Audio transmission, image acquisition device permission management method, device and electronic device

Abstract

The present application discloses a method, apparatus and electronic device for audio transmission and image acquisition device permission management, which relates to the field of security technology and is used to reduce system power consumption, improve recognition efficiency, avoid causing noise pollution to others, and avoid privacy leakage. The method includes: obtaining a target image collected by an image acquisition device; wherein the target image includes a plurality of target persons; respectively performing biometric recognition on the plurality of target persons according to the target image to obtain the information to be played of the target persons; wherein the information to be played includes the biometric recognition result of the target person, and / or other information of the target person obtained based on the biometric recognition result of the target person; determining the positions of the target persons according to the target image; controlling the audio playback device to send the information to be played to the positions of the target persons in different propagation directions respectively.

Description

Technical Field

[0001] This application relates to the field of security technologies, and in particular to methods, devices, and electronic devices for audio transmission, image acquisition device permission management. Background Art

[0002] Currently, electronic devices with face recognition are widely used in various complex scenarios, such as public places like schools, companies, shopping malls, and stations. When the number of people is large during peak hours in these public places, to improve the efficiency of face recognition, electronic devices need to be able to have the ability to recognize multiple faces. Most traditional electronic devices are used to process single faces, and some devices for processing multiple faces have high power consumption due to frequent recognition of multiple people in the picture. In addition, when an electronic device broadcasts voice messages for the information obtained through face recognition (such as health information), since there are multiple people in the application scenario, it is easy to cause noise pollution to others and result in the leakage of privacy information. Summary of the Invention

[0003] This application provides an audio transmission method, an electronic device, and a storage medium, which are used to reduce system power consumption, improve recognition efficiency, avoid causing noise pollution to others, and avoid privacy leakage.

[0004] To achieve the above technical objectives, this application adopts the following technical solutions:

[0005] In a first aspect, an embodiment of this application provides an audio transmission method. This method acquires a target image collected by an image acquisition device; where the target image includes multiple target persons; based on the target image, biometric recognition is performed on the multiple target persons respectively to obtain the information to be played for the target persons; where the information to be played includes the biometric recognition result of the target person, and / or other information of the target person obtained based on the biometric recognition result of the target person; based on the target image, the positions of the target persons are determined; and an audio playback device is controlled to send the information to be played to the positions of the target persons in different propagation directions respectively.

[0006] It can be understood that biometric recognition is performed on the target persons included in the target image to obtain the information to be played for the target persons, and the information to be played is sent to the target persons in the direction where the positions of the target persons are located, avoiding causing noise pollution to others and at the same time avoiding privacy leakage.

[0007] In one implementation, the above target image includes multiple candidate persons, and the biometric recognition is face recognition. The method includes: based on the target image, intention recognition is performed on the multiple candidate persons respectively to obtain intention recognition results of the multiple candidate persons; the intention recognition result is used to represent whether the candidate person has the intention of biometric recognition; based on the intention recognition results of the multiple candidate persons, the candidate persons with the intention of biometric recognition are determined as target persons.

[0008] It is understandable that when there are multiple persons in an image, it is necessary to judge the intentions of multiple persons, perform face recognition on the persons with recognition intentions, reduce the system power consumption, and improve the recognition efficiency.

[0009] In another implementation manner, the multiple candidate persons include a first candidate person. The intention recognition result of the first candidate person includes: the number of eyeballs of the first candidate person included in the target image; based on the intention recognition results of the multiple candidate persons, determining the candidate person with a biometric recognition intention as the target person includes: if the number of eyeballs of the first candidate person included in the target image is 2, then determining the first candidate person as the target person.

[0010] It is understandable that, for the number of eyeballs of any one first candidate person among the multiple candidate persons, to judge whether the first candidate person has a recognition intention, this method can quickly obtain the intention recognition result, which is simple and efficient.

[0011] In another implementation manner, the target image includes multiple persons; the method further includes: when the number of the multiple persons is greater than a first preset number, determining multiple candidate persons from the multiple persons; wherein, the number of the multiple candidate persons is equal to the first preset number, and the multiple candidate persons are the persons whose distances from the image acquisition device meet a first preset condition; when the number of the multiple persons is less than or equal to the first preset number, determining the multiple persons as the multiple candidate persons.

[0012] It is understandable that due to the hardware limitations of the electronic device, the number of persons that can be processed is limited. Therefore, based on the hardware performance of the electronic device, a third preset number is set, and the multiple persons in the target image are processed in batches. The persons selected for each processing are candidate persons. This method selects candidate persons based on the distances between the multiple candidate persons and the image acquisition device. The persons closer to the image acquisition device indicate a higher recognition intention, so they are processed preferentially. This method of processing candidate persons in batches can avoid the limitation of the number of persons processed due to hardware limitations.

[0013] In another implementation, determining the candidate person with a biometric intention as the target person based on the intention recognition results of multiple candidate persons includes: when the number of persons with a biometric intention among the multiple candidate persons is equal to the second preset number, determining each candidate person among the multiple candidate persons as the target person; wherein, the second preset number is less than or equal to the first preset number; when the number of persons with a biometric intention among the multiple candidate persons is less than the second preset number, based on the difference between the second preset number and the number of persons with a biometric intention, selecting the difference number of persons from the non-candidate persons among the multiple persons as supplementary candidate persons, and the supplementary candidate persons are the persons whose distance from the image acquisition device meets the second preset condition; respectively performing intention recognition on at least one supplementary candidate person according to the target image to obtain the intention recognition results of the at least one supplementary candidate person; and determining the persons with a biometric intention among the multiple candidate persons and the supplementary candidate persons as the target persons.

[0014] It can be understood that when the number of persons with a biometric intention among the multiple candidate persons does not meet the second preset number, the difference number of persons can be selected from the non-candidate persons for intention recognition, so that the number of persons with a biometric intention is equal to the second preset number. This method enables the maximum number of persons that can be processed in each round, improving the biometric efficiency.

[0015] In another implementation, the above method further includes: obtaining the information to be displayed of the target person based on the biometric result, performing privacy protection on the information to be displayed, and controlling the screen to output the information to be displayed after privacy protection.

[0016] It can be understood that when the target person information needs to be output through the screen, privacy protection can be performed on it to avoid leakage of privacy information.

