CN104954673A - Camera rotating control method and user terminal - Google Patents

Abstract

The embodiment of the invention discloses a camera rotation control method and a user terminal. Wherein, the method includes: acquiring the target voice of the target person to be photographed; determining the target area where the target person is located according to the propagation direction of the target voice, and rotating the camera to the target area; according to a preset screening strategy, Screening out a target person matching the target voice from a plurality of people in the target area; determining a target position where the target person is located, and adjusting the camera to the target position. The implementation of the embodiment of the present invention can improve the accuracy of the rotation position of the camera.

Description

A camera rotation control method and user terminal

technical field

The present invention relates to the technical field of intelligent terminals, in particular to a camera rotation control method and a user terminal.

Background technique

With the continuous development of electronic technology, more and more user terminals (such as mobile phones, tablet computers, etc.) are equipped with rotating cameras. When the user takes pictures by rotating the camera, in order to achieve a better photo effect, it is usually necessary to manually adjust the rotation angle of the camera, and then take pictures through the rotation camera after the rotation angle of the rotation camera is adjusted. However, manually adjusting the rotation angle of the rotating camera usually cannot adjust the rotating camera to an ideal position well, and the rotating camera needs to be adjusted several times to adjust the rotating camera to an ideal position. It can be seen that, in the prior art, manually adjusting the rotation angle of the rotating camera of the user terminal is cumbersome and has low accuracy.

Contents of the invention

Embodiments of the present invention provide a camera rotation control method and a user terminal, which can improve the accuracy of the camera rotation position.

The first aspect of the embodiment of the present invention discloses a camera rotation control method, including:

Obtain the target voice of the target person to be photographed;

determining the target area where the target person is located according to the propagation direction of the target sound, and rotating the camera to the target area;

Screening out a target person matching the target voice from a plurality of people in the target area according to a preset screening strategy;

A target position where the target person is located is determined, and the camera is adjusted to the target position.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the acquiring the target voice of the target person to be photographed includes:

Receive ambient sound including the sound of the target person to be photographed;

According to the pre-stored target voice characteristics of the target person, from the received environmental sounds, sounds that do not match the target voice characteristics are filtered out, so as to obtain the target person's voice.

In combination with the first aspect or the first possible implementation manner of the first aspect, in the second possible implementation manner of the first aspect, the preset screening strategy includes a face screening strategy, and the preset screening strategy The strategy is to select a target person who matches the target voice from a plurality of characters in the target area, including:

According to the human face screening strategy, a target human face matching the target voice is selected from a plurality of human faces in the target area;

The target person is determined according to the target face.

With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, according to the face screening strategy, the faces in the target area are screened out The target face that the target voice matches, including:

Acquiring target sound characteristics of the target sound;

According to the target sound feature, query the face corresponding to the target sound feature from the pre-stored correspondence between the sound feature and the face;

Comparing the queried human face corresponding to the target sound feature with the multiple human faces in the target area, when the queried human face corresponding to the target sound feature is When a human face is matched, the matched human face is determined as the target human face.

In combination with the first aspect or the first possible implementation manner of the first aspect, in the fourth possible implementation manner of the first aspect, the preset screening strategy includes a human body model screening strategy, and the preset screening strategy The strategy is to select a target person who matches the target voice from a plurality of characters in the target area, including:

Extracting human body models of multiple people in the target area from the preview image of the camera;

According to the mannequin screening strategy, a target mannequin matching the target voice is selected from the mannequins of multiple persons in the target area;

The target person is determined according to the target human body model.

With reference to the fourth possible implementation manner of the first aspect, in the fifth possible implementation manner of the first aspect, according to the human body model screening strategy, the human body models of multiple people in the target area are selected A target manikin matching the target voice, comprising:

Acquiring target sound characteristics of the target sound;

According to the target sound feature, from the correspondence between the pre-stored sound feature and the human body model, query the human body model corresponding to the target sound feature;

comparing the queried human body model corresponding to the target sound feature with the human body models of multiple people in the target area; When one of the human body models of the character matches, the matched human body model is determined as the target human body model.

The second aspect of the embodiment of the present invention discloses a user terminal, including:

An acquisition module, configured to acquire the target voice of the target person to be photographed;

A rotation module, configured to determine the target area where the target person is located according to the propagation direction of the target sound, and rotate the camera to the target area;

A screening module, configured to select a target person matching the target voice from multiple persons in the target area according to a preset screening strategy;

An adjustment module, configured to determine the target position where the target person is, and adjust the camera to the target position.

With reference to the second aspect, in a first possible implementation manner of the second aspect, the obtaining module includes:

A receiving unit, configured to receive ambient sound including the sound of the target person to be photographed;

A filtering unit, configured to filter out sounds that do not match the target voice characteristics from the received ambient sounds according to the pre-stored target voice characteristics of the target person, so as to obtain the voice of the target person .

