CN117351424A

CN117351424A - Method, device, equipment and storage medium for monitoring personnel in and out machine room

Info

Publication number: CN117351424A
Application number: CN202311378212.9A
Authority: CN
Inventors: 陈淑蓉; 万辉辉; 胡雨风; 宫婉钰
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-10-23
Filing date: 2023-10-23
Publication date: 2024-01-05

Abstract

The application relates to a method, a device, a computer device, a storage medium and a computer program product for monitoring personnel in and out of a machine room, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: acquiring three-dimensional information corresponding to target personnel entering and exiting a financial service server room, and identifying living information and non-living information corresponding to the target personnel from the three-dimensional information; according to the living body information, obtaining an identity recognition result of a target person and a behavior recognition result corresponding to the target person; according to the non-living body information, obtaining an accessory identification result of accessories carried by the target personnel; and displaying the identification result, the behavior identification result and the accessory identification result on the three-dimensional information in the monitoring display interface. By adopting the method, the financial business server room can be monitored more comprehensively.

Description

Method, device, equipment and storage medium for monitoring personnel in and out machine room

Technical Field

The present application relates to the field of financial science and technology, and in particular, to a method, an apparatus, a computer device, a storage medium and a computer program product for monitoring personnel in and out of a machine room.

Background

With the development of the financial science and technology field, a monitoring method of a financial business server room is presented, and whether equipment and accessories in the server room are abnormal or not is monitored in real time through a camera.

However, in the above technical solution, the financial service server room also has the characteristics of multiple personnel entering and exiting, complex personnel entering and exiting, and the like, and the lack of monitoring for personnel entering and exiting in the room can make the monitoring on the financial service server room not comprehensive enough.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for monitoring personnel in and out of a financial business server room more comprehensively.

In a first aspect, the application provides a method for monitoring personnel in and out of a machine room. The method comprises the following steps:

acquiring three-dimensional information corresponding to a target person entering and exiting a financial service server room, and identifying living information and non-living information corresponding to the target person from the three-dimensional information;

obtaining an identification result of the target personnel and a behavior identification result corresponding to the target personnel according to the living body information;

Obtaining a fitting identification result of the fitting carried by the target person according to the non-living body information;

and displaying the identification result, the behavior identification result and the accessory identification result on three-dimensional information in a monitoring display interface.

In one embodiment, the identifying the living body information and the non-living body information corresponding to the target person from the three-dimensional information includes: dividing the three-dimensional information into a plurality of three-dimensional unit information, and acquiring current three-dimensional unit information from the plurality of three-dimensional unit information; based on the current three-dimensional unit information, obtaining a shape and a motion track corresponding to the current three-dimensional unit information; if the shape and the motion trail meet the living body judging condition, the current three-dimensional unit information is the living body information; and if the shape and the motion trail meet the non-living body judging condition, the current three-dimensional unit information is the non-living body information.

In one embodiment, the obtaining, according to the non-living body information, a fitting identification result of a fitting carried by the target person includes: if the non-living body information is not zero, determining that the target person carries an accessory, and detecting whether the non-living body information has reflection point information or not; the reflection point information is used for representing that the accessory is an accessory contained in an accessory information base; if the non-living body information does not contain the reflection point information, the accessory identification result is that the accessory is abnormal; if the non-living body information contains the reflection point information, acquiring image information corresponding to the accessory, and acquiring accessory types corresponding to the accessory from the accessory information base according to the image information; and obtaining an accessory identification result of the accessory carried by the target person under the condition that the reflecting point information exists in the non-living body information based on the accessory type.

In one embodiment, the obtaining, based on the accessory type, an accessory identification result of the accessory carried by the target person when the reflection point information exists in the non-living body information includes: under the condition that reflection point information exists in the non-living body information, if the accessory information is matched with the personnel identity information, the accessory identification result is that the accessory is normal; and if the accessory information is not matched with the personnel identity information, the accessory identification result is that the accessory is abnormal.

In one embodiment, the living body information includes facial information and limb dynamic information of the target person; the step of obtaining the identification result of the target person and the corresponding behavior identification result of the target person according to the living body information comprises the following steps: according to the facial information, personnel identity information of the target personnel is obtained, and according to the limb dynamic information, personnel behavior information corresponding to the target personnel is obtained; and obtaining an identity recognition result corresponding to the target person by using the personnel identity information, and obtaining a behavior recognition result corresponding to the target person by using the personnel behavior information.

In one embodiment, the obtaining, by using the person identity information, an identity recognition result corresponding to the target person includes: if the personnel identity information is contained in the pre-obtained computer room staff library, the identity recognition result corresponding to the target personnel is that the personnel identity is normal; if the personnel identity information is not in the pre-obtained computer room personnel library, the identity recognition result corresponding to the target personnel is abnormal personnel identity.

