CN112383615A - Residential building entrance guard security system and method based on edge calculation - Google Patents
Residential building entrance guard security system and method based on edge calculation Download PDFInfo
- Publication number
- CN112383615A CN112383615A CN202011259591.6A CN202011259591A CN112383615A CN 112383615 A CN112383615 A CN 112383615A CN 202011259591 A CN202011259591 A CN 202011259591A CN 112383615 A CN112383615 A CN 112383615A
- Authority
- CN
- China
- Prior art keywords
- event
- visitor
- information
- edge
- edge computing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims description 28
- 230000001815 facial effect Effects 0.000 claims description 7
- 230000006399 behavior Effects 0.000 description 23
- 238000012545 processing Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
Abstract
The utility model provides a residential building entrance guard security system and a method based on edge calculation, which comprises the following steps: the system comprises edge computing nodes, edge servers and cloud servers; the edge compute node, as a local device, is configured to: receiving visitor visiting information and image information of visitors, establishing an event, carrying out face recognition, number recognition and behavior recognition on the visitors, and classifying danger levels of the event; the edge server is communicated with at least one edge computing node, receives all level events uploaded by the edge computing node, screens the level events, and uploads screened event information to the cloud server; the cloud server is configured to issue information to owners involved in the screened events.
Description
Technical Field
The disclosure belongs to the technical field of intelligent buildings, and particularly relates to a residential building entrance guard security system and method based on edge calculation.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In community property management, access control and security systems are related to the life and property safety of owners. In the traditional field, security systems mainly rely on unit building doors and surveillance cameras.
Generally speaking, the surveillance cameras of all communities can be centralized in one surveillance room for manual surveillance, the workload of surveillance personnel is large and inaccurate, effective security conditions cannot be provided, serious security events are generated under general conditions, rapid reaction is difficult to make, and the hysteresis for protecting the security of lives and properties of owners is large.
Disclosure of Invention
In order to overcome the defects of the prior art, the residential building entrance guard security system based on edge computing is provided, cloud computing is replaced by the local computing nodes, the residential building entrance guard security system has the advantages of being good in real-time performance and confidentiality, and private information of an owner is guaranteed not to be revealed. The application of the edge computing node in the access security system can improve the working efficiency of monitoring personnel and reduce the workload.
In order to achieve the above object, one or more embodiments of the present disclosure provide the following technical solutions:
in a first aspect, a residential building entrance guard security system based on edge computing is disclosed, comprising:
the system comprises edge computing nodes, edge servers and cloud servers;
the edge compute node, as a local device, is configured to: receiving visitor location information and visitor image information, establishing an event, carrying out face recognition, number recognition and behavior recognition on visitors, and classifying danger levels of the event;
the edge server is communicated with at least one edge computing node, receives all level events uploaded by the edge computing node, screens the level events, and uploads screened event information to the cloud server;
the cloud server is configured to issue information to owners involved in the screened events.
In a further technical scheme, the edge computing node is an open platform type intelligent computer, and the computed data is transmitted through the internet.
According to the technical scheme, the system comprises a camera module, specifically comprises a unit door camera and a floor camera, personnel images collected by the unit door camera are transmitted to an edge computing node and used for completing a face recognition task, and personnel images collected by the floor camera are used for completing a number recognition task.
According to the technical scheme, the edge computing server locally stores personnel information in the residential building, the edge computing node compares the received information with the information stored by the edge computing server when judging the identity of the visitor, and if the received information is consistent with the information stored by the edge computing server, the personnel in the residential building are locally stored.
According to the technical scheme, the cloud server is communicated with the cloud platform, the cloud platform serves as an integral information issuing platform and comprises a property end and a client, and the client receives property management information related to residents and security event information pushed by the property management information.
The property terminal functions include viewing video surveillance, broadcasting warnings, issuing event information, viewing past events and their surveillance videos. The data processing comprises the classification and storage of events.
According to the further technical scheme, after obtaining visitor information, the edge computing node establishes an event, and information related to the visitor is defined as the content of the event;
and after the event is established, comparing the acquired visitor information with the facial features of the owner in the database of the edge computing server to determine the identity of the visitor.
In a further technical scheme, the edge server marks the event.
