CN111583485A

CN111583485A - Community access control system, access control method and device, access control unit and medium

Info

Publication number: CN111583485A
Application number: CN202010299883.6A
Authority: CN
Inventors: 马原; 韩立通
Original assignee: Beijing Pengsi Technology Co ltd
Current assignee: Beijing Pengsi Technology Co ltd
Priority date: 2020-04-16
Filing date: 2020-04-16
Publication date: 2020-08-25

Abstract

The disclosure provides a residential area access control system, an access control method and device and an access control unit. A specific implementation mode of the community access control system comprises the following steps: the system comprises a monitoring server and at least one access control unit, wherein the access control unit is connected with the monitoring server through a network, and each access control unit comprises control equipment, a camera electrically connected with the control equipment and an electric door lock. The control equipment sends the video stream acquired by the camera to a monitoring server in real time for storage; if the control equipment detects a face verification request of a user, requesting a current video stream from a monitoring server and intercepting a face image from the current video stream, and then determining whether the intercepted face image is matched with a verification face image in a verification face image library stored in the control equipment; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the matching. According to the embodiment, the face recognition part is specifically controlled by the user on the premise of ensuring the safety of the cell, and the privacy worry of the user is solved.

Description

Community access control system, access control method and device, access control unit and medium

Technical Field

The disclosure relates to the technical field of entrance guard and monitoring, in particular to a residential area entrance guard system, an entrance guard control method and device, an entrance guard unit and a medium.

Background

The intelligent community is characterized in that dynamic analysis and control of the entrance and exit of the community are achieved by arranging a large number of cameras around the community, face verification and identification are achieved by arranging the cameras at the door of a user room or the door of a unit building, and the like, so that the trouble that the user needs to carry a community access control card is avoided.

However, most of the existing smart communities uniformly store information of people who can legally enter the owner's family, such as names, face images, mobile phone numbers and the like, by property, which increases the risk of information privacy disclosure of members of the owner's family. In addition, when the population of the owner changes, the owner needs to go to the property to update the corresponding personnel information, which brings inconvenience to the owner. Also, the large number of cameras deployed at cell borders, cell building doorways, user room doorways, etc., may result in frequent amortization of the costs of the associated material purchases by the cell owner.

Disclosure of Invention

The disclosure provides a residential area access control system, an access control method and device, an access control unit and a medium.

In a first aspect, the present disclosure provides a residential area access control system, including monitoring server and at least one entrance guard unit, wherein, every entrance guard unit and above-mentioned monitoring server network connection, every entrance guard unit includes controlgear and camera and electric door lock of being connected with this controlgear electricity, wherein: the control device is configured to: acquiring a video stream acquired by a camera electrically connected with the control equipment in real time, and sending the acquired video stream to the monitoring server; the monitoring server is configured to: in response to receiving a video stream sent by a control device, correspondingly storing the received video stream and a device identifier of the control device sending the received video stream; the control device is configured to: responding to the face verification request of the user, and sending a current video stream acquisition request to the monitoring server, wherein the current video stream acquisition request comprises the equipment identifier of the control equipment; the monitoring server is configured to: in response to receiving a current video stream acquisition request sent by a control device, sending a video stream, which corresponds to a device identifier in the received current video stream acquisition request and is recorded between a preset time length before the current time and the current time, to the control device sending the received current video stream acquisition request; the control device is configured to: in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image is matched with a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

In some optional embodiments, the access control unit further comprises a face authentication request key and/or an infrared sensor electrically connected to the control device; and the control device is configured to: in response to determining that the face verification request of the user is detected, sending a current video stream acquisition request to the monitoring server, including: the control device is configured to: the method comprises the steps of responding to the fact that a human face verification request key electrically connected with the control device is pressed, determining that an infrared sensor electrically connected with the control device detects a living body, determining that a human face verification request of a user is detected, and sending a current video stream acquisition request to the monitoring server.

In some optional embodiments, data is transmitted between the monitoring server and the control device in each access control unit by using an encryption protocol.

In some optional embodiments, the control device is configured to: in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device, the method includes: the control device is configured to: in response to receiving the video stream sent by the monitoring server, determining whether a living human face object is detected according to the received video stream; in response to determining that a live face object is detected, a face image is cut from the received video stream, and a determination is made as to whether the cut face image matches a verification face image in a verification face image library stored in the control device.

In some optional embodiments, the control device is configured to: determining whether a live face object is detected from the received video stream, comprising: the control device is configured to: acquiring a front frame image and a rear frame image which are adjacent in time from a received video stream; determining a difference image of the gray level image of the previous frame image and the gray level image of the subsequent frame image; carrying out binarization processing on the difference image to obtain a binarized image; and determining whether a living human face object is detected according to whether the binary image comprises a connected region and/or the foreground pixel point ratio of the binary image, wherein the foreground pixel point ratio of the binary image is the ratio of the number of pixels of which the pixel value is the foreground pixel value in the binary image to the total number of pixels in the binary image, and the foreground pixel value is the pixel value for representing the foreground part in the binary image.

In some optional embodiments, the control device is configured to: determining whether a living human face object is detected according to whether the binary image comprises a connected region and/or the ratio of foreground pixel points of the binary image, comprising the following steps: the control device is configured to: carrying out erosion processing on the binary image to obtain an eroded binary image; carrying out expansion processing on the erosion binary image to obtain an erosion expansion binary image; and determining whether the living human face object is detected according to whether the erosion expansion binary image comprises a connected region and/or the ratio of foreground pixel points of the erosion expansion binary image.

In some optional embodiments, the at least one access control unit comprises at least one building access control unit disposed at a building entrance and/or at least one room access control unit disposed at a room entrance in a building, and the building access control unit further comprises a room number input component electrically connected to the control device; and the control device is configured to: determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device, including: the control device in the room entrance guard unit is configured to: determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device; the control device in the landing door access unit is configured to: acquiring a room number input by a user from a room number input part electrically connected with the control device; in response to determining that the acquired room number belongs to the set of in-building room numbers stored in the control device, determining whether the intercepted face image matches a verification face image corresponding to the acquired room number in a verification face image library stored in the control device; in response to determining that the acquired room number does not belong to the set of in-building room numbers stored in the control device, determining whether the intercepted facial image matches a verification facial image in a library of verification facial images stored in the control device.