In one embodiment, the obtaining, by using the person behavior information, a behavior recognition result corresponding to the target person includes: if the obtained abnormal behavior library contains the personnel behavior information, the behavior recognition result corresponding to the target personnel is abnormal personnel behavior; if the obtained abnormal behavior library does not have the personnel behavior information, the behavior recognition result corresponding to the target personnel is that the personnel behavior is normal.

In a second aspect, the application further provides a personnel monitoring device for an access machine room. The device comprises:

the information acquisition module is used for acquiring three-dimensional information corresponding to a target person entering and exiting the financial service server room, and identifying living information and non-living information corresponding to the target person from the three-dimensional information;

The identity and behavior recognition module is used for obtaining an identity recognition result of the target person and a behavior recognition result corresponding to the target person according to the living body information;

the accessory identification module is used for obtaining an accessory identification result of accessories carried by the target personnel according to the non-living body information;

and the personnel monitoring module is used for displaying the identification result, the behavior identification result and the accessory identification result on the three-dimensional information in the monitoring display interface.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

According to the method, the device, the computer equipment, the storage medium and the computer program product for monitoring the personnel in the machine room, the three-dimensional information corresponding to the target personnel in the financial business server machine room is obtained, and the living information and the non-living information corresponding to the target personnel are identified from the three-dimensional information; according to the living body information, obtaining an identity recognition result of a target person and a behavior recognition result corresponding to the target person; according to the non-living body information, obtaining an accessory identification result of accessories carried by the target personnel; and displaying the identification result, the behavior identification result and the accessory identification result on the three-dimensional information in the monitoring display interface. According to the method, living information and non-living information corresponding to target personnel are obtained from three-dimensional information corresponding to the target personnel entering and exiting the financial service server room, then the identity recognition result and the behavior recognition result of the target personnel are obtained according to the living information, then the accessory recognition result of accessories carried by the target personnel is obtained according to the non-living information, and finally the personnel entering and exiting the financial service server room are monitored according to the identity recognition result, the behavior recognition result and the accessory recognition result. By adopting the method, the financial business server room can be monitored more comprehensively.

Drawings

FIG. 1 is a flow chart of a method for monitoring personnel in and out of a machine room in one embodiment;

FIG. 2 is a flow chart of acquiring living body information and non-living body information according to an embodiment;

FIG. 3 is a flowchart of a method for obtaining a fitting identification result according to an embodiment;

FIG. 4 is a flowchart of another embodiment for obtaining a fitting identification result;

FIG. 5 is a block diagram of a machine room personnel management apparatus based on three-dimensional modeling in one embodiment;

FIG. 6 is a flow diagram of a machine room personnel management method based on three-dimensional modeling in one embodiment;

FIG. 7 is a block diagram of a personnel monitoring device in an access room in one embodiment;

fig. 8 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

It should be noted that, the term "first\second" related to the embodiment of the present invention is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second" may interchange a specific order or precedence where allowed. It is to be understood that the "first\second" distinguishing aspects may be interchanged where appropriate to enable embodiments of the invention described herein to be implemented in sequences other than those illustrated or described.

In one embodiment, as shown in fig. 1, a method for monitoring personnel in and out of a machine room is provided, and the embodiment is applied to a terminal for illustration by using the method, it can be understood that the method can also be applied to a server, and can also be applied to a system comprising the terminal and the server, and is realized through interaction between the terminal and the server. In this embodiment, the method includes the steps of:

step S101, three-dimensional information corresponding to target personnel entering and exiting the financial service server room is obtained, and living information and non-living information corresponding to the target personnel are identified from the three-dimensional information.

The financial service server room is a server room for preventing a financial service server, the target person is a manager for managing the server in the financial service server room, the three-dimensional information refers to three-dimensional modeling image information of the target person displayed on the monitoring display platform, then the living body information is three-dimensional modeling image information of the target person, and the non-living body information is three-dimensional modeling image information of accessories carried by the target person, wherein the living body information can be point position information of a person with the head of the target person as a main identification target, facial image information of different target persons, action information of other parts such as hands and legs of the target person, non-living body information can be static information of other parts such as hands and legs of the target person, light reflecting point information of the accessories, real object image information and depth information of the accessories are captured optically.

