Control method and control system of access control device

Abstract

The invention relates to a control method and a control system of an access control device, and the control method comprises the following steps: when a detection message of the access control device is received, a zero terminal collects real-time video data, and stores the real-time video data to a cloud server by using a first channel; the zero terminal performs face recognition on the face image information in the real-time video data; if the recognized target face feature is not matched with the face feature pre-stored in the zero terminal, the zero terminal notifies the cloud server to send a visitor verification message to the user terminal; the cloud server responds to a video call request initiated by the user terminal, sends a call connection instruction to the zero terminal and the user terminal, establishes a second channel for a video call, and performs speed limiting processing on the first channel; and the zero terminal receives an access control lock operation instruction sent by the user terminal and sends the access control lock operation instruction to the door lock control module. According to the invention, the user experience of the access control device can be effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of access control devices, and in particular to a control method and a control system for an access control device. Background Art

[0002] Access control equipment is a system that monitors and manages entrances and exits, and can be used in private homes, public rental apartments, and office spaces. There are many types of access control equipment available, mainly including password access control, biometric access control, and card access control. Among them, biometric access control generally uses monitoring equipment to collect biometric information, such as videos containing facial information, to identify and compare the collected biometric information, and then confirm whether to unlock the door based on the comparison results.

[0003] However, in the existing technology, most biometric access control systems often require frequent communication and interaction between the access control terminal and the cloud in order to identify and confirm the visitor's facial features, which is not only not conducive to stable transmission, but also affects the recognition efficiency. In addition, when the visitor's identity is unclear and a video call is required, for users with poor network environment, it is very easy to encounter problems such as choppy calls and unstable video transmission during calls, thus affecting the user experience.

[0004] Therefore, it is necessary to provide a new technical solution to improve one or more problems existing in the above solutions.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The purpose of the embodiments of the present disclosure is to provide a control method and control system for an access control device, which can not only improve the recognition efficiency, but also help to improve the stability of the interaction between users and visitors and enhance the user experience.

[0007] According to a first aspect of an embodiment of the present disclosure, a control method for an access control device is provided, which is applied to a control system of the access control device, wherein the control system includes a zero terminal, a cloud server, and an access control device connected in real time, and the method includes:

[0008] When receiving a detection message from the access control device, the zero terminal collects real-time video data of the target person and stores the real-time video data to the cloud server using the first channel;

[0009] The zero terminal performs face recognition on the face image information in the real-time video data:

[0010] If the identified target facial features do not match the facial features pre-stored in the zero terminal, the zero terminal notifies the cloud server to send a visitor verification message to the user terminal;

[0011] The cloud server responds to the video call request initiated by the user terminal by sending a call connection instruction to the null terminal and the user terminal, establishing a second channel for the video call, and limiting the data transmission rate of the first channel;

[0012] The zero terminal receives the access lock operation instruction sent by the user terminal, and sends the access lock operation instruction to the door lock control module of the access control device.

[0013] In an exemplary embodiment of the present disclosure, after establishing the second channel for the video call, the method further includes:

[0014] The null terminal receives a video call mode instruction sent by the user terminal, where the video call mode instruction includes a high-definition mode instruction, a smooth mode instruction, and a portrait mode instruction;

[0015] According to the video call mode instruction, the null terminal uses a corresponding encoding method to encode the collected real-time video data to obtain code stream data;

[0016] The null terminal sends the code stream data to the user terminal.

[0017] In an exemplary embodiment of the present disclosure, according to the video call mode instruction, the null terminal uses a corresponding encoding method to encode the collected real-time video data, including:

[0018] When the video call mode sent by the user terminal is a high-definition mode instruction, the null terminal encodes the real-time video data using a YUV444 encoding method;

[0019] When the video call mode sent by the user terminal is a smooth mode instruction, the null terminal encodes the real-time video data using a YUV420 encoding method;

[0020] When the video call mode sent by the user terminal is a portrait mode instruction, the zero terminal divides the portrait area and the non-portrait area in the real-time video data, and encodes the portrait area using YUV444 encoding, and encodes the non-portrait area using YUV420 encoding.

[0021] In an exemplary embodiment of the present disclosure, in the step of the zero terminal performing face recognition on the face image information in the real-time video data, the method further includes:

[0022] If the recognized target facial features match the facial features pre-stored in the zero terminal, the zero terminal sends a door opening instruction to the door lock control module and stops collecting real-time video data.

[0023] In an exemplary embodiment of the present disclosure, after the target facial features are successfully matched with the pre-stored authorized facial features, the method further includes:

[0024] The zero terminal determines matching time information and matching face information, and sends the matching time information and the matching face information to the cloud server.

[0025] In an exemplary embodiment of the present disclosure, the method further includes:

[0026] When the zero terminal detects that the access control is closed abnormally, the zero terminal emits a prompt tone and notifies the cloud server to send access control closing abnormality notification information to the user terminal.

[0027] In an exemplary embodiment of the present disclosure, the method further includes:

[0028] When the zero terminal detects that the external power supply of the access control device is abnormal, the zero terminal switches the external power supply mode to the built-in battery power supply mode.

