A door access call control method and device, a door access device, and a storage medium

Abstract

The application discloses a door access call control method and device, a door access equipment and a storage medium, relates to the technical field of communication, and can improve the confidentiality and security of door access management. The method comprises the following steps: in response to receiving a door access call request, performing call behavior detection on at least one person in a monitored video; in the case where no person with a call behavior is detected, acquiring the number of eyes of each person and the distance from the door access equipment; in the case where at least one first person exists, determining the first person with the minimum distance from the door access equipment among the at least one first person as a target call person; in the case where no first person exists but at least one second person exists, determining the second person with the minimum distance from the door access equipment among the at least one second person as the target call person; determining the position of the target call person, and playing response information of the door access call request to the target call person in a targeted manner according to the position of the target call person.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to an access control call control method, device, access control equipment, and storage medium. Background Technology

[0002] As living standards improve, people have higher requirements for their living environment, and the security system of residential communities is receiving more and more attention. Among them, access control is an important part of community security management.

[0003] In related technologies, to facilitate communication between visitors and residents or to receive access control notifications, access control devices (such as door intercoms) typically broadcast audio messages to visitors. However, this method allows unrelated individuals (those other than visitors) to hear the notifications when multiple people are near the access control device, resulting in poor confidentiality and low security for access control management. Summary of the Invention

[0004] This application provides an access control call control method, device, access control equipment, and storage medium, which can be used to improve the confidentiality and security of access control management.

[0005] In a first aspect, embodiments of this application provide an access control call control method, the method comprising: in response to receiving an access control call request, detecting call behavior of at least one person appearing in a surveillance video, the call behavior being used to characterize the operation that triggers the access control call request; if no person with call behavior is detected from the surveillance video, obtaining the number of eyes of each person in the surveillance video and the distance of each person from the access control device; if at least one first person exists, determining the first person with the smallest distance from the access control device among the at least one first person as the target caller, the first person being a person with two eyes in the surveillance video; if no first person exists but at least one second person exists, determining the second person with the smallest distance from the access control device among the at least one second person as the target caller, the second person being a person with one eye in the surveillance video; determining the location of the target caller based on the surveillance video, and playing response information of the access control call request to the target caller in a targeted manner according to the location of the target caller.

[0006] The technical solution provided in this application offers at least the following advantages: When no person with calling behavior (i.e., the operation that triggers an access control call request) is identified from the surveillance video, the target caller is determined based on the number of eyes of the person and their distance from the access control device. Furthermore, response information is directed to the target caller to improve the confidentiality and security of access control management. It is understood that when a target caller triggers an access control call request, they generally need to be close to and pay attention to the access control device. This means that the target caller is closer to the access control device (i.e., closer to the access control device), and their eyes should be captured by the surveillance video (i.e., more focused on the access control device). Therefore, the target caller can be identified accurately based on the distance between each person and the access control device and the number of eyes in the current image frame.

[0007] In some embodiments, the above-mentioned location is world coordinates; the above-mentioned determination of the location of the target caller based on surveillance video includes: determining the pixel coordinates of the target caller based on surveillance video; and performing coordinate transformation on the pixel coordinates of the target caller to obtain the world coordinates of the target caller.

[0008] Based on this, the world coordinates of the target caller can be determined through surveillance video.

[0009] In some embodiments, determining the location of a target caller based on surveillance video includes: extracting a local image related to the target caller from the current video frame image of the surveillance video; detecting the target part of the local image to obtain the location of the target part of the target caller; the target part includes: the ear or the head.

[0010] In this way, the direction of the access control device's response information can be determined based on the location of the target part of the caller, so that the response information is played in a targeted manner to the target part of the caller (such as the ear or head where it is convenient to receive the information), thereby improving the confidentiality of access control management.

[0011] In some embodiments, the method further includes: recording the facial position of the target caller based on the surveillance video; redetermining the position of the target part of the target caller after the facial position of the target caller changes; and adjusting the playback direction of the response information according to the redetermined position of the target part of the target caller so that the playback direction is aligned with the target part of the target caller.

[0012] Based on this, the information playback direction can be readjusted as the target caller moves (e.g., as the target caller's face position changes), so that the audio playback direction always follows the target part of the target caller, realizing real-time directional audio playback and improving the confidentiality and security of access control management.

[0013] In some embodiments, the method further includes: identifying the single person as the target caller when at least one person appearing in the surveillance video is a single person; or, identifying the person with calling behavior in the surveillance video as the target caller when a person with calling behavior is detected in the surveillance video.

[0014] Understandably, if only one person is visible in the surveillance video, that person is most likely the target caller for the access control call request. Alternatively, the target caller who engages in calling behavior can be selected from the surveillance video (e.g., if multiple people are visible in the video, the person engaging in calling behavior can be selected from among them). Based on this, the response information for the access control call request can be accurately and directed to the target caller, preventing unauthorized personnel from obtaining the full content of the response information, thus improving the confidentiality and security of access control management.

[0015] In some embodiments, the aforementioned calling behavior includes one or more of the following: making a specified gesture, issuing a calling command, touching or pressing the calling control of the access control device, or standing in a preset area associated with the access control device.

[0016] In some embodiments, the above-described method of playing the access control call request response information to the target caller in a targeted manner based on the target caller's location includes: determining the distance of the target caller relative to the access control device based on the target caller's location; determining a target volume based on the distance between the target caller and the access control device, and the correspondence between distance and volume, wherein the target volume is the volume corresponding to the distance between the target caller and the access control device; and playing the access control call request response information to the target caller in a targeted manner based on the target caller's location using the target volume.