In a second aspect, the present disclosure provides an access control method, which is applied to a control device in each access control unit in a residential access control system, where the residential access control system includes a monitoring server and at least one access control unit, each access control unit is connected to the monitoring server via a network, each access control unit includes a control device, a camera electrically connected to the control device, and an electric door lock, and the method includes: the method comprises the steps of acquiring a video stream acquired by a camera electrically connected with the control equipment in real time, and sending the acquired video stream to the monitoring server, wherein the monitoring server responds to the received video stream sent by the control equipment and correspondingly stores the received video stream and an equipment identifier of the control equipment which sends the received video stream; responding to a face verification request of a user, and sending a current video stream acquisition request to the monitoring server, wherein the current video stream acquisition request comprises an equipment identifier of the control equipment, and the monitoring server responds to the received current video stream acquisition request sent by the control equipment, and sends a video stream, which corresponds to the equipment identifier in the received current video stream acquisition request and is recorded between a preset time length before the current time and the current time, to the control equipment sending the received current video stream acquisition request; in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image is matched with a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

In some optional embodiments, the access control unit further comprises a face authentication request key and/or an infrared sensor electrically connected to the control device; and the sending a current video stream acquisition request to the monitoring server in response to determining that the face verification request of the user is detected comprises: the method comprises the steps of responding to the fact that a human face verification request key electrically connected with the control device is pressed, determining that an infrared sensor electrically connected with the control device detects a living body, determining that a human face verification request of a user is detected, and sending a current video stream acquisition request to the monitoring server.

In some optional embodiments, the intercepting, in response to receiving the video stream sent by the monitoring server, a facial image from the received video stream, and determining whether the intercepted facial image matches a verification facial image in a verification facial image library stored in the control device, includes: in response to receiving the video stream sent by the monitoring server, determining whether a living human face object is detected according to the received video stream; in response to determining that a live face object is detected, a face image is cut from the received video stream, and a determination is made as to whether the cut face image matches a verification face image in a verification face image library stored in the control device.

In some optional embodiments, the determining whether the living human face object is detected according to the received video stream includes: acquiring a front frame image and a rear frame image which are adjacent in time from a received video stream; determining a difference image of the gray level image of the previous frame image and the gray level image of the subsequent frame image; carrying out binarization processing on the difference image to obtain a binarized image; and determining whether a living human face object is detected according to whether the binary image comprises a connected region and/or the foreground pixel point ratio of the binary image, wherein the foreground pixel point ratio of the binary image is the ratio of the number of pixels of which the pixel value is the foreground pixel value in the binary image to the total number of pixels in the binary image, and the foreground pixel value is the pixel value for representing the foreground part in the binary image.

In some optional embodiments, the determining whether the living human face object is detected according to whether the binarized image includes a connected region and/or according to a foreground pixel proportion of the binarized image includes: carrying out erosion processing on the binary image to obtain an eroded binary image; carrying out expansion processing on the erosion binary image to obtain an erosion expansion binary image; and determining whether the living human face object is detected according to whether the erosion expansion binary image comprises a connected region and/or the ratio of foreground pixel points of the erosion expansion binary image.

In some optional embodiments, the at least one access control unit comprises at least one building access control unit disposed at a building entrance and/or at least one room access control unit disposed at a room entrance in a building, and the building access control unit further comprises a room number input component electrically connected to the control device; and the above determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device includes: acquiring a room number input by a user from a room number input part electrically connected with the control device; in response to determining that the acquired room number belongs to the set of in-building room numbers stored in the control device, determining whether the intercepted face image matches a verification face image corresponding to the acquired room number in a verification face image library stored in the control device; in response to determining that the acquired room number does not belong to the set of in-building room numbers stored in the control device, determining whether the intercepted facial image matches a verification facial image in a library of verification facial images stored in the control device.

The third aspect, this disclosure provides an entrance guard control device, is applied to the controlgear among every entrance guard's unit in the district access control system, and wherein, above-mentioned district access control system includes monitoring server and at least one entrance guard's unit, and every entrance guard's unit and above-mentioned monitoring server network connection, every entrance guard's unit include controlgear and with this controlgear electric camera and electric door lock that is connected, above-mentioned device includes: the monitoring server responds to the received video stream sent by the control equipment and correspondingly stores the received video stream and the equipment identification of the control equipment which sends the received video stream; a video stream obtaining unit configured to send a current video stream obtaining request to the monitoring server in response to determining that a face verification request of a user is detected, wherein the current video stream obtaining request includes an equipment identifier of the control equipment, and the monitoring server sends, in response to receiving the current video stream obtaining request sent by the control equipment, a video stream corresponding to the equipment identifier in the received current video stream obtaining request and having a recording time between a preset time length before the current time and the current time to the control equipment sending the received current video stream obtaining request; a face verification unit configured to intercept a face image from the received video stream in response to receiving the video stream transmitted by the monitoring server, and determine whether the intercepted face image matches a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

In some optional embodiments, the access control unit further comprises a face authentication request key and/or an infrared sensor electrically connected to the control device; and the video stream acquisition unit is further configured to: the method comprises the steps of responding to the fact that a human face verification request key electrically connected with the control device is pressed, determining that an infrared sensor electrically connected with the control device detects a living body, determining that a human face verification request of a user is detected, and sending a current video stream acquisition request to the monitoring server.

In a fourth aspect, the present disclosure provides an access control unit comprising: the camera is used for shooting videos and images; an electric door lock for opening or closing the door lock; with the camera with the controlgear that electric door lock electricity is connected, controlgear includes: one or more processors; a storage device having one or more programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement the method as described in any of the embodiments of the second aspect.

In a fifth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by one or more processors, implements the method as described in any of the embodiments in the second aspect.

The utility model provides a district access control system, access control method and device, entrance guard unit and medium, through moving face identification and verification part to the entrance guard unit local of arranging at user's room gate or unit building gate, keep daily real-time video monitoring at the property or dispatch the monitoring server that central monitoring system corresponds of institute, realized guaranteeing to have solved user's privacy worry with face identification's part by the concrete management and control of user under the prerequisite of district security, convenience of customers updates personnel's information at any time, the property or dispatch institute can guarantee the security of building through the entrance guard unit of deployment at user's room gate or unit building gate again simultaneously.

Drawings

Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is a schematic block diagram of one embodiment of a residential access control system according to the present disclosure;

FIG. 2 is a flow chart of one embodiment of a method of access control according to the present disclosure;

fig. 3 is a schematic diagram of an application scenario of the access control method according to the present disclosure;

fig. 4A is a flow chart of yet another embodiment of a method of access control according to the present disclosure;

FIG. 4B is an exploded flow diagram of one embodiment of step 403 in the embodiment shown in FIG. 4A;

FIG. 4C is a schematic diagram of one embodiment of a binarized image according to the present disclosure;

FIG. 4D is a schematic diagram of yet another embodiment of a binarized image according to the present disclosure;

FIG. 4E is a schematic diagram of yet another embodiment of a binarized image according to the present disclosure;

FIG. 4F is a schematic diagram of one embodiment of an erosion dilated binarized image corresponding to the binarized image shown in FIG. 4;

FIG. 5 is a schematic structural diagram of one embodiment of an access control device according to the present disclosure;

fig. 6 is a schematic diagram of a computer system suitable for implementing the control device in the access control unit of the present disclosure.