[0029] According to a second aspect of an embodiment of the present disclosure, a control system for an access control device is provided, the control system comprising a zero terminal, a cloud server and an access control device connected in real time;

[0030] The zero terminal is used to collect real-time video data of the target person when receiving a detection message from the access control device, and store the real-time video data to the cloud server using the first channel; perform face recognition on the face image information in the real-time video data: if the recognized target face features do not match the face features pre-stored in the zero terminal, notify the cloud server to send a visitor verification message to the user terminal;

[0031] The cloud server is used to respond to the video call request initiated by the user terminal, send a call connection instruction to the null terminal and the user terminal, establish a second channel for the video call, and limit the data transmission rate of the first channel;

[0032] The zero terminal is also used to receive the access lock operation instruction sent by the user terminal, and send the access lock operation instruction to the door lock control module of the access control device.

[0033] In an exemplary embodiment of the present disclosure, the zero terminal further includes:

[0034] A first receiving module, configured to receive a video call mode instruction sent by the user terminal;

[0035] An encoding module, used to encode the collected real-time video data using a corresponding encoding method according to the video call mode instruction to obtain code stream data;

[0036] The first sending module is used to send the code stream data to the user terminal.

[0037] In an exemplary embodiment of the present disclosure, the encoding module includes a first encoding unit, a second encoding unit and a third encoding unit; wherein,

[0038] The first encoding unit is used to encode the real-time video data using a YUV444 encoding method when the video call mode sent by the user terminal is a high-definition mode instruction;

[0039] The second encoding unit is used to encode the real-time video data using a YUV420 encoding method when the video call mode sent by the user terminal is a smooth mode instruction;

[0040] The third encoding unit is used to divide the portrait area and the non-portrait area in the real-time video data when the video call mode sent by the user terminal is a portrait mode instruction, and encode the portrait area using the YUV444 encoding method and encode the non-portrait area using the YUV420 encoding method.

[0041] The technical solution provided by the present disclosure may have the following beneficial effects:

[0042] In the embodiments of the present disclosure, on the one hand, the collection work will not start until the zero terminal receives the detection message that the access control device detects the target person, so as to reduce resource consumption, and when the zero terminal performs face recognition, it only needs to match the recognized target face features with the face features pre-stored in the zero terminal, that is, the zero terminal does not need to communicate and interact with the cloud server during face recognition, which can improve the recognition efficiency; on the other hand, when the target face features do not match the authorized face features pre-stored in the zero terminal, the user will receive a visitor verification message at the user terminal, and then actively initiate a video call request to the cloud server. With the help of the second channel for video calls established by the cloud server, during the call, the zero terminal can send real-time video data to the user terminal, so that the user can view the facial features of the target person on the user terminal when communicating with the target person by voice. At the same time, during the call, the data transmission rate of the first channel is limited so that the data transmission rate of the second channel is relatively improved, which is conducive to improving the fluency of the call between the user and the visitor and the stability of the call video transmission, thereby improving the user experience.

[0043] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0045] Figure 1 A flowchart showing a method for controlling a door access control device in an exemplary embodiment of the present disclosure;

[0046] Figure 2 A schematic diagram showing a partial structure of a control system of a door access control device in an exemplary embodiment of the present disclosure Figure 1 ;

[0047] Figure 3 A schematic diagram showing a partial structure of a control system of a door access control device in an exemplary embodiment of the present disclosure Figure 2 . DETAILED DESCRIPTION

[0048] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0049] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0050] In this example implementation, a control method for an access control device is first provided, which is applied to the control system of the access control device, wherein the control system includes a zero terminal, a cloud server and an access control device connected in real time; wherein the zero terminal and the access control device together constitute an intelligent access control device, which is similar in appearance to an existing intelligent door lock, and the intelligent access control device is installed on the user's entrance door to realize intelligent access control; the cloud server is located in the cloud. Figure 1 As shown in , the control method may include the following steps:

[0051] Step S101: When receiving a detection message from the access control device, the zero terminal collects real-time video data of the target person and uses the first channel to store the real-time video data to the cloud server; wherein the target person can be understood as a visitor, and the first channel is a communication channel for transmitting data between the real-time connected zero terminal and the cloud server.

[0052] Step S102: The zero terminal performs face recognition on the face image information in the real-time video data:

[0053] If the identified target facial features do not match the facial features pre-stored in the zero terminal, it indicates that the target person is not a visitor authorized by the user to pass through the access control, and can also be understood as an untrusted visitor. In this case, the zero terminal notifies the cloud server to send a visitor verification message to the user terminal to inform the user that an unidentified visitor has visited, and waits for the user to confirm the visitor's identity information before performing further operations;

[0054] Among them, the recognized target facial features are obtained by the zero terminal performing facial recognition on facial image information in real-time video data, and the zero terminal stores facial features that the user can authorize to pass.

[0055] It should be noted that after the user receives the visitor verification information, the user can initiate a request for a video call with the corresponding access control device to the cloud server through the user terminal.

[0056] Step S103: In response to the video call request initiated by the user terminal, the cloud server sends a call connection instruction to the null terminal and the user terminal, establishes a second channel for the video call, and limits the data transmission rate of the first channel;

[0057] In the case where the cloud server manages multiple access control devices, the cloud server will send a call connection instruction to the zero terminal of a corresponding access control device to establish a second channel for video calls between the user terminal and the corresponding zero terminal.