[0017] It should be understood that the volume of sound decreases as the distance travels. When multiple people are present, the person making the call is generally closer to the access control device than others. Therefore, the response information is played at a targeted volume towards the target person, ensuring they can clearly hear the audio. This ensures that the audio continues to travel to other people after the volume has decreased to a level imperceptible to the human ear. This improves the confidentiality and security of access control management.

[0018] Secondly, embodiments of this application provide an access control call control device, which includes: a personnel determination module, a personnel positioning module, and an information playback module. The personnel determination module is used to, in response to receiving an access control call request, detect the calling behavior of at least one person appearing in the surveillance video, where the calling behavior characterizes the operation that triggers the access control call request; if no person with calling behavior is detected in the surveillance video, it obtains the number of eyes of each person in the surveillance video and the distance of each person from the access control device; if at least one first person exists, it determines the first person with the smallest distance from the access control device among the at least one first person as the target caller, where the first person is the person with two eyes in the surveillance video; if there is no first person but at least one second person exists, it determines the second person with the smallest distance from the access control device among the at least one second person as the target caller, where the second person is the person with one eye in the surveillance video; the personnel positioning module is used to determine the location of the target caller based on the surveillance video; and the information playback module is used to directionally play the access control call request response information to the target caller according to the location of the target caller.

[0019] In some embodiments, the aforementioned location is world coordinates; the aforementioned personnel positioning module is specifically used to determine the pixel coordinates of the target caller based on the surveillance video; and to perform coordinate transformation on the pixel coordinates of the target caller to obtain the world coordinates of the target caller.

[0020] In some embodiments, the personnel positioning module is specifically used to extract a local image related to the target caller from the current video frame image of the surveillance video; to detect the target part of the local image to obtain the location of the target part of the target caller; the target part includes: ear or head.

[0021] In some embodiments, the personnel positioning module described above is also used to record the facial location of the target caller based on surveillance video.

[0022] In some embodiments, the above-mentioned information playback module is further configured to adjust the playback direction of the response information according to the newly determined location of the target part of the target caller, so that the playback direction is aligned with the target part of the target caller.

[0023] In some embodiments, the personnel determination module is further configured to determine the single person as the target caller when at least one person appearing in the surveillance video is a single person; or, when a person with calling behavior is detected from the surveillance video, determine the person with calling behavior in the surveillance video as the target caller.

[0024] In some embodiments, the aforementioned calling behavior includes one or more of the following: making a specified gesture, issuing a calling command, touching or pressing the calling control of the access control device, or standing in a preset area associated with the access control device.

[0025] In some embodiments, the above-mentioned information playback module is specifically used to determine the distance of the target caller relative to the access control device based on the location of the target caller; determine the target volume based on the distance between the target caller and the access control device, and the correspondence between distance and volume, wherein the target volume is the volume corresponding to the distance between the target caller and the access control device; and play the response information of the access control call request to the target caller in a directional manner using the target volume based on the location of the target caller.

[0026] Thirdly, embodiments of this application provide an access control device, including: a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code including computer instructions; wherein, when the processor executes the computer instructions, it causes the access control device to perform an access control call control method as described in the first aspect and any of its possible design embodiments.

[0027] Fourthly, embodiments of this application provide a computer-readable storage medium including computer instructions that, when executed on a computer (e.g., an access control device or an access control call control device), cause the computer (e.g., the access control device or access control call control device) to perform the access control call control method provided in the first aspect and possible implementations.

[0028] Fifthly, embodiments of this application provide a computer program product containing computer instructions that, when executed on a computer (e.g., an access control device or an access control call control device), cause the computer (e.g., the access control device or access control call control device) to perform the methods provided in the first aspect and possible implementations described above.

[0029] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the controller's processor, or it may be packaged separately from the controller's processor; this application does not impose any limitations on this.

[0030] For a detailed description of aspects two through five and their various implementations in this application, please refer to the detailed description in aspect one and its various implementations. The beneficial effects of aspects two through five and their various implementations can be found in the analysis of the beneficial effects of aspect one and its various implementations; they will not be repeated here. Attached Figure Description

[0031] Figure 1This is a schematic diagram of the structure of an access control and call system according to some embodiments. Figure 1 ;

[0032] Figure 2 This is a schematic diagram of the structure of an access control and call system according to some embodiments. Figure 2 ;

[0033] Figure 3 This is a flowchart illustrating an access control call control method according to some embodiments. Figure 1 ;

[0034] Figure 4 This is a flowchart illustrating an access control call control method according to some embodiments. Figure 2 ;

[0035] Figure 5 This is a flowchart illustrating an access control call control method according to some embodiments. Figure 3 ;

[0036] Figure 6 This is a flowchart illustrating an access control call control method according to some embodiments. Figure 4 ;

[0037] Figure 7 This is a flowchart illustrating an access control call control method according to some embodiments. Figure 5 ;

[0038] Figure 8 This is a schematic diagram of the structure of an access control call control device according to some embodiments. Figure 1 ;

[0039] Figure 9 This is a schematic diagram of the structure of an access control call control device according to some embodiments. Figure 2 . Detailed Implementation

[0040] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0042] As described in the background section, access control is a crucial component of community security management. In related technologies, to facilitate communication between visitors and residents or to receive access control notifications, access control devices typically broadcast audio messages to visitors. However, this method allows unrelated individuals (those other than visitors) to hear the notifications when multiple people are present near the access control device, resulting in poor confidentiality and low security.

