Community security management protection system based on Internet of Things

Abstract

The invention discloses a community security management protection system based on the Internet of Things, which comprises a community security management system. The community security management system comprises a community monitoring unit, a community access control unit, a community distress call unit, a community security personnel information management unit, a community security instrument information management unit and a community security distress call unit; through multi-stage access control management, a strict access control system is formed, the security and protection safety in a community is improved, whether personnel entering the community belong to a community owner or not is judged through face recognition, multi-time comparison is adopted, the accuracy is improved, when it is judged that the personnel in the community belong to non-owners, an alarm is given in time, security personnel track and determine the identity, and the security and protection safety of the community is improved. And the calling devices are arranged in the community and the owner room, so that timely help calling is facilitated, emergency rescue of policemen, fire fighting and rescue is facilitated, security and protection personnel and facilities are publicized, and the owner can conveniently supervise the security and protection personnel and facilities.

Description

Technical Field

[0001] The present invention relates to the technical field of residential security management, and in particular to a residential security management and protection system based on the Internet of Things. Background Art

[0002] With the continuous improvement of people's living standards, people's concept of housing has evolved from the initial simple living function to the humanized demand for housing. Safe, comfortable, fast, healthy and convenient smart communities have become the development trend of residential communities, among which security is the primary goal of smart communities. The realization of security in smart communities has gradually developed from a security prevention system that mainly relies on manpower to a security prevention system that relies on intelligence.

[0003] Smart community is a new concept of community management. It combines new generation information technologies such as the Internet of Things, big data, cloud computing, mobile Internet, artificial intelligence, etc. to build an advanced, reliable and necessary system in the community to intelligently manage and collect information on people, cars, houses and equipment, and provide community residents with a safe, comfortable and convenient smart living environment. It forms a new management form of community based on information and intelligent management and services, and is a derivative in the life cycle of security development.

[0004] Establish intelligent monitoring systems, video intercoms, parking systems, alarm systems, and smart home systems, and use a modular design and in-depth integrated management platform to unify resources, integrate supervision, and conduct intelligent analysis, forming a dynamic and efficient system environment, achieving information sharing, and creating a safe, comfortable, convenient, and efficient community environment. This is the overall architecture that community intelligent security should form.

[0005] In the Chinese invention patent with application publication number CN108073124A, a community security management and protection system based on the Internet of Things is disclosed, including a community security management and protection system, the community security management and protection system includes a community intersection access monitoring and management system, a community security information monitoring and management system and a community access control security control and management system, the output end and input end of the community security management and protection system are both electrically connected to the input end and output end of the Internet of Things, and the output end and input end of the community intersection access monitoring and management system are electrically connected to the input end and output end of the Internet of Things. The present invention manages and protects the security and safety of the community, prevents situations that endanger the safety of residents in the community, improves the protection effect on residents, monitors each entrance and exit of the community in real time through the community intersection access monitoring and management system, prevents fighting and theft in the community, and can quickly resolve this problem when it occurs, which is convenient for the management of community security and improves the safety of the community.

[0006] However, in combination with the existing technology and the above application, there are still some problems in the existing technology. For example, it is impossible to identify pedestrians inside the community, which makes it easy for outsiders to mix in, and it is easy for illegal elements to enter, which endangers the security management in the community, or the entry of illegal advertisement posting personnel, which affects the environment in the community. In addition, the security notices inside the community cannot be clearly displayed, which is not convenient for the owners to supervise. Access control management is particularly important. Strict access control management can effectively reduce the difficulty of security inside the community.

[0007] To this end, the present invention provides a community security management and protection system based on the Internet of Things. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies in the prior art, the present invention provides a community security management and protection system based on the Internet of Things. Through multi-level access control management, a strict access control system is formed, which can reduce the entry of social personnel and improve the security of the community. It can also determine whether the personnel entering the community are community owners through face recognition, and use multiple comparisons to improve the accuracy. If it is determined that the personnel inside the community are not owners, the police will be promptly reported, and the security personnel will track and determine their identities, thereby reducing the entry of outsiders and improving the security level of the community. In addition, calling devices are provided in the community and in the owners' rooms to facilitate timely calls for help and emergency rescue by the police, fire and ambulance, and the security personnel and facilities are publicized to facilitate supervision by the owners, thereby solving the technical problems recorded in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A community security management and protection system based on the Internet of Things, including a community security management system, wherein the community security management system includes a community monitoring unit, a community access control unit, a community emergency call unit, a community security personnel information management unit, a community security equipment information management unit and a community security emergency call unit;