[0058] Step S104: the zero terminal receives the access lock operation instruction sent by the user terminal, and sends the access lock operation instruction to the door lock control module of the access control device;

[0059] Among them, the access control lock operation instructions include access control opening instructions and access control anti-locking instructions. If the user confirms that the target person is a trusted visitor, the access control opening instruction will be sent to the zero terminal through the user terminal. If the user confirms that the target person is an untrusted visitor, the access control anti-locking instruction will be sent to the zero terminal through the user terminal.

[0060] In the embodiments of the present disclosure, on the one hand, the collection work will not start until the zero terminal receives the detection message that the access control device detects the target person, so as to reduce resource consumption, and when the zero terminal performs face recognition, it only needs to match the recognized target face features with the face features pre-stored in the zero terminal, that is, the zero terminal does not need to communicate and interact with the cloud server during face recognition, which can improve the recognition efficiency; on the other hand, when the target face features do not match the authorized face features pre-stored in the zero terminal, the user will receive a visitor verification message at the user terminal, and then actively initiate a video call request to the cloud server. With the help of the second channel for video calls established by the cloud server, during the call, the zero terminal can send real-time video data to the user terminal, so that the user can view the facial features of the target person on the user terminal when communicating with the target person by voice. At the same time, during the call, the data transmission rate of the first channel is limited so that the data transmission rate of the second channel is relatively improved, which is conducive to improving the fluency of the call between the user and the visitor and the stability of the call video transmission, thereby improving the user experience.

[0061] Below, each step of the above method in this example implementation will be described in more detail.

[0062] Specifically, in step S101, the access control device needs to maintain real-time detection of whether there is a target person within the preset monitoring range. This can ensure that once the infrared sensor of the access control device detects the target person, it can promptly notify the zero terminal control to turn on the camera and collect real-time video data of the target person to avoid missing the target person's visit.

[0063] It should be noted that when the zero terminal receives a detection message from the access control device, the zero terminal will send a prompt message to the cloud server, and the prompt message may include the time when the infrared sensor detects the target person and the time when the camera is turned on.

[0064] Further, in step S101, using the first channel to store the real-time video data in the cloud server may include the following steps:

[0065] Step S1011: the null terminal encodes the collected real-time video data;

[0066] Step S1012: The zero terminal sends the encoded real-time video data to the cloud server.

[0067] By storing the collected real-time video data in the cloud server for backup, it is convenient for users to retrieve, cache and download to the user terminal.

[0068] It should be noted that the cloud server can be set with a storage time for video data, and the corresponding stored data will be automatically deleted upon expiration.

[0069] Specifically, the zero terminal in step S102 performs face recognition on the face image information in the real-time video data, which may include the following steps:

[0070] Step S1021: the zero terminal extracts a target video frame including facial image information of a target person from the real-time video data;

[0071] Step S1022: The zero terminal performs face recognition on the face image information in the target video frame to obtain the target face features of the target person.

[0072] The above-mentioned target video frames include one or several frames of video images containing facial image information. The zero terminal directly performs image recognition and local matching on the collected facial image information without the need for frequent communication and interaction with the cloud server. This can reduce data forwarding delay and effectively improve recognition speed.

[0073] Specifically, in step S102, when the zero terminal performs face recognition on the face image information in the real-time video data, the control method further includes:

[0074] If the recognized target facial features match the facial features pre-stored in the zero terminal, the zero terminal sends a door opening command to the door lock control module and stops collecting real-time video data.

[0075] If the target facial features match the pre-stored authorized facial features, it indicates that the target person is a visitor authorized by the user to pass through the access control, that is, the target person is a trusted visitor, and the facial recognition is successful. If the facial recognition is successful, the zero terminal sends the access control opening command to the door lock control module, and the door lock control module controls the access control to unlock and allow the visitor to pass.

[0076] In addition, when the target face features match the pre-stored authorized face features, the zero terminal controls the camera to turn off and stop collecting real-time video data, which can save resources. When the infrared sensor of the access control device detects a new target person, it notifies the zero terminal to turn on the camera to collect real-time video data of the target person.

[0077] Optionally, when the target facial features successfully match the pre-stored authorized facial features and the zero terminal sends a door access opening instruction to the door lock control module, the zero terminal will notify the cloud server to send a visitor pass message to the user terminal to inform the user that the target person has passed the door access.

[0078] Furthermore, in step S102, after the target facial features are successfully matched with the pre-stored authorized facial features, the control method further includes:

[0079] The zero terminal determines the matching time information and the matching face information, and sends the matching time information and the matching face information to the cloud server;

[0080] The matching time information is the moment when the face recognition is successful, and the matching face information is the target face features of the current successful face recognition.

[0081] After the target facial features are successfully matched with the pre-stored authorized facial features, the matching time information and the matching facial information need to be determined, and the matching time information and the matching facial information need to be sent to the cloud server for storage for backup.

[0082] Optionally, when the zero terminal receives the doorbell trigger information, the zero terminal notifies the cloud server to send a visitor verification message to the user terminal, and uses a video call to let the user confirm the visitor's identity information. This method saves time and quickly confirms the visitor's identity information for untrusted visitors.