Detailed Description

The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 shows a schematic structural diagram of an embodiment of a residential quarter entrance guard system according to the present disclosure.

As shown in fig. 1, the cell gate inhibition system 100 may include a monitoring server 101, a network 102 and

gate inhibition units

103, 104, 105, where the gate inhibition unit 103 may include a control device 1031, a camera 1032 electrically connected to the control device 1031 and a power door lock 1033, the gate inhibition unit 104 may include a control device 1041, a camera 1042 electrically connected to the control device 1041 and a power door lock 1043, and the gate inhibition unit 105 may include a control device 1051, a camera 1052 electrically connected to the control device 1051 and a power door lock 1053.

The network 102 serves to provide a medium of communication links between the

control devices

1031, 1041, 1051 and the monitoring server 101. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The

control devices

1031, 1041, 1051 may interact with the server 101 through the network 102 to receive or transmit messages or the like. The

control devices

1031, 1041, and 1051 may have various client applications that satisfy the application scenario, such as a video capture application, an access control application, a face recognition application, and the like.

The

control devices

1031, 1041, and 1051 may be individually configured controllers, such as a Programmable Logic Controller (PLC), a single chip microcomputer, and an industrial Controller; or the equipment consists of other electronic devices which have input/output ports and have the operation control function; or a computer device installed with applications for access control methods. For example, the

control devices

1031, 1041, 1051 may include, but are not limited to, the following: a Central Processing Unit (CPU), an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

The

control devices

1031, 1041, and 1051 may respectively control whether the

cameras

1032, 1042, and 1052 capture videos or images, and the

control devices

1031, 1041, and 1051 may also respectively acquire videos or images captured by the

cameras

1032, 1042, and 1052 and send the videos or images to the monitoring server 101.

The

control devices

1031, 1041, and 1051 may respectively control the opening or closing of the

electric door locks

1033, 1043, and 1053, or may respectively acquire the current states (for example, the open states or the closed states) of the

electric door locks

1033, 1043, and 1053.

In the present disclosure, a cell refers to an area with a limited manageable range, and may be, for example, a spatial area composed of residential cells, residential communities, streets, villages, schools, vegetable markets, office buildings and the like with a limited number of functional units of living, working, business and the like.

For convenience of illustration, the following description will be given by taking residential areas as an example, and other types of cells can be understood in the same way.

In some optional embodiments, the

door access unit

103, 104 or 105 may further include a face authentication request button and/or an infrared sensor electrically connected to a control device included therein. Here, when the face authentication request key is pressed, the control device electrically connected to the face authentication request key may be triggered to send a current video stream acquisition request to the monitoring server. And the infrared sensor is used for detecting whether a living body passes through a preset range. When the infrared sensor detects whether a living body passes through the preset range, the control device electrically connected with the face verification request key can be triggered to send a current video stream acquisition request to the monitoring server.

In some optional embodiments, data may be transmitted between the monitoring server 101 and the

control devices

1031, 1041, 1051 using an encrypted protocol. Among other things, the encryption protocol may include, but is not limited to, encryption protocols now known or developed in the future, such as: a Secure Sockets Layer (SSL) protocol or a Transport Layer Security (TLS) protocol.

In some optional embodiments, the

access control units

103, 104, and 105 may be all room access control units at doors of all buildings in the cell where the cell access control system is located, the

access control units

103, 104, and 105 may also be all floor access control units at doors of all buildings in the cell where the cell access control system is located, and the

access control units

103, 104, and 105 may also include both room access control units at doors of all buildings in the cell where the cell access control system is located and floor access control units at doors of all buildings in the cell where the cell access control system is located. The building door access control unit can further comprise a room number input component electrically connected with the control equipment, and the control equipment in the building door access control unit can acquire the room number input by the user through the room number input component.

The monitoring server 101 may be a server providing various services, for example, store the video streams received from the

control devices

1031, 1041, and 1051 in correspondence with the device identifiers of the control devices that send the video streams, and send the corresponding current videos to the control devices that send the current video stream acquisition requests when receiving the current video stream acquisition requests sent by the

control devices

1031, 1041, and 1051.

The monitoring server 101 may be hardware or software. When the monitoring server 101 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the monitoring server 101 is software, it may be implemented as a plurality of software or software modules (for example, for providing a video monitoring service), or may be implemented as a single software or software module. And is not particularly limited herein.

As one example, a typical monitoring server may be a Closed-Circuit Television monitoring system (CCTV).

It should be noted that the access control method provided by the present disclosure is generally executed by the

control devices

1021, 1031, 1041, and accordingly, the access control apparatus is generally disposed in the

control devices

1021, 1031, 1041.

It should be understood that the number of gate inhibition units, networks and monitoring servers in fig. 1 is merely illustrative. There may be any number of access units, networks and monitoring servers, as desired for implementation.

Continuing to refer to fig. 2, a flow 200 of one embodiment of a method of access control according to the present disclosure is shown. The method can be applied to the control equipment in each access control unit in a community access control system. Here, the residential quarter entrance guard system may include a monitoring server and at least one entrance guard unit, each entrance guard unit being network-connected to the monitoring server, each entrance guard unit including a control device, and a camera and an electric door lock electrically connected to the control device. The access control method comprises the following steps:

step 201, acquiring a video stream acquired by a camera electrically connected with the control device in real time, and sending the acquired video stream to a monitoring server.

In this embodiment, an execution main body (for example, the control device shown in fig. 1) of the access control method may acquire, in real time, a video stream captured by a camera electrically connected to the control device, and send the acquired video stream to a monitoring server. In this way, the monitoring server may store the received video stream and the device identifier of the control device that transmitted the received video stream in correspondence in response to receiving the video stream transmitted by the control device. In practice, the device identifier of the control device that transmits the received video stream may be encapsulated in the metadata of the video stream, and then the monitoring server may parse the device identifier and the video to be stored from the metadata of the received video stream.