[0043] To address this, this application provides an access control call control method. The core idea of ​​this method is to determine the target caller based on the number of eyes of each person and their distance from the access control device when no person with calling behavior (i.e., the operation that triggers the access control call request) is identified from the surveillance video. Then, a response message is played to the target caller to improve the confidentiality and security of access control management. It is understood that when the target caller triggers the access control call request, they generally need to be close to and pay attention to the access control device. This means that the target caller is closer to the access control device (i.e., closer to the access control device), and their eyes should be captured by the surveillance video (i.e., more focused on the access control device). Therefore, the target caller can be identified accurately based on the distance between each person and the access control device and the number of eyes in the current image frame.

[0044] The access control call method provided in this application can be applied to any scenario requiring access control call control, such as a call scenario between an external visitor and an indoor resident, a call scenario between a tourist and a ticket seller at the counter, or a call scenario between a security room and an external person, etc., without specific limitations. For the sake of subsequent explanation, the access control call control system involved in this application will first be given an overall introduction below.

[0045] Figure 1This is a schematic diagram of the structure of an access control and call system provided in an embodiment of this application. (Refer to...) Figure 1 The access control and call control system 100 includes an access control device 101 and an indoor unit 102. The access control device 101 and the indoor unit 102 can communicate with each other via wired or wireless means.

[0046] The access control device 101 is used to send instruction information, audio information, and / or image information (including image frame information of the monitoring video) of external visitors to the indoor unit 102, and to receive instruction information, audio information, and / or image information sent by the indoor unit 102. Furthermore, the access control device 101 is used to execute the access control call control method provided in this application. Optionally, the access control device 101 can detect, receive, and / or respond to access control call requests from external visitors. Optionally, the access control device 101 can acquire the monitoring video of the access control device area. Optionally, the access control device 101 can play audio in a directional manner. Optionally, the access control device 101 can adjust the playback direction of the audio. Optionally, the access control device 101 can display an indoor monitoring screen, which is a video screen generated based on the video data sent by the indoor unit 102.

[0047] Indoor unit 102 is used to receive instruction information, audio information, and / or image information from visitors sent by access control device 101, and to send instruction information, audio information, and / or image information from residents inside the building to access control device 101. Optionally, indoor unit 102 can capture indoor monitoring images and / or indoor audio information. Optionally, indoor unit 102 can display monitoring video of the access control area transmitted by access control device 101. Optionally, indoor unit 102 has an alarm function. Optionally, indoor unit 102 can send unlocking commands to access control device 101.

[0048] In some embodiments, the access control device 101 may be installed at the entrance of a building, and the indoor unit 102 may be installed in the corresponding resident's room; or, the access control device 101 may be installed at the entrance of a residential community, and the indoor unit 102 may be installed in the corresponding security room of the community. It should be understood that the above-described installation methods of the access control device 101 and the indoor unit 102 are merely examples, and the access control device 101 and the indoor unit 102 can be installed in any situation requiring access control management or access control calls, and this application does not impose specific limitations on them.

[0049] To more clearly explain the working principle of the access control and call system, the components of the access control and call system are explained here. For example... Figure 2 As shown, Figure 2 The diagram shows a schematic of an access control and call system.

[0050] Reference Figure 2The access control device 101 includes the following trigger module 1011, first audio acquisition module 1012, first camera module 1013, ranging module 1014, first audio playback module 1015, first display module 1016, and first communication module 1017.

[0051] The trigger module 1011 is used to receive instruction information from visitors. For example, the trigger module 1011 can receive and / or detect access control call requests from visitors; or, for example, when there are multiple indoor units in the access control call system, the trigger module 1011 can receive the address of the target indoor unit input by the visitor. The trigger module 1011 includes, but is not limited to, the following triggering methods: dialing, button pressing, touch control, gesture, or voice.

[0052] The first audio acquisition module 1012 is used to acquire sounds near the access control device in order to obtain the voice of the target caller. Optionally, the acquired sound can also be identified to assist the access control device in receiving and / or detecting access control call requests. For example, if the acquired sound content is detected to be a preset call password, the access control call request corresponding to that call password is received.

[0053] The first camera module 1013 is used to acquire surveillance video near the access control device to obtain a monitoring image including the target caller. Optionally, the first camera module 1013 can also perform image recognition on the surveillance video to determine the target caller. For example, the first camera module 1013 can be used to identify a preset area associated with the access control device 101 and identify the person standing in the preset area as the target caller. As another example, the first camera module 1013 can identify a person making a specified gesture in the surveillance video and identify the person making the specified gesture as the target caller.

[0054] The ranging module 1014 is used to obtain the distance between personnel in the surveillance video and the access control device 101. Optionally, the ranging module 1014 can perform ranging using a lidar. Optionally, the ranging module 1014 can also be integrated with the first camera module 1013 or other camera modules (not shown in the figure) to obtain the distance between personnel in the surveillance video and the access control device 101 through monocular ranging analysis, binocular ranging analysis, or depth image ranging analysis.

[0055] The first audio playback module 1015 is used to play access control prompts or response information from the indoor unit 102. For example, the first audio playback module 1015 can play a prompt tone indicating successful door opening. Alternatively, the first audio playback module 1015 can play voice information from the indoor user transmitted from the indoor unit 102. Optionally, the first audio playback module 1015 can adjust the direction of audio playback. Optionally, the first audio playback module 1015 can adjust the volume of audio playback. For example, the first audio playback module 1015 can determine the target volume based on the distance between the target caller and the access control device.