[0083] It should be noted that the visitor verification message received by the user can be displayed on the user terminal in the form of a pop-up window with a prompt sound, so that the user can be informed of the visitor verification message in time, and then make a video call with the target person in time to confirm the identity information of the target person.

[0084] It should also be noted that after the user receives the visitor verification message, he can click on the pop-up window on the user terminal to enter the access control device management interface and initiate a video call to the access control device. When the user terminal manages multiple access control devices, the user can select the corresponding access control device on the user terminal to initiate a video call; the cloud server will receive the video call request initiated by the user terminal, send a call connection instruction to the zero terminal matched by the corresponding access control device, and also send a call connection instruction to the user terminal, so that the corresponding zero terminal and the user terminal respond to the call connection instruction and establish a second channel for the video call.

[0085] Specifically, in step S103, the cloud server sends a call connection instruction to the zero terminal and the user terminal in response to the video call request initiated by the user terminal. The zero terminal and the user terminal establish a second channel for the video call in response to the call connection instruction. The zero terminal can send audio and video data to the user terminal through the second channel.

[0086] Specifically, in step S103, after the second channel for video calls is established, the data transmission rate of the first channel is limited, so that the data transmission rate of the second channel can be improved. The speed limit processing of the data transmission rate of the first channel can be set according to the user's network environment. For example, when the user's network environment is poor, the data transmission rate of the first channel is set as low as possible; when the user's network environment is good, the data transmission rate of the first channel can be appropriately limited, but it is necessary to ensure that the data transmission of the second channel is not stuck. This embodiment does not limit the specific value of the data transmission rate of the first channel.

[0087] In the case where the cloud server manages multiple access control devices, the cloud server will send a call connection instruction to the zero terminal of a corresponding access control device to establish a second channel for video calls between the user terminal and the corresponding zero terminal.

[0088] It should be noted that during a video call, the user can select the video call quality on the user terminal according to the network environment to ensure a smooth conversation between the user and the visitor.

[0089] Optionally, after establishing the second channel for the video call in step S103, the control method further includes:

[0090] Step S301: The null terminal receives a video call mode instruction sent by a user terminal, wherein the video call mode instruction includes a high-definition mode instruction, a smooth mode instruction, and a portrait mode instruction;

[0091] Step S302: According to the video call mode instruction, the null terminal uses a corresponding encoding method to encode the collected real-time video data to obtain code stream data;

[0092] Step S303: the null terminal sends the code stream data to the user terminal.

[0093] The above-mentioned zero terminal encodes the collected real-time video data using the corresponding encoding method according to the received video call mode instruction to adapt to network environments with different communication qualities, and ensures that in network environments with various communication qualities, users can talk with visitors smoothly and the call video transmission is stable.

[0094] Specifically, in step S302, according to the video call mode instruction, the null terminal uses a corresponding encoding method to encode the collected real-time video data, which may include the following steps:

[0095] Step S3021: When the video call mode sent by the user terminal is a high-definition mode instruction, the null terminal encodes the real-time video data using the YUV444 encoding method;

[0096] Step S3022: When the video call mode sent by the user terminal is a smooth mode instruction, the null terminal encodes the real-time video data using a YUV420 encoding method;

[0097] Step S3023: When the video call mode sent by the user terminal is a portrait mode instruction, the zero terminal divides the portrait area and the non-portrait area in the real-time video data, and encodes the portrait area using the YUV444 encoding method and encodes the non-portrait area using the YUV420 encoding method.

[0098] It should be noted that when the network environment is in the case of poor communication quality, the user can choose to send a smooth mode command to the zero terminal to ensure smooth calls between users and visitors and stable call video transmission; when the network environment is in the case of good communication quality, the user can choose to send a high-definition mode command to the zero terminal to ensure smooth calls between users and visitors and stable call video transmission, while enhancing the clarity of call videos; when the network environment is in the case of average communication quality, the user can choose to send a portrait mode command to the zero terminal, which is conducive to ensuring smooth calls between users and visitors and stable call video transmission, while enhancing the clarity of call videos.

[0099] In the above-mentioned network environments with different communication qualities, the zero terminal uses different encoding methods to encode real-time video data. Especially when the network environment is in the condition of average communication quality, by dividing the portrait area and non-portrait area in the real-time video data, and using YUV444 encoding method to encode the portrait area, and using YUV420 encoding method to encode the non-portrait area, it can ensure smooth calls between users and visitors, stable call video transmission, and enhance the clarity of call videos.

[0100] For example, the access lock operation instructions include access lock opening instructions and access lock anti-locking instructions. If the user confirms that the target person is a trusted visitor, the access lock opening instruction will be sent to the zero terminal through the user terminal. If the user confirms that the target person is an untrusted visitor, the access lock anti-locking instruction will be sent to the zero terminal through the user terminal.

[0101] It should be noted that if the user confirms that the target person is a suspicious person and the suspicious person is likely to make dangerous actions, the user can also directly perform a one-key alarm operation on the user terminal.