[0017] In a second aspect, an image acquisition device permission management method is provided in an embodiment of the present application. The method obtains a target image acquired by the image acquisition device; wherein, the target image includes multiple target persons; respectively performing face permission authentication on the multiple target persons according to the target image to obtain the information to be played of the target persons; wherein, the information to be played includes the result of the face permission authentication of the target persons, and / or other information of the target persons obtained based on the face permission authentication result of the target persons; determining the binaural positions of the target persons according to the target image; and controlling the audio playback device to send the information to be played to the binaural positions of the target persons in different propagation directions respectively.

[0018] It can be understood that based on the face permission authentication result of the target person, the method obtains the information to be played for the target person with face permission, and plays the information to be played at the positions where the two ears of the target person are located. This method can accurately send the information to be played to the positions where the two ears of the target person are located, effectively avoiding noise pollution to others and avoiding privacy leakage at the same time.

[0019] In one implementation, the target image includes multiple candidate persons, and the method further includes: respectively performing intention recognition on the multiple candidate persons according to the target image to obtain intention recognition results of the multiple candidate persons; wherein, the intention recognition result includes the number of eyeballs of the candidate person; when the number of eyeballs of the candidate person is 2, the candidate person has the intention of face permission authentication; based on the intention recognition results of the multiple candidate persons, the candidate person with the intention of face permission authentication is determined as the target person.

[0020] It can be understood that when the image includes multiple candidate persons, it is necessary to judge the intentions of the multiple candidate persons, and judge the face permission authentication intention of the candidate person based on the number of eyeballs of the candidate person. For the person with the authentication intention, face permission authentication is performed. This method can quickly screen the authentication intentions of the candidate persons, reduce the system power consumption, and improve the authentication efficiency.

[0021] In another implementation, the target image includes multiple persons; the method further includes: when the number of the multiple persons is greater than a third preset number, determining multiple candidate persons from the multiple persons; wherein, the number of the multiple candidate persons is equal to the third preset number, and the multiple candidate persons are the persons whose distances from the image acquisition device meet the third preset condition; when the number of the multiple persons is less than or equal to the third preset number, the multiple persons are determined as the multiple candidate persons.

[0022] It can be understood that due to the hardware limitation of the electronic device, the number of persons that can be processed is limited. Therefore, based on the hardware performance of the electronic device, a third preset number is set to process the multiple persons in the target image in batches. Each time, the selected persons for processing are the candidate persons. This method selects the candidate persons based on the distances between the multiple candidate persons and the image acquisition device. The person closer to the image acquisition device indicates a higher recognition intention, so it is processed preferentially. This method of processing the candidate persons in batches can avoid the limitation of the number of processed persons caused by hardware limitations.

[0023] In a third aspect, the present application provides an audio transmission device. The audio transmission device includes each module applying the method of the first aspect or any possible design manner in the first aspect.

[0024] Fourth aspect, the present application provides an image acquisition device permission management apparatus, which includes each module of the method applied to the second aspect or any possible design manner in the second aspect.

[0025] Fifth aspect, the present application provides an electronic device, including a memory and a processor. The memory and the processor are coupled; the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device is caused to execute the audio transmission method as described in the first aspect and any possible design manner thereof; or, when the processor executes the computer instructions, the electronic device is caused to execute the image acquisition device permission management method as described in the second aspect and any possible design manner thereof.

[0026] Sixth aspect, the present application provides a computer-readable storage medium, which includes computer instructions. Wherein, when the computer instructions run on an electronic device, the electronic device is caused to execute the audio transmission method as described in the first aspect and any possible design manner thereof; or, when the computer instructions run on an electronic device, the electronic device is caused to execute the image acquisition device permission management method as described in the second aspect and any possible design manner thereof.

[0027] Seventh aspect, the present application provides a computer program product, which includes computer instructions. Wherein, when the computer instructions run on an electronic device, the electronic device is caused to execute the audio transmission method as described in the first aspect and any possible design manner thereof; or, when the computer instructions run on an electronic device, the electronic device is caused to execute the image acquisition device permission management method as described in the second aspect and any possible design manner thereof.

[0028] For the specific descriptions of the third aspect to the seventh aspect and their various implementation manners in the present application, reference may be made to the detailed descriptions in the first aspect or the second aspect and their various implementation manners; and, for the beneficial effects of the third aspect to the seventh aspect and their various implementation manners, reference may be made to the beneficial effect analysis in the first aspect or the second aspect and their various implementation manners, which will not be elaborated herein.

[0029] These aspects or other aspects of the present application will be more clearly understood in the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the implementation environment involved in an audio transmission method provided by an embodiment of the present application;

[0031] Figure 2 It is a flowchart of an audio transmission method provided by an embodiment of the present application;

[0032] Figure 3 A face information diagram of a candidate person in a target image provided by an embodiment of the present application;

[0033] Figure 4 A flowchart for determining the recognition intention of a candidate person provided by an embodiment of the present application;

[0034] Figure 5 A flowchart for performing face recognition on a target person provided by an embodiment of the present application;

[0035] Figure 6 A schematic diagram of a face image of a target person collected by an image acquisition device provided by an embodiment of the present application;

[0036] Figure 7 A position relationship diagram between an image acquisition device and a target person provided by an embodiment of the present application;

[0037] Figure 8 A schematic diagram of an audio playback device sending information to be played of a target person provided by an embodiment of the present application;

[0038] Figure 9 A flowchart of a method for managing the permissions of an image acquisition device provided by an embodiment of the present application;

[0039] Figure 10 A schematic structural diagram of an audio transmission device provided by an embodiment of the present application;

[0040] Figure 11 A schematic structural diagram of a device for managing the permissions of an image acquisition device provided by an embodiment of the present application;

[0041] Figure 12 A schematic structural diagram of another electronic device provided by an embodiment of the present application. Detailed implementation manners

[0042] Hereinafter, terms such as "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", or "third" etc. may explicitly or implicitly include one or more of such features.

[0043] Currently, electronic devices with face recognition are widely used in various complex scenarios. When the application scenario has a large number of people during peak hours, to improve the face recognition efficiency, the electronic device needs to be able to have the ability to recognize and authenticate multiple people. In the prior art, electronic devices with the function of recognizing and authenticating multiple people mainly have the following problems:

[0044] 1. When performing face recognition on multiple people, due to frequently performing face recognition on all people in the picture, the device power consumption is relatively high and it is easy to cause confusion in the recognition logic.

[0045] 2. When the electronic device performs voice broadcast on the information obtained through face recognition, due to the presence of multiple people in the application scenario, it is easy to cause noise pollution to others and result in the leakage of privacy information.