The mark refers to the event characteristics, including the level of the event and the person corresponding to the event, and the marking function of the event is to facilitate the corresponding processing of the edge node, for example, two persons enter the camera area from front to back and appear again after leaving the camera area, and can be re-identified and correspond to the previously established event.
And marking is to add the face recognition information of the personnel as event information for storage, and compare the face recognition information with the event information when the personnel appears again to determine that the event corresponds to the event.
In a second aspect, a working method of a residential building entrance guard security system based on edge computing is disclosed, which comprises the following steps:
after obtaining the identity information of the visitor, the edge computing node firstly establishes an event and defines the information related to the visitor as the content of the event;
after establishing an event, the edge computing node compares the acquired visitor information with the facial features of the owner in the database to determine the identity of the visitor;
when the visitor arrives at each floor, the floor camera identifies the identity and the behavior of the visitor, firstly determines whether the visitor is the visitor who collects information before, then judges whether the floor where the visitor stays is consistent with the collected information, and judges the danger level of the event based on the stay time on the floor;
when a visitor enters a destination or leaves a residential building, the edge node classifies events according to security threat degrees, stores all levels of events in the edge server, screens event information of set danger levels, uploads the event information to the cloud server, informs a business owner related to the events through a cloud platform client, and obtains event video content related to the business owner from the edge computing node.
According to the further technical scheme, when the residence time of the visitor in the corridor is within a first set range, the safety threat of the event is judged to be low, and the risk level of the event is defined as level 2;
when the residence time of the visitor in the corridor is in a second set range, the edge node defines the danger level of the event as 3 level;
when the danger level reaches level 3, the edge server notifies security personnel of the monitoring room through the property management module;
if the visitor behavior poses a life safety threat to the owner, the event risk level is defined as level 4.
Further technical scheme, to one-level dangerous event keep the photo, do not keep the video, to second grade dangerous event, keep the photo, the video is kept to the short time, to third grade dangerous event, keep photo and video for a long time, and this kind of event keeps observing the control picture, to fourth grade dangerous event, the image data is kept in order as the evidence forever to blockade building door, broadcast warning and warn the owner.
The above one or more technical solutions have the following beneficial effects:
according to the edge computing technology in the technical scheme, cloud computing is replaced by the local computing nodes, the edge computing technology has the advantages of being good in instantaneity and confidentiality, and private information of an owner is guaranteed not to be leaked. The application of the edge computing node in the access security system can improve the working efficiency of monitoring personnel, reduce the workload, improve the response speed to security events, better protect the life and property safety of owners, and reduce the occurrence of 'no awareness in advance and video turning over after the events'.
The technical scheme can better prevent the occurrence of community security events, quickly process the security events and protect the life and property safety of community owners. The method has the advantages that the working efficiency of monitoring personnel, the problem solving speed and the information privacy of owners are considered at the same time, and meanwhile, the security event processing method is essentially judged by property management personnel, so that the condition that the interests of the owners and visitors are damaged due to algorithm rigid can not occur.
The technical scheme can automatically acquire visitor information and behavior establishment events, identify identities and automatically judge whether behavior modes of visitors threaten life and property safety of residents. The system has stronger flexibility for processing events, and for behaviors which possibly form security threats, the processing mode is to inform monitoring personnel to carry out subjective judgment through the property management system, and simultaneously store related video records and carry out event marking.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a specific architecture of the system shown in an embodiment of the present disclosure;
FIG. 2 is a flow diagram illustrating the flow of information in an event according to an embodiment of the present disclosure;
FIG. 3 is a flowchart of the overall operation of the system when an event occurs, according to an embodiment of the present disclosure;
fig. 4 is an operation flow of an access security system in an embodiment of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example one
The embodiment discloses residential building entrance guard security protection system based on edge calculation, should include at least in residential building entrance guard security protection system of edge calculation:
the system comprises edge computing nodes, edge servers and cloud servers;
an edge compute node as a local device configured to: receiving visitor visiting information and image information of visitors, establishing an event, carrying out face recognition, number recognition and behavior recognition on the visitors, and classifying danger levels of the event;
the edge server is communicated with at least one edge computing node, receives all level events uploaded by the edge computing node, screens the level events and uploads screened event information to the cloud server;
the cloud server is configured to issue information to owners involved in the screened events.