[0102] Specifically, in step S104, if the access lock operation instruction sent by the user terminal to the zero terminal is an access control opening instruction, the door lock control module will receive the access control opening instruction, and control the access control to unlock the door, allowing visitors to pass; if the access lock operation instruction sent by the user terminal to the zero terminal is an access control anti-lock instruction, the door lock control module will receive the access control anti-lock instruction, and control the access control to perform an anti-lock operation, not allowing visitors to pass, while further strengthening security protection.

[0103] It should also be noted that the user terminal can manage multiple access control devices. When the user terminal receives multiple visitor verification messages from the access control devices, the user terminal can reply and confirm in sequence according to the time sequence of the multiple access control devices sending the visitor verification messages. For example, when multiple zero terminals corresponding to multiple access control devices notify the cloud server to send visitor verification messages to the user terminal, the user terminal will prioritize the zero terminal that sent the message the earliest in the order in which the messages were sent, and the remaining visitor verification messages will be treated as pending tasks, waiting for the user to initiate video call requests to the corresponding access control devices in sequence.

[0104] In one embodiment, the control method further includes:

[0105] When the zero terminal receives the monitoring start command sent by the user terminal, the zero terminal controls the camera to turn on, collects real-time video data of the target person, and sends the real-time video data to the cloud server for storage.

[0106] Users can load and display real-time video data stored on the cloud server through the user terminal and view the surveillance video within the preset monitoring range.

[0107] In one embodiment, the control method further includes:

[0108] When the zero terminal detects that the access control is closed abnormally, the zero terminal emits a prompt sound and notifies the cloud server to send access control closing abnormality notification information to the user terminal.

[0109] When the zero terminal detects that the access control device is abnormally closed, it means that the access control device is abnormally locked; by issuing a prompt sound and notifying the cloud server to send access control abnormality notification information to the user terminal, the user can be effectively reminded to promptly confirm the locking status of the access control device to ensure that the access control device is locked normally.

[0110] In one embodiment, the control method further includes:

[0111] When the zero terminal detects that the external power supply of the access control device is abnormal, the zero terminal switches the external power supply mode to the built-in battery power supply mode.

[0112] In normal power supply mode, the access control device uses an external power supply mode, such as using household AC power to power the access control device. Therefore, when the above zero terminal detects that the external power supply of the access control device is abnormal, it means that the external power supply mode is abnormal. For example, when encountering emergencies such as power outages or failures of the household AC power, the zero terminal can switch the external power supply mode to the built-in battery power supply mode, wherein the built-in battery power supply mode uses the built-in battery in the access control device to power the access control device. It should be noted that after the external power supply mode returns to normal, the zero terminal switches the built-in battery power supply mode back to the external power supply mode.

[0113] Optionally, when an abnormality in the external power supply of the access control device is detected, the cloud server is notified to send power supply abnormality notification information to the user terminal so that the user can be informed of the power supply abnormality information in a timely manner.

[0114] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc. In addition, it is also easy to understand that these steps may be, for example, executed synchronously or asynchronously in multiple modules / processes / threads.

[0115] Furthermore, in this example embodiment, a control system for a access control device is also provided, which is applied to the access control device, and the control system includes a real-time connected zero terminal, a cloud server and an access control device, wherein the zero terminal and the access control device together constitute an intelligent access control device, and its appearance is similar to an existing smart door lock. The smart access control device is installed on the user's entrance door to realize intelligent access control; the cloud server is located in the cloud.

[0116] The zero terminal is used to collect real-time video data of the target person when receiving the detection message of the access control device, and store the real-time video data to the cloud server using the first channel; perform face recognition on the face image information in the real-time video data: if the recognized target face features do not match the face features pre-stored in the zero terminal, notify the cloud server to send a visitor verification message to the user terminal;

[0117] The cloud server is used to respond to the video call request initiated by the user terminal, send a call connection instruction to the null terminal and the user terminal, establish a second channel for the video call, and limit the data transmission rate of the first channel;

[0118] The zero terminal is also used to receive the access lock operation instruction sent by the user terminal, and send the access lock operation instruction to the door lock control module of the access control device.

[0119] In the embodiments of the present disclosure, the zero terminal will start the collection work only when it receives the detection message that the access control device detects the target person, so as to reduce resource consumption. The zero terminal does not need to communicate and interact with the cloud server when performing face recognition, which can improve the recognition efficiency. In addition, during the call, the cloud server will limit the data transmission rate of the first channel so that the data transmission rate of the second channel can be relatively improved. This is conducive to improving the fluency of calls between users and visitors and the stability of call video transmission, thereby improving the user experience.

[0120] It should be noted that, when the cloud server manages multiple access control devices, the cloud server will send a call connection instruction to the zero terminal of a corresponding access control device to establish a second channel for video calls between the user terminal and the corresponding zero terminal.

[0121] Next, the above-mentioned control system in this example embodiment will be described in more detail.

[0122] refer to Figure 2 As shown in , the zero terminal may include an image acquisition module 110, a face recognition module 120, a first matching processing module 130 and a second matching processing module 140. Among them:

[0123] The image acquisition module 110 is used to collect real-time video data of the target person when receiving a detection message from the access control device, and store the real-time video data to the cloud server using the first channel;

[0124] The face recognition module 120 is used to perform face recognition on the face image information in the real-time video data to obtain the target face features;

[0125] The first matching processing module 130 is used to send a door lock opening instruction to the door lock control module of the access control device and send a stop acquisition instruction to the image acquisition module 110 if the recognized target facial features match the facial features pre-stored in the zero terminal;

[0126] The second matching processing module 140 is used to notify the cloud server to send a visitor verification message to the user terminal if the recognized target facial features do not match the facial features pre-stored in the zero terminal.