[0013] The community monitoring unit monitors the community through various cameras, and various cameras are set at various intersections in the community, as well as community gates, unit entrances, children's places and garages. Various cameras are strictly prohibited from aiming at user doors and windows, and cameras near units are strictly prohibited from using full-angle cameras for monitoring. Various cameras used for monitoring in the community monitoring unit have face recognition functions. By extracting features from the collected image information, the faces of pedestrians are obtained for recognition, and by querying the facial information of the owner in the community database for comparison, it is determined whether the pedestrian is the owner of the community. After three unsuccessful inquiries, the community security is called to verify the identity of the person;

[0014] The community access control unit is arranged at the entrance of the community and at the entrance of the unit, and is used to detect people entering the community and the unit. The community access control unit includes an access card recognition module, a facial recognition module and a password recognition module. The identity of the visitor is determined by the access card recognition module, the facial recognition module and the password recognition module. After three determinations, that is, the password, access card and face are recognized three times, and the visitor cannot be recognized or the access control cannot be opened, it is determined that the visitor is not a member of the community;

[0015] The face recognition function is compared and determined by the following formula:

[0016] Collect facial features, combine with the owner's facial information in the community database, and set the collected facial feature points to compare with the owner's facial feature points.

[0017]

[0018] Among them, P(H I Δ) is the posterior probability, that is, the similarity after facial comparison. If the similarity is above 60%, it is determined to be the same person. In the three verifications, the first one must be above 60% to be directly determined as the owner. If the first comparison result is less than 60%, the subsequent two comparison results must be greater than 60% to be determined as the owner. If only one of the subsequent comparison results is greater than 60%, or both are less than 60%, it is determined not to be the owner. N is the feature set for comparison and judgment, i represents the detection of a feature in the feature set, P(ΔH I ) is the likelihood probability of being the same person, P(H I ) is the prior probability that they are the same person, P(ΔH E ) is the likelihood probability that they are not the same person, P(H E ) is the prior probability that they are not the same person.

[0019] Furthermore, the community emergency call unit is used by the owner to call the property, that is, an emergency call device is installed in the owner's home, which is mainly used to call security or property staff through the emergency call device when danger occurs in the owner's home or when an unknown person visits.

[0020] Furthermore, the community security personnel information management unit is used to publicize the information of security personnel in the community, including the security personnel's name, age, training method, training duration, security company and contact number, for owners to check, and the training of security personnel needs to be publicized in the community security management system in advance to facilitate supervision by the owners. Security training includes theoretical knowledge learning and safety protection training.

[0021] Furthermore, the community security equipment information management unit is used to publicize the security facilities in the community, including the purchase records, purchase amounts, purchasers, types of security facilities, maintenance records, replacement records, and maintenance and replacement masters of the security facilities. The community security equipment information management unit updates and publicizes the information on the community security management system every month.

[0022] Furthermore, the community security rescue unit is used to make emergency rescue calls when an emergency accident occurs in the community. The community security rescue unit includes fire rescue calls, ambulance rescue calls and police rescue calls. The fire rescue call is used to call the fire brigade for help when a fire occurs in the community. The ambulance rescue call is used to call the hospital for help when a safety accident occurs in the community. The police rescue call is used to report an incident when a fight, theft or illegal intrusion occurs in the community.

[0023] Furthermore, the community security management system uploads data through the Internet of Things and establishes a query page on the Internet of Things. The community security management system makes it easy for the owner's mobile terminal and the property management company terminal to log in and query through the Internet of Things. The login of the owner's mobile terminal is distributed through the property management company terminal, that is, the account is formed by combining the owner's residential building, residential unit, residential floor and residential room number. When the owner logs in for the first time, real-name authentication is required to confirm the owner's identity information.