[0046] Based on this, the embodiment of the present application provides an audio transmission method. This method performs intention recognition on multiple candidate persons in the image, performs biometric recognition on the candidate persons with biometric recognition intention in the intention recognition result, obtains the information to be played of the target person through the biometric recognition result, and then sends directional audio information to the target person through the position of the target person in the image. It can be understood that biometric recognition is performed on the target person included in the target image to obtain the information to be played of the target person, and the information to be played is sent to the target person in the direction of the position of the target person, so as to avoid noise pollution to others and avoid privacy leakage at the same time.

[0047] The following will describe in detail the implementation manner of the embodiment of the present application in conjunction with the drawings.

[0048] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the implementation environment involved in an audio transmission method provided by an embodiment of the present application. As Figure 1 shown, this implementation environment may include: an image acquisition device 110, an electronic device 120, a screen 130 (optional), and an audio playback device 140.

[0049] The image acquisition device 110 is used to acquire face images. For example, the image acquisition device 110 may be a camera. Specifically, the image acquisition device 110 is used to acquire face images of at least one person who pre-enters the field of view of the image acquisition device 110.

[0050] The electronic device 120 is used to receive the face images of at least one person acquired by the image acquisition device, perform face recognition on them, and can also be used to output the information obtained based on the face recognition result through the screen 130, and can also be used to output the information obtained based on the face recognition result through the audio playback device 140.

[0051] The screen 130 is used to output the face recognition result and / or the information obtained based on the face recognition result under the control of the electronic device 120.

[0052] The audio playback device 140 is used to output information obtained based on the face recognition result under the control of the electronic device 120. The audio playback device 140 can be a super-directional speaker, which is used to generate highly directional sound, that is, to emit sound waves with concentrated energy and only propagate in a specified direction, or it can also send non-directional sound.

[0053] Exemplarily, the electronic device 120 can be a terminal, such as a mobile phone, a tablet computer, a desktop computer, a laptop computer, a notebook computer, a netbook, etc., or it can also be a server. The specific form of the electronic device in the embodiments of the present application is not particularly limited.

[0054] The image acquisition device 110, the electronic device 120, the screen 130, and the audio playback device 140 can be integrally provided in pairs or all integrally provided, or they can be provided independently. The embodiments of the present application do not limit how the devices included in the implementation environment are set. When they are provided independently, the distance between the installation positions of the image acquisition device 110, the screen 130, and the audio playback device 140 is less than a threshold, and the installation position of the electronic device is not limited.

[0055] The embodiments of the present application also provide a method for managing the permissions of an image acquisition device. The implementation environment involved is referred to Figure 1 the implementation environment shown.

[0056] In an application scenario, the above-mentioned electronic device 120 can be applied to a subway health detection channel. Devices for automatically detecting the health status of passengers are set at each entrance channel of the subway. When a passenger wants to pass through the subway channel, the image acquisition device 110 at the channel entrance will collect the face images (biological information) of multiple passengers. The electronic device 120 will perform intention recognition on the passengers in the collected images, perform face recognition (biometric recognition) on the passengers with the intention of passing through the channel, obtain the health status of the person from the server storing the health information based on the face recognition information, and transmit the health status to the corresponding person's ear in the form of voice through the audio playback device 140. At the same time, the screen 130 displays the person's health status (such as healthy) and the name after privacy processing (such as: Li**, healthy). If the health status of the person does not meet the requirements, the electronic device can issue a prompt to prompt the staff to intercept the passenger.

[0057] In another application scenario, the above-mentioned electronic device 120 can be applied to company attendance check-in. When going to work during the morning rush hour, there are many employees who need to check in for attendance. At this time, multiple people can check in for attendance simultaneously. The image acquisition device 110 acquires the target images of multiple employees. After receiving the target images, the electronic device 120 authenticates and identifies (biometric identification) the face information of the employees therein. If the authentication and identification are successful, at this time, the electronic device 120 controls the audio playback device 140 to send directional audio (such as Li ** has checked in) to the ears of the employee by detecting the positions of the ears of the employee in the target image, and at the same time, the screen 130 displays the information that the employee has checked in.

[0058] The audio transmission method or the image acquisition device permission management method provided by the embodiments of the present application can be applied to the electronic device 120. The execution subject of the audio transmission method provided by the embodiments of the present application can also be an audio transmission device; the execution subject of the image acquisition device permission management method provided by the embodiments of the present application can also be an image acquisition device permission management device. The audio transmission device or the image acquisition device permission management device can be an electronic device, or an application program (APP) installed on the electronic device that provides the audio transmission device or the image acquisition device permission management function, or the central processing unit (CPU) in the electronic device, or a control module in the electronic device for executing the audio transmission device or the image acquisition device permission management method. In the following, the method provided by the embodiments of the present application is taken as an example of an electronic device for description.

[0059] The following describes the audio transmission method provided by the embodiments of the present application:

[0060] Please refer to Figure 2 , which is a flowchart of an audio transmission method provided by the embodiments of the present application. This method can be applied to the above-mentioned electronic device. As Figure 2 shown, this method can include S101 - S116.

[0061] S101: The electronic device acquires the target images acquired by the image acquisition device. Among them, the target images include multiple persons.

[0062] S102: The electronic device determines whether the number of multiple persons is greater than a first preset number.

[0063] If so (that is, the number of multiple persons is greater than the first preset number), execute S103;

[0064] If not (that is, the number of multiple persons is less than or equal to the first preset number), execute S104.

[0065] Due to the hardware limitations of the electronic device, the number of personnel that can be processed in one round is limited. Therefore, based on the hardware performance of the electronic device, a first preset number is set.

[0066] The first preset number is the number of personnel in the target image that the electronic device can perform intention recognition on at most each time.

[0067] S103: The electronic device determines multiple candidate personnel from multiple personnel; among them, the number of multiple candidate personnel is equal to the first preset number, and the multiple candidate personnel are the personnel whose distance from the image acquisition device meets the first preset condition.

[0068] The first preset condition includes: the personnel whose rankings reach the top first preset number when sorted in ascending order of the distance from the image acquisition device.

[0069] In an example, there are 10 personnel in the target image collected by the image acquisition device, the number of the first preset number of personnel is 5, and the distances between the 10 personnel and the image acquisition device are 0.1 meter, 0.15 meter, 0.2 meter, 0.22 meter, 0.25 meter, 0.3 meter, 0.4 meter, 0.5 meter, 0.55 meter, and 0.6 meter respectively when sorted in ascending order. Then the electronic device preferentially selects the top 5 people closest to the image acquisition device from the 10 people for intention recognition.