[0127] After the target facial features are successfully matched with the pre-stored authorized facial features, the first matching processing module 130 can send a stop acquisition instruction to the image acquisition module 110, so that the image acquisition module 110 stops acquiring real-time video data of the target person to save resources; when the infrared sensor of the access control device detects a new target person, the image acquisition module 110 is notified to control the camera to be turned on to acquire real-time video data of the target person.

[0128] The access control device mentioned in this embodiment includes an infrared sensor, a camera and an audio component installed on the entrance door. For example, the infrared sensor is installed near the handle of the entrance door, the camera is installed near the cat's eye of the entrance door, and the audio component and the communication component are installed inside the door frame of the entrance door. The control system of the access control device proposed in this embodiment is applied to the access control device, which can control the operation of the access control device and realize the access control function.

[0129] When the access control device mentioned in this embodiment is in normal operation, the infrared sensor remains turned on to detect in real time whether there is a target person within the preset sensing range. When the infrared sensor detects the target person, the image acquisition module 110 of the zero terminal will control the camera and audio components to turn on and perform the operation of collecting real-time video data of the target person, and encode the collected real-time video data and transmit it to the cloud server. The face recognition module 120 will perform face recognition on the real-time video data collected by the image acquisition module 110 to obtain the target face features.

[0130] When the zero terminal of this embodiment receives the call connection instruction sent by the cloud server, it will control the camera and audio components of the access control device to turn on, so as to establish a second channel for the video call.

[0131] It should be noted that the cloud server, user terminal and zero terminal are connected to each other through 4G / 5G communication equipment. Under normal operation, the zero terminal maintains a connection with the cloud server to store the collected real-time video data in time when the target person suddenly appears.

[0132] In the embodiments of the present disclosure, on the one hand, when the image acquisition module 110 of the zero terminal receives a detection message that the access control device has detected a target person, the acquisition work will be started to reduce resource consumption, and when the face recognition module 120 of the zero terminal performs face recognition, it only needs to match the recognized target face features with the face features pre-stored in the zero terminal, that is, the face recognition module 120 does not need to communicate and interact with the cloud server during face recognition, which can improve the recognition efficiency; on the other hand, when the target face features do not match the authorized face features pre-stored in the zero terminal, the user will receive a visitor verification message at the user terminal. Message, and then actively initiate a video call request to the cloud server. With the help of the second channel for video calls established by the cloud server, during the call, the image acquisition module 110 of the zero terminal can send real-time video data to the user terminal, so that the user can view the facial features of the target person on the user terminal when communicating with the target person by voice. At the same time, during the call, the zero terminal limits the data transmission rate of the first channel to relatively improve the data transmission rate of the second channel. This is conducive to improving the fluency of calls between users and visitors and the stability of call video transmission, thereby improving the user experience.

[0133] Specifically, the face recognition module 120 includes an extraction processing unit and a recognition and comparison unit, wherein:

[0134] The extraction processing unit is used to extract the target video frame including the facial image information of the target person from the real-time video data;

[0135] The recognition and comparison unit is used to perform face recognition on the face image information in the target video frame to obtain the target face features of the target person.

[0136] The above-mentioned target video frame includes one or several frames of video images containing facial image information. The zero-terminal face recognition module 120 directly performs image recognition and local matching on the collected facial image information, which can reduce data forwarding delay and effectively improve recognition speed.

[0137] For example, when the first matching processing module 130 is working, if the target facial features match the pre-stored authorized facial features, it means that the target person is a visitor authorized by the user to pass through the door, that is, the target person is a trusted visitor, and the facial recognition is successful. If the facial recognition is successful, the unlocking operation is performed to allow the visitor to pass.

[0138] In one embodiment, the zero terminal further includes:

[0139] A determination module, used to determine matching time information and matching face information when the target face feature matches the pre-stored authorized face feature successfully;

[0140] The second sending module is used to send the matching time information and the matching face information to the cloud server.

[0141] The above-mentioned determination module is used to determine the matching time information and the matching face information, and the second sending module is used to send the matching time information and the matching face information to the cloud server for storage for backup use.

[0142] Optionally, the zero terminal further includes:

[0143] The trigger processing module is used to notify the cloud server to send a visitor verification message to the user terminal when receiving the doorbell trigger information. This can save time and quickly confirm the visitor's identity information for untrusted visitors.

[0144] It should be noted that the visitor verification message received by the user can be displayed on the user terminal in the form of a pop-up window with a prompt sound, so that the user can be informed of the visitor verification message in time, and then talk to the target person in time to confirm the identity information of the target person.

[0145] It should also be noted that after the user receives the visitor verification message, he can click the pop-up window on the user terminal to enter the access control device management interface and initiate a video call to the access control device.

[0146] It should be noted that during a call between a user and a visitor, the user can select the video call quality on the user terminal according to the network environment to ensure a smooth call between the user and the visitor.