In combination with the second aspect or the first possible implementation manner of the second aspect, in the second possible implementation manner of the second aspect, the preset screening strategy includes a face screening strategy, and the screening module includes:

A first screening unit, configured to select a target face matching the target voice from multiple faces in the target area according to a face screening strategy;

A first determining unit, configured to determine the target person according to the target person's face.

With reference to the second possible implementation manner of the second aspect, in a third possible implementation manner of the second aspect, the first screening unit includes:

a first acquisition subunit, configured to acquire target sound features of the target sound;

The first query subunit is used to query the human face corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the human face according to the target voice feature;

The first comparison subunit is configured to compare the queried human face corresponding to the target sound feature with multiple human faces in the target area, when the queried human face corresponding to the target sound feature is the same as the When one of the multiple faces in the target area matches, the matched face is determined as the target face.

In combination with the second aspect or the first possible implementation manner of the second aspect, in a fourth possible implementation manner of the second aspect, the preset screening strategy includes a human model screening strategy, and the screening module includes:

An extracting unit, configured to extract human body models of multiple people in the target area from the preview image of the camera;

The second screening unit is configured to select a target mannequin that matches the target voice from the mannequins of multiple people in the target area according to the mannequin screening strategy;

A second determining unit, configured to determine the target person according to the target human body model.

With reference to the fourth possible implementation manner of the second aspect, in a fifth possible implementation manner of the second aspect, the second screening unit includes:

The second acquisition subunit is used to acquire the target sound feature of the target sound;

The second query subunit is used to query the human body model corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the human body model according to the target voice feature;

The second comparison subunit is used to compare the queried human body model corresponding to the target sound feature with the human body models of multiple people in the target area, when the queried human body model corresponding to the target sound feature When the model matches one of the multiple human body models in the target area, the matched human body model is determined as the target human body model.

In the embodiment of the present invention, the user terminal obtains the target voice of the target person to be photographed, determines the target area where the target person is located according to the propagation direction of the target voice, and rotates the camera to the target area; further, according to the preset screening strategy, from The target person matching the target voice is selected from the multiple persons in the target area, and after the target position of the target person is determined, the user terminal can adjust the camera to the target position. Through the embodiment of the present invention, the user recognizes the target area where the target voice of the target person is located, rotates the camera to the approximate position of the target area, further determines the specific position of the target person in the target area, and adjusts the camera to the target area. The specific position, so that the accuracy of the camera rotation position can be improved.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

FIG. 1 is a schematic flowchart of a camera rotation control method disclosed in an embodiment of the present invention;

Fig. 2 is a schematic flow chart of another camera rotation control method disclosed in an embodiment of the present invention;

Fig. 3 is a schematic flowchart of another camera rotation control method disclosed in an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a user terminal disclosed in an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention;

Fig. 8 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The embodiment of the invention discloses a camera rotation control method and a user terminal, which can improve the accuracy of the camera rotation position. Each will be described in detail below.

In the embodiment of the present invention, the user terminal may include, but not limited to, a smart phone, a notebook computer, a personal computer (Personal Computer, PC), a personal digital assistant (Personal Digital Assistant, PDA), a mobile Internet device (Mobile Internet Device, MID), Various user terminals such as smart wearable devices (such as smart watches and smart bracelets), among which, the operating system of the user terminal may include but not limited to Android operating system, IOS operating system, Symbian (Symbian) operating system, Black Berry (Blackberry) ) operating system, Windows Phone8 operating system, etc., the embodiments of the present invention are not limited.

Please refer to FIG. 1 . FIG. 1 is a schematic flowchart of a camera rotation control method disclosed in an embodiment of the present invention. As shown in Fig. 1, the method may include but not limited to the following steps.

S101. Obtain a target voice of a target person to be photographed.

In the embodiment of the present invention, the user terminal may acquire the target voice of the target person to be photographed through a built-in voice acquisition device (such as a microphone).

As an optional implementation manner, the specific implementation manner in which the user terminal acquires the target voice of the target person to be photographed may include the following steps.

11) Receive ambient sound including the sound of the target person to be photographed.

12) According to the pre-stored target voice characteristics of the target person, from the received environmental sounds, sounds that do not match the target voice characteristics are filtered out to obtain the target person's voice.

In this embodiment, since there may be other sounds in the environment where the target person is located, such as the voice of other people speaking or noise, the sound received by the user terminal is the environment including the sound of the target person to be photographed. sound, the user terminal can acquire the target voice features of the target person stored in advance, and further extract the sound features of each sound from the received environmental sound, and compare the target voice features with the extracted sound features of each sound Comparing, obtaining the sound features consistent with the target sound features from the extracted sound features, and determining the sound matching the sound features. This makes it possible to filter out voices that do not match the target's vocal characteristics to obtain the voice of the target person. Wherein, the sound characteristics of each sound may include three, such as pitch, loudness, and timbre. The target voice characteristics of the target person stored in the user terminal may include any one or more of pitch, loudness, and timbre.