[0070] The remaining personnel among the multiple personnel are non-candidate personnel. Select the next round of multiple candidate personnel from the personnel among the multiple non-candidate personnel who meet the first preset condition. When the number of non-candidate personnel is less than the first preset number, then all the remaining non-candidate personnel are used as the next round of multiple candidate personnel.

[0071] After executing S103, execute S105.

[0072] S104: The electronic device determines multiple personnel as multiple candidate personnel.

[0073] In an example, the number of multiple personnel is 4, and the number of the first preset number of personnel is 5, then the 4 people are determined as candidate personnel.

[0074] S105: The electronic device respectively performs intention recognition on multiple candidate personnel according to the target image, and obtains intention recognition results of the multiple candidate personnel. Among them, the intention recognition result is used to represent whether the candidate personnel has the intention of biometric recognition.

[0075] Intention recognition refers to judging the biometric recognition intention of the candidate personnel in the target image.

[0076] Biometric recognition can include: face recognition or iris recognition.

[0077] In an example, as Figure 3 shownFigure 3 It is a face information diagram of 5 candidate persons in the obtained target image. Based on the face information of these 5 candidate persons, intention recognition is performed on these 5 candidate persons.

[0078] In a possible implementation, multiple candidate persons include a first candidate person; the intention recognition result of the first candidate person includes: the number of eyeballs of the first candidate person included in the target image.

[0079] The first candidate person is any one of the multiple candidate persons. The intention recognition result of the first candidate person includes: the number of eyeballs of the first candidate person included in the target image, and the number of eyeballs can be 2 / 1 / 0.

[0080] In an example, as Figure 4 shown, Figure 4 It is a flowchart for determining the biometric (face recognition or iris recognition) intention of the candidate person based on the number of eyeballs of the first candidate person. When the biometric intention of the first candidate person is relatively high, generally facing the image acquisition device directly with a frontal face, at this time, the image acquisition device can capture two eyeballs of each candidate person; when the biometric intention of each candidate person is relatively low (such as just passing by the image acquisition device), at this time, the number of eyeballs of the candidate person captured by the image acquisition device is 0 or 1. When the number of eyeballs is 2, it is determined that there is a biometric intention, and when the number of eyeballs is 0 or 1, it is determined that there is no biometric intention.

[0081] In another possible implementation, the intention recognition method may further include: judging the movement trend of the first candidate person in the target image and at least one second image, where the acquisition time of at least one second image has a time interval within a time threshold from the acquisition time of the target image. When the movement trend tends towards the image acquisition device, it indicates that the first candidate person has a biometric intention, and when the movement trend is away from the image acquisition device, it indicates that the first candidate person has no biometric intention. This method can be used to judge the recognition intentions of multiple candidate persons in the target image.

[0082] In S103, based on the distances between multiple persons and the image acquisition device, the first preset number of persons with the closest distances are selected and determined as multiple candidate persons. Since the closer to the image acquisition device, the higher the intention of performing biometric recognition, multiple candidate persons are selected by distance.

[0083] S106: The electronic device judges the number of persons among multiple candidate persons who have the intention of biometric recognition.

[0084] When the number of persons among multiple candidate persons who have the intention of biometric recognition is equal to the second preset number, execute S107.

[0085] When the number of persons with the intention of biometric recognition among multiple candidate persons is less than a second preset number, S108 is executed.

[0086] The multiple candidate persons include a first candidate person; the first candidate person is any one of the multiple candidate persons.

[0087] The intention recognition result of the first candidate person indicating the intention of biometric recognition includes: the number of eyeballs of the first candidate person included in the target image is 2.

[0088] S107: The electronic device determines each of the multiple candidate persons as a target person.

[0089] The second preset number is less than or equal to the first preset number. The second preset number is the number of persons for face recognition. Generally, since the face recognition information is stored in the message queue of the electronic device and processed sequentially, the number of persons that the electronic device can process for face recognition is not limited. At this time, the second preset number is set based on the first preset number, that is, the second preset number can be set to be the same as the first preset number.

[0090] In an example, when the number of multiple candidate persons is 5, when the number of persons with the intention of face recognition among the multiple candidate persons is 5 and the second preset number is also 5, the 5 persons with the intention of face recognition are determined as target persons.

[0091] After the determination of the target persons in this round is completed, the selected target persons enter the processing in S107. At the same time, the electronic device selects persons who meet the first preset condition from the non-candidate persons among the multiple persons as candidate persons for the next round, and continues the intention recognition for the next round until the intention recognition and judgment of all the multiple persons in the target image are completed.

[0092] After S107 ends, S113 is executed.

[0093] S108: The electronic device determines whether there are remaining non-candidate persons. The non-candidate persons are the remaining persons among the multiple persons after the candidate persons are selected.

[0094] If there are, S109 is executed; if not, S112 is executed.

[0095] S109: The electronic device selects a difference number of persons from the non-candidate persons among the multiple persons as supplementary candidate persons based on the difference between the second preset number and the number of persons with the intention of biometric recognition. Among them, the supplementary candidate persons are the persons whose distance from the image acquisition device meets the second preset condition.

[0096] The second preset condition is the personnel whose distances from the image acquisition device rank among the top difference quantity in ascending order. If the number of remaining non-candidate personnel is greater than or equal to the difference quantity of personnel, then select the personnel with the difference quantity. If the number of remaining non-candidate personnel is less than the difference quantity of personnel, then all the remaining non-candidate personnel are used as supplementary candidate personnel.

[0097] S110: The electronic device respectively performs intention recognition on at least one supplementary candidate personnel according to the target image to obtain the intention recognition results of at least one supplementary candidate personnel.

[0098] S111: When the number of personnel with biometric intention in the intention recognition results among multiple candidate personnel and supplementary candidate personnel is equal to the second preset quantity, the electronic device determines the candidate personnel with biometric intention in the intention recognition results among multiple candidate personnel and supplementary candidate personnel as the target personnel; otherwise, repeat S109 - S111 until the number of candidate personnel with biometric intention in the intention recognition results is equal to the second preset quantity or there are no remaining non-candidate personnel among multiple personnel.