In a further implementation example, fig. 1 is an architecture diagram of an intelligent access control and security system based on edge computing according to an embodiment, please refer to fig. 1, where the intelligent access control and security system is applicable to most urban residential districts. The system comprises a unit access control keyboard module 101, a high-definition access control camera 102, a floor camera 103, an edge computing node 104, a property management system 105, an edge computing server 106, a cloud server 107 and a cloud platform 108.
Fig. 4 is an operation flow of the access security system. The system deduces the identity, purpose and behavior of the visitor according to an intelligent operation method, determines whether security threats exist to owners or not through objective conditions and subjective judgment of property personnel, can improve the working efficiency of property security personnel, and reduces the workload.
In an intelligent access and security system, a unit access keyboard module 101 is an important module for determining the identity and destination of a coming person.
Generally, the visitor is notified to the owner through the unit access keypad so that the visitor's destination can be determined. After entering the unit door, the visitor performs a face recognition module through the high-definition camera 102 and the edge node 104 to acquire identity information of the visitor.
Every floor all sets up floor camera and edge calculation node, a plurality of edge calculation nodes correspond an edge calculation server, set up for seat or many resident's buildings as the unit, edge calculation node can support more complicated intelligent program operation, can carry out the operation of data, save and transmit, provide the calculation service of single or multiple floor, mainly include calculation tasks such as face identification, number of people discernment, time judgement, can operate the multiple software of upgrading, can carry out data transmission through the internet.
The operation content of the edge calculation node is face identification, number identification, time judgment, event grade judgment and the like. Storing the event with the content not ended. And the transmission content uploads the finished event information and the related monitoring record to an edge computing server for storage.
Specifically, the edge computing node is an open platform type intelligent computer, can carry multiple functions, and can process computing tasks including but not limited to an access security system, a property management system and an energy management system. The edge computing node can quickly complete most of computing work, ensure that security work is quick and real-time, can perform face recognition and number recognition, quickly determine the danger level of visitors by comparing with a database, can perform personnel behavior judgment, improve or reduce the danger level of visitors, determine whether the security personnel need to manually determine whether the visitor behavior is legal or not,
the edge computing server is used for receiving computing results and collected data of edge nodes and sending corresponding key information to the cloud server, and the cloud platform is used for issuing visitor information and property management information. The edge computing server is used for locally storing personnel information in a residential building, supporting the edge computing node to quickly judge the identity of a visitor and preventing privacy information of an owner from being leaked.
According to the technical scheme, the edge computing server is local, so that the response speed is high. Because the content is not uploaded to the Internet, the security performance is good.
The edge computing server is also communicated with a property management module, the property management module comprises a traditional monitoring picture module and a notification alarm system, and the effect of the edge computing server is to notify security personnel and call out related monitoring pictures at the first time when the edge computing node judges that the behavior of the visitor needs to be artificially judged.
According to the technical scheme, the visitor target and the identity are known through the cell entrance guard; judging the target of the visitor through the floor camera; determining, via the algorithmic logic of the edge computing node, whether the guest poses a security threat; judging whether the actual behavior of the visitor generates a security threat or not by the property management personnel; the personnel event processing method is completely determined by the property management personnel, and the system only carries out notification and event information storage.
The technical scheme disclosed by the invention judges the identity, the purpose and the behavior of the visitor, so that monitoring personnel do not need to monitor a large number of monitoring pictures all day, the workload of property management personnel is reduced, and the working efficiency is increased. The edge computing node module collects visitor information through a unit door keyboard and each floor camera. Judging the destination of the visitor through the key of the visitor; carrying out face recognition through cameras before and after entering a building door; and comparing the visitor information with the owner face information in the database to judge whether the visitor is the visitor or not and judge the destination floor of the visitor.
The edge computing nodes identify the number of people according to the cameras of each floor, judge whether the residence time of visitors threatens the safety of residents or not through programs stored in the edge computing nodes, and judge whether monitoring personnel need to observe, warn and alarm according to logic (namely logic for judging personnel danger levels shown by an algorithm). And manual intervention is not considered at a low risk level, so that the possibility of leakage of owner privacy information is reduced, and the workload of property management personnel is reduced. And the monitoring personnel is notified at a higher risk level, so that the final event processing result is judged by the personnel, and the possibility of oolong events caused by program logic death is reduced.