Specifically, when a target person enters and exits the machine room, the information acquisition device acquires the information of the target person, and three-dimensional modeling processing is performed to obtain three-dimensional information corresponding to the target person. Wherein, information acquisition device mainly contains: the infrared sensor is used for automatically sensing the moving direction of the target person in and out of the target person; the image collector adopts a plurality of high-speed depth cameras and optical cameras to start three-dimensional image collection of target personnel in a monitoring range, realizes collection and capture of main target feature points (face, hand and shielding) from different angles (front, back, left side, right side and top), and the image collector needs to emphasize that the depth camera adopts infrared rays as a light source, records light source intensity information and the time from the light source to pixel points in an image, can identify the distance from each pixel point in the image to the camera, and obtains image color and depth values. The optical camera is composed of an optical lens, emits infrared light outwards, and the infrared light contacts with the reflecting point in the monitoring range to generate reflection for special article identification (the reflecting point is posted by the default of the real object accessory in the warehouse, and the reflecting point is not posted by the real object accessory in the non-warehouse). And finally, carrying out feature extraction and identification on each part of the target personnel through sub-three-dimensional information of the front, back, left side, right side and top of the target personnel in the three-dimensional information, and identifying living body information and non-living body information corresponding to the target personnel from the three-dimensional information.

Step S102, according to the living body information, the identity recognition result of the target personnel and the behavior recognition result corresponding to the target personnel are obtained.

The identity recognition result is the recognition result of the identity information of the target person, and comprises the identity normal recognition result corresponding to the target person in the library and the identity abnormal recognition result corresponding to the target person not in the library; the behavior recognition result is a recognition result of the behavior of the target person, and the behavior recognition result is a behavior abnormality recognition result corresponding to abnormal behaviors such as rescue behaviors and falling behaviors and a normal behavior recognition result corresponding to normal behaviors.

Specifically, according to facial information in the living body information, personnel identity information of a target personnel is obtained, and then according to limb dynamic information in the living body information, personnel behavior information corresponding to the target personnel is obtained; if the personnel identity information is abnormal, the identity recognition result corresponding to the target personnel is abnormal, and if the personnel identity information is normal, the identity recognition result corresponding to the target personnel is normal; if the personnel behavior information is abnormal, the behavior recognition result corresponding to the target personnel is abnormal, and if the personnel behavior information is normal, the behavior recognition result corresponding to the target personnel is normal.

Step S103, according to the non-living body information, the accessory identification result of the accessory carried by the target person is obtained.

The accessories carried by the target personnel are articles carried by the target personnel in and out of the machine room, and the accessory identification results are normal accessory identification results corresponding to the accessories in the warehouse and abnormal accessory identification results corresponding to the accessories not in the warehouse.

Specifically, if the non-living body information is not zero, that is, the non-living body information is not present, it is determined that the target person does not carry the accessory, if the non-living body information is not zero, that is, the non-living body information is present, it is determined that the target person carries the accessory, if the target person carries the accessory, it is detected whether the non-living body information has the reflection point information, and if the non-living body information does not have the reflection point information, the accessory identification result is that the accessory is abnormal. If the reflecting point information exists in the non-living body information, the image information corresponding to the accessory is acquired, the accessory type corresponding to the accessory is acquired from the accessory information base according to the image information, and if the reflecting point information exists in the non-living body information, the accessory is normal in the accessory identification result if the accessory information is matched with the personnel identity information, and is abnormal if the accessory information is not matched with the personnel identity information.

And step S104, displaying the identification result, the behavior identification result and the accessory identification result on the three-dimensional information in the monitoring display interface.

The monitoring display interface is a display interface for monitoring personnel to enter and exit the machine room.

Specifically, on the basis of displaying three-dimensional information of a target person in a monitoring display interface, an identification result, a behavior identification result and a fitting identification result are identified on the original three-dimensional information and displayed.

In the method for monitoring the personnel in the machine room, three-dimensional information corresponding to the target personnel in the financial business server machine room is obtained, and living information and non-living information corresponding to the target personnel are identified from the three-dimensional information; according to the living body information, obtaining an identity recognition result of a target person and a behavior recognition result corresponding to the target person; according to the non-living body information, obtaining an accessory identification result of accessories carried by the target personnel; and displaying the identification result, the behavior identification result and the accessory identification result on the three-dimensional information in the monitoring display interface. According to the method, living information and non-living information corresponding to target personnel are obtained from three-dimensional information corresponding to the target personnel entering and exiting the financial service server room, then the identity recognition result and the behavior recognition result of the target personnel are obtained according to the living information, then the accessory recognition result of accessories carried by the target personnel is obtained according to the non-living information, and finally the personnel entering and exiting the financial service server room are monitored according to the identity recognition result, the behavior recognition result and the accessory recognition result. By adopting the method, the financial business server room can be monitored more comprehensively.

In one embodiment, as shown in fig. 2, the identification of the living body information and the non-living body information corresponding to the target person from the three-dimensional information includes the following steps:

step S201, dividing the three-dimensional information into a plurality of three-dimensional unit information, and acquiring current three-dimensional unit information from the plurality of three-dimensional unit information.

The three-dimensional unit information is a unit part of the three-dimensional information, and the current three-dimensional unit information is the current three-dimensional unit information.