[0056] The first display module 1016 is used to display a first access control management interface. This interface can display one or more of the following: monitoring footage from the first camera module 1013, a dial-up interface, or indoor monitoring footage transmitted from the indoor unit 102. The first display module 1016 can be a liquid crystal display (LCD) or an organic light-emitting diode (OLED) display. This application does not limit the specific type, size, or resolution of the first display module 1016.

[0057] The first communication module 1017 is used to establish a communication connection with the indoor unit 102. The first communication module 1017 can be a component that communicates with external devices or servers according to various communication protocol types. For example, the first communication module 1017 may include at least one of the following: a wireless communication technology (Wi-Fi) module, a Bluetooth module, a wired Ethernet module, and a near-field communication (NFC) module, as well as other network communication protocol chips or near-field communication protocol chips, and an infrared receiver. This application does not impose specific limitations on this.

[0058] The indoor unit 102 includes a second audio acquisition module 1021, a second camera module 1022, a second audio playback module 1023, a second display module 1024, and a second communication module 1025.

[0059] The second audio acquisition module 1021 is used to collect indoor sound in order to obtain the voice information of the indoor residents.

[0060] The second camera module 1022 is used to acquire indoor monitoring images.

[0061] The second audio playback module 1023 is used to play access control notification information or audio information transmitted from the access control device 101. For example, the second audio playback module 1023 can play a called notification tone. As another example, the second audio playback module 1023 can play the voice information of the target caller transmitted from the access control device 101.

[0062] The second display module 1024 is used to display a second access control management interface. This second access control management page can display one or more of the following: indoor monitoring images captured by the second camera module 1022, or monitoring images transmitted from the access control device 101. The configuration of the second display module 1024 can be referred to the above description of the first display module 1016, and will not be repeated here.

[0063] The second communication module 1025 is used to establish a communication connection with the access control device 101. The second communication module 1025 can be a component that communicates with external devices or servers according to various communication protocol types. The configuration of the second communication module 1025 can be referred to the above description of the first communication module 1017, and will not be repeated here.

[0064] It should be noted that the modules in the access control device 101 and indoor unit 102 described above are merely examples. In practical applications, each module can be deployed independently or integrated. Furthermore, access control device 101 and indoor unit 102 may not include all of the aforementioned modules. For example, even if access control device 101 does not include the first display module 1016, access control device 101 can still acquire monitoring video including the target caller through the first camera module 1013, and then direct response information to the target caller. This application embodiment does not impose specific limitations in this regard.

[0065] although Figure 2 As not shown, the access control device 101 and the indoor unit 102 may also include power modules (such as batteries and power management chips) that supply power to the various components, as well as storage modules. The storage modules may include high-speed random access memory, and may also include non-volatile memory, such as disk storage devices, flash memory devices, or other volatile solid-state storage devices. This application does not impose specific limitations on this.

[0066] For ease of understanding, the access control call control method provided in this application will be described in detail below with reference to the accompanying drawings.

[0067] Figure 3 This is a schematic diagram of an access control call control method proposed in this application. The following describes the implementing entity as... Figure 1 Taking the access control device shown as an example, the access control call control method provided in this application will be explained. Figure 3 As shown, the access control call method includes the following steps S101 to S105:

[0068] S101. In response to receiving an access control call request, perform call behavior detection on at least one person appearing in the surveillance video.

[0069] Among them, the call behavior is used to characterize the operation that triggers the access control call request.

[0070] In some embodiments, the calling behavior includes one or more of the following: making a specified gesture, issuing a calling command, touching or pressing the calling control of the access control device, or standing in a preset area associated with the access control device. It should be understood that this application does not specifically limit the content of the calling behavior.

[0071] In some embodiments, call behavior detection is used to detect whether there are people in the surveillance video who are making calls, that is, people who trigger access control call requests.

[0072] In some embodiments, an access control call request includes one or more of a conversation request, a video request, or a door opening request.

[0073] In some embodiments, access control call requests may be triggered by dialing, pressing keys, touch, gestures, or voice, and this application does not impose any restrictions on this.

[0074] In some embodiments, the aforementioned surveillance video may be a surveillance video generated in real time by a camera module built into the access control device or a camera module connected to the access control device, or it may be a surveillance video generated by reading data from a storage module built into the access control device or a storage module connected to the access control device.

[0075] In some embodiments, in response to receiving an access control call request, the access control device further performs the following steps: sending the monitoring video and / or audio information corresponding to the access control device to the indoor unit; or receiving the indoor monitoring video and / or indoor audio information transmitted by the indoor unit.

[0076] Furthermore, considering that multiple users reside within a building, the access control system may have multiple indoor units. To ensure accurate data transmission between the access control equipment and the indoor units, the aforementioned access control call request may also include the target indoor unit address, which can be set by the visitor. The aforementioned sending of the access control equipment's corresponding surveillance video and / or audio information to the indoor unit; or receiving the indoor surveillance video and / or indoor audio information transmitted by the indoor unit, can be specifically implemented as follows: based on the target indoor unit address, sending the access control equipment's corresponding surveillance video and / or audio information to the target indoor unit; or receiving the target indoor surveillance video and / or indoor audio information transmitted by the target indoor unit.

[0077] In some embodiments, step S101 is specifically implemented as: based on multiple consecutive frames of images in the surveillance video containing the current video frame image, call behavior detection is performed on each of the at least one person.

[0078] It should be understood that since a call may be a continuous action in time, detecting a call based on multiple consecutive frames of images containing the current video frame can improve the accuracy of the detection.