Here, the device identification of the control device is used to uniquely distinguish the control device in each gate inhibition unit serviced by the monitoring server. For example, when the monitoring server is a video monitoring system server of a cell a, a cell B and a cell C, the served objects are the entrance guard units installed at the doorways or the doorways of the buildings in the cell a, the cell B and the cell C, and the device identifier of the control device may be, for example, the following format for distinguishing the cell, the doorways and the room numbers: "a-1-708", where "a" denotes the a cell, "1" denotes the building No. 1, and "708" denotes the 708 room, although if it is desired to denote that the control device in the access control unit at the door can write the room number part thereof to a preset specific room number, for example to "000". For example, the device identifier may be a distinguishable unique code of the control device or the camera, and the device identifier of the control device may be a Media Access control address (MAC) of the control device or the camera electrically connected to the control device, a Serial Number (SN), or the like.

It should be noted that the control device in each access control unit in the cell access control system may continuously perform step 201 under the condition of power-on, so that the video collected by the camera in each access control unit may be continuously stored in the monitoring server, that is, the monitoring server may provide the video monitoring service.

Step 202, in response to determining that the face verification request of the user is detected, sending a current video stream acquisition request to the monitoring server.

In this embodiment, the execution subject may send the current video stream acquisition request to the monitoring server when determining that the face verification request of the user is detected. Wherein the current video stream acquisition request may include a device identification of the control device. In this way, the monitoring server may, in response to receiving the current video stream acquisition request sent by the control device, send the video stream corresponding to the device identifier in the received current video stream acquisition request and having the recording time between the preset time length before the current time and the current time, to the control device that sent the received current video stream acquisition request. Here, the preset time period may be preset according to the requirement of residents in the cell served by the monitoring server, or according to the network condition between the monitoring server and the control device in each access control unit served by the monitoring server, or according to the age of the residents in the cell served by the monitoring server. For example, if the age subject of the resident in the cell served by the monitoring server is the elderly, the preset time period may be 2 seconds; the preset time period may be 1.5 seconds if it is a middle-aged person, and 1 second if it is a young person. For another example, the network status between the monitoring server and the control devices in each access control unit served by the monitoring server is good, and the preset time length may be 2 seconds; the preset time period may be 1.5 seconds if the network conditions are general, and 1 second if it is a young person.

In addition, the monitoring server can also set different preset durations for different control devices, so that the monitoring server can firstly acquire the device identifier in the received current video stream acquisition request when receiving the current video stream acquisition request sent by the control device, then determine the preset duration corresponding to the acquired device identifier, and then send the video stream corresponding to the determined device identifier and between the determined preset duration before the recording time is the current time and the current time to the control device sending the received current video stream acquisition request.

In this embodiment, the execution subject may determine whether the face verification request of the user is detected in various implementations.

In some optional embodiments, the access control unit may further include a face authentication request key and/or an infrared sensor electrically connected to the control device. In this way, the control device may determine that the face authentication request of the user is detected in a case where it is detected that a face authentication request key electrically connected to the control device is pressed, and/or in a case where it is determined that an infrared sensor electrically connected to the control device detects a living body.

Step 203, in response to receiving the video stream sent by the monitoring server, capturing a face image from the received video stream, and determining whether the captured face image matches a verification face image in a verification face image library stored in the control device.

In this embodiment, the execution subject may, in a case where a video stream sent by the monitoring server is received, first intercept a face image from the received video stream, and then determine whether the intercepted face image matches a verification face image in a verification face image library stored in the control device.

It should be noted that the method for capturing image frames from video can be implemented in various manners in the art, for example, using videoapply, js call, etc. in OpenCV (Open Source Computer Vision Library, which is a cross-platform Computer Vision Library that is initiated and developed by intel corporation, issued with BSD license authorization, and can be used freely in the business and research fields).

Here, the execution subject may adopt various implementations to intercept the face image from the received video stream, and this disclosure is not limited in this regard. For example, the execution subject may start from a first frame image in the received video stream, detect whether a face image is included in the frame image, and if it is detected that the face image is included in the frame image, intercept the face image in the frame image and do not continue the detection. And if the image of the frame is detected not to comprise the face image, starting the detection of the next frame until the last frame in the received video stream is also detected. If all frames in the received video stream are detected completely and no face image is detected, the execution main body can intercept an image of a preset area from any frame image in the received video stream as the face image. For another example, the execution subject may also directly capture an image of a preset region captured from any frame image in the received video stream as a face image.

Here, the execution body may determine whether the intercepted face image matches a verification face image in a verification face image library stored in the control device in various implementations. For example, the execution subject may first extract the facial image features of the intercepted facial image according to a preset facial image feature extraction method. And then determining the face image characteristics corresponding to each verified face image in a verified face image library stored in the control equipment. Then, the execution subject may determine whether there is a verification face image in the verification face image library, where a similarity between the corresponding face image feature and the image feature of the intercepted face image is greater than a preset similarity threshold. If so, determining that the intercepted face image matches a verification face image in a verification face image library stored in the control device. If it is determined that the face image does not exist, it is determined that the intercepted face image does not match a verification face image in a verification face image library stored in the control apparatus.

The preset facial image feature extraction method may be any currently known and future developed facial image feature extraction method, and the disclosure does not specifically limit this. For example, the preset face image feature extraction method may be: algebraic feature-based methods and knowledge-based characterization methods. The algebraic feature-based method may include linear feature extraction and nonlinear feature extraction. And linear feature extraction may include principal component analysis (also called K-L transformation), independent component analysis, and Fisher linear discriminant analysis. Nonlinear feature extraction may include kernel-based feature extraction and manifold learning-dominated feature extraction methods. The kernel-based feature extraction may be, for example, Convolutional Neural Networks (CNNs).

The knowledge-based characterization method mainly obtains feature data which is helpful for face classification according to shape description of face organs and distance characteristics between the face organs, and feature components of the feature data generally comprise Euclidean distance, curvature, angle and the like between feature points. The human face is composed of parts such as eyes, nose, mouth, and chin, and geometric description of the parts and their structural relationship can be used as important features for recognizing the human face, and these features are called geometric features. The knowledge-based face characterization mainly comprises a geometric feature-based method and a template matching method.

The similarity between the facial image features may be various similarities. For example, the inverse of euclidean distance, the inverse of mahalanobis distance, the inverse of manhattan distance, cosine similarity, correlation coefficient, and the like.

It should be noted that, in order to reduce the storage space and the computing resource requirement required by the control device, the face image feature corresponding to each verified face image in the verified face image library may be stored in the control device instead of storing the verified face images. In this way, the execution subject can directly obtain the facial image features corresponding to each verification facial image in the verification facial image library stored in the control device without calculation.