[0024] Furthermore, the community monitoring unit includes a monitoring camera and a night vision camera. The monitoring camera is used to be installed inside the community, and the night vision camera is used to be installed at the gate of the community and the unit door, so as to facilitate security monitoring at night, and to facilitate the identification of vehicles entering and leaving the garage, as well as security monitoring in the garage. The community monitoring unit also includes a feature extraction module and a face recognition module. The feature extraction module is used to extract features of faces, so as to facilitate the face recognition module to compare the face information in the community database to determine whether the pedestrian is an owner in the community.

[0025] Furthermore, before extracting features, the feature extraction module first performs image grayscale processing on the collected image information, converts the image into a grayscale image, and performs calculation and analysis through the third-order image color moment. The image color moment includes first-order moment, second-order moment and third-order moment. For an image in RGB color space, i = 1, 2, 3, the following E i , δ i , S i represents the first-order color moment on the i-th channel, P ij Represents the color value of the i-th channel of the j-th pixel;

[0026] The first-order color moment uses the first-order origin moment to reflect the overall brightness of the image:

[0027]

[0028] The second-order color moment uses the square root of the second-order center distance to reflect the distribution range of image colors:

[0029]

[0030] The third-order color moment uses the cube root of the third-order center distance, reflecting the symmetry of the image color distribution:

[0031]

[0032] And the grayscale image is subjected to dimensionality reduction and normalization as follows.

[0033] Furthermore, the feature extraction module uses a deep convolutional neural network for calculation and processing, and the calculation formula of the deep convolutional neural network is as follows:

[0034] The input image matrix and the subsequent convolution kernel, assuming the input matrix size is w, the convolution kernel size is k, the stride is s, and the number of zero-filling layers is p, the calculation formula for the size of the feature map generated after convolution is:

[0035]

[0036] The input formula is:

[0037] V=cosv2(W,X,"valid")+b,

[0038] The output formula is:

[0039]

[0040] The above input and output formulas are for each convolutional layer. Each convolutional layer has a different weight matrix W, and W, X, and Y are in matrix form. For the last fully connected layer, set to the Lth layer, the output is y in vector form. L , the expected output is d, valid is the activation function, through the matrix size w, the features are gradually extracted on the facial image, and Y is the output feature matrix, countless facial features are collected through the matrix size w, and then analyzed and processed through the comparison formula.

[0041] Furthermore, the community access control unit includes a community gate access control and a unit building access control. The community gate access control and the unit building access control are both equipped with an access card recognition module, a facial recognition module, a password recognition module, a floor call module, and a voice and video module. The access card recognition module, the facial recognition module, and the password recognition module are used to realize door opening control of the community gate access control and the unit building access control. The floor call module and the voice and video module are used for visitors to confirm with visiting owners through a call, and then the community gate access control and the unit building access control are opened through a control switch in the owner's house. The unit building access control also includes an access control alarm module. The access control alarm module is used to alarm and call security personnel when the password recognition module enters an incorrect password three times, or when the owner determines through the floor call module and the voice and video module that he does not recognize the visitor, and then alarm and call security personnel.

[0042] (III) Beneficial effects

[0043] The present invention provides a community security management and protection system based on the Internet of Things, which has the following beneficial effects:

[0044] The present invention forms a strict access control system through multi-level access control management, which can reduce the entry of social personnel and improve the security of the community. The two-level access control management is carried out through the community gate access control and the unit building access control to prevent outsiders from entering the community and even prevent outsiders from entering the building, thereby improving the security of the community. The access card recognition module, the facial recognition module, and the password recognition module are decoded in multiple ways to facilitate the owners to enter and exit the community. For outsiders, three failed accesses are used to determine and the security guard is directly called for safe expulsion. If the outsiders are relatives or friends of the owner, the owner can be called through the floor call module and the voice and video module, or through video connection, and the access control can be opened by the owner.