As another optional implementation manner, before step S101, the method may further include the following steps.

21) Receive camera opening instruction;

22) Output prompt information, which is used to prompt input of information to be verified;

23) Receive the information to be verified input in response to the prompt information;

24) Verify whether the information to be verified is consistent with the preset verification information set in advance;

25) When it is verified that the information to be verified is consistent with the preset verification information, the camera is turned on in response to the camera opening instruction.

In this embodiment, the instruction to turn on the camera may be an instruction input by the user, for example, the user clicks a camera application icon on the user terminal.

In this embodiment, the information to be verified may include but not limited to password to be verified, fingerprint information to be verified, face shape information to be verified, iris information to be verified, retina information to be verified, and voiceprint information to be verified. Several combinations.

In this embodiment, the preset verification information may include but not limited to a preset verification password, a preset verification fingerprint information, a preset verification face shape information, a preset verification iris information, a preset verification retina information, and a preset Verify any one or a combination of voiceprint information.

In this embodiment, the aforementioned preset verification information may include fingerprint string information and the input time corresponding to each fingerprint; correspondingly, verifying whether the information to be verified is consistent with the preset verification information may include the following steps.

Verify whether the fingerprint string is the same as the fingerprint string included in the preset verification information, and whether the difference between the input time of the same fingerprint is less than the preset value; when the verification fingerprint string is the same as the fingerprint string included in the preset verification information, and the same fingerprint When the difference between the input times is smaller than the preset value, it can be verified that the information to be verified is consistent with the preset verification information; otherwise, it can be verified that the information to be verified is inconsistent with the preset verification information. Wherein, by implementing this implementation manner, it is possible to prevent an illegal user from turning on the camera on the user terminal, thereby effectively preventing the user terminal from being arbitrarily operated by the illegal user.

S102. Determine the target area where the target person is located according to the propagation direction of the target sound, and rotate the camera to the target area.

In the embodiment of the present invention, the user terminal determines the target area where the target person is located according to the propagation direction of the target sound, and rotates the camera to the target area.

Specifically, after the user terminal acquires the target sound of the target person to be photographed, it can identify the direction from which the target sound is transmitted, and the user terminal can determine the target area where the target person is located according to the propagation direction, that is, the approximate area range , after the target area is determined, the camera can be rotated to the target area.

S103. According to a preset screening strategy, select a target person matching the target voice from multiple persons in the target area.

In the embodiment of the present invention, the user terminal screens out a target person who matches the target voice from multiple people in the target area according to a preset screening strategy. Wherein, the preset screening strategy may include but not limited to a face screening strategy or a mannequin screening strategy. That is, the user terminal may screen and identify the target person according to the face or screen and identify the target person according to the human body model.

In an embodiment, the user terminal may select a target face that matches the target voice from multiple faces in the target area according to the face screening strategy, and then determine the target person according to the target face.

In another embodiment, the user terminal can extract the human body models of multiple people in the target area from the preview image of the camera, and filter out the human body models of the multiple people in the target area according to the human body model screening strategy. The matched target human body model, and then the target person is determined according to the target human body model.

S104. Determine the target position where the target person is, and adjust the camera to the target position.

In the embodiment of the present invention, after the user terminal determines the target person, it can further determine the target position of the target person through the built-in GPS (Global Positioning System, Global Positioning System), so that the user terminal can further adjust the camera, The camera is rotated to the position where the target person is, and after the angle of the camera is rotated, the user terminal can use the camera to take pictures of the target person.

In the method flow described in FIG. 1, the user terminal obtains the target voice of the target person to be photographed, determines the target area where the target person is located according to the propagation direction of the target sound, and rotates the camera to the target area; further, according to the preset The screening strategy is to select the target person who matches the target voice from multiple people in the target area, and after determining the target position of the target person, the user terminal can adjust the camera to the target position. Through the embodiment of the present invention, the user terminal recognizes the target area where the target voice of the target person is located, rotates the camera to the approximate position of the target area, further determines the specific position of the target person in the target area, and adjusts the camera to the approximate position of the target area. This specific position can improve the accuracy of the camera rotation position.

Please refer to FIG. 2 . FIG. 2 is a schematic flowchart of another camera rotation control method disclosed in an embodiment of the present invention. As shown in Figure 2, the method may include the following steps:

S201. The user terminal acquires a target voice of a target person to be photographed.

S202. The user terminal determines the target area where the target person is located according to the propagation direction of the target sound, and rotates the camera to the target area.