In a specific example, the image features corresponding to each verification face image in the verification face image library can be generated in advance by the following method, and the face image features of the intercepted face image can be generated by the same method: firstly, identifying each face organ object included in a face image (for example, an intercepted face image or a verification face image in a verification face image library) by calling a related function provided by OpenCV, wherein the face organ object includes eyes, ears, a nose and a mouth; then, at least one of the following characteristic values is extracted based on the geometric size of the face organ object obtained by recognition: width between the two eyes (i.e., the farthest distance and/or the closest distance between the two eyes), width of each of the two eyes, width of the nose, width of the mouth, width between the outermost ends of the two ears, height of each of the two ears; and finally, generating a face feature vector by using at least one extracted feature value, wherein the generated face feature vector is the face image feature corresponding to the operated face image. When determining whether the image features of the intercepted face image are matched with the image features corresponding to the verification face images in the verification face image library, firstly generating the face image features of the intercepted face image according to the method, then calculating the Euclidean distance between the obtained face image features and the face image features corresponding to the corresponding verification face images in the verification face image library stored in the control equipment, and if the calculated Euclidean distance is smaller than a preset Euclidean distance threshold value, determining matching; otherwise, if not, a mismatch is determined.

In some optional embodiments, the at least one access control unit included in the residential access control system may include at least one building access control unit disposed at a building entrance and/or at least one room access control unit disposed at a room entrance in a building, and the building access control unit may further include a room number input component electrically connected to the control device.

When the control device is a control device in a room access control unit, step 203 may be to determine whether the intercepted face image matches a verification face image in a verification face image library stored in the control device.

When the control device is a control device in a building entrance guard unit, step 203 may be to determine whether the intercepted face image matches a verification face image in a verification face image library stored in the control device. Step 203 may also be performed as follows:

first, a room number input by a user is acquired from a room number input section electrically connected to the control device.

Then, in response to determining that the acquired room number belongs to the set of in-building room numbers stored in the control device, it is determined whether the intercepted face image matches a verification face image corresponding to the acquired room number in a verification face image library stored in the control device.

That is, here, when the room number input by the user is the room number of the room in the building in which the entrance guard unit to which the control device belongs is installed, it is not necessary to match the intercepted face image with all the face images in the verification face image library stored in the control device, but it is only necessary to first determine the verification face image corresponding to the acquired room number in the verification face image library stored in the control device, and then determine whether the intercepted face image is the verification face image corresponding to the acquired room number in the verification face image library stored in the control device. Such an embodiment reduces the amount of computation by the control device, which in turn reduces the computational resource requirements on the control device itself. In addition, the entrance guard unit is arranged at the entrance of the building, so that the economic cost of arranging the entrance guard unit at the door of a household room of a user can be reduced.

Finally, in response to determining that the acquired room number does not belong to the set of in-building room numbers stored in the control device, it is determined whether the intercepted face image matches a verification face image in a verification face image library stored in the control device.

That is, if the room number input by the user is not the room number in the building where the entrance guard unit to which the control device belongs is installed, the intercepted face image needs to be matched with all face images in the verification face image library stored in the control device.

And step 204, responding to the matching, and controlling the unlocking of the electric door lock electrically connected with the control equipment.

In this embodiment, if it is determined in step 203 that the intercepted face image matches the verification face image in the verification face image library stored in the control device, that indicates that the current user of the access control unit to which the control device belongs is a verification user, the execution agent may control the electric door lock electrically connected to the control device to unlock, that is, control the electric door lock in the access control unit to which the control device belongs to unlock. And then, the process of verifying the user through the human face image and enabling the user to enter the system under the condition that the verification is passed is realized.

With continued reference to fig. 3, fig. 3 is a schematic view of an application scenario of the access control method according to the embodiment. In the application scenario of fig. 3, a door access unit 302 is installed on an entrance of a room 301, and the door access unit 302 includes a control device 3021, a camera 3022, an electric door lock 3023, and a face authentication request key 3024. Among them, the control apparatus 3021 is electrically connected to the camera 3021, the electric door lock 3033, and the face authentication request key 3024, respectively. When the electric door lock 3023 is opened, the door of the room 301 is opened. When the electric door lock 3023 is closed, the door of the room 301 is closed. When the door access unit 302 is in a power-on state, the camera 3022 continuously records video, and the control device 3021 transmits a video stream recorded by the camera 3022 to the monitoring server 303 in real time for storage. The user 304 walks in front of the door of the room 301, and the user wishes to enter the room 301, and therefore the user presses the face authentication request button 3024. The control apparatus 3021 detects that the face authentication request key 3024 is pressed, and therefore, transmits a current video stream acquisition request 305 to the monitoring server 303, the monitoring server 303 receives the current video stream acquisition request 305, transmits a video stream 306 between 2 seconds before the current time and the current time, which is stored in the monitoring server and corresponds to the control apparatus 3021, the control apparatus 3021 intercepts a face image from the video stream 306, and determines that the face image matches three face images in a family member face image library in the room 301 stored in the control apparatus 3021, and the control apparatus 3021 controls the electric door lock 3023 to be opened, and the user 304 can enter the room 301.

In the method provided by the embodiment of the disclosure, the control device sends the video stream acquired by the camera in the access control unit to the monitoring server for storage in real time, and acquires the current latest video stream from the monitoring server under the condition that the user triggers the face verification request, and performs face verification on the current user of the access control unit based on the acquired current latest video stream, and controls the electric door lock of the access control unit to be unlocked under the condition that the verification is passed. Then, the face image library for verification of the user is stored in the local control equipment of the access control unit instead of the monitoring server, the face verification process is also executed in the local control equipment of the access control unit, the privacy of the user can be prevented from being leaked, and the monitoring video record shot by the camera in the access control unit of the user is stored in the monitoring server, so that the overall safety of the community is ensured.

Referring further to fig. 4, a flow 400 of yet another embodiment of a method for access control is shown. The method can be applied to the control equipment in each access control unit in a community access control system. Here, the residential quarter entrance guard system may include a monitoring server and at least one entrance guard unit, each entrance guard unit being network-connected to the monitoring server, each entrance guard unit including a control device, and a camera and an electric door lock electrically connected to the control device. The access control method comprises the following steps:

step 401, acquiring a video stream acquired by a camera electrically connected with the control device in real time, and sending the acquired video stream to a monitoring server.

Step 402, in response to determining that a face verification request of a user is detected, sending a current video stream acquisition request to a monitoring server.

In this embodiment, the specific operations of step 401 and step 402 are substantially the same as the operations of step 201 and step 202 in the embodiment shown in fig. 2, and are not described again here.

In step 403, in response to receiving the video stream sent by the monitoring server, it is determined whether a living human face object is detected according to the received video stream.