Specifically, three-dimensional information is input into a pre-trained three-dimensional information segmentation model, the three-dimensional information is segmented into a plurality of three-dimensional unit information, and current three-dimensional unit information is acquired.

Step S202, based on the current three-dimensional unit information, the shape and the motion trail corresponding to the current three-dimensional unit information are obtained.

The shape is the shape outline of the current three-dimensional unit information, and the motion trail is the path through which the current three-dimensional unit information moves.

Specifically, three-dimensional pixel points forming the current three-dimensional unit information are obtained, coordinates of the three-dimensional pixel points are input into a pre-trained shape recognition model to obtain a shape corresponding to the current three-dimensional unit information, then a center three-dimensional pixel point of the current three-dimensional unit information is obtained, and a motion track corresponding to the current three-dimensional unit information is obtained according to the motion track of the center three-dimensional pixel point.

In step S203, if the shape and the motion trajectory meet the living body determination condition, the current three-dimensional unit information is living body information.

The living body judging condition is that the shape accords with the shape of a shape library of a preset human body part, and the movement track is matched with the movement habit of the human body part corresponding to the shape.

Specifically, if the shape belongs to the shape of the shape library of the preset human body part, and the motion trail is matched with the motion habit of the human body part corresponding to the shape, the current three-dimensional unit information is living body information.

In step S204, if the shape and the motion trajectory belong to the non-living body determination condition, the current three-dimensional unit information is non-living body information.

The living body judging condition is that the shape does not belong to the shape of a preset human body part shape library, or the movement track is not matched with the movement habit of the human body part corresponding to the shape.

Specifically, if the shape does not belong to the shape of the preset human body part shape library, or the movement track is not matched with the movement habit of the human body part corresponding to the shape, the current three-dimensional unit information is non-living information.

In this embodiment, the three-dimensional information is divided into a plurality of three-dimensional unit information to obtain the shape and the motion trajectory corresponding to the current three-dimensional unit information, and then if the shape and the motion trajectory meet the living body determination condition, the current three-dimensional unit information is the living body information, and if the shape and the motion trajectory belong to the non-living body determination condition, the current three-dimensional unit information is the non-living body information, so that the living body information and the non-living body information corresponding to the target person can be accurately identified from the three-dimensional information.

In one embodiment, as shown in fig. 3, according to the non-living body information, a fitting identification result of a fitting carried by a target person is obtained, which includes the following steps:

step S301, if the non-living body information is not zero, determining that the target person carries an accessory, and detecting whether the non-living body information has reflection point information or not; the reflection point information is used to characterize the accessory as an accessory contained in an accessory information library.

The information of the reflection points is obtained by shooting the reflection points of accessories attached to an accessory information base in advance, and the accessory information base is the accessory information recorded in a financial service server room.

Specifically, if the non-living body information does not exist, it is determined that the target person carries the accessory, and whether the non-living body information exists or not is detected.

In step S302, if no reflection point information exists in the non-living body information, the accessory identification result is that the accessory is abnormal. Specifically, if the reflection point information does not exist in the non-living body information, the accessory is not recorded in the financial service server room, namely the accessory identification result is that the accessory is abnormal.

Step S303, if the reflecting point information exists in the non-living body information, acquiring image information corresponding to the accessory, and acquiring the accessory type corresponding to the accessory from an accessory information base according to the image information.

The image information is a three-dimensional data image corresponding to the accessory, and the accessory type is the type of the accessory.

Specifically, if the reflection point information exists in the non-living body information, the accessory is an accessory recorded in a financial service server room, namely, the accessory identification result is that the accessory is normal, then image information corresponding to the accessory is obtained, the specific model of the accessory is determined according to the image information, and then the accessory type corresponding to the accessory is obtained from an accessory information base according to the specific model of the accessory, wherein the accessory type comprises but is not limited to equipment, wires, tools, modules, other types and the like.

Step S304, based on the accessory type, acquiring an accessory identification result of the accessory carried by the target person when the reflection point information exists in the non-living body information.

Specifically, according to whether the fitting type is matched with the target person, the fitting identification result of the fitting carried by the target person is judged in the case that the reflection point information exists in the non-living body information.

In this embodiment, if the non-living body information is not zero, the target person is determined to carry the accessory, whether the non-living body information has the reflection point information is detected, if the non-living body information does not have the reflection point information, the accessory identification result is that the accessory is abnormal, if the non-living body information has the reflection point information, the image information corresponding to the accessory is obtained, the accessory type corresponding to the accessory is obtained from the accessory information base according to the image information, and finally, the accessory identification result of the accessory carried by the target person can be reasonably and accurately obtained according to whether the accessory type is matched with the target person or not, and under the condition that the reflection point information exists in the non-living body information, the accessory identification result of the accessory carried by the target person is judged.