[0147] In one embodiment, reference Figure 3 As shown in , the null terminal further includes a first receiving module 210, an encoding module 220 and a first sending module 230, wherein:

[0148] The first receiving module 210 is used to receive the video call mode instruction sent by the user terminal;

[0149] The encoding module 220 is used to encode the collected real-time video data using a corresponding encoding method according to the video call mode instruction to obtain code stream data;

[0150] The first sending module 230 is used to send the code stream data to the user terminal.

[0151] Through the cooperation of the above-mentioned first receiving module 210, encoding module 220 and first sending module 230, after the second channel for video calls is established, the encoding module 220 can use the corresponding encoding method to encode the real-time video data to be transmitted according to the video call mode instruction received by the first receiving module 210, so as to adapt to network environments with different communication qualities and ensure that in network environments with various communication qualities, users can talk with visitors smoothly and the call video transmission is stable.

[0152] Furthermore, the encoding module includes a first encoding unit, a second encoding unit and a third encoding unit; wherein,

[0153] The first encoding unit is used to encode the real-time video data using a YUV444 encoding method when the video call mode sent by the user terminal is a high-definition mode instruction;

[0154] The second encoding unit is used to encode the real-time video data using a YUV420 encoding method when the video call mode sent by the user terminal is a smooth mode instruction;

[0155] The third encoding unit is used to divide the portrait area and the non-portrait area in the real-time video data when the video call mode sent by the user terminal is a portrait mode instruction, and encode the portrait area using the YUV444 encoding method and encode the non-portrait area using the YUV420 encoding method.

[0156] Through the cooperation of the first encoding unit, the second encoding unit and the third encoding unit, different encoding methods can be used to encode real-time video data for network environments with different communication qualities. In particular, when the network environment is in a general communication quality, the portrait area and the non-portrait area in the real-time video data can be divided by the third encoding unit, and the portrait area is encoded by the YUV444 encoding method, and the non-portrait area is encoded by the YUV420 encoding method. This can ensure that the user and the visitor have smooth conversations and stable call video transmission, and can also enhance the clarity of the call video.

[0157] When the network environment is in the case of poor communication quality, the real-time video data can be encoded by the second encoding unit using the YUV420 encoding method to ensure smooth conversations between users and visitors and stable call video transmission; when the network environment is in the case of good communication quality, the real-time video data can be encoded by the first encoding unit using the YUV444 encoding method to ensure smooth conversations between users and visitors and stable call video transmission while enhancing the clarity of the call video.

[0158] In one embodiment, the zero terminal further includes a second receiving module and a collection processing module, wherein:

[0159] The second receiving module is used to receive the monitoring start instruction sent by the user terminal;

[0160] The acquisition and processing module is used to control the camera to start when receiving the monitoring start command sent by the user terminal, collect real-time video data of the target person, and send the real-time video data to the cloud server for storage.

[0161] Through the cooperation of the above-mentioned second receiving module and the acquisition and processing module, when the user needs to actively view the monitoring of the access control device, the second receiving module can receive the monitoring start instruction sent by the user terminal. When the second receiving module receives the monitoring start instruction sent by the user terminal, the acquisition and processing module collects the real-time video data of the target person and sends the real-time video data to the cloud server for storage; in this way, the user can load and display the real-time video data stored on the cloud server through the user terminal, so as to view the surveillance video within the preset monitoring range.

[0162] Example, reference Figure 2 As shown in , the zero terminal may further include a third receiving module 150, which is used to receive the access lock operation instruction sent by the user terminal and send the access lock operation instruction to the door lock control module of the access control device.

[0163] Specifically, the door lock operation instruction includes a door opening instruction and a door anti-lock instruction. If the user confirms that the target person is a trusted visitor, the third receiving module 150 will receive the door opening instruction sent by the user terminal and send the door opening instruction to the door lock control module; if the user confirms that the target person is an untrusted visitor, the third receiving module 150 will receive the door anti-lock instruction sent by the user terminal and send the door anti-lock instruction to the door lock control module.

[0164] It should be noted that if the user confirms that the visitor is a suspicious person, he or she can also perform a one-key alarm operation directly on the user terminal.

[0165] In one embodiment, the zero terminal further includes:

[0166] The first exception handling module is used to issue a prompt sound and notify the cloud server to send access control closure exception notification information to the user terminal when an access control closure exception is detected.

[0167] When the first exception handling module detects an access control closing abnormality, it indicates that the access control device is locked abnormally; by issuing a prompt sound and notifying the cloud server to send an access control closing abnormality notification message to the user terminal, the user can be effectively reminded to promptly confirm the locking status of the access control device to ensure that the access control device is locked normally.

[0168] In one embodiment, the zero terminal further includes:

[0169] The second exception handling module is used to switch the external power supply mode to the built-in battery power supply mode when an abnormality in the external power supply of the access control device is detected, and to notify the cloud server to send power supply abnormality notification information to the user terminal.

[0170] When the second exception handling module detects that the external power supply of the access control device is abnormal, it notifies the cloud server to send power supply abnormality notification information to the user terminal so that the user can be informed of the power supply abnormality information in time.