In order to prevent a person from verifying with a face in a photo and further causing the control device to open an electric door lock in the access control unit, which may cause a hidden danger to the safety of a real household, an execution subject of the access control method (for example, the control device shown in fig. 1) may adopt a known or future developed living human face object detection method when receiving a video stream sent by the monitoring server, determine whether a living human face object is detected according to the received video stream, and if it is determined that the living human face object is detected, go to step 404 to continue execution.

It is known that blinking is an unavoidable physiological phenomenon of a human, and that blinking is approximately ten times per minute in a non-pathological case, based on the physiological mechanism of the human. It is easy to understand that blinking is a phenomenon unique to a living person, and a picture or a face model cannot perform the process, so that the living body detection can be realized by a blink detection method. Based on the above analysis, in some alternative embodiments, step 403 may include sub-steps 4031 through 4034 as shown in fig. 4B, please refer to fig. 4B, where fig. 4B illustrates an exploded flowchart of one embodiment of step 403 in the embodiment shown in fig. 4A. This step 403 may include the following sub-steps:

sub-step 4031, the temporally adjacent previous and subsequent frame images are acquired from the received video stream.

Here, the execution main body may acquire two images adjacent to each other at any time from the received video stream, and determine that a time between the acquired two images is a previous image and a time after the previous image is a next image.

Sub-step 4032, the difference image of the grayscale image of the previous frame image and the grayscale image of the next frame image is determined.

Here, the executing body may first generate the grayscale images of the previous frame image and the subsequent frame image determined in step 4031, respectively, and then determine the difference image of the grayscale images of the previous frame image and the subsequent frame image, respectively, by using various grayscale image generation methods. And the pixel value of each pixel point in the determined difference image is the difference of the pixel value of the corresponding pixel point in the gray image of the previous frame image minus the pixel value of the corresponding pixel point in the gray image of the next frame image.

And a substep 4033 of performing binarization processing on the difference image to obtain a binarized image.

Here, the execution body may perform binarization processing on the difference image obtained in sub-step 4032 by using various grayscale image binarization processing methods to obtain a binarized image. Specifically, the following can be performed: for each pixel point in the binarized image, if the pixel value of the corresponding pixel point in the difference image is greater than or equal to the preset gray value threshold, the pixel value of the pixel point is set as a foreground pixel value (for example, 255), and the foreground is displayed in the binarized image correspondingly. And if the pixel value of the corresponding pixel point in the difference image is smaller than the preset gray value threshold, setting the pixel value of the pixel point as a background pixel value (for example, 0), and displaying the pixel value as a preset background color in the binary image, wherein the foreground pixel value is different from the background pixel value, and the corresponding preset foreground color is also different from the preset background color.

And a substep 4034 for determining whether the living human face object is detected according to whether the binary image includes a connected region and/or the ratio of foreground pixel points of the binary image.

It can be understood that if a video of a face photo is shot by a camera in the access control unit, and because a person in the photo cannot blink, most of pixel points or even all pixel points in the binarized image obtained according to the flow from substep 4031 to substep 4033 will be in a preset background color. For example, a piece of black as shown in the image shown in fig. 4C, that is, the preset background color is black. For a living person, corresponding regions of the eye region in the blinking and non-blinking images are different due to the blinking phenomenon, the pixel values of the pixel points at the corresponding positions of the eye region in the binarized image obtained according to the procedure from sub-step 4031 to sub-step 4033 may represent a preset foreground color, for example, an image shown in fig. 4D, where the preset foreground color is white and the preset background color is black. As can be seen from fig. 4D, the connected region of the eye portion exists in the binarized image shown in fig. 4D, and only the pixel points with the preset background pixel value may also have the pixel points with the preset foreground pixel value.

According to the analysis, the execution subject can determine whether the living human face object is detected according to whether the binary image comprises the connected region and/or the foreground pixel ratio of the binary image. The foreground pixel point ratio of the binary image is the ratio of the number of pixel points of which the pixel value is the foreground pixel value in the binary image to the total number of pixel points in the binary image, and the foreground pixel value is the pixel value used for representing the foreground part in the binary image. Specifically, the execution subject may determine that the living human face object is detected when at least one of the following two conditions is satisfied, the two conditions including: the method comprises the following steps that 1, a binary image comprises a connected region; and 2, comparing the foreground pixel dot proportion of the binary image with a preset foreground proportion threshold value, wherein the preset foreground proportion threshold value is a positive number which is greater than 0 and smaller than 1.

It should be noted that how to determine whether the binary image includes the connected region is a prior art widely studied and applied at present, and is not described herein again.

In practice, in the process of detecting a living human face object by using the sub-steps 4031 to 4034, if the ambient light changes or the human head slightly shakes, which may cause that the pixel values of the pixel points in other regions except the eye region in the binarized image generated in the sub-step 4033 may also be the preset foreground color pixel values, so that interference is caused when determining whether the binarized image includes a connected region, for example, a small black dot or a beard is on the user's face, and the slight shake of the user's head may cause that the preset foreground color pixel values are correspondingly presented in the binarized image in these regions. To solve the above problem, sub-step 4034 may also be performed as follows:

firstly, the binary image is subjected to erosion processing to obtain an eroded binary image.

And then, carrying out expansion processing on the obtained erosion binary image to obtain an erosion expansion binary image.

And finally, determining whether the living human face object is detected according to whether the erosion expansion binary image comprises a connected region and/or the ratio of foreground pixel points of the erosion expansion binary image.

By carrying out erosion processing on the binary image, tiny and trivial areas in the image can be eliminated, and large blocks in the image are strengthened and reserved; and then expansion processing is carried out, and the broken area and the gapped texture can be connected, so that the quality of the image is improved, and the stray light interference is effectively inhibited.

It should be noted that the specific operations of erosion processing on the image and dilation processing on the image are the prior art widely studied and applied at present, and are not described herein again.

As an example, fig. 4E and 4F may be referred to, where fig. 4E is a schematic diagram of another embodiment of the binarized image, and fig. 4F is a diagram of an erosion expanded binarized image obtained by performing erosion processing and then expansion processing on the binarized image shown in fig. 4E.

According to the alternative embodiment, the interference of the ambient light or the slight shake of the human head on the detection of the living human face object can be removed, and the accuracy of the detection of the living human face object can be improved.

Step 404, capturing a face image from the received video stream, and determining whether the captured face image matches a verification face image in a verification face image library stored in the control device.

In this embodiment, the specific operation of step 404 is substantially the same as the operation of step 203 in the embodiment shown in fig. 2, and is not repeated here.

And 405, controlling unlocking of an electric door lock electrically connected with the control equipment in response to the matching determination.

In this embodiment, the specific operation of step 405 is substantially the same as the operation of step 204 in the embodiment shown in fig. 2, and is not described herein again.