[0079] In some embodiments, such as Figure 4 As shown, step S101 can be specifically implemented as steps S1011 to S1013:

[0080] S1011. In response to receiving an access control call request, obtain the current video frame image of the monitoring video.

[0081] It should be understood that the access control call request has been described in detail above, and will not be repeated here.

[0082] In some examples, the above-mentioned acquisition of the current image frame of the surveillance video can be specifically implemented as: acquiring the current image frame of the surveillance video in real time, frame by frame.

[0083] In other examples, obtaining the current image frame of the surveillance video can be specifically implemented as follows: detecting whether the number of captured frames of the surveillance video has reached a preset number of frames; if the number of captured frames has reached the preset number of frames, then determining the image frame in the surveillance video when the number of captured frames reaches the preset number of frames as the current video image frame.

[0084] S1012. Perform face detection on the current video frame image and identify at least one person in the current video frame image.

[0085] It should be noted that step S1012 is used to identify one or more persons in the current video frame image in order to further detect calling behavior of each person. The face detection described above is only one way to achieve this function. Those skilled in the art should understand that at least one person in the current video frame image can also be identified by other means. For example, identification can be achieved through human contour detection, etc. This application does not specifically limit this method.

[0086] S1013. Detect the calling behavior of at least one person appearing in the surveillance video.

[0087] The call behavior detection is used to detect whether there are personnel making call behaviors in the surveillance video. Optionally, the call behavior includes one or more of the following: making a specified gesture, issuing a call command, touching or pressing the call control of the access control device, or standing in a preset area associated with the access control device.

[0088] S102. If no person with calling behavior is detected in the surveillance video, obtain the number of eyes of each person in the surveillance video and the distance of each person from the access control device.

[0089] In some embodiments, obtaining the number of eyes of each person in the surveillance video can be specifically implemented as follows: performing human body recognition on the surveillance video to determine the human body detection box of each person in the surveillance video; performing eye recognition on the human body detection box of each person to determine the number of eyes of each person in the surveillance video. It should be understood that face recognition can also be performed on the surveillance video before eye recognition, or eye recognition can be performed directly. This application does not limit the specific method for obtaining the number of eyes.

[0090] In some embodiments, the distance between each person and the access control device can be measured by the access control device itself or by an external device connected to the access control device. For example, the distance between each person and the access control device can be measured using ranging methods such as monocular ranging analysis, binocular ranging analysis, depth image ranging, and lidar ranging analysis. This application does not specifically limit the ranging method.

[0091] The following example uses binocular ranging analysis. Access control devices can include multiple imaging modules to acquire two visible light images of each person, thereby determining the distance between each person and the access control device. For example, such as... Figure 5 As shown, obtaining the distance between each person in the surveillance video and the access control device can be specifically implemented through the following steps S1021 to S1023:

[0092] S1021. Acquire a first visible light image and a second visible light image including each person.

[0093] The first visible light image and the second visible light image are two different images of each person taken at the same time. Optionally, the first and second visible light images can be captured by a binocular camera module included in the access control device itself; alternatively, the first and second visible light images can be captured by a binocular rangefinder device connected externally to the access control device. It should be noted that the device capturing the first and second visible light images of each person should be located in the same position as the access control device.

[0094] In some examples, after acquiring the first and second visible light images of each person, further image preprocessing is required, such as image denoising and image distortion correction, to improve the accuracy of ranging.

[0095] S1022. Determine the position of each person in the first visible light image and the position of each person in the second visible light image.

[0096] The positions of each person in the first visible light image and the second visible light image can be manually delineated or determined through human body recognition using deep learning.

[0097] S1023. Perform parallax calculation and depth analysis on the position of each person in the first visible light image and the position of each person in the second visible light image to determine the temperature measurement distance between each person and the access control device. Specific algorithms for parallax calculation and depth analysis can be found in relevant technical documents and will not be elaborated here.

[0098] It should be noted that the above method of measuring distance through binocular ranging analysis is only an example, and this application does not impose specific limitations on the method of measuring distance.

[0099] S103. In the case of at least one first person, the first person who is closest to the access control device among the at least one first person shall be identified as the target caller.

[0100] The first person is the one whose eyes appear to be two in the surveillance video.

[0101] Understandably, when triggering an access control call request, the target caller typically needs to be close to and pay attention to the access control device. This means the target caller is closer to the device (i.e., closer to the device) and their eyes should be captured by the surveillance video (i.e., more focused on the device). Generally, the target caller will look at the device with both eyes. Therefore, the first person closest to the device (i.e., the person with two eyes in the surveillance video) can be prioritized as the target caller, thus accurately identifying them.

[0102] S104. In the case where there is no first person but there is at least one second person, the second person who is the closest to the access control device among the at least one second person shall be identified as the target caller.

[0103] The second person is the person in the surveillance video who has only one eye.

[0104] Considering that people may move, each person appearing in the surveillance video may only have one eye visible. In this case, the second person closest to the access control device (the person with only one eye visible in the video) can be identified as the target caller. Based on this, the accuracy of identifying the target caller can be improved.

[0105] S105. Determine the location of the target caller based on the surveillance video, and according to the location of the target caller, play the response information of the access control call request to the target caller in a targeted manner.

[0106] In some embodiments, the location of the target caller can be the location of a target body part, such as the ear or head. It should be understood that the target body part can also be other preset body parts, such as the face, and there is no specific limitation thereto.

[0107] Furthermore, the above-mentioned method of determining the location of the target caller based on surveillance video can be specifically implemented as follows: extracting a local image related to the target caller from the current video frame of the surveillance video; detecting the target part in the local image to obtain the location of the target part of the target caller. Optionally, the target part includes: the ear or the head.