[0045] And through face recognition, it is determined whether the person entering the community is the owner of the community. When recognizing the face, the facial features are extracted through a deep convolutional neural network, and the extracted features are compared with the facial information of the owner in the community database to determine whether the pedestrian is the owner. Multiple comparisons are used to improve the accuracy. If it is determined that the person inside the community is not the owner, the police will be called in time, and the security personnel will track and determine the identity, reduce the entry of outsiders, and improve the security level of the community;

[0046] In addition, call devices are installed in the community and in the owners' rooms, which is convenient for timely calls for help and emergency rescue by police, fire and ambulance. Security personnel and facilities are publicized to facilitate supervision by owners. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic diagram of the structure of a community security management and protection system based on the Internet of Things in the present invention;

[0048] Figure 2 A schematic diagram of a cell monitoring unit in a cell security management and protection system based on the Internet of Things in the present invention;

[0049] Figure 3 It is a schematic diagram of a community access control unit in the community security management and protection system based on the Internet of Things in the present invention;

[0050] Figure 4 It is a schematic diagram of a community security personnel information management unit in the community security management and protection system based on the Internet of Things in the present invention;

[0051] Figure 5 It is a schematic diagram of a community security equipment information management unit in the community security management and protection system based on the Internet of Things in the present invention;

[0052] Figure 6 It is a schematic diagram of a community security call unit in the community security management and protection system based on the Internet of Things in the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1-6 The present invention provides a community security management and protection system based on the Internet of Things, including a community security management system, wherein the community security management system includes a community monitoring unit, a community access control unit, a community emergency unit, a community security personnel information management unit, a community security equipment information management unit and a community security emergency unit;

[0055] The community monitoring unit monitors the community through various cameras, and various cameras are set at various intersections in the community, as well as community gates, unit entrances, children's places and garages. Various cameras are strictly prohibited from aiming at user doors and windows, and cameras near units are strictly prohibited from using full-angle cameras for monitoring. Various cameras used for monitoring in the community monitoring unit have face recognition functions. By extracting features from the collected image information, the faces of pedestrians are obtained for recognition, and by querying the facial information of the owner in the community database for comparison, it is determined whether the pedestrian is the owner of the community. After three unsuccessful inquiries, the community security is called to verify the identity of the person;

[0056] The community access control unit is arranged at the entrance of the community and at the entrance of the unit, and is used to detect people entering the community and the unit. The community access control unit includes an access card recognition module, a facial recognition module and a password recognition module. The identity of the visitor is determined by the access card recognition module, the facial recognition module and the password recognition module. After three determinations, that is, the password, access card and face are recognized three times, and the visitor cannot be recognized or the access control cannot be opened, it is determined that the visitor is not a member of the community;

[0057] The face recognition function is compared and determined by the following formula:

[0058] Collect facial features, combine with the owner's facial information in the community database, and set the collected facial feature points to compare with the owner's facial feature points.

[0059]

[0060] Among them, P(H IΔ) is the posterior probability, that is, the similarity after facial comparison. If the similarity is above 60%, it is determined to be the same person. In the three verifications, the first one must be above 60% to be directly determined as the owner. If the first comparison result is less than 60%, the subsequent two comparison results must be greater than 60% to be determined as the owner. If only one of the subsequent comparison results is greater than 60%, or both are less than 60%, it is determined not to be the owner. N is the feature set for comparison and judgment, i represents the detection of a feature in the feature set, P(ΔH I ) is the likelihood probability of being the same person, P(H I ) is the prior probability that they are the same person, P(ΔH E ) is the likelihood probability that they are not the same person, P(H E ) is the prior probability that they are not the same person.

[0061] In order to facilitate timely calling of security personnel or property management for help in case of danger in the owner's home or the elderly fainting; in this embodiment, preferably, the community emergency call unit is used by the owner to call the property management, that is, an emergency call device is installed in the owner's home, which is mainly used for calling security or property management staff through the emergency call device when danger occurs in the owner's home or when an unknown person visits.

[0062] In order to manage the security personnel within the community, improve the work ability of the security personnel within the community, and improve the security level of the community, in this embodiment, preferably, the community security personnel information management unit is used to publicize the information of the security personnel in the community, including the name, age, training method, training duration, security company and contact number of the security personnel, for the owners to check, and the training of the security personnel needs to be publicized in advance on the community security management system to facilitate the supervision of the owners. The security training includes theoretical knowledge learning and safety protection training.

