality of persons using cameras in the data room; Determine whether the identities of the multiple persons are legal based on the facial data.

5. The method for determining the personnel distance in a data center scenario according to claim 1 is characterized in that: Also includes: When the distance between the multiple persons exceeds a preset threshold, an early warning message is issued.

6. A device for determining the distance between people in a data center, characterized in that: include: A data acquisition module is used to acquire the imaging data of multiple personnel in the data room in real time; A quantity determination module, used to determine the quantity of standard reference objects between the multiple persons according to the imaging picture data; A distance determination module, used to determine the distance between the multiple persons according to the number of standard reference objects; The real-time acquisition of imaging data of multiple persons in a data room includes: Numbering multiple cameras in the data room; Establishing a mapping relationship between cabinet channels and camera numbers in the data room; Determine the positions of the multiple persons according to the mapping relationship to obtain the imaging picture data in real time; The determining the number of standard reference objects between the multiple persons according to the imaging picture data comprises: Establishing index information of a plurality of standard reference objects in the data room; Determine the number of standard reference objects between the multiple persons according to the positions and the index information, specifically: According to the difference in the accumulated pixel values ​​between adjacent standard reference objects, the array indexes of the positions where the floor gaps appear in the X and Y directions are recorded respectively, and the floor gap position data index of the corresponding channel and the data information of the accumulated pixel values ​​in the X and Y directions are added to the mapping table between the cabinet channel and the camera point information; then, based on the personnel position data index information and the floor gap position data index information, the number of interference objects between the standard reference objects in the X and Y directions at the positions where multiple personnel appear is counted, and N-1 is the number of floors between the personnel.

7. 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 program, the steps of the method for determining the distance between people based on the data center scenario according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for determining the distance between people based on a data center scenario as described in any one of claims 1 to 5 are implemented.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method for determining the distance between people based on a data center scenario as described in any one of claims 1 to 5 are implemented.

Images