[0099] In an example, assume that the number of multiple personnel in the target image is 8, the first preset quantity is 5, and the second preset quantity is 5. At this time, the number of candidate personnel is 5. Perform intention recognition on the 5 candidate personnel. If the number of personnel with biometric intention in the obtained intention recognition results is 5, all these 5 people are determined as the target personnel, and the remaining 3 non-candidate personnel are subjected to the next round of intention recognition; if the number of personnel with biometric intention in the obtained intention recognition results is 3, then select 2 people from the remaining 3 non-candidate personnel as supplementary candidate personnel, perform intention recognition on these 2 people. When the intention recognition results of these 2 people are with biometric intention, then jointly determine these 2 people and the 3 people with biometric intention in the candidate personnel's intention recognition results as the target personnel, and the remaining 1 non-candidate personnel enters the next round of intention recognition; if the number of personnel with biometric intention in the obtained intention recognition results is 1, then use all the remaining 3 non-candidate personnel as supplementary candidate personnel for intention recognition. When the intention recognition results of these 3 people are with biometric intention, then jointly determine these 3 people and the 1 person with biometric intention in the candidate personnel's intention recognition results as the target personnel.

[0100] After S111 ends, execute S113.

[0101] S112: The electronic device determines the personnel with biometric intention as the target personnel based on the intention recognition results of multiple candidate personnel.

[0102] S113: The electronic device respectively performs biometric recognition on multiple target personnel according to the target image to obtain the information to be played of the target personnel.

[0103] Among them, the information to be played includes the biometric recognition result of the target person, and / or other information of the target person obtained based on the biometric recognition result of the target person.

[0104] In one example, in a health detection scenario, when biometric recognition is successful, relevant face health information is obtained based on the biometric recognition result. At this time, the information to be played may include: recognition successful, health status. The health status is used to characterize the degree of health, for example: healthy, sub-healthy or unhealthy. In another example, in a health detection scenario, when biometric recognition fails, the information to be played may include: recognition failed.

[0105] In one example, biometric recognition includes face recognition, such as Figure 5 shown Figure 5 is the process of the electronic device performing face recognition on the target person. The electronic device performs face recognition on the target person according to the distance between the target person and the image acquisition device and processes them in sequence, giving priority to processing the face of the target person closer to the image acquisition device.

[0106] In one example, biometric recognition includes face recognition. The electronic device performs face recognition on the target person, compares the face information of the target person with the face information in the medical database, and obtains the health information of the target person from the medical database.

[0107] S114: The electronic device determines the position of the target person according to the target image.

[0108] Optionally, according to the target image, determine the positions of the two ears of the target person.

[0109] In one example, the positions of the two ears of the target person can be determined based on the position of the center of the target person's eyebrows. As Figure 6 shown Figure 6 is a schematic diagram of a face image of a target person captured by the image acquisition device. The two ears of the target person are captured in the figure. A three-dimensional coordinate system is established with the image acquisition device as the coordinate origin (as shown in the figure). The electronic device locates the center of the eyebrows at the coordinate (x0, y0, z0) through an image recognition algorithm. The angle between the two ears and the image acquisition device is α. The distances between the image acquisition device and the center of the eyebrows and the two ears are basically the same, set as L = Lr = Ll; as Figure 7 shown Figure 7 is a diagram of the positional relationship between the image acquisition device and a target person. The height of the image acquisition device from the ground is h. Based on the existing technology, the three-dimensional coordinates of the left ear can be calculated as: (xl, yl, zl), and the three-dimensional coordinates of the right ear can be calculated as: (xr, yr, zr).

[0110] S115: The electronic device controls the audio playback device to send the information to be played to the position of the target person in different propagation directions respectively.

[0111] Optionally, based on the order of the distances from the multiple target persons to the image acquisition device from small to large, the information to be played is sent to the binaural positions of the multiple target persons respectively in sequence.

[0112] When sending the information to be played directionally, specifically: based on the binaural positions of the target persons, the modulated left-channel audio and right-channel audio information are sent to the left and right ears of the target persons in the space respectively through the directional audio transmission technology, and only the corresponding target persons can receive the information to be played.

[0113] By sending the information to be played through the directional sound wave, it is possible to avoid interfering with other persons. At the same time, since only the corresponding target persons can receive the sound wave, personal privacy can also be protected.

[0114] Such as Figure 8 shown, Figure 8 In the figure, when the number of target persons included in the target image is 5, it is an example diagram of the electronic device controlling the audio playback device to send the information to be played to the binaural positions of the target persons respectively.

[0115] S116: The electronic device obtains the information to be displayed of the target person based on the biometric result, performs privacy protection on the information to be displayed, and controls the screen to output the information to be displayed after privacy protection.

[0116] The information to be displayed is the information obtained based on the biometric result of the target person. The information to be displayed may contain the privacy information of the target person, and privacy protection needs to be performed on it. For example: when the name of the target person is included in the second information, the name can be processed with *, such as Li**.

[0117] Please refer to Figure 9 , which is a flowchart of a method for managing the permissions of an image acquisition device provided by an embodiment of the present application. This method can be applied to the above-mentioned electronic device. Such as Figure 9 shown, this method may include S201 - S209.

[0118] S201: The electronic device obtains the target image collected by the image acquisition device. Among them, the target image includes multiple persons.

[0119] S202: The electronic device determines whether the number of multiple persons is greater than a third preset number.

[0120] If so (that is, the number of multiple persons is greater than the third preset number), execute S203;

[0121] If not (i.e., the number of multiple persons is less than or equal to the third preset quantity), execute S204.

[0122] S203: The electronic device determines multiple candidate persons from the multiple persons.

[0123] Among them, the number of multiple candidate persons is equal to the third preset quantity, and the multiple candidate persons are the persons whose distances from the image acquisition device meet the third preset condition.

[0124] S204: The electronic device determines the multiple persons as multiple candidate persons.

[0125] S205: The electronic device respectively performs intention recognition on the multiple candidate persons according to the target image, and obtains the intention recognition results of the multiple candidate persons. Among them, the intention recognition result includes the number of candidate persons' eyeballs.

[0126] When the number of candidate persons' eyeballs is 2, the candidate person has the intention of face permission authentication.

[0127] S206: The electronic device determines the candidate persons with the intention of face permission authentication as target persons based on the intention recognition results of the multiple candidate persons.

[0128] S207: The electronic device respectively performs face permission authentication on the multiple target persons according to the target image to obtain the information to be played of the target persons.

[0129] Among them, the information to be played includes the result of the face permission authentication of the target person, and / or other information of the target person obtained based on the face permission authentication result of the target person.