S203. The user terminal selects a target face that matches the target voice from multiple faces in the target area according to the face screening strategy.

In the embodiment of the present invention, because each person's face is different, each person's matching voice is also different, therefore, the user terminal can filter out the target face that matches the target voice from multiple faces in the target area.

As an optional implementation manner, the specific implementation manner in which the user terminal screens out a target face that matches the target voice from multiple faces in the target area according to the face screening strategy may include the following steps.

11) Obtain the target sound feature of the target sound.

12) According to the target voice feature, query the face corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the face.

13) Compare the face corresponding to the queried target sound feature with multiple faces in the target area, when the face corresponding to the queried target sound feature matches one of the multiple faces in the target area , and determine the matching face as the target face.

In this embodiment, the user terminal may obtain pre-stored target sound features, or extract target sound features from the acquired target sound, where the target sound features may include any one or more of pitch, loudness, and timbre. kind. The user terminal may query the face corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the face based on the target voice feature. Further, comparing the face corresponding to the queried target sound feature with multiple faces in the target area, when the face corresponding to the queried target sound feature matches one of the multiple faces in the target area , determine the matching face as the target face.

Specifically, the user terminal can collect multiple face images of the target area through the camera, and further, determine the size, position, distance and other attributes of the facial features such as the iris, nose, and mouth corners of each face image according to the eigenvector method, Then calculate their geometric features to form a feature vector that can describe each face. The user terminal queries the face corresponding to the target voice feature, that is, queries the face feature vector corresponding to the target voice feature. The user terminal compares the face feature vector corresponding to the target voice feature found with the feature vector of each face collected, and when the matching degree of comparison reaches a preset matching degree (such as 90%), it can Determining the collected face that reaches the preset matching degree as the target face.

S204. The user terminal determines the target person according to the target face.

In the embodiment of the present invention, since the face feature vectors of each person are different, after the user terminal determines the target face, it can determine the target person to which the target face belongs.

S205. The user terminal determines the target position where the target person is, and adjusts the camera to the target position.

In the method flow described in FIG. 2, the user terminal acquires the target voice of the target person to be photographed, determines the target area where the target person is located according to the propagation direction of the target voice, and rotates the camera to the target area; further, according to the face The screening strategy is to select the target face that matches the target voice from multiple faces in the target area. After the target person is determined according to the target face, the user terminal can determine the target position where the target person is located. In this way, the user terminal can The camera can be adjusted to the target position. Through the embodiment of the present invention, the user terminal can combine the target voice and the face screening strategy to filter out the face that matches the target voice from multiple faces to determine the target person, and then determine the location of the target person. After adjusting the camera to This position can improve the accuracy of the camera rotation position.

Please refer to FIG. 3 . FIG. 3 is a schematic flowchart of another camera rotation control method disclosed in an embodiment of the present invention. As shown in Figure 3, the method may include the following steps:

S301. The user terminal acquires a target voice of a target person to be photographed.

S302. The user terminal determines the target area where the target person is located according to the propagation direction of the target sound, and rotates the camera to the target area.

S303. The user terminal extracts human body models of multiple people in the target area from the preview image of the camera.

In the embodiment of the present invention, the preview image of the camera includes multiple characters, and the user terminal can extract the human body model of each character according to each character, wherein the human body model is a three-dimensional anatomical structure, including the size, shape, and The position and its spatial relationship, the size of each tissue and organ of the extracted human body model can be the same as the size of each tissue and organ of a real person, or can form a certain ratio, for example: the size of each tissue and organ of the extracted human body model is the same as that of a real person 20% of the size of each tissue organ etc.

S304. According to the mannequin screening strategy, the user terminal selects a target mannequin that matches the target voice from the mannequins of multiple people in the target area.

In the embodiment of the present invention, due to the size of each person's body and size, there will be a certain degree of difference in the size of each tissue and organ. Therefore, the user terminal can filter out the target that matches the target voice from the human body models of multiple people in the target area. mannequin.

As an optional implementation manner, the specific implementation manner in which the user terminal selects a target mannequin matching the target voice from the mannequins of multiple persons in the target area according to the mannequin screening strategy may include the following steps.

11) Obtain the target sound feature of the target sound.

12) According to the target voice feature, query the human body model corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the human body model.

13) Comparing the human body model corresponding to the queried target sound feature with the human body models of multiple characters in the target area, when the human body model corresponding to the queried target sound feature and the human body models of multiple characters in the target area When a human body model is matched, the matched human body model is determined as the target human body model.

In this embodiment, the user terminal may obtain pre-stored target sound features, or extract target sound features from the acquired target sound, where the target sound features may include any one or more of pitch, loudness, and timbre. kind. The user terminal may query the human body model corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the human body model based on the target voice feature. Further, the human body model corresponding to the queried target sound feature is compared with the human body models of multiple people in the target area. When a human body model is matched, the matched human body model is determined as the target human body model.