As can be seen from fig. 4, compared to the embodiment corresponding to fig. 2, the step of performing face verification in case a live face object is detected is highlighted. Therefore, the scheme described in the embodiment can further improve the safety of the access control unit.

With further reference to fig. 5, as an implementation of the method shown in the above diagrams, the present disclosure provides an embodiment of an access control apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to a control device in each access unit in a residential access control system, where the residential access control system may include a monitoring server and at least one access control unit, each access control unit is connected to the monitoring server through a network, and each access control unit may include a control device, a camera electrically connected to the control device, and an electric door lock.

As shown in fig. 5, the access control device 500 of the present embodiment includes: a video stream transmitting unit 501, a video stream acquiring unit 502, and a face verification unit 503. The video stream sending unit 501 is configured to obtain a video stream acquired by a camera electrically connected to the control device in real time, and send the obtained video stream to the monitoring server, where the monitoring server responds to receiving the video stream sent by the control device, and correspondingly stores the received video stream and a device identifier of the control device sending the received video stream; a video stream obtaining unit 502 configured to, in response to determining that a face verification request of a user is detected, send a current video stream obtaining request to the monitoring server, where the current video stream obtaining request includes an apparatus identifier of the control apparatus, and the monitoring server, in response to receiving the current video stream obtaining request sent by the control apparatus, sends a video stream, which corresponds to the apparatus identifier in the received current video stream obtaining request and has a recording time between a preset time length before the current time and the current time, to the control apparatus sending the received current video stream obtaining request; and a face verification unit 503 configured to intercept a face image from the received video stream in response to receiving the video stream transmitted by the monitoring server, and determine whether the intercepted face image matches a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

In this embodiment, specific processing of the video stream sending unit 501, the video stream obtaining unit 502, and the face verification unit 503 of the access control device 500 and technical effects thereof may refer to related descriptions of step 201, step 202, and step 203 in the corresponding embodiment of fig. 2, which are not described herein again.

In some optional embodiments, the access control unit may further include a face authentication request key and/or an infrared sensor electrically connected to the control device; and the video stream acquiring unit 502 may be further configured to: the method comprises the steps of responding to the fact that a human face verification request key electrically connected with the control device is pressed, determining that an infrared sensor electrically connected with the control device detects a living body, determining that a human face verification request of a user is detected, and sending a current video stream acquisition request to the monitoring server.

In some optional embodiments, data may be transmitted between the monitoring server and the control device in each access control unit by using an encryption protocol.

In some optional embodiments, the intercepting, in response to receiving the video stream sent by the monitoring server, a facial image from the received video stream, and determining whether the intercepted facial image matches a verification facial image in a verification facial image library stored in the control device, may include: in response to receiving the video stream sent by the monitoring server, determining whether a living human face object is detected according to the received video stream; in response to determining that a live face object is detected, a face image is cut from the received video stream, and a determination is made as to whether the cut face image matches a verification face image in a verification face image library stored in the control device.

In some optional embodiments, the determining whether the living human face object is detected according to the received video stream may include: acquiring a front frame image and a rear frame image which are adjacent in time from a received video stream; determining a difference image of the gray level image of the previous frame image and the gray level image of the subsequent frame image; carrying out binarization processing on the difference image to obtain a binarized image; and determining whether a living human face object is detected according to whether the binary image comprises a connected region and/or the foreground pixel point ratio of the binary image, wherein the foreground pixel point ratio of the binary image is the ratio of the number of pixels of which the pixel value is the foreground pixel value in the binary image to the total number of pixels in the binary image, and the foreground pixel value is the pixel value for representing the foreground part in the binary image.

In some optional embodiments, the determining whether the living human face object is detected according to whether the binarized image includes a connected region and/or according to a foreground pixel proportion of the binarized image may include: carrying out erosion processing on the binary image to obtain an eroded binary image; carrying out expansion processing on the erosion binary image to obtain an erosion expansion binary image; and determining whether the living human face object is detected according to whether the erosion expansion binary image comprises a connected region and/or the ratio of foreground pixel points of the erosion expansion binary image.

In some optional embodiments, the at least one access control unit may include at least one building access control unit disposed at a building entrance and/or at least one room access control unit disposed at a room entrance in a building, and the building access control unit may further include a room number input component electrically connected to the control device; and the above determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device may include: acquiring a room number input by a user from a room number input part electrically connected with the control device; in response to determining that the acquired room number belongs to the set of in-building room numbers stored in the control device, determining whether the intercepted face image matches a verification face image corresponding to the acquired room number in a verification face image library stored in the control device; in response to determining that the acquired room number does not belong to the set of in-building room numbers stored in the control device, determining whether the intercepted facial image matches a verification facial image in a library of verification facial images stored in the control device.

It should be noted that, details of implementation and technical effects of each unit in the access control device provided by the present disclosure may refer to descriptions of other embodiments in the present disclosure, and are not described herein again.

Referring now to fig. 6, there is shown a schematic block diagram of a computer system 600 suitable for implementing the control devices in the access control unit of the present disclosure. The control device shown in fig. 6 is only an example, and should not bring any limitation to the function and the range of use of the present disclosure.

As shown in fig. 6, computer system 600 includes at least one processor 601, a memory 602, a bus 603, an Input/Output (I/O) interface 604, an Input unit 605, and an Output unit 606. Wherein at least one processor 601, a memory 602, and an I/O interface 604 are connected to each other through a bus 603. An input unit 605 and an output unit 606 are connected to the bus 603 via the I/O interface 604.

Here, the method according to the present disclosure may be implemented as a computer program and stored in the memory 602. The processor 601 in the control device 600 embodies the entrance guard control function defined in the method of the present disclosure by calling the above-described computer program stored in the memory 602. The input unit 605 may include a camera, and the output unit 606 may include a device for executing a control instruction, such as a power door lock. In some embodiments, the input unit 605 may further include a face authentication request key, an infrared sensor, a room number input part, and the like.

The following components are also connected: a communication unit 607 including a Network interface card such as a LAN (Local Area Network) card, a modem, a WiFi module, a mobile Network module, or the like. The communication unit 607 performs communication processing via a network such as the internet.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication unit 607. The computer program, when executed by the at least one processor 601, performs the above-described functions defined in the methods of the present disclosure.

It should be noted that the computer readable medium in the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, Python, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in this disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a video stream transmitting unit, a video stream acquiring unit, and a face verification unit. The names of these units do not in some cases constitute a limitation on the units themselves, and for example, the video stream transmission unit may also be described as a "unit that acquires a video stream captured by a camera electrically connected to the control apparatus in real time".