[0130] S208: The electronic device determines the positions of the two ears of the target person according to the target image.

[0131] S209: The electronic device controls the audio playback device to send the information to be played to the positions of the two ears of the target person in different propagation directions respectively.

[0132] For the relevant descriptions in S201 - S209, refer to the relevant content of S101 - S116.

[0133] Based on this, an audio transmission method provided by an embodiment of the present application performs intention recognition on multiple candidate persons in an image, performs biometric recognition on the candidate persons with biometric recognition intention in the intention recognition results, obtains the to-be-played information of the target person through the biometric recognition results, and then sends directional audio information to the target person according to the position of the target person in the image. It can be understood that biometric recognition is performed on the target person included in the target image to obtain the to-be-played information of the target person, and the to-be-played information is sent to the target person in the direction of the position of the target person, avoiding noise pollution to others and at the same time avoiding privacy leakage.

[0134] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. To implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or 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 to exceed the scope of the present application.

[0135] An embodiment of the present application also provides an audio transmission device 200. As Figure 10 shown, it is a schematic structural diagram of an audio transmission device 200 provided by an embodiment of the present application.

[0136] Among them, the audio transmission device 200 includes: an acquisition module 210, configured to acquire a target image acquired by an image acquisition device; where the target image includes multiple target persons; a recognition module 220, configured to perform biometric recognition on the multiple target persons respectively according to the target image to obtain the to-be-played information of the target person; where the to-be-played information includes the biometric recognition result of the target person, and / or other information of the target person obtained based on the biometric recognition result of the target person; a determination module 230, configured to determine the position of the target person according to the target image; a control module 240, configured to control the audio playback device to send the to-be-played information to the position of the target person in different propagation directions respectively.

[0137] Optionally, the target image includes multiple candidate persons, the biometric recognition is face recognition, and the recognition module 220 is further configured to perform intention recognition on the multiple candidate persons respectively according to the target image to obtain the intention recognition results of the multiple candidate persons; the intention recognition results are used to represent whether the candidate persons have the intention of biometric recognition; the determination module 230 is further configured to determine the candidate persons with biometric recognition intention as the target persons based on the intention recognition results of the multiple candidate persons;

[0138] Optionally, multiple candidate persons include a first candidate person; the intention recognition result of the first candidate person includes: the number of eyeballs of the first candidate person included in the target image; the determination module 230 is specifically configured to, if the number of eyeballs of the first candidate person included in the target image is 2, determine the first candidate person as the target person;

[0139] Optionally, the target image includes multiple persons; the determination module 230 is further configured to: when the number of multiple persons is greater than a first preset number, determine multiple candidate persons from the multiple persons; wherein, the number of multiple candidate persons is equal to the first preset number, and the multiple candidate persons are persons whose distance from the image acquisition device satisfies a first preset condition; when the number of multiple persons is less than or equal to the first preset number, determine the multiple persons as multiple candidate persons;

[0140] Optionally, the determination module 230 is further configured to, when the number of persons with biometric intention among the multiple candidate persons is equal to a second preset number, determine each candidate person among the multiple candidate persons as the target person; wherein, the second preset number is less than or equal to the first preset number; when the number of persons with biometric intention among the multiple candidate persons is less than the second preset number, based on the difference between the second preset number and the number of persons with biometric intention, select the difference number of persons from the non-candidate persons among the multiple persons as supplementary candidate persons, and the supplementary candidate persons are persons whose distance from the image acquisition device satisfies a second preset condition;

[0141] The recognition module 220 is further configured to, according to the target image, respectively perform intention recognition on at least one supplementary candidate person to obtain the intention recognition result of the at least one supplementary candidate person;

[0142] The determination module 230 is further configured to determine the persons with biometric intention among the multiple candidate persons and the supplementary candidate persons as the target persons;

[0143] Optionally, the acquisition module 210 is further configured to obtain the information to be displayed of the target person based on the biometric result; the audio transmission device further includes a privacy protection module 250 for performing privacy protection on the information to be displayed; the control module 240 is further configured to control the screen to output the information to be displayed after privacy protection.

[0144] The embodiment of the present application further provides an image acquisition device permission management device 300. As Figure 11 shown, it is a schematic structural diagram of an image acquisition device permission management device 300 provided by the embodiment of the present application.

[0145] Among them, the image acquisition device permission management device 300 includes: an acquisition module 310, configured to acquire a target image acquired by an image acquisition device; wherein, the target image includes a plurality of target persons; a permission authentication module 320, configured to perform face permission authentication on the plurality of target persons respectively according to the target image to obtain the to-be-played information of the target persons; wherein, the to-be-played information includes the result of the face permission authentication of the target persons, and / or other information of the target persons obtained based on the face permission authentication result of the target persons; a determination module 330, configured to determine the positions of the two ears of the target persons according to the target image; a control module 340 is configured to control an audio playback device to send the to-be-played information to the positions of the two ears of the target persons respectively in different propagation directions.

[0146] Optionally, the target image includes a plurality of candidate persons, and the image acquisition device permission management device further includes an intention recognition module 350, configured to perform intention recognition on the plurality of candidate persons respectively according to the target image to obtain intention recognition results of the plurality of candidate persons; wherein, the intention recognition result includes the number of eyeballs of the candidate persons; when the number of eyeballs of the candidate person is 2, the candidate person has the intention of face permission authentication; the determination module 330 is further configured to determine the candidate persons with the intention of face permission authentication as target persons based on the intention recognition results of the plurality of candidate persons;

[0147] Optionally, the target image includes a plurality of persons; the determination module 330 is further configured to: when the number of the plurality of persons is greater than a third preset number, determine a plurality of candidate persons from the plurality of persons; wherein, the number of the plurality of candidate persons is equal to the third preset number, and the plurality of candidate persons are the persons whose distance from the image acquisition device meets a third preset condition; when the number of the plurality of persons is less than or equal to the third preset number, determine the plurality of persons as the plurality of candidate persons.

[0148] Figure 12 It is a schematic structural diagram of another electronic device 400 provided by an embodiment of the present application. As Figure 12 shown, the electronic device 400 includes a processor 401, a memory 402, and a network interface 403.

[0149] Among them, the processor 401 includes one or more CPUs. The CPU can be a single-core CPU (single-CPU) or a multi-core CPU (multi-CPU).

[0150] The memory 402 includes but is not limited to RAM, ROM, EPROM, flash memory, or optical memory, etc.