Specifically, the user terminal can collect multiple people in the target area through the camera, and then extract the human body model of each character through the built-in human body model extraction device, wherein the extracted human body model includes the size, shape, and position of each tissue and organ and its spatial relationship. The user terminal queries the human body model corresponding to the target sound feature, and can compare the size, shape, position and spatial relationship of each tissue and organ included in the human body model corresponding to the target sound feature with the extracted human body model of each character. The size, shape, position and spatial relationship of the tissues and organs are compared one by one. When the matching degree of the comparison reaches the preset matching degree (such as 90%), the extracted human body model that reaches the preset matching degree can be determined as Target mannequin.

S305. The user terminal determines the target person according to the target human body model.

In the embodiment of the present invention, after the user terminal determines the target human body model from the multiple extracted human body models, it can determine the target person to which the target human body model belongs.

S306. The user terminal determines the target position where the target person is, and adjusts the camera to the target position.

In the method flow described in FIG. 3, the user terminal acquires the target voice of the target person to be photographed, determines the target area where the target person is located according to the propagation direction of the target sound, and rotates the camera to the target area; further, from the camera's Extract the mannequins of multiple people in the target area from the preview image, and select the target mannequin that matches the target voice from the mannequins of multiple people in the target area according to the mannequin screening strategy, and determine the target mannequin according to the target mannequin After that, the user terminal can determine the target position where the target person is, so that the user terminal can adjust the camera to the target position. Through the embodiment of the present invention, the user terminal can combine the target voice and the mannequin screening strategy to filter out the target mannequin that matches the target voice from multiple mannequins to determine the target person, and then determine the location of the target person. Camera to this position, which can improve the accuracy of camera rotation position.

The following is the embodiment of the device of the present invention, which is used to implement the method in the method embodiment of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown. If the specific technical details are not disclosed, please Refer to the above-mentioned method embodiment of the present invention.

Please refer to FIG. 4, which is a schematic structural diagram of a user terminal disclosed in an embodiment of the present invention. As shown in FIG. 4, the user terminal may include: an acquisition module 401, a rotation module 402, a screening module 403, and an adjustment module 404, in:

The acquisition module 401 is configured to acquire the target voice of the target person to be photographed.

In the embodiment of the present invention, the acquiring module 401 can acquire the target voice of the target person to be photographed through a built-in voice acquiring device (such as a microphone).

The rotation module 402 is configured to determine the target area where the target person is located according to the propagation direction of the target sound, and rotate the camera to the target area.

In the embodiment of the present invention, the rotation module 402 determines the target area where the target person is located according to the propagation direction of the target sound, and rotates the camera to the target area.

Specifically, after the acquisition module 401 acquires the target sound of the target person to be photographed, it can identify the direction from which the target sound propagates, and the rotation module 402 can determine the target area where the target person is located according to the propagation direction, that is, approximately Area range, after the target area is determined, the camera can be rotated to the target area.

The screening module 403 is configured to select a target person who matches the target voice from multiple persons in the target area according to a preset screening strategy.

In the embodiment of the present invention, the screening module 403 screens out a target person who matches the target voice from multiple people in the target area according to a preset screening strategy. Wherein, the preset screening strategy may include but not limited to a face screening strategy or a mannequin screening strategy. That is, the screening module 403 can screen and identify the target person according to the human face or screen and identify the target person according to the human body model.

The adjustment module 404 is configured to determine the target position where the target person is, and adjust the camera to the target position.

In the embodiment of the present invention, after the screening module 403 determines the target person, the adjustment module 404 can further determine the target position of the target person through the built-in GPS (Global Positioning System, Global Positioning System), so that the adjustment module 404 can The camera can be further adjusted so that the camera rotates to the position where the target person is. After the camera is rotated at an angle, the user terminal can use the camera to take pictures of the target person.

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention. The user terminal shown in FIG. 5 is further optimized on the basis of the user terminal shown in FIG. Compared with the user terminal shown in Figure 4, the user terminal shown in Figure 5 may include not only all the modules of the user terminal shown in Figure 4, but also:

A receiving module 405, configured to receive a camera opening instruction;

The output module 406 is used to output prompt information, and the prompt information is used to prompt input of information to be verified;

The above-mentioned receiving module 405 is also configured to receive the information to be verified inputted in response to the prompt information;

A verification module 407, configured to verify whether the information to be verified is consistent with the preset verification information set in advance;

The opening module 408 is configured to respond to the camera opening instruction and open the camera when the verification module 407 verifies that the information to be verified is consistent with the preset verification information.

In this embodiment, the instruction to turn on the camera may be an instruction input by the user, for example, the user clicks a camera application icon on the user terminal.