The owner information collection is completed through the property management system, is directly stored in the edge computing server, cannot be uploaded to the cloud platform, and guarantees that the owner information cannot be leaked on the Internet. After the low-risk level visitor determines that no security threat exists, the event and the monitoring content of the visitor are stored in the edge computing server, and the risk of privacy information disclosure is reduced.
The property management system is communicated with the owner and security personnel through the edge nodes and the cloud platform, and can actively inform the security personnel and alarm through the access control equipment and the cloud platform client when a security event occurs, so that the flexibility of the system for processing the event is ensured.
In one embodiment of the invention, the visitor information comprises facial feature information, floor stay information, destination information and video behavior information.
In an embodiment of the invention, the calculation tasks such as face recognition, people number recognition and behavior recognition are undertaken through the edge nodes, so that the calculation speed and the transmission speed are increased, and the real-time performance is better. Can correspond visitor and incident through the discernment of posture and dress in the edge calculation node, through video acquisition visitor action information, like visitor dwell time, visitor's the upstairs and downstairs many times, signal such as visitor's floor owner warning can all judge that the visitor constitutes the threat to building owner's security of lives and property.
The number recognition can be realized by various existing technologies, belongs to the prior art, is not explained in detail here, and the behavior recognition is mainly judged by the stay time of contact persons in a certain layer.
In an embodiment of the invention, the identity information of the visitor is stored in the edge computing server, and is not uploaded to a cloud platform for public display, so that the privacy of the identity information of the owner and the visitor is ensured.
In an embodiment of the invention, the edge computing server stores facial information characteristics of the owners in the building, and aims to reduce the disturbance of security personnel on the owners in the building and facilitate the use of the owners.
In one embodiment of the invention, the potential threat level of the visitor is judged through face recognition, floor monitoring and residence time, and whether a monitoring person is informed to judge is determined.
In one embodiment of the invention, the visitor visit is taken as an event for storage, processing, notification and public notice, wherein only the event really threatening the safety of the lives and properties of the owners is disclosed.
In an embodiment of the invention, the visitor information can be automatically judged under the condition of not losing owner data information through the calculation of the edge calculation node and the storage of the edge calculation server, so that the purposes of recording and security protection are achieved.
In an embodiment of the invention, the cloud platform as an integral information publishing platform comprises a property end and a client end, and the client end can receive property management information and important security event information related to residents.
In an embodiment of the invention, the property management module comprises a traditional monitoring module and an automatic security alarm module, wherein when a serious event judged by the edge calculation module occurs, a monitoring person is notified through the automatic security alarm module and a monitoring image of an event occurrence place is cut in, so that the security efficiency and the real-time property are improved.
Example II
The purpose in this embodiment is to provide a working method of a residential building entrance guard security system based on edge computing, specifically, including:
the edge compute node 104, upon obtaining the guest identity information, first creates an event, defining information associated with the guest as the event content.
The edge computing node 104, upon establishing the event, compares the collected guest information to the owner facial features in the database to determine the identity of the person (guest or owner).
After the visitor arrives at each floor, the floor camera 103 identifies the identity and behavior of the visitor, first determines whether the visitor is the visitor who previously acquired information, then determines whether the visitor stays at the floor consistent with the acquired information, and determines whether the visitor stays at the floor for too long.
When the visitor stays in the corridor for a short time, the security threat of the event can be judged to be low, and the risk level of the event is defined as level 2.
When the visitor stays in the corridor for too long time (5-10 minutes), the edge node defines the danger level of the event as 3, and property personnel are required to process the event.
When the danger level reaches level 3, the system automatically notifies security personnel in the monitoring room through the property management module 105, and the security personnel checks the visitor monitoring video through the property management module 105, so that the behavior of the visitor is subjectively judged and then fed back to the system.
After the security personnel subjectively judge, under the condition that the behavior of the visitor has life safety threat to the owner, the system is fed back, and then the system defines the risk level of the event as 4 levels.
When the danger level of the event reaches 4 grades, the monitoring personnel can select the processing modes including the modes of blocking the building door, broadcasting an alarm to the owner, rapidly alarming and the like.