In one embodiment, as shown in fig. 4, based on the accessory type, when the reflection point information exists in the non-living body information, the accessory identification result of the accessory carried by the target person is obtained, which includes the following steps:

in step S401, if the reflection point information exists in the non-living body information, if the accessory information matches with the personal identification information, the accessory identification result is that the accessory is normal.

Specifically, when the reflection point information exists in the non-living body information, if the accessory information is identical to the personnel identity information, the accessory identification result is that the accessory is normal.

In step S402, if the accessory information does not match with the personnel identity information, the accessory identification result is that the accessory is abnormal.

Specifically, when the reflection point information exists in the non-living body information, if the accessory information is inconsistent with the personnel identity information, the accessory identification result is that the accessory is normal.

In this embodiment, under the condition that the reflection point information exists in the non-living body information, if the accessory information is matched with the personnel identity information, the accessory identification result is that the accessory is normal, and if the accessory information is not matched with the personnel identity information, the accessory identification result is that the accessory is abnormal, so that the accessory identification result of the accessory carried by the target personnel can be reasonably and accurately obtained.

In one embodiment, the living body information includes face information of the target person and limb dynamic information; according to living body information, obtaining an identity recognition result of a target person and a behavior recognition result corresponding to the target person, wherein the method comprises the following steps of:

according to the facial information, personnel identity information of a target person is obtained, and according to limb dynamic information, personnel behavior information corresponding to the target person is obtained; and obtaining an identity recognition result corresponding to the target person by using the person identity information, and obtaining a behavior recognition result corresponding to the target person by using the person behavior information.

The face information is a face three-dimensional data image of the target person, and the limb dynamic information is a limb movement track combination of the target person.

Specifically, inputting the facial information into a pre-obtained facial recognition model to obtain personnel identity information of a target personnel, and then obtaining an identity recognition result corresponding to the target personnel according to whether the personnel identity information is in a preset personnel identity information base; inputting the limb dynamic information into a pre-obtained limb dynamic identification model to obtain behavior information of the target personnel, and obtaining a behavior identification result corresponding to the target personnel according to whether the personnel behavior information is in a preset abnormal behavior information base.

According to the embodiment, the personnel identity information of the target personnel is obtained according to the face information, then the personnel identity information is utilized to obtain the identity recognition result corresponding to the target personnel, and then the personnel behavior information corresponding to the target personnel is obtained according to the limb dynamic information; and the behavior information of the personnel is utilized to obtain the behavior recognition result corresponding to the target personnel, so that the behavior recognition result and the identity recognition result of the target personnel can be reasonably and accurately obtained.

In one embodiment, the step of obtaining the identity recognition result corresponding to the target person by using the person identity information includes the following steps:

if the pre-obtained computer room staff library contains staff identity information, the identity recognition result corresponding to the target staff is that the staff identity is normal; if no personnel identity information exists in the pre-obtained computer room personnel library, the identity recognition result corresponding to the target personnel is abnormal personnel identity.

The machine room staff library is a machine room staff list recorded in the financial business machine room.

Specifically, when personnel identity information is contained in the machine room personnel library, the identity recognition result is normal to personnel identity, and then when no personnel identity information is contained in the machine room personnel library, the identity recognition result is abnormal to personnel identity.

In this embodiment, if the machine room staff library contains staff identity information, the identity recognition result is that the staff identity is normal, and if the machine room staff library does not have staff identity information, the identity recognition result is that the staff identity is abnormal, so that whether the identity recognition result corresponding to the target staff is that the staff identity is abnormal can be accurately and reasonably judged.

In one embodiment, the behavior recognition result corresponding to the target person is obtained by using the person behavior information, and the method comprises the following steps:

if the obtained abnormal behavior library contains personnel behavior information, the behavior recognition result corresponding to the target personnel is abnormal personnel behavior; if no personnel behavior information exists in the obtained abnormal behavior library, the behavior recognition result corresponding to the target personnel is that the personnel behaviors are normal.

The abnormal behavior library is a list of abnormal behaviors when personnel enter and exit the machine room in advance.

Specifically, when the abnormal behavior library contains personnel behavior information, the behavior recognition result is that the personnel behavior is abnormal, and when the abnormal behavior library does not contain personnel behavior information, the behavior recognition result is that the personnel behavior is normal.

In this embodiment, when the abnormal behavior library includes the personnel behavior information, the behavior recognition result is that the personnel behavior is abnormal, and when the abnormal behavior library does not include the personnel behavior information, the behavior recognition result is that the personnel behavior is normal, so that whether the behavior recognition result corresponding to the target personnel is that the personnel behavior is abnormal can be accurately and reasonably determined.