[0063] In order to manage the security facilities within the community and disclose the finances of the security facilities to facilitate supervision by the owners, in this embodiment, preferably, the community security equipment information management unit is used to publicize the security facilities in the community, including the purchase records of the security facilities, the purchase amount, the purchaser, the type of security facilities, the maintenance records of the security facilities, the replacement records, and the maintenance and replacement masters. The community security equipment information management unit updates and publicizes the information on the community security management system every month.

[0064] In order to improve the safety of the community, when a dangerous accident occurs, timely call for help can be made to ensure the personal safety and property safety of the owners in the community. In this embodiment, preferably, the community security call for help unit is used to make an emergency call for help when an emergency dangerous accident occurs in the community. The community security call for help unit includes fire alarm call, ambulance call and police call. The fire alarm call is used to call for help from the fire brigade when a fire occurs in the community. The ambulance call is used to call for help from the hospital when a safety accident occurs in the community. The police call is used to report a fight, theft or illegal intrusion in the community.

[0065] In order to make it convenient for owners to log in to the community security management system for viewing and to supervise the security management of the community, and in order to achieve standardized management, it is necessary to manage the owners in real name. In this embodiment, preferably, the community security management system uploads data through the Internet of Things, and establishes a query page on the Internet of Things. The community security management system makes it convenient for owners' mobile terminals and property management company terminals to log in and query through the Internet of Things. The login of the owner's mobile terminal is distributed through the property management company terminal, that is, the owner's residential building, residential unit, residential floor and residential room number are combined to form an account. When the owner logs in for the first time, real-name authentication is required to confirm the owner's identity information.

[0066] In order to realize monitoring within the community, night vision cameras are installed on important roads to improve security protection at night, and to identify and manage vehicles and personnel entering and leaving. In this embodiment, preferably, the community monitoring unit includes a monitoring camera and a night vision camera. The monitoring camera is used to be installed inside the community, and the night vision camera is used to be installed at the gate of the community and the unit door, which is convenient for security monitoring at night, and is convenient for identifying vehicles entering and leaving the garage, as well as security monitoring in the garage. The community monitoring unit also includes a feature extraction module and a face recognition module. The feature extraction module is used to extract features of the face, which is convenient for the face recognition module to compare the face information with the face information in the community database to determine whether the pedestrian is the owner of the community.

[0067] In order to facilitate the feature collection of the person's face and eliminate the influence of color, in this embodiment, preferably, the feature extraction module performs image grayscale processing on the collected image information before feature extraction, converts the image into a grayscale image, and performs calculation and analysis through the third-order image color moment. The image color moment includes first-order moment, second-order moment and third-order moment. For the image in RGB color space, i=1, 2, 3, the following E i ,δ i , S irepresents the first-order color moment on the i-th channel, P ij Represents the color value of the i-th channel of the j-th pixel;

[0068] The first-order color moment uses the first-order origin moment to reflect the overall brightness of the image:

[0069]

[0070] The second-order color moment uses the square root of the second-order center distance to reflect the distribution range of image colors:

[0071]

[0072] The third-order color moment uses the cube root of the third-order center distance, reflecting the symmetry of the image color distribution:

[0073]

[0074] And the grayscale image is subjected to dimensionality reduction and normalization as follows.

[0075] In order to extract the facial features of the person and perform calculation and analysis processing through the comparison algorithm, in this embodiment, preferably, the feature extraction module uses a deep convolutional neural network for calculation processing, and the calculation formula of the deep convolutional neural network is as follows:

[0076] The input image matrix and the subsequent convolution kernel, assuming the input matrix size is w, the convolution kernel size is k, the stride is s, and the number of zero-filling layers is p, the calculation formula for the size of the feature map generated after convolution is:

[0077]

[0078] The input formula is:

[0079] V=cosv2(W,X,"valid")+b,

[0080] The output formula is:

[0081]

[0082] The above input and output formulas are for each convolutional layer. Each convolutional layer has a different weight matrix W, and W, X, and Y are in matrix form. For the last fully connected layer, set to the Lth layer, the output is y in vector form. L , the expected output is d, valid is the activation function, through the matrix size w, the features are gradually extracted on the facial image, and Y is the output feature matrix, countless facial features are collected through the matrix size w, and then analyzed and processed through the comparison formula.