When a visitor enters a destination or leaves a residential building, the edge node 104 classifies events according to security threat degrees, stores all levels of events in the edge server 106, screens event information of 3-4 levels of security threat degrees, uploads the event information to the cloud server 107, informs a proprietor related to the event through a cloud platform client, and obtains event video content related to the proprietor from the edge computing node through a property management module.
Fig. 2 is a data flow of the whole system, in which there are three kinds of input signals including unit door dial data, unit door video signals and floor video signals.
The cell gate dialing data may determine: 1. whether the visitor has a unit door key; 2. the destination of the guest is several layers.
The cell gate video signal may determine: visitor identity information.
The floor video signal may determine: 1. visitor identity information 2, visitor dwell time; 3. visitor behavior information.
FIG. 3 is a risk level hierarchy for visitors, with the system determining the severity of the event by the risk level as a basis for retaining visual evidence.
301 level one dangerous event, namely the owner goes home and normal visitor without any suspicious behavior, is not handled generally, and the photo is kept, and the video is not kept.
302 second-level dangerous events, namely that strangers enter floors and arrive at the floors and the floors judged by the dialing data of the unit door do not accord with each other, the processing mode is to keep photos and keep videos for a short time.
303, judging the visitor as a suspicious person when the visitor or stranger stays in the floor public space for too long, wherein the processing mode is to keep photos and videos for a long time, and the event needs security monitoring personnel to continuously observe monitoring pictures and subjectively judge the behavior of the visitor.
The safety protection monitoring personnel judges that the visitors do dangerous behaviors which damage the life and property safety of the owners, or the owners automatically inform the safety protection personnel through the property management system in the 304 level dangerous events. The processing mode is to permanently store the image data as evidence, provide a plurality of processing modes through the system, including blocking the building door, broadcasting warning, warning the owner, needing security and monitoring personnel to alarm or taking mandatory measures to ensure the life and property safety of the owner, and inform the damaged owner of the event content information only through the cloud platform.
The technical scheme mainly comprises the steps of collecting information, establishing an event, collecting new information, increasing a danger level, informing a monitoring person, storing the event, and having the advantages of edge calculation that the small calculation problem can be quickly and directly solved at the tail end, and meanwhile, the data in the nodes can not be uploaded to the cloud end due to the fact that the calculation process is at the end point, so that the private data of a user can be well protected. Compared with conventional calculation, the edge calculation can be calculated and optimized by using group intelligence, and the problems of inaccurate measurement, poor control and the like of the existing building intelligent system are solved.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. The utility model provides a residential building entrance guard security protection system based on edge calculation, characterized by includes:
the system comprises edge computing nodes, edge servers and cloud servers;
the edge compute node, as a local device, is configured to: receiving visitor location information and visitor image information, establishing an event, carrying out face recognition, number recognition and behavior recognition on visitors, and classifying danger levels of the event;
the edge server is communicated with at least one edge computing node, receives all level events uploaded by the edge computing node, screens the level events, and uploads screened event information to the cloud server;
the cloud server is configured to issue information to owners involved in the screened events.
2. The residential building entrance guard security system based on edge computing as claimed in claim 1, wherein the edge computing node is an open platform type intelligent computer, and the computed data is transmitted through internet.
3. The residential building entrance guard security system based on edge calculation as claimed in claim 1, further comprising camera modules, being a cell door camera and a floor camera, wherein the personnel images collected by the cell door camera are transmitted to the edge calculation node for completing the human face recognition task, and the personnel images collected by the floor camera are used for completing the people number recognition task.
4. The residential building entrance guard security system based on edge computing as claimed in claim 1, wherein the edge computing server locally stores personnel information in the residential building, the edge computing node compares the received information with the information stored by the edge computing server when judging the identity of the visitor, and if the received information is consistent with the information stored by the edge computing server, the edge computing node locally stores the personnel in the residential building.
5. The residential building entrance guard security system based on edge computing as claimed in claim 1, wherein the cloud server is in communication with a cloud platform, the cloud platform as an integral information distribution platform comprises a property end and a client end, and the client end receives property management information related to residents and pushed security event information.