As another aspect, the present disclosure also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: the method comprises the steps of acquiring a video stream acquired by a camera electrically connected with the control equipment in real time, and sending the acquired video stream to the monitoring server, wherein the monitoring server responds to the received video stream sent by the control equipment and correspondingly stores the received video stream and an equipment identifier of the control equipment which sends the received video stream; responding to a face verification request of a user, and sending a current video stream acquisition request to the monitoring server, wherein the current video stream acquisition request comprises an equipment identifier of the control equipment, and the monitoring server responds to the received current video stream acquisition request sent by the control equipment, and sends a video stream, which corresponds to the equipment identifier in the received current video stream acquisition request and is recorded between a preset time length before the current time and the current time, to the control equipment sending the received current video stream acquisition request; in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image is matched with a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept as defined above. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. The utility model provides a district access control system, includes monitoring server and at least one entrance guard unit, wherein, every entrance guard unit with monitoring server internet access, every entrance guard unit include controlgear and the camera and the electric door lock of being connected with this controlgear electricity, wherein:

the control device is configured to: acquiring a video stream acquired by a camera electrically connected with the control equipment in real time, and sending the acquired video stream to the monitoring server;

the monitoring server is configured to: in response to receiving a video stream sent by a control device, correspondingly storing the received video stream and a device identifier of the control device sending the received video stream;

the control device is configured to: in response to determining that a face verification request of a user is detected, sending a current video stream acquisition request to the monitoring server, wherein the current video stream acquisition request comprises an equipment identifier of the control equipment;

the monitoring server is configured to: in response to receiving a current video stream acquisition request sent by a control device, sending a video stream, which corresponds to a device identifier in the received current video stream acquisition request and is recorded between a preset time length before the current time and the current time, to the control device sending the received current video stream acquisition request;

the control device is configured to: in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

2. The residential access control system according to claim 1, wherein the access control unit further comprises a face authentication request key and/or an infrared sensor electrically connected to the control device; and

the control device is configured to: in response to determining that a face verification request of a user is detected, sending a current video stream acquisition request to the monitoring server, including:

the control device is configured to: the method comprises the steps of responding to the fact that a human face verification request key electrically connected with the control device is pressed, determining that an infrared sensor electrically connected with the control device detects a living body, determining that a human face verification request of a user is detected, and sending a current video stream acquisition request to the monitoring server.

3. The residential access control system of claim 1, wherein the control device is configured to: in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device, including:

the control device is configured to:

in response to receiving the video stream sent by the monitoring server, determining whether a living human face object is detected according to the received video stream;

in response to determining that a live face object is detected, a face image is cut from the received video stream, and a determination is made as to whether the cut face image matches a verification face image in a verification face image library stored in the control device.

4. The residential access control system of claim 3, wherein the control device is configured to: determining whether a live face object is detected from the received video stream, comprising:

the control device is configured to:

acquiring a front frame image and a rear frame image which are adjacent in time from a received video stream;

determining a difference image of the gray level image of the previous frame image and the gray level image of the subsequent frame image;

carrying out binarization processing on the difference image to obtain a binarized image;

and determining whether a living human face object is detected or not according to whether a connected region is included in the binary image or not and/or the foreground pixel point ratio of the binary image, wherein the foreground pixel point ratio of the binary image is the ratio of the number of pixels of which the pixel values are foreground pixel values in the binary image to the total number of the pixel points in the binary image, and the foreground pixel value is the pixel value for representing the foreground part in the binary image.

5. The residential access control system of any one of claims 1-4, wherein the at least one access control unit comprises at least one floor access control unit disposed at a floor entrance and/or at least one room access control unit disposed at a room entrance in a building, the floor access control unit further comprising a room number input component electrically connected to the control device; and

the control device is configured to: determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device, including:

the control device in the room entrance guard unit is configured to: determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device;

the control device in the landing door access unit is configured to:

acquiring a room number input by a user from a room number input part electrically connected with the control device;

in response to determining that the acquired room number belongs to the set of in-building room numbers stored in the control device, determining whether the intercepted face image matches a verification face image corresponding to the acquired room number in a verification face image library stored in the control device;

in response to determining that the acquired room number does not belong to the set of in-building room numbers stored in the control device, determining whether the intercepted facial image matches a verification facial image in a library of verification facial images stored in the control device.

6. The access control method is applied to control equipment in each access control unit in a community access control system, wherein the community access control system comprises a monitoring server and at least one access control unit, each access control unit is connected with the monitoring server through a network, each access control unit comprises control equipment, a camera and an electric door lock, the camera and the electric door lock are electrically connected with the control equipment, and the method comprises the following steps:

the method comprises the steps of acquiring a video stream acquired by a camera electrically connected with the control equipment in real time, and sending the acquired video stream to the monitoring server, wherein the monitoring server responds to the received video stream sent by the control equipment and correspondingly stores the received video stream and an equipment identifier of the control equipment which sends the received video stream;

in response to determining that a face verification request of a user is detected, sending a current video stream acquisition request to the monitoring server, wherein the current video stream acquisition request comprises an equipment identifier of the control equipment, and in response to receiving the current video stream acquisition request sent by the control equipment, the monitoring server sends a video stream, which corresponds to the equipment identifier in the received current video stream acquisition request and is recorded between a preset time length before the current time and the current time, to the control equipment sending the received current video stream acquisition request;

in response to receiving the video stream sent by the monitoring server, intercepting a face image from the received video stream, and determining whether the intercepted face image matches a verification face image in a verification face image library stored in the control device; and controlling unlocking of an electric door lock electrically connected with the control device in response to determining the match.

7. The method of claim 6, wherein the access control unit further comprises a face authentication request key and/or an infrared sensor electrically connected to the control device; and

the sending a current video stream acquisition request to the monitoring server in response to determining that a face verification request of the user is detected includes:

the method comprises the steps of responding to the fact that a human face verification request key electrically connected with the control device is pressed, determining that an infrared sensor electrically connected with the control device detects a living body, determining that a human face verification request of a user is detected, and sending a current video stream acquisition request to the monitoring server.

8. The method of claim 6, wherein the intercepting of the facial image from the received video stream in response to receiving the video stream sent by the monitoring server, the determining whether the intercepted facial image matches a verification facial image in a library of verification facial images stored in the control device, comprises:

9. The method of claim 8, wherein the determining from the received video stream whether a live human face object is detected comprises:

10. An access control unit comprising:

the camera is used for shooting videos and images;

an electric door lock for opening or closing the door lock;

with the camera with the controlgear that electric door lock electricity is connected, controlgear includes:

one or more processors;

a storage device having one or more programs stored thereon,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 6-9.