[0108] In this way, the direction of the access control device's response information can be determined based on the location of the target part of the caller, so that the response information is played in a targeted manner to the target part of the caller (such as the ear or head where it is convenient to receive the information), thereby improving the confidentiality of access control management.

[0109] In some embodiments, the location of the target caller is the world coordinates of the target caller. The above-mentioned determination of the location of the target caller based on surveillance video is specifically implemented by the following steps: determining the pixel coordinates of the target caller based on the surveillance video; performing coordinate transformation on the pixel coordinates of the target caller to obtain the world coordinates of the target caller.

[0110] In some examples, converting pixel coordinates to world coordinates can be achieved through a series of coordinate system transformations. For instance, this can be done by converting from pixel coordinates to image coordinates, from image coordinates to camera coordinates, and from camera coordinates to world coordinates. The pixel coordinate system has its origin at the top left corner of the image (e.g., a video frame), with its horizontal axis parallel to the bottom edge of the image and its vertical axis parallel to the height of the image. The image coordinate system has its origin at the center of the image, with its horizontal axis parallel to the bottom edge of the image and its vertical axis parallel to the height of the image. The camera coordinate system is a three-dimensional coordinate system centered on the camera's light source. The world coordinate system is the absolute coordinate system of the objective three-dimensional world.

[0111] For ease of understanding, the following exemplifies a coordinate transformation method for converting pixel coordinates to world coordinates: Based on surveillance video, determine the pixel coordinates of the target caller; based on the affine transformation relationship between the image coordinate system and the pixel coordinate system, convert the pixel coordinates of the target caller to image coordinates. Based on the projection transformation relationship between the camera coordinate system and the image coordinate system, convert the image coordinates of the target caller to camera coordinates. Based on the rigid body transformation relationship between the world coordinate system and the camera coordinate system, convert the camera coordinates of the target caller to world coordinates. It should be understood that both the world coordinate system and the camera coordinate system are three-dimensional coordinate systems, only with different coordinate representations. Therefore, camera coordinates in the camera coordinate system can be converted to world coordinates in the world coordinate system using rotation and translation matrices.

[0112] Based on this, the pixel coordinates of the target caller can be converted into world coordinates.

[0113] In some embodiments, the response information includes: access control opening prompts and / or indoor audio information. It should be understood that the response information may also include other content, and this application does not impose specific limitations on it.

[0114] In some embodiments, step S105 is specifically implemented as follows: based on the location of the target caller, adjusting the audio playback module built into the access control device (e.g., Figure 2 The first audio playback module 1015 in the middle is adjusted to adjust the sound emission angle so that the sound emission direction is aimed at the location of the target caller, and then the response information of the access control call request is played.

[0115] In some embodiments, considering that audio volume attenuates with increasing distance, to improve the confidentiality of access control management, the audio volume corresponding to the response information can be set so that the audio corresponding to the response information can be clearly conveyed to the target caller, and that when the audio propagation distance exceeds the distance between the access control device and the target caller, the audio volume of the response information has attenuated to a level that is difficult for the human ear to distinguish. For example, as... Figure 6 As shown, the above-mentioned method of playing the access control call request response information to the target caller based on the target caller's location can be specifically implemented through the following steps S1051 to S1053:

[0116] S1051. Determine the distance between the target caller and the access control device based on the location of the target caller.

[0117] In some examples, the distance between the target caller and the access control device can be measured by the access control device itself or by an external device connected to the access control device. For example, the distance between the target caller and the access control device can be measured using ranging methods such as monocular ranging analysis, binocular ranging analysis, depth image ranging, and lidar ranging analysis. This application does not specifically limit the ranging method.

[0118] S1052. Based on the distance between the target caller and the access control device, and the correspondence between distance and volume, determine the target volume, which is the volume corresponding to the distance between the target caller and the access control device.

[0119] S1053. Based on the location of the target caller, use the target volume to directionally play the response information of the access control call request to the target caller.

[0120] It should be understood that if multiple people are present in the scenario, the target caller is generally closer to the access control device than others. Therefore, the response information is played directionally to the target caller at a targeted volume, ensuring that the target caller can clearly hear the corresponding audio. Furthermore, by the time the audio reaches other people, its volume has attenuated to a level imperceptible to the human ear. This improves the confidentiality and security of access control management.

[0121] It should be understood that Figure 3 The provided technical solution offers at least the following benefits: It should be understood that when a target caller initiates an access control call request, they generally need to be close to and pay attention to the access control device. This means the target caller is closer to the device (i.e., closer to the device) and their eyes should be captured by the surveillance video (i.e., more focused on the device). Therefore, the target caller can be identified based on the distance between each person and the access control device, as well as the number of eyes in the current image frame, allowing for accurate identification. Thus, even when no person with calling behavior (i.e., initiating an access control call request) is identified from the surveillance video, the target caller can be determined based on the number of eyes and their distance from the access control device. Furthermore, targeted playback of response information to the target caller improves the confidentiality and security of access control management.

[0122] In some embodiments, considering that the target caller's location may change, it can be further determined whether the target caller has moved, so as to adjust the audio output direction so that the adjustment of the audio output direction always follows the target caller's position. For example, as... Figure 7 As shown, after step S105, the method further includes the following step S106:

[0123] S106. Based on the surveillance video, record the facial position of the target caller; after the facial position of the target caller changes, re-determine the position of the target part of the target caller; based on the re-determined position of the target part of the target caller, adjust the playback direction of the response information so that the playback direction is aligned with the target part of the target caller.