In this embodiment, the information to be verified may include but not limited to password to be verified, fingerprint information to be verified, face shape information to be verified, iris information to be verified, retina information to be verified, and voiceprint information to be verified. Several combinations.

In this embodiment, the preset verification information may include but not limited to a preset verification password, a preset verification fingerprint information, a preset verification face shape information, a preset verification iris information, a preset verification retina information, and a preset Verify any one or a combination of voiceprint information.

In this embodiment, the above-mentioned preset verification information may include fingerprint string information and the input time corresponding to each fingerprint; then correspondingly, the verification module 407 verifying whether the information to be verified is consistent with the preset verification information may include the following steps:

Verify whether the fingerprint string is the same as the fingerprint string included in the preset verification information, and whether the difference between the input time of the same fingerprint is less than the preset value, if the verification fingerprint string is the same as the fingerprint string included in the preset verification information, and the same fingerprint If the difference between the input times is smaller than the preset value, it can be verified that the information to be verified is consistent with the preset verification information; otherwise, it can be verified that the information to be verified is inconsistent with the preset verification information. Wherein, by implementing this implementation manner, it is possible to prevent an illegal user from turning on the camera on the user terminal, thereby effectively preventing the user terminal from being arbitrarily operated by the illegal user.

Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention, wherein, the user terminal shown in FIG. 6 is further optimized on the basis of the user terminal shown in FIG. 4, Compared with the user terminal shown in FIG. 4, the user terminal shown in FIG. 6 includes all modules of the user terminal shown in FIG. 4, and the obtaining module 401 may include:

a receiving unit 4011, configured to receive ambient sound including the sound of the target person to be photographed;

The filtering unit 4012 is configured to filter out sounds that do not match the target voice characteristics from the received environmental sounds according to the pre-stored target voice characteristics of the target person, so as to obtain the target person's voice.

In this embodiment, since there may be other sounds in the environment where the target person is located, such as the voice of other people speaking or noise, the sound received by the receiving unit 4011 includes the sound of the target person to be photographed. Environmental sound, the user terminal can obtain the target voice feature of the target person stored in advance, further, from the received environmental sound, extract the sound feature of each sound, and combine the target sound feature with the extracted sound feature of each sound Once compared, the sound features consistent with the target sound features are obtained from the extracted sound features, and the sound matching the sound features is determined, so that the filtering unit 4012 can filter out sounds that do not match the target sound features to obtain The target person's voice. Wherein, each sound may include three main characteristics, such as pitch, loudness, and timbre. The target voice characteristics of the target person stored in the user terminal may include any one or more of pitch, loudness, and timbre.

Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention, wherein, the user terminal shown in FIG. 7 is further optimized on the basis of the user terminal shown in FIG. 4, Compared with the user terminal shown in FIG. 4 , except that the user terminal shown in FIG. 7 includes all modules of the user terminal shown in FIG. 4 , the screening module 403 may include:

The first screening unit 4031 is configured to select a target face matching the target voice from multiple faces in the target area according to the face screening strategy;

The first determining unit 4032 is configured to determine the target person according to the target person's face.

In the embodiment of the present invention, because each person's face is different, each person's matching voice is also different, therefore, the first screening unit 4031 can filter out the target face that matches the target voice from multiple faces in the target area , the first determining unit 4032 can determine the target person to which the target face belongs.

As an optional implementation manner, the above-mentioned first screening unit 4031 may include:

The first acquisition subunit 40311 is used to acquire the target sound feature of the target sound;

The first query subunit 40312 is used to query the face corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the face according to the target voice feature;

The first comparison subunit 40313 is used to compare the human face corresponding to the queried target sound feature with multiple human faces in the target area, when the queried human face corresponding to the target voice feature is compared with multiple human faces in the target area When one of the faces matches, the matching face is determined as the target face.

In this embodiment, the first acquiring subunit 40311 can acquire the pre-stored target sound features, or extract the target sound features from the acquired target sounds, where the target sound features can include any of pitch, loudness, and timbre. one or more. The first query subunit 40312 may query the face corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the face based on the target voice feature. Further, the first comparison subunit 40313 compares the face corresponding to the queried target voice feature with multiple faces in the target area, when the face corresponding to the queried target voice feature is compared with multiple faces in the target area When one of the faces matches, the matching face is determined as the target face.

Specifically, the user terminal can collect multiple face images of the target area through the camera, and further, determine the size, position, distance and other attributes of the facial features such as the iris, nose, and mouth corners of each face image according to the eigenvector method, Then calculate their geometric features to form a feature vector that can describe each face. The first query subunit 40312 queries the face corresponding to the target voice feature, that is, queries the face feature vector corresponding to the target voice feature. The first comparison subunit 40313 compares the face feature vector corresponding to the target voice feature found with the feature vector of each face collected, and when the matching degree of comparison reaches the preset matching degree (such as 90%) ), the collected face that reaches the preset matching degree can be determined as the target face.