[0171] In normal power supply mode, the access control device uses an external power supply mode, such as using household AC power to power the access control device. Therefore, when the above-mentioned detection of an abnormality in the external power supply of the access control device indicates that an abnormality has occurred in the external power supply mode, for example, when encountering emergencies such as a power outage or failure of the household AC power, the second exception handling module can switch the external power supply mode to a built-in battery power supply mode, wherein the built-in battery power supply mode uses a built-in battery in the access control device to power the access control device. It should be noted that after the external power supply mode returns to normal, the second exception handling module switches the built-in battery power supply mode back to the external power supply mode.

[0172] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0173] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units for concretization. The components displayed as modules or units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0174] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A control method for an access control device, applied to a control system of the access control device, characterized in that: The control system includes a real-time connected zero terminal, a cloud server and an access control device, and the method includes: When receiving a detection message from the access control device, the zero terminal collects real-time video data of the target person and stores the real-time video data to the cloud server using the first channel; The zero terminal performs face recognition on the face image information in the real-time video data: If the identified target facial features do not match the facial features pre-stored in the zero terminal, the zero terminal notifies the cloud server to send a visitor verification message to the user terminal; The cloud server responds to the video call request initiated by the user terminal by sending a call connection instruction to the null terminal and the user terminal, establishing a second channel for the video call, and limiting the data transmission rate of the first channel; The zero terminal receives the access lock operation instruction sent by the user terminal, and sends the access lock operation instruction to the door lock control module of the access control device.

2. The control method of the access control device according to claim 1, characterized in that: After establishing the second channel for the video call, the method further includes: The null terminal receives a video call mode instruction sent by the user terminal, where the video call mode instruction includes a high-definition mode instruction, a smooth mode instruction, and a portrait mode instruction; According to the video call mode instruction, the null terminal uses a corresponding encoding method to encode the collected real-time video data to obtain code stream data; The null terminal sends the code stream data to the user terminal.

3. The control method of the access control device according to claim 2, characterized in that: According to the video call mode instruction, the zero terminal uses a corresponding encoding method to encode the collected real-time video data, including: When the video call mode sent by the user terminal is a high-definition mode instruction, the null terminal encodes the real-time video data using a YUV444 encoding method; When the video call mode sent by the user terminal is a smooth mode instruction, the null terminal encodes the real-time video data using a YUV420 encoding method; When the video call mode sent by the user terminal is a portrait mode instruction, the zero terminal divides the portrait area and the non-portrait area in the real-time video data, and encodes the portrait area using YUV444 encoding, and encodes the non-portrait area using YUV420 encoding.

4. The control method of the access control device according to claim 1, characterized in that: In the step of performing face recognition on the face image information in the real-time video data by the zero terminal, the method further includes: If the recognized target facial features match the facial features pre-stored in the zero terminal, the zero terminal sends a door opening instruction to the door lock control module and stops collecting real-time video data.

5. The control method of the access control device according to claim 4, characterized in that: After the target facial features are successfully matched with the pre-stored authorized facial features, the method further includes: The zero terminal determines matching time information and matching face information, and sends the matching time information and the matching face information to the cloud server.

6. The control method of the access control device according to claim 1, characterized in that: The method further comprises: When the zero terminal detects that the access control is closed abnormally, the zero terminal emits a prompt tone and notifies the cloud server to send access control closing abnormality notification information to the user terminal.

7. The control method of the access control device according to claim 1, characterized in that: The method further comprises: When the zero terminal detects that the external power supply of the access control device is abnormal, the zero terminal switches the external power supply mode to the built-in battery power supply mode.

8. A control system for an access control device, characterized in that: The control system includes a zero terminal, a cloud server and an access control device connected in real time; The zero terminal is used to collect real-time video data of the target person when receiving a detection message from the access control device, and store the real-time video data to the cloud server using the first channel; perform face recognition on the face image information in the real-time video data: if the recognized target face features do not match the face features pre-stored in the zero terminal, notify the cloud server to send a visitor verification message to the user terminal; The cloud server is used to respond to the video call request initiated by the user terminal, send a call connection instruction to the null terminal and the user terminal, establish a second channel for the video call, and limit the data transmission rate of the first channel; The zero terminal is also used to receive the access lock operation instruction sent by the user terminal, and send the access lock operation instruction to the door lock control module of the access control device.

9. The control system of the access control device according to claim 8, characterized in that: The zero terminal also includes: A first receiving module, configured to receive a video call mode instruction sent by the user terminal; An encoding module, used to encode the collected real-time video data using a corresponding encoding method according to the video call mode instruction to obtain code stream data; The first sending module is used to send the code stream data to the user terminal.

10. The control system of the access control device according to claim 9, characterized in that: The encoding module includes a first encoding unit, a second encoding unit and a third encoding unit; wherein, The first encoding unit is used to encode the real-time video data using a YUV444 encoding method when the video call mode sent by the user terminal is a high-definition mode instruction; The second encoding unit is used to encode the real-time video data using a YUV420 encoding method when the video call mode sent by the user terminal is a smooth mode instruction; The third encoding unit is used to divide the portrait area and the non-portrait area in the real-time video data when the video call mode sent by the user terminal is a portrait mode instruction, and encode the portrait area using the YUV444 encoding method and encode the non-portrait area using the YUV420 encoding method.

Images