In an application embodiment, a machine room personnel management device based on three-dimensional modeling is provided, as shown in fig. 5, and mainly includes the following components: the system comprises a personnel information acquisition device, an information transmission device, a personnel identification information processing device and a three-dimensional modeling display device. The connection relationship between the personnel information acquisition device and the three-dimensional modeling display device is that the output port of the personnel information acquisition device is connected with the input port of the personnel identification information processing device through the information transmission device, and the output port of the personnel identification information processing device is connected with the three-dimensional modeling display device through the information transmission device.

The personnel information acquisition device has the function of scanning the three-dimensional information of the complete state of personnel entering and exiting the machine room. The information transmission device is used for transmitting the three-dimensional scanning information acquired by the personnel information acquisition device and the three-dimensional recognition result information processed by the personnel recognition information processing device. The personnel identification information processing device has the functions of combining the three-dimensional information of the complete body states of personnel entering and exiting the machine room, which is captured by the personnel information acquisition device transmitted by the information transmission device, and combining the existing personnel library to perform personnel type identification, held accessory identification, abnormal behavior and abnormal article carrying identification. The personnel identification information processing device comprises a three-dimensional information disassembling unit, a three-dimensional information analyzing unit and a three-dimensional information integrating unit. The connection relationship between the three-dimensional information disassembly unit and the personnel identification information processing device is that the output port of the three-dimensional information disassembly unit is connected with the input port of the personnel identification information processing device, the input port of the three-dimensional information analysis unit is connected with the output port of the three-dimensional information disassembly unit, and the input port of the three-dimensional information integration unit is connected with the output port of the three-dimensional information analysis unit. The three-dimensional information disassembling unit is used for disassembling three-dimensional information of personnel entering and exiting the machine room according to the body part; the three-dimensional information analysis unit has the functions of analyzing face information of personnel according to the characteristics of body parts and screening a personnel information base for distinguishing information and types of personnel entering and exiting; analyzing hand information of personnel, screening a fitting information base, and distinguishing fittings held by the personnel; and analyzing the information of other body parts such as hands, legs and the like of the personnel, and confirming the abnormal behaviors of the personnel and the carrying information of abnormal articles. The three-dimensional information integration unit is used for integrating the processing results of the three-dimensional information analysis unit in three dimensions to give complete information of people entering and exiting. The three-dimensional modeling display device has the functions of displaying the types of the in-out personnel and the accessories which are recognized by the personnel recognition information processing device on the basic framework of the visual machine room, displaying the abnormal behaviors and abnormal articles of the in-out personnel and providing alarming and reminding for operation and maintenance personnel of the machine room.

In an application embodiment, a machine room personnel management method based on three-dimensional modeling is further provided, as shown in fig. 6, specifically including the following steps:

step 1: when people enter and exit the machine room, the information acquisition device can acquire the information of entering and exiting the machine room, store the complete three-dimensional information of the people and perform information acquisition processing.

The information acquisition device mainly comprises: the infrared sensor is used for automatically sensing the human body and the moving direction of the human body in and out; the image collector adopts a plurality of high-speed depth cameras and optical cameras to start three-dimensional image collection for personnel in an in-out monitoring range, and realizes collection and capture of main target characteristic points (face, hand and shielding) from different angles (front, back, left side, right side and top). The depth camera adopts infrared rays as a light source, records the intensity information of the light source and the time from the light source to pixel points in the image, can identify the distance from each pixel point in the image to the camera, and acquires the color and depth value of the image. The optical camera is composed of an optical lens, emits infrared light outwards, and the infrared light contacts with the reflecting point in the monitoring range to generate reflection for special article identification (the reflecting point is posted by the default of the real object accessory in the warehouse, and the reflecting point is not posted by the real object accessory in the warehouse).

Step 2: the information transmission device receives the information scanned by the information acquisition device and transmits the information to the personnel identification information processing device for further processing.

Step 3: the personnel identification information processing device enters a three-dimensional information disassembling unit through the received personnel three-dimensional information to conduct information identification and disassembly.

The three-dimensional information disassembly unit is used for carrying out feature extraction and identification through the front, back, left side, right side, top video and image information acquired at the same moment, so as to realize the disassembly of the following contents: living body information: a. personnel point location information taking the head of a human body as a main identification target; b. facial image information of different persons; c. capturing the motion of other parts such as hands, legs and the like; non-living body information: capturing static objects at other parts such as hands, legs and the like, and a, optically capturing object reflection point information; b. physical image information and depth information.

Step 4: and a three-dimensional information analysis unit of the personnel identification information processing device, which is used for combining living body information, confirming the number of people by using personnel point positions, carrying out face detection analysis by using different person face image information, screening a personnel information base, distinguishing whether the personnel in and out are in-base personnel or not, and if yes, turning to step 5, otherwise turning to step 9.

The method comprises the following steps: the person identification information processing device processes the non-living body information of the person in the warehouse as the face analysis result, judges whether accessories are carried, if the non-living body information exists, judges that the person identification information processing device is yes, and goes to the step 6, otherwise goes to the step 8.