Please refer to FIG. 8. FIG. 8 is a schematic structural diagram of another user terminal disclosed in an embodiment of the present invention, wherein, the user terminal shown in FIG. 8 is further optimized on the basis of the user terminal shown in FIG. 4, Compared with the user terminal shown in FIG. 4 , except that the user terminal shown in FIG. 8 includes all modules of the user terminal shown in FIG. 4 , the screening module 403 may include:

The extracting unit 4033 is configured to extract human body models of multiple people in the target area from the preview image of the camera.

In the embodiment of the present invention, the preview image of the camera includes multiple characters, and the extraction unit 4033 can extract the human body model of each character according to each character, wherein the human body model is a three-dimensional anatomical structure, including the size and shape of tissues and organs , position and its spatial relationship, the size of each tissue and organ of the extracted human body model can be the same as the size of each tissue and organ of a real person, or can form a certain ratio, for example: the size of each tissue and organ of the extracted human body model is real 20% of the size of each tissue and organ of the character, etc.

The second screening unit 4034 is configured to select a target mannequin that matches the target voice from the mannequins of multiple people in the target area according to the mannequin screening strategy.

In the embodiment of the present invention, due to the size of each person's body and size, there will be a certain degree of difference in the size of each tissue and organ. Therefore, the user terminal can filter out the target that matches the target voice from the human body models of multiple people in the target area. mannequin.

The second determination unit 4035 is configured to determine the target person according to the target human body model.

In the embodiment of the present invention, after the second screening unit 4034 determines the target human body model from the extracted multiple human body models, the second determining unit 4035 can determine the target person to which the target human body model belongs.

As an optional implementation manner, the second screening unit 4034 may include:

The second acquisition subunit 40341 is used to acquire the target sound feature of the target sound;

The second query subunit 40342 is used to query the human body model corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the human body model according to the target voice feature;

The second comparison subunit 40343 is used to compare the human body model corresponding to the queried target sound feature with the human body models of multiple people in the target area. When one of the human body models of the plurality of characters matches, the matched human body model is determined as the target human body model.

In this embodiment, the second acquiring subunit 40341 can acquire the pre-stored target sound features, or extract the target sound features from the acquired target sounds, where the target sound features can include any of pitch, loudness and timbre. one or more. The second query subunit 40342 may query the human body model corresponding to the target voice feature from the pre-stored correspondence between the voice feature and the human body model based on the target voice feature. Further, the second comparison subunit 40343 compares the human body model corresponding to the queried target sound feature with the human body models of multiple people in the target area. When one of the human body models of the plurality of characters matches, the matched human body model is determined as the target human body model.

Specifically, the user terminal can collect multiple people in the target area through the camera, and the extraction unit 4033 extracts the human body model of each character through the built-in human body model extraction device, wherein the extracted human body model includes the size of each tissue and organ, Shape, position and its spatial relationship. The second query subunit 40342 queries the human body model corresponding to the target sound feature, and the second comparison subunit 40343 can extract the size, shape, position and spatial relationship of each tissue and organ included in the human body model corresponding to the target sound feature The size, shape, position and spatial relationship of each tissue and organ included in the human body model of each character are compared one by one. When the matching degree of comparison reaches the preset matching degree (such as 90%), the The extracted human body model with a preset matching degree is determined as the target human body model.

In the user terminal described in FIGS. 4 to 8 , the acquisition module 401 acquires the target voice of the target person to be photographed, and the rotation module 402 determines the target area where the target person is located according to the propagation direction of the target voice, and rotates the camera to the target area Further, the screening module 403 screens out the target person who matches the target voice from multiple people in the target area according to the preset screening strategy, and after the adjustment module 404 determines the target position where the target person is located, the camera can be adjusted to the target Location. According to the embodiment of the present invention, the rotation module 402 recognizes the target area where the target voice of the target person is located, and after rotating the camera to the approximate position of the target area, the adjustment module 404 further determines the specific position of the target person in the target area, And adjust the camera to the specific position, so that the accuracy of the rotation position of the camera can be improved.

It should be noted that, for the sake of simple description, all the aforementioned method embodiments are expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence. Because according to the application, certain steps may be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions and units involved are not necessarily required by this application.

In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.

The above disclosures are only preferred embodiments of the present invention, and certainly cannot limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims (12)

1. a camera method of controlling rotation, is characterized in that, comprising:

Obtain the target sound of target person to be captured;

According to the direction of propagation of described target sound, determine the target area at described target person place, and camera is rotated to described target area;

According to default screening strategy, from multiple personages of described target area, filter out the target person mated with described target sound;

Determine the target location at described target person place, and described camera is adjusted to described target location.