[0151] Optionally, the processor 401 implements the audio transmission method or the image acquisition device permission management method provided in the embodiments of the present application by reading the instructions stored in the memory 402, or the processor 401 implements the audio transmission method or the image acquisition device permission management method provided in the embodiments of the present application by the instructions stored internally. In the case where the processor 401 implements the method in the above embodiments by reading the instructions stored in the memory 402, the memory 402 stores the instructions for implementing the audio transmission method or the image acquisition device permission management method provided in the embodiments of the present application.

[0152] The network interface 403 is a wired interface (port), such as an FDDI or GE interface. Alternatively, the network interface 403 is a wireless interface. It should be understood that the network interface 403 includes multiple physical ports, and the network interface 403 is used to receive images. Optionally, the electronic device further includes a bus 404, and the above-mentioned processor 401, memory 402, and network interface 403 are usually interconnected through the bus 404, or are interconnected in other ways.

[0153] In actual implementation, the acquisition module 210, identification module 220, determination module 230, control module 240, and privacy protection module 250 of the electronic device 400 can be implemented by the processor invoking the computer program code in the memory. The specific execution process can refer to the description in the above method section and will not be elaborated here.

[0154] In actual implementation, the acquisition module 310, permission authentication module 320, determination module 330, control module 340, and intention recognition module 350 of the image acquisition device permission management device 300 can be implemented by the processor invoking the computer program code in the memory. The specific execution process can refer to the description in the above method section and will not be elaborated here.

[0155] Another embodiment of the present application further provides an electronic device, including a memory and a processor. The memory and the processor are coupled; the memory is used to store computer program code, and the computer program code includes computer instructions. Among them, when the processor executes the computer instructions, the electronic device executes each step of the method shown in the above method embodiment.

[0156] Another embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions run on an electronic device, the electronic device executes each step of the method flow executed by the electronic device in the above method embodiment.

[0157] Another embodiment of the present application further provides a chip system, which is applied to an electronic device. The chip system includes one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected by lines. The interface circuits are configured to receive signals from the memory of the electronic device and send the signals to the processors, and the signals include computer instructions stored in the memory. When the processor of the electronic device executes the computer instructions, the electronic device executes each step performed by the electronic device in the method flow shown in the above method embodiment.

[0158] In another embodiment of the present application, there is also provided a computer program product, which includes computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute each step performed by the electronic device in the method flow shown in the above method embodiment.

[0159] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer execution instructions are loaded and executed on a computer, the flow or function according to the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more media integrated therein. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0160] The above are only the specific embodiments of the present application. Those skilled in the art of the present technology can think of changes or substitutions according to the specific embodiments provided by the present application, and all should be covered within the protection scope of the present application.

Claims

1. An audio transmission method, characterized in that, Including: Obtain a target image collected by an image acquisition device; the target image includes a plurality of candidate persons; According to the target image, perform intention recognition on the plurality of candidate persons respectively to obtain intention recognition results of the plurality of candidate persons; The intention recognition result is used to represent whether the candidate person has the intention of biometric recognition; When the number of persons with the intention of biometric recognition among the plurality of candidate persons is less than a second preset number, based on the difference between the second preset number and the number of persons with the intention of biometric recognition, select the difference number of persons from non-candidate persons among the plurality of persons as supplementary candidate persons, and the supplementary candidate persons are persons whose distance from the image acquisition device meets a second preset condition; the second preset condition is that the persons ranked in the top difference number in terms of the distance from the image acquisition device from small to large; According to the target image, perform intention recognition on at least one of the supplementary candidate persons respectively to obtain intention recognition results of at least one of the supplementary candidate persons; Determine the persons with the intention of biometric recognition among the plurality of candidate persons and the supplementary candidate persons as target persons; According to the target image, perform biometric recognition on a plurality of target persons respectively to obtain the information to be played of the target persons; wherein, the information to be played includes the biometric recognition result of the target person, and / or other information of the target person obtained based on the biometric recognition result of the target person; According to the target image, determine the positions of the target persons; Control the audio playback device to send the information to be played to the positions of the target persons in different propagation directions respectively.

2. The method according to claim 1, characterized in that The biometric recognition is face recognition.

3. The method according to claim 2, wherein The intention recognition result of the first candidate person includes: the number of eyeballs of the first candidate person included in the target image; the first candidate person is any candidate person among the plurality of candidate persons and the supplementary candidate persons; The step of determining the persons with the intention of biometric recognition among the plurality of candidate persons and the supplementary candidate persons as the target persons includes: If the number of eyeballs of the first candidate person included in the target image is 2, then determine the first candidate person as the target person.

4. The method according to claim 2, wherein The target image includes a plurality of persons; the method further includes: When the number of the plurality of persons is greater than a first preset number, determine the plurality of candidate persons from the plurality of persons; wherein, the number of the plurality of candidate persons is equal to the first preset number, and the plurality of candidate persons are persons whose distance from the image acquisition device meets a first preset condition; When the number of the plurality of persons is less than or equal to the first preset number, determine the plurality of persons as the plurality of candidate persons.

5. The method according to claim 4, characterized in that The method further includes: When the number of persons with the intention of biometric recognition among the plurality of candidate persons is equal to the second preset number, determine each candidate person among the plurality of candidate persons as a target person; wherein, the second preset number is less than or equal to the first preset number.

6. The method according to claim 1, characterized in that, The method further includes: Obtain the information to be displayed of the target person based on the biometric recognition result, perform privacy protection on the information to be displayed, and control the screen to output the information to be displayed after privacy protection.

7. A method for managing the permissions of an image acquisition device, characterized in that, Including: Obtain the target image collected by the image acquisition device; The target image includes multiple candidate persons; According to the target image, perform intention recognition on the multiple candidate persons respectively to obtain the intention recognition results of the multiple candidate persons; The intention recognition result is used to represent whether the candidate person has the intention of biometric recognition; When the number of persons with the intention of biometric recognition among the multiple candidate persons is less than the second preset number, based on the difference between the second preset number and the number of persons with the intention of biometric recognition, select the difference number of persons from the non-candidate persons among the multiple persons as supplementary candidate persons, and the supplementary candidate persons are persons whose distance from the image acquisition device meets the second preset condition; the second preset condition is that the persons ranked in the top difference number in terms of the distance from the image acquisition device from small to large; According to the target image, perform intention recognition on at least one of the supplementary candidate persons respectively to obtain the intention recognition results of at least one of the supplementary candidate persons; Determine the persons with the intention of biometric recognition among the multiple candidate persons and the supplementary candidate persons as the target persons; According to the target image, perform face permission authentication on multiple target persons respectively to obtain the information to be played of the target persons; wherein, the information to be played includes the result of the face permission authentication of the target persons, and / or other information of the target persons obtained based on the face permission authentication result of the target persons; According to the target image, determine the positions of the two ears of the target person; Control the audio playback device to send the information to be played to the positions of the two ears of the target person in different propagation directions respectively.