Step 6: and judging whether accessories held by the in-and-out personnel are in-store accessories according to the real object reflection point information in the non-living body information, if yes, turning to the step 7, otherwise turning to the step 8.

Step 7: for the in-library accessories, the accessory information library (mainly classified into equipment, wire, tool, module and other types) is screened according to the physical image information and depth information in the non-living body information, the specific accessory types are distinguished, and personnel and accessory information are stored, and the step goes to step 8.

Step 8: analyzing according to motion capture of other parts such as hands, legs and the like in the living body information, matching a body state abnormal behavior library (dynamic gesture recognition (e.g. help seeking) and dynamic body state recognition (e.g. fall)), judging whether the behavior is abnormal, if yes, turning to step 9, otherwise turning to step 10;

step 9: if the step 4 is judged to be "no", the machine room entrance and exit personnel are determined to be abnormal, if the step 6 is judged to be "no", the machine room entrance and exit accessories are determined to be abnormal, the machine room entrance and exit accessories are determined to carry abnormal articles, if the step 7 is judged to be "yes", the machine room entrance and exit personnel are determined to be abnormal, and the step 10 is proceeded.

Step 10: and (5) judging the step 8 to be no, and judging that the personnel entering and exiting the machine room are normal (the personnel in the warehouse, the personnel not carrying accessories or the accessories carried in the warehouse, and no abnormal behavior exists). And proceeds to step 11.

Step 11: the three-dimensional information integrating unit integrates the information of the abnormal information processed and analyzed in the step 8 into an abnormal database (personnel, articles and behaviors), and integrates the normal database (storing in and out records (information of personnel in the library, no abnormal behaviors, information of parts not carried/carried in the library) of the normal information processed and analyzed in the step 7.

Step 12: the personnel identification information processing device transmits normal/abnormal database information to the three-dimensional modeling display device through the information transmission device by integrating a unit processing result completion instruction.

Step 13: the three-dimensional modeling display device displays the normal/abnormal behaviors of the type of the person entering and exiting and the type of the accessory held by the person identification information processing device on the basis of the visual machine room through the function of receiving information, displays the abnormal behaviors of the person entering and exiting and the abnormal objects, and provides alarming reminding for operation and maintenance personnel of the machine room.

In the method, the invention provides the visual management method for the machine room access personnel based on the three-dimensional modeling, which aims at the situations of multiple access personnel and complex access personnel of the research machine room personnel, solves the problem of insufficient management of the personnel and accessories of the existing machine room, greatly reduces the manpower, material resources and time of the operation and maintenance personnel of the machine room, and can monitor and manage the machine room more comprehensively.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides an access room personnel monitoring device for realizing the access room personnel monitoring method. The implementation scheme of the solution provided by the device is similar to the implementation scheme described in the above method, so the specific limitation in the embodiment of the one or more personnel monitoring devices for the access machine room provided below may refer to the limitation of the personnel monitoring method for the access machine room in the above description, and will not be repeated here.

In one embodiment, as shown in fig. 7, there is provided a personnel monitoring apparatus for an access room, including: an information acquisition module 701 module, an identity and behavior recognition module 702, an accessory recognition module 703 and a personnel monitoring module 704, wherein:

the information acquisition module 701 is configured to acquire three-dimensional information corresponding to a target person entering and exiting the financial service server room, and identify living information and non-living information corresponding to the target person from the three-dimensional information;

the identity and behavior recognition module 702 is configured to obtain, according to the living body information, an identity recognition result of a target person and a behavior recognition result corresponding to the target person;

the accessory identification module 703 is configured to obtain an accessory identification result of an accessory carried by the target person according to the non-living information;

and the personnel monitoring module 704 is used for displaying the identification result, the behavior identification result and the accessory identification result on the three-dimensional information in the monitoring display interface.

In one embodiment, the information obtaining module 701 is further configured to divide the three-dimensional information into a plurality of three-dimensional unit information, and obtain current three-dimensional unit information from the plurality of three-dimensional unit information; based on the current three-dimensional unit information, obtaining a shape and a motion track corresponding to the current three-dimensional unit information; if the shape and the motion trail meet the living body judging conditions, the current three-dimensional unit information is living body information; if the shape and the motion trail meet the non-living body judging condition, the current three-dimensional unit information is non-living body information.

In one embodiment, the accessory identification module 703 is further configured to determine that the target person carries the accessory if the non-living body information is not zero, and detect whether the non-living body information has reflective point information; the reflection point information is used for representing the fitting as the fitting contained in the fitting information base; if the non-living body information does not contain the reflection point information, the accessory identification result is that the accessory is abnormal; if the non-living body information contains the reflection point information, acquiring image information corresponding to the accessory, and acquiring accessory types corresponding to the accessory from an accessory information base according to the image information; based on the fitting type, a fitting identification result of the fitting carried by the target person is obtained when the reflection point information exists in the non-living body information.