6. The residential building entrance guard security system based on edge computing as claimed in claim 1, wherein said edge computing node establishes an event after obtaining the identity information of the visitor, and defines the information related to the visitor as the content of the event;
and after the event is established, comparing the acquired visitor information with the facial features of the owner in the database of the edge computing server to determine the identity of the visitor.
7. An edge computing based home building access security system as claimed in claim 1, wherein the edge server marks the event.
8. A working method of a residential building entrance guard security system based on edge calculation is characterized by comprising the following steps:
after obtaining the identity information of the visitor, the edge computing node firstly establishes an event and defines the information related to the visitor as the content of the event;
after establishing an event, the edge computing node compares the acquired visitor information with the facial features of the owner in the database to determine the identity of the visitor;
when the visitor arrives at each floor, the floor camera identifies the identity and the behavior of the visitor, firstly determines whether the visitor is the visitor who collects information before, then judges whether the floor where the visitor stays is consistent with the collected information, and judges the danger level of the event based on the stay time on the floor;
when a visitor enters a destination or leaves a residential building, the edge node classifies events according to security threat degrees, stores all levels of events in the edge server, screens event information of set danger levels, uploads the event information to the cloud server, informs a business owner related to the events through a cloud platform client, and obtains event video content related to the business owner from the edge computing node.
9. A working method of a residential building entrance guard security system based on edge calculation is characterized in that when a visitor stays in a corridor for a first set range, the security threat of an event is judged to be low, and the danger level of the event is defined as level 2;
when the residence time of the visitor in the corridor is in a second set range, the edge node defines the danger level of the event as 3 level;
when the danger level reaches level 3, the edge server notifies security personnel of the monitoring room through the property management module;
if the visitor behavior poses a life safety threat to the owner, the event risk level is defined as level 4.
10. The working method of the residential building entrance guard security system based on the edge calculation as claimed in claim 1, wherein the photo and the video are preserved for the first-level dangerous event, the photo and the video are preserved for the second-level dangerous event, the photo and the video are preserved for a short time, the photo and the video are preserved for a long time for the third-level dangerous event, the monitoring picture is continuously observed for the event, the image data is permanently preserved for the fourth-level dangerous event as evidence, and the building door, the broadcast warning and the owner warning are blocked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011259591.6A CN112383615A (en) | 2020-11-12 | 2020-11-12 | Residential building entrance guard security system and method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011259591.6A CN112383615A (en) | 2020-11-12 | 2020-11-12 | Residential building entrance guard security system and method based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112383615A true CN112383615A (en) | 2021-02-19 |
Family
ID=74583051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011259591.6A Pending CN112383615A (en) | 2020-11-12 | 2020-11-12 | Residential building entrance guard security system and method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112383615A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222637A (en) * | 2021-02-26 | 2021-08-06 | 深圳前海微众银行股份有限公司 | Architecture method, device, equipment, medium and program product of store visitor information |
| CN113593103A (en) * | 2021-07-26 | 2021-11-02 | 武汉畅途网络科技有限公司 | Intelligent management system for entrance guard of intelligent community based on face recognition |
| CN114005214A (en) * | 2021-11-17 | 2022-02-01 | 北京金和网络股份有限公司 | Access control method and access control system |
| CN115273369A (en) * | 2022-07-22 | 2022-11-01 | 常州星宇车灯股份有限公司 | Intelligent household security monitoring device and monitoring method thereof |
| CN116389533A (en) * | 2023-06-06 | 2023-07-04 | 天津中新智冠信息技术有限公司 | Alarm management system and method based on Internet of things |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446680A (en) * | 2018-05-07 | 2018-08-24 | 西安电子科技大学 | A kind of method for secret protection in face authentication system based on edge calculations |