8. The method according to claim 7, wherein The intention recognition result includes the number of eyeballs of the candidate person; when the number of eyeballs of the candidate person is 2, the candidate person has the intention of face permission authentication; Based on the intention recognition results of the multiple candidate persons, determine the candidate persons with the intention of face permission authentication as the target persons.

9. The method according to claim 8, wherein The target image includes multiple persons; the method further includes: When the number of the multiple persons is greater than the third preset number, determine the multiple candidate persons from the multiple persons; wherein, the number of the multiple candidate persons is equal to the third preset number, and the multiple candidate persons are persons whose distance from the image acquisition device meets the third preset condition; When the number of the multiple persons is less than or equal to the third preset number, determine the multiple persons as the multiple candidate persons.

10. An audio transmission device, characterized in that, Including: An acquisition module, configured to acquire a target image collected by an image acquisition device; the target image includes multiple candidate persons; An identification module is configured to perform intention recognition on the multiple candidate persons respectively according to the target image to obtain the intention recognition results of the multiple candidate persons; The intention recognition result is used to represent whether the candidate person has the intention of biometric recognition; The determination module is configured to, when the number of persons with biometric intent among the multiple candidate persons is less than a second preset number, select the difference number of persons from the non-candidate persons among the multiple persons as supplementary candidate persons based on the difference between the second preset number and the number of persons with biometric intent, where the supplementary candidate persons are persons whose distance from the image acquisition device satisfies a second preset condition; the second preset condition is that the persons whose distances from the image acquisition device are ranked from small to large reach the top difference number of persons; The recognition module is further configured to, according to the target image, respectively perform intent recognition on at least one of the supplementary candidate persons to obtain intent recognition results of at least one of the supplementary candidate persons; The determination module is further configured to determine the persons with biometric intent among the multiple candidate persons and the supplementary candidate persons as target persons; The recognition module is further configured to, according to the target image, respectively perform biometric recognition on the multiple target persons to obtain the information to be played of the target persons; where the information to be played includes the biometric recognition results of the target persons, and / or other information of the target persons obtained based on the biometric recognition results of the target persons; The determination module is further configured to determine the positions of the target persons according to the target image; The control module is configured to control the audio playback device to send the information to be played to the positions of the target persons in different propagation directions respectively.

11. The audio transmission device according to claim 10, characterized in that, The biometric recognition is face recognition; The intent recognition result of the first candidate person includes: the number of eyeballs of the first candidate person included in the target image; the determination module is specifically configured to, if the number of eyeballs of the first candidate person included in the target image is 2, determine the first candidate person as the target person; the first candidate person is any candidate person among the multiple candidate persons and the supplementary candidate persons; The target image includes multiple persons; the determination module is further configured to: when the number of the multiple persons is greater than a first preset number, determine the multiple candidate persons from the multiple persons; where the number of the multiple candidate persons is equal to the first preset number, and the multiple candidate persons are persons whose distance from the image acquisition device satisfies a first preset condition; when the number of the multiple persons is less than or equal to the first preset number, determine the multiple persons as the multiple candidate persons; The determination module is further configured to, when the number of persons with biometric intent among the multiple candidate persons is equal to the second preset number, determine each candidate person among the multiple candidate persons as a target person; where the second preset number is less than or equal to the first preset number; The acquisition module is further configured to obtain the information to be displayed of the target persons based on the biometric recognition results; The audio transmission device further includes a privacy protection module for protecting the privacy of the information to be displayed; The control module is further configured to control the screen to output the information to be displayed after privacy protection.

12. An image acquisition device permission management device, characterized in that, Including: An acquisition module for acquiring a target image captured by an image acquisition device; The target image includes a plurality of candidate persons; An intention recognition module for respectively performing intention recognition on the plurality of candidate persons according to the target image to obtain intention recognition results of the plurality of candidate persons; A determination module for, when the number of persons with biometric intention among the plurality of candidate persons is less than a second preset number, selecting the difference number of persons as supplementary candidate persons from non-candidate persons among the plurality of persons based on the difference between the second preset number and the number of persons with biometric intention, where the supplementary candidate persons are persons whose distance from the image acquisition device satisfies a second preset condition; the second preset condition is that the persons whose distance from the image acquisition device ranks among the top difference number in ascending order of distance; The intention recognition module is further configured to respectively perform intention recognition on at least one of the supplementary candidate persons according to the target image to obtain intention recognition results of at least one of the supplementary candidate persons; The determination module is further configured to determine the persons with biometric intention among the plurality of candidate persons and the supplementary candidate persons as target persons; An authority authentication module for respectively performing face authority authentication on a plurality of target persons according to the target image to obtain the information to be played of the target persons; wherein, the information to be played includes the result of the face authority authentication of the target persons, and / or other information of the target persons obtained based on the face authority authentication result of the target persons; The determination module is further configured to determine the positions of the two ears of the target persons according to the target image; A control module for controlling an audio playback device to send the information to be played to the positions of the two ears of the target persons in different propagation directions respectively.

13. The image acquisition device permission management apparatus according to claim 12, Characterized in that Wherein, the intention recognition result includes the number of eyeballs of the candidate persons; when the number of eyeballs of the candidate persons is 2, the candidate persons have the intention of face authority authentication; the determination module is further configured to determine the candidate persons with the intention of face authority authentication as the target persons based on the intention recognition results of the plurality of candidate persons; The target image includes a plurality of persons; the determination module is further configured to: when the number of the plurality of persons is greater than a third preset number, determine the plurality of candidate persons from the plurality of persons; wherein, the number of the plurality of candidate persons is equal to the third preset number, and the plurality of candidate persons are persons whose distance from the image acquisition device satisfies a third preset condition; when the number of the plurality of persons is less than or equal to the third preset number, determine the plurality of persons as the plurality of candidate persons.

14. An electronic device, characterized in that, Including a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, and the computer program code includes computer instructions; wherein, when the processor executes the computer instructions, the electronic device executes the method according to any one of claims 1-6 or claims 7-9.

Images