[0083] In order to manage the people entering and leaving the community and to facilitate the entry and exit of the community owners, a combination of multiple access control methods is adopted. In order to facilitate the visits of the owners' relatives and friends, a floor call module and a voice and video module are set to determine the identity. In this embodiment, preferably, the community access control unit includes a community gate access control and a unit building access control. The community gate access control and the unit building access control are both equipped with an access card recognition module, a facial recognition module, a password recognition module, a floor call module, and a voice and video module. The access card recognition module, the facial recognition module, and the password recognition module are used to achieve The community gate access control and the unit building access control are used for door opening control. The floor call module and the voice and video module are used for visitors to confirm with the visiting owner through a call. Then, the community gate access control and the unit building access control are opened through the control switch in the owner's house. The unit building access control also includes an access control alarm module. The access control alarm module is used to call the security personnel when the password recognition module enters the wrong password three times, or when the owner determines that the visitor is not recognized by the floor call module and the voice and video module, the owner calls the security personnel.

[0084] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0085] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0089] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0090] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0091] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0092] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A community security management and protection system based on the Internet of Things, characterized in that: It includes a community security management system, which includes a community monitoring unit, a community access control unit, a community emergency call unit, a community security personnel information management unit, a community security equipment information management unit and a community security emergency call unit; The community monitoring unit monitors the community through various cameras, and various cameras are set at various intersections in the community, as well as community gates, unit entrances, children's places and garages. Various cameras are strictly prohibited from aiming at user doors and windows, and cameras near units are strictly prohibited from using full-angle cameras for monitoring. Various cameras used for monitoring in the community monitoring unit have face recognition functions. By extracting features from the collected image information, the faces of pedestrians are obtained for recognition, and by querying the facial information of the owner in the community database for comparison, it is determined whether the pedestrian is the owner of the community. After three unsuccessful inquiries, the community security is called to verify the identity of the person; The community access control unit is arranged at the entrance of the community and at the entrance of the unit, and is used to detect people entering the community and the unit. The community access control unit includes an access card recognition module, a facial recognition module and a password recognition module. The identity of the visitor is determined by the access card recognition module, the facial recognition module and the password recognition module. After three determinations, that is, the password, access card and face are recognized three times, and the visitor cannot be recognized or the access control cannot be opened, it is determined that the visitor is not a member of the community; The face recognition function is compared and determined by the following formula: Collect facial features, combine with the owner's facial information in the community database, and set the collected facial feature points to compare with the owner's facial feature points. Among them, P(H I Δ) is the posterior probability, that is, the similarity after facial comparison. If the similarity is above 60%, it is determined to be the same person. In the three verifications, the first one must be above 60% to be directly determined as the owner. If the first comparison result is less than 60%, the subsequent two comparison results must be greater than 60% to be determined as the owner. If only one of the subsequent comparison results is greater than 60%, or both are less than 60%, it is determined not to be the owner. N is the feature set for comparison and judgment, i represents the detection of a feature in the feature set, P(ΔH I ) is the likelihood probability of being the same person, P(H I ) is the prior probability that they are the same person, P(ΔH E ) is the likelihood probability that they are not the same person, P(H E ) is the prior probability that they are not the same person.

2. According to the Internet of Things-based community security management and protection system of claim 1, it is characterized by: The community emergency call unit is used for the owner to call the property management, that is, an emergency call device is installed in the owner's home, which is mainly used to call security or property management staff through the emergency call device when danger occurs in the owner's home or when an unknown person visits.

3. According to the Internet of Things-based community security management and protection system of claim 1, it is characterized by: The community security personnel information management unit is used to publicize the information of security personnel in the community, including the security personnel's name, age, training method, training duration, security company and contact number, for owners to check. In addition, the training of security personnel needs to be publicized in the community security management system in advance to facilitate supervision by owners. Security training includes theoretical knowledge learning and safety protection training.

4. The community security management and protection system based on the Internet of Things according to claim 1 is characterized by: The community security equipment information management unit is used to publicize the security facilities in the community, including the purchase records, purchase amounts, purchasers, types of security facilities, maintenance records, replacement records, and maintenance and replacement masters of security facilities. The community security equipment information management unit updates and publicizes the information on the community security management system every month.