| CN109257569A (en) * | 2018-10-24 | 2019-01-22 | 广东佳鸿达科技股份有限公司 | Security protection video monitoring analysis method |
| CN109544052A (en) * | 2019-01-30 | 2019-03-29 | 南京我在智能科技有限公司 | A kind of intelligence community management system based on Internet of Things edge calculations server |
| CN209265530U (en) * | 2018-12-28 | 2019-08-16 | 金威建设集团有限公司 | A kind of community visitor intelligence register system |
| CN110428522A (en) * | 2019-07-24 | 2019-11-08 | 青岛联合创智科技有限公司 | A kind of intelligent safety and defence system of wisdom new city |
| CN110992562A (en) * | 2019-11-25 | 2020-04-10 | 上海商汤智能科技有限公司 | Access control method and device, electronic equipment and storage medium |
-
2020
- 2020-11-12 CN CN202011259591.6A patent/CN112383615A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446680A (en) * | 2018-05-07 | 2018-08-24 | 西安电子科技大学 | A kind of method for secret protection in face authentication system based on edge calculations |
| CN109257569A (en) * | 2018-10-24 | 2019-01-22 | 广东佳鸿达科技股份有限公司 | Security protection video monitoring analysis method |
| CN209265530U (en) * | 2018-12-28 | 2019-08-16 | 金威建设集团有限公司 | A kind of community visitor intelligence register system |
| CN109544052A (en) * | 2019-01-30 | 2019-03-29 | 南京我在智能科技有限公司 | A kind of intelligence community management system based on Internet of Things edge calculations server |
| CN110428522A (en) * | 2019-07-24 | 2019-11-08 | 青岛联合创智科技有限公司 | A kind of intelligent safety and defence system of wisdom new city |
| CN110992562A (en) * | 2019-11-25 | 2020-04-10 | 上海商汤智能科技有限公司 | Access control method and device, electronic equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222637A (en) * | 2021-02-26 | 2021-08-06 | 深圳前海微众银行股份有限公司 | Architecture method, device, equipment, medium and program product of store visitor information |
| CN113593103A (en) * | 2021-07-26 | 2021-11-02 | 武汉畅途网络科技有限公司 | Intelligent management system for entrance guard of intelligent community based on face recognition |
| CN113593103B (en) * | 2021-07-26 | 2023-07-04 | 郑州海诺电子科技有限公司 | Intelligent community access control intelligent management system based on face recognition |
| CN114005214A (en) * | 2021-11-17 | 2022-02-01 | 北京金和网络股份有限公司 | Access control method and access control system |
| CN115273369A (en) * | 2022-07-22 | 2022-11-01 | 常州星宇车灯股份有限公司 | Intelligent household security monitoring device and monitoring method thereof |
| CN116389533A (en) * | 2023-06-06 | 2023-07-04 | 天津中新智冠信息技术有限公司 | Alarm management system and method based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112383615A (en) | Residential building entrance guard security system and method based on edge calculation | |
| CN109064698B (en) | Resident security early warning method and resident security early warning system | |
| CN110334563B (en) | Community security management method and system based on big data | |
| CN106454250A (en) | Intelligent recognition and early warning processing information platform | |
| CN103578240A (en) | Security and protection service network based on Internet of Things | |
| CN109410497B (en) | Bridge opening space safety monitoring and alarming system based on deep learning | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| CN109286788A (en) | A kind of safety defense monitoring system based on cloud computing | |
| CN111212274A (en) | Intelligent building security system | |
| CN112466078B (en) | Intelligent security system | |
| CN106303382A (en) | A kind of emergency command comprehensive management platform based on Internet of Things | |
| US10586130B2 (en) | Method, system and apparatus for providing access to videos | |
| CN112002094A (en) | Cell personnel management method based on triangular positioning | |
| CN116614717B (en) | Video monitoring method and system for intelligent community | |
| CN115273369A (en) | Intelligent household security monitoring device and monitoring method thereof | |
| CN113672689A (en) | Intelligent frontier defense information processing system and method | |
| CN114358980A (en) | Intelligent community property management system and method based on Internet of things | |
| JP4592383B2 (en) | Suspicious person notification system | |
| KR102084687B1 (en) | Security operation service method and system for detecting illegal photography | |
| JP2006120084A5 (en) | ||
| CN111311862A (en) | Monitoring method for suspicious personnel or suspicious behaviors | |
| CN115913998A (en) | PCTSE intelligent park state evaluation method and system | |
| CN116208633A (en) | Artificial intelligence service platform system, method, equipment and medium | |
| KR100974944B1 (en) | Security system for apartment complex and service method thereof | |
| CN210573994U (en) | Networking type access control mainboard based on security chip |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210219 |
|
| RJ01 | Rejection of invention patent application after publication |