[0124] The specific algorithm for recording face location can refer to relevant technologies, and this application does not impose any restrictions on it.

[0125] Based on this, the information playback direction can be readjusted as the target caller moves (e.g., as the target caller's face position changes), so that the audio playback direction always follows the target part of the target caller, realizing real-time directional audio playback and improving the confidentiality and security of access control management.

[0126] In some embodiments, when at least one person appears in the surveillance video and is a single person, that single person can be identified as the target caller. It is understood that if only one person appears in the surveillance video, that person is most likely the target caller corresponding to the access control call request. Based on this, the response information of the access control call request can be accurately and directed to the target caller, preventing unauthorized personnel from obtaining the full content of the response information, thus improving the confidentiality and security of access control management.

[0127] Considering that there may be one or more people in the surveillance video, but the target caller is usually only one person, in order to avoid interference from irrelevant personnel (i.e., people other than the target caller) to the access control call system, the target caller can be further identified from the surveillance video.

[0128] In some embodiments, the method further includes: identifying the person exhibiting calling behavior in the surveillance video as the target caller when such behavior is detected from the surveillance video. Based on this, the response information for the access control call request can be accurately and directed to the target caller.

[0129] In some embodiments, the access control device executes the access control call control method provided in this application by default; or, in response to receiving a user's instruction to enable directional audio playback, it executes the access control call control method provided in this application.

[0130] As a concrete example, referring to steps one through six, the following is an exemplary flow of an access control call method:

[0131] Step 1: In response to receiving an access control call request, perform face detection on the image frames in the surveillance video.

[0132] Step 2: If the number of faces detected in the surveillance video is one, then that person is identified as the target caller; or, if the number of faces detected is greater than one, then target behavior detection is performed on multiple people displayed in the surveillance video.

[0133] Step 3: If a person with calling behavior is detected from the surveillance video, the person with calling behavior is identified as the target caller; or, if no person with calling behavior is detected from the surveillance video, it is determined whether there is at least one first person in the surveillance video.

[0134] Step 4: If there is at least one first person, the first person who is closest to the access control device among the at least one first person shall be identified as the target caller; or, if there is no first person but there is at least one second person, the second person who is closest to the access control device among the at least one second person shall be identified as the target caller.

[0135] Step 5: Determine the location of the target caller based on the surveillance video, and then, according to the location of the target caller, play the response information of the access control call request to the target caller in a targeted manner.

[0136] Step 6: Detect whether the target caller's face location has changed. If it has changed, refer to the above steps to re-determine the target caller's location, and based on the re-determined target caller's location, play the access control call request response information to the target caller in a targeted manner.

[0137] It should be understood that the specific embodiments described above are only one of the many implementation methods provided in this application, and do not constitute a specific limitation on this application.

[0138] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0139] like Figure 8 As shown, this application provides an access control call control device for performing... Figure 3The access control call control method shown is illustrated. The access control call control device 300 includes: a personnel identification module 301, a personnel positioning module 302, and an information playback module 303.

[0140] In some embodiments, the personnel determination module 301 is configured to, in response to receiving an access control call request, detect the calling behavior of at least one person appearing in the surveillance video, wherein the calling behavior is used to characterize the operation that triggers the access control call request; if no person with calling behavior is detected from the surveillance video, obtain the number of eyes of each person in the surveillance video and the distance of each person from the access control device; if at least one first person exists, determine the first person with the smallest distance from the access control device among the at least one first person as the target calling person, wherein the first person is the person with two eyes in the surveillance video; if there is no first person but there is at least one second person, determine the second person with the smallest distance from the access control device among the at least one second person as the target calling person, wherein the second person is the person with one eye in the surveillance video.

[0141] In some embodiments, the personnel positioning module 302 is used to determine the location of the target caller based on surveillance video.

[0142] In some embodiments, the information playback module 303 is configured to play response information of the access control call request to the target caller in a targeted manner based on the location of the target caller.

[0143] In some embodiments, the aforementioned location is world coordinates; the aforementioned personnel positioning module 302 is specifically used to determine the pixel coordinates of the target caller based on the surveillance video; and to perform coordinate transformation on the pixel coordinates of the target caller to obtain the world coordinates of the target caller.

[0144] In some embodiments, the personnel positioning module 302 is specifically used to extract a local image related to the target caller from the current video frame image of the surveillance video; to detect the target part of the local image to obtain the location of the target part of the target caller; the target part includes: ear or head.

[0145] In some embodiments, the personnel positioning module 302 is further configured to record the facial location of the target caller based on surveillance video.

[0146] In some embodiments, the information playback module 303 is further configured to adjust the playback direction of the response information according to the newly determined location of the target part of the target caller, so that the playback direction is aligned with the target part of the target caller.

[0147] In some embodiments, the personnel determination module 301 is further configured to determine the single person as the target caller when at least one person appearing in the surveillance video is a single person; or, when a person with calling behavior is detected from the surveillance video, determine the person with calling behavior in the surveillance video as the target caller.

[0148] In some embodiments, the aforementioned calling behavior includes one or more of the following: making a specified gesture, issuing a calling command, touching or pressing the calling control of the access control device, or standing in a preset area associated with the access control device.

[0149] In some embodiments, the information playback module 303 is specifically used to determine the distance of the target caller relative to the access control device based on the location of the target caller; determine the target volume based on the distance between the target caller and the access control device, and the correspondence between distance and volume, wherein the target volume is the volume corresponding to the distance between the target caller and the access control device; and play the response information of the access control call request to the target caller in a directional manner using the target volume based on the location of the target caller.