In one embodiment, the accessory identification module 703 is further configured to, if the accessory information matches with the personnel identity information in the case where the reflection point information exists in the non-living body information, determine that the accessory is normal; if the accessory information is not matched with the personnel identity information, the accessory identification result is that the accessory is abnormal.

In one embodiment, the identity and behavior recognition module 702 is further configured to obtain personnel identity information of the target personnel according to the facial information, and obtain personnel behavior information corresponding to the target personnel according to the limb dynamic information; and obtaining an identity recognition result corresponding to the target person by using the person identity information, and obtaining a behavior recognition result corresponding to the target person by using the person behavior information.

In one embodiment, the identity and behavior recognition module 702 is further configured to, if the pre-obtained machine room staff library includes staff identity information, determine that the identity recognition result corresponding to the target staff is that the staff identity is normal; if no personnel identity information exists in the pre-obtained computer room personnel library, the identity recognition result corresponding to the target personnel is abnormal personnel identity.

In one embodiment, the identity and behavior recognition module 702 is further configured to, if the obtained abnormal behavior library includes personnel behavior information, determine that the behavior recognition result corresponding to the target personnel is abnormal; if no personnel behavior information exists in the obtained abnormal behavior library, the behavior recognition result corresponding to the target personnel is that the personnel behaviors are normal.

All or part of the modules in the personnel monitoring device of the access machine room can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by the processor, implements a method for monitoring personnel in and out of a machine room. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. The method for monitoring personnel in and out of a machine room is characterized by comprising the following steps:

2. The method according to claim 1, wherein the identifying the living body information and the non-living body information corresponding to the target person from the three-dimensional information includes:

dividing the three-dimensional information into a plurality of three-dimensional unit information, and acquiring current three-dimensional unit information from the plurality of three-dimensional unit information;

based on the current three-dimensional unit information, obtaining a shape and a motion track corresponding to the current three-dimensional unit information;

if the shape and the motion trail meet the living body judging condition, the current three-dimensional unit information is the living body information;

and if the shape and the motion trail meet the non-living body judging condition, the current three-dimensional unit information is the non-living body information.

3. The method according to claim 1, wherein the obtaining, based on the non-living body information, a fitting recognition result of the fitting carried by the target person includes:

If the non-living body information is not zero, determining that the target person carries an accessory, and detecting whether the non-living body information has reflection point information or not; the reflection point information is used for representing that the accessory is an accessory contained in an accessory information base;

if the non-living body information does not contain the reflection point information, the accessory identification result is that the accessory is abnormal;

if the non-living body information contains the reflection point information, acquiring image information corresponding to the accessory, and acquiring accessory types corresponding to the accessory from the accessory information base according to the image information;

and obtaining an accessory identification result of the accessory carried by the target person under the condition that the reflecting point information exists in the non-living body information based on the accessory type.

4. The method according to claim 3, wherein the obtaining, based on the accessory type, an accessory identification result of an accessory carried by the target person in a case where reflection point information exists in the non-living body information includes:

under the condition that reflection point information exists in the non-living body information, if the accessory information is matched with the personnel identity information, the accessory identification result is that the accessory is normal;

And if the accessory information is not matched with the personnel identity information, the accessory identification result is that the accessory is abnormal.

5. The method according to claim 1, wherein the living body information includes facial information and limb dynamic information of the target person;

the step of obtaining the identification result of the target person and the corresponding behavior identification result of the target person according to the living body information comprises the following steps:

according to the facial information, personnel identity information of the target personnel is obtained, and according to the limb dynamic information, personnel behavior information corresponding to the target personnel is obtained;

and obtaining an identity recognition result corresponding to the target person by using the personnel identity information, and obtaining a behavior recognition result corresponding to the target person by using the personnel behavior information.

6. The method of claim 5, wherein the obtaining, by using the person identity information, the identity recognition result corresponding to the target person includes:

if the personnel identity information is contained in the pre-obtained computer room staff library, the identity recognition result corresponding to the target personnel is that the personnel identity is normal;

If the personnel identity information is not in the pre-obtained computer room personnel library, the identity recognition result corresponding to the target personnel is abnormal personnel identity.

7. The method according to claim 5, wherein the obtaining, by using the person behavior information, a behavior recognition result corresponding to the target person includes:

if the obtained abnormal behavior library contains the personnel behavior information, the behavior recognition result corresponding to the target personnel is abnormal personnel behavior;

if the obtained abnormal behavior library does not have the personnel behavior information, the behavior recognition result corresponding to the target personnel is that the personnel behavior is normal.

8. An access room personnel monitoring device, the device comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.