5. The community security management and protection system based on the Internet of Things according to claim 1 is characterized by: The community security rescue unit is used to make emergency rescue calls when an emergency accident occurs in the community. The community security rescue unit includes fire rescue calls, ambulance rescue calls and police rescue calls. The fire rescue call is used to call the fire department for help when a fire occurs in the community. The ambulance rescue call is used to call the hospital for help when a safety accident occurs in the community. The police rescue call is used to report a fight, theft or illegal intrusion in the community.

6. The community security management and protection system based on the Internet of Things according to claim 1 is characterized by: The community security management system uploads data through the Internet of Things and establishes a query page on the Internet of Things. The community security management system makes it easy for the owner's mobile terminal and the property management company terminal to log in and query through the Internet of Things. The login of the owner's mobile terminal is distributed through the property management company terminal, that is, the account is formed by combining the owner's residential building, residential unit, residential floor and residential room number. When the owner logs in for the first time, real-name authentication is required to confirm the owner's identity information.

7. The community security management and protection system based on the Internet of Things according to claim 1 is characterized by: The community monitoring unit includes a monitoring camera and a night vision camera. The monitoring camera is used to be installed inside the community, and the night vision camera is used to be installed at the gate of the community and the unit door, so as to facilitate security monitoring at night, and to facilitate the identification of vehicles entering and leaving the garage, as well as security monitoring in the garage. The community monitoring unit also includes a feature extraction module and a face recognition module. The feature extraction module is used to extract features of faces, so as to facilitate the face recognition module to compare the face information with the face information in the community database to determine whether the pedestrian is the owner of the community.

8. The community security management and protection system based on the Internet of Things according to claim 7 is characterized by: Before extracting features, the feature extraction module first performs image grayscale processing on the collected image information, converts the image into a grayscale image, and performs calculation and analysis through the third-order image color moment. The image color moment includes first-order moment, second-order moment and third-order moment. For an image in RGB color space, i = 1, 2, 3, the following E i ,δ i , S i represents the first-order color moment on the i-th channel, P ij Represents the color value of the i-th channel of the j-th pixel; The first-order color moment uses the first-order origin moment to reflect the overall brightness of the image: The second-order color moment uses the square root of the second-order center distance to reflect the distribution range of image colors: The third-order color moment uses the cube root of the third-order center distance, reflecting the symmetry of the image color distribution: And the grayscale image is subjected to dimensionality reduction and normalization as follows.

9. The community security management and protection system based on the Internet of Things according to claim 8 is characterized by: The feature extraction module uses a deep convolutional neural network for calculation and processing. The calculation formula of the deep convolutional neural network is as follows: The input image matrix and the subsequent convolution kernel, assuming the input matrix size is w, the convolution kernel size is k, the stride is s, and the number of zero-filling layers is p, the calculation formula for the size of the feature map generated after convolution is: The input formula is: V=cosv2(W,X,"valid")+b, The output formula is: The above input and output formulas are for each convolutional layer. Each convolutional layer has a different weight matrix W, and W, X, and Y are in matrix form. For the last fully connected layer, set to the Lth layer, the output is y in vector form. L , the expected output is d, valid is the activation function, through the matrix size w, the features are gradually extracted on the facial image, and Y is the output feature matrix, countless facial features are collected through the matrix size w, and then analyzed and processed through the comparison formula.

10. The community security management and protection system based on the Internet of Things according to claim 1, characterized in that: The community access control unit includes a community gate access control and a unit building access control. The community gate access control and the unit building access control are both provided with an access card recognition module, a facial recognition module, a password recognition module, a floor call module, and a voice and video module. The access card recognition module, the facial recognition module, and the password recognition module are used to realize the door opening control of the community gate access control and the unit building access control. The floor call module and the voice and video module are used for the visitor to make a call confirmation with the visiting owner, and then open the community gate access control and the unit building access control through the control switch in the owner's house. The unit building access control also includes an access control alarm module. The access control alarm module is used to call the security personnel when the password recognition module is entered three times and the password is still wrong, or when the owner determines that the visitor is not recognized through the floor call module and the voice and video module, the security personnel are called.

Images