[0150] It should be noted that, Figure 8 The module division shown is illustrative and represents only one logical functional division; in actual implementation, other division methods are possible. For example, two or more functions can be integrated into a single processing module. These integrated modules can be implemented either in hardware or as software functional modules.

[0151] In implementing the functions of the integrated modules described above using hardware, this application also provides an access control device 400 as described in the above embodiments. For example... Figure 9 As shown, the access control device 400 includes: a processor 402 and a bus 404. Optionally, the access control device may also include a memory 401; optionally, the access control device may also include a communication interface 403.

[0152] Processor 402 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 402 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 402 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0153] Communication interface 403 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0154] The memory 401 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0155] As one possible implementation, the memory 401 can exist independently of the processor 402. The memory 401 can be connected to the processor 402 via a bus 404 and is used to store instructions or program code. When the processor 402 calls and executes the instructions or program code stored in the memory 401, it can implement the access control call method provided in this embodiment.

[0156] In another possible implementation, the memory 401 can also be integrated with the processor 402.

[0157] Bus 404 can be an extended industry standard architecture (EISA) bus, etc. Bus 404 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0158] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the access control device can be divided into different functional modules to complete all or part of the functions described above.

[0159] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. The program can be stored in the aforementioned computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be the memory of any of the foregoing embodiments. The aforementioned computer-readable storage medium can also be the external storage device based on the access control device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the access control device. Further, the aforementioned computer-readable storage medium can include both internal storage units and external storage devices of the access control device. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the access control device. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0160] This application also provides a computer program product comprising a computer program that, when run on a computer (e.g., an access control device or an access control call control device), causes the computer to execute any of the access control call control methods provided in the above embodiments.

[0161] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0162] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0163] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for access control and call management, characterized in that, The method includes: In response to receiving an access control call request, at least one person appearing in the surveillance video is detected to perform a call behavior, wherein the call behavior is used to characterize the operation that triggered the access control call request; If no person making a call is detected in the surveillance video, obtain the number of eyes of each person in the surveillance video and the distance of each person from the access control device; In the presence of at least one first person, the first person who is closest to the access control device among the at least one first person is identified as the target caller, and the first person is the person in the surveillance video who has two eyes; In the case where there is no first person but there is at least one second person, the second person who is the closest to the access control device among the at least one second person is determined as the target caller. The second person is the person in the surveillance video who has one eye. Based on the surveillance video, the location of the target caller is determined, and the response information of the access control call request is played to the target caller in a targeted manner according to the location of the target caller.

2. The method according to claim 1, characterized in that, The location is in world coordinates; determining the location of the target caller based on the surveillance video includes: Based on the surveillance video, determine the pixel coordinates of the target caller; The pixel coordinates of the target caller are transformed to obtain the world coordinates of the target caller.

3. The method according to claim 1, characterized in that, Determining the location of the target caller based on the surveillance video includes: Extract a local image related to the target caller from the current video frame of the surveillance video; The target part is detected in the local image to obtain the location of the target part of the target caller; the target part includes: ear or head.

4. The method according to claim 3, characterized in that, The method further includes: Based on the surveillance video, the facial location of the target caller is recorded; After the target caller's face position changes, the position of the target part of the target caller is re-determined; Based on the redefined location of the target part of the target caller, the playback direction of the response information is adjusted so that the playback direction is aligned with the target part of the target caller.

5. The method according to claim 1, characterized in that, The method further includes: When at least one person appears in the surveillance video and is a single person, that single person is identified as the target caller; or, If a person with calling behavior is detected from the surveillance video, the person with calling behavior in the surveillance video is identified as the target caller.

6. The method according to claim 1, characterized in that, The calling behavior includes one or more of the following: Make a specified gesture, issue a call command, touch or press the call control of the access control device, or stand in a preset area associated with the access control device.

7. The method according to any one of claims 1 to 6, characterized in that, The step of playing the access control call request response information to the target caller based on the target caller's location includes: Based on the location of the target caller, determine the distance of the target caller relative to the access control device; Based on the distance between the target caller and the access control device, and the correspondence between distance and volume, the target volume is determined, wherein the target volume is the volume corresponding to the distance between the target caller and the access control device; Based on the location of the target caller, the response information of the access control call request is played to the target caller in a targeted manner using the target volume.

8. An access control call control device, characterized in that, The device includes: The personnel identification module is used to detect the calling behavior of at least one person appearing in the surveillance video in response to receiving an access control call request. The calling behavior is used to characterize the operation that triggers the access control call request. If no person with calling behavior is detected from the surveillance video, the module obtains the number of eyes of each person in the surveillance video and the distance of each person from the access control device. If at least one first person exists, the first person with the smallest distance from the access control device among the at least one first person is identified as the target calling person. The first person is the person in the surveillance video with two eyes. If there is no first person but at least one second person exists, the second person with the smallest distance from the access control device among the at least one second person is identified as the target calling person. The second person is the person in the surveillance video with one eye. The personnel positioning module is used to determine the location of the target caller based on the surveillance video; The information playback module is used to play the response information of the access control call request to the target caller in a targeted manner according to the location of the target caller.

9. An access control device, characterized in that, include: A memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code including computer instructions; When the processor executes the computer instructions, it causes the access control device to perform the access control call control method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer instructions; When the computer instructions are executed on the computer, the computer causes the computer to perform the access control call control method as described in any one of claims 1 to 6.

Images