2. method according to claim 1, is characterized in that, the target sound of described acquisition target person to be captured, comprising:

Receive the ambient sound comprising the sound of target person to be captured;

According to the target sound feature of the described target person prestored, from the described ambient sound received, filtering and the unmatched sound of described target sound feature, to obtain the sound of described target person.

3. method according to claim 1 and 2, it is characterized in that, described default screening strategy comprises face screening strategy, and described basis presets screening strategy, from multiple personage of described target area, filter out the target person mated with described target sound, comprising:

According to face screening strategy, from multiple faces of described target area, filter out the target face mated with described target sound;

Described target person is determined according to described target face.

4. method according to claim 3, is characterized in that, described according to face screening strategy, filters out the target face mated with described target sound, comprising from multiple faces of described target area:

Obtain the target sound feature of described target sound;

According to described target sound feature, from the corresponding relation of the sound characteristic prestored and face, inquire about the face that described target sound feature is corresponding;

Multiple faces of face corresponding for the described target sound feature inquired and described target area are compared, when the face that the described target sound feature inquired is corresponding mates with people's appearance in multiple faces of described target area, the face matched is defined as target face.

5. method according to claim 1 and 2, it is characterized in that, described default screening strategy comprises manikin screening strategy, and described basis presets screening strategy, from multiple personage of described target area, filter out the target person mated with described target sound, comprising:

The manikin of multiple personages of described target area is extracted from the preview image of described camera;

According to manikin screening strategy, from the manikin of multiple personages of described target area, filter out the target body model mated with described target sound;

Described target person is determined according to described target body model.

6. method according to claim 5, is characterized in that, described according to manikin screening strategy, filters out the target body model mated with described target sound, comprising from the manikin of multiple personages of described target area:

Obtain the target sound feature of described target sound;

According to described target sound feature, from the corresponding relation of the sound characteristic prestored and manikin, inquire about the manikin that described target sound feature is corresponding;

The manikin of multiple personages of manikin corresponding for the described target sound feature inquired and described target area is compared, when a manikin in the manikin of multiple personages of manikin corresponding to the described target sound feature inquired and described target area matches, the manikin matched is defined as target body model.

7. a user terminal, is characterized in that, comprising:

Acquisition module, for obtaining the target sound of target person to be captured;

Rotary module, for the direction of propagation according to described target sound, determines the target area at described target person place, and rotates to described target area by camera;

Screening module, for according to presetting screening strategy, filters out the target person mated with described target sound from multiple personages of described target area;

Adjusting module, for determining the target location at described target person place, and is adjusted to described target location by described camera.

8. user terminal according to claim 7, is characterized in that, described acquisition module comprises:

Receiving element, for receiving the ambient sound of the sound comprising target person to be captured;

Filtering unit, for the target sound feature according to the described target person prestored, from the described ambient sound received, filtering and the unmatched sound of described target sound feature, to obtain the sound of described target person.

9. the user terminal according to claim 7 or 8, is characterized in that, described default screening strategy comprises face screening strategy, and described screening module comprises:

First screening unit, for according to face screening strategy, filters out the target face mated with described target sound from multiple faces of described target area;

First determining unit, for determining described target person according to described target face.

10. user terminal according to claim 9, is characterized in that, described first screening unit comprises:

First obtains subelement, for obtaining the target sound feature of described target sound;

First inquiry subelement, for according to described target sound feature, from the corresponding relation of the sound characteristic prestored and face, inquires about the face that described target sound feature is corresponding;

First comparer unit, for multiple faces of face corresponding for the described target sound feature inquired and described target area are compared, when the face that the described target sound feature inquired is corresponding mates with people's appearance in multiple faces of described target area, the face matched is defined as target face.

11. user terminals according to claim 7 or 8, it is characterized in that, described default screening strategy comprises manikin screening strategy, and described screening module comprises:

Extraction unit, for extracting the manikin of multiple personages of described target area in the preview image from described camera;

Second screening unit, for according to manikin screening strategy, filters out the target body model mated with described target sound from the manikin of multiple personages of described target area;

Second determining unit, for determining described target person according to described target body model.

12. user terminals according to claim 11, is characterized in that, described second screening unit comprises:

Second obtains subelement, for obtaining the target sound feature of described target sound;

Second inquiry subelement, for according to described target sound feature, from the corresponding relation of the sound characteristic prestored and manikin, inquires about the manikin that described target sound feature is corresponding;

Second comparer unit, manikin for the multiple personages by manikin corresponding for the described target sound feature inquired and described target area is compared, when a manikin in the manikin of multiple personages of manikin corresponding to the described target sound feature inquired and described target area matches, the manikin matched is defined as target body model.