WO2022052833A1 - Television sound adjustment method, television and storage medium - Google Patents

Abstract

Disclosed in the present application are a television sound adjustment method, a television and a storage medium. The method comprises: acquiring and recognizing a target area image to obtain a recognition result; according to the recognition result, determining whether a left ear area and a right ear area exist; if yes, according to the left ear area, the right ear area, a field of view of a camera, a standard definition, a standard vertical distance, a horizontal distance between left and right loudspeakers and preset coefficients, acquiring left ear position information and right ear position information; acquiring left channel difference parameters and right channel difference parameters according to the left ear position information and the right ear position information left; adjusting a left channel signal and a right channel signal according to the left channel difference parameters and the right channel difference parameters to obtain an adjusted left channel signal and an adjusted right channel signal; and performing playback according to the adjusted left channel signal and the adjusted right channel signal.

Description

TV sound adjustment method, TV and storage medium

priority information

This application claims the priority of the Chinese patent application filed on September 10, 2020 with application number 202010951644.4, the entire contents of which are incorporated herein by reference.

technical field

The present application relates to the field of smart TVs, and in particular, to a TV sound adjustment method, a TV, and a computer-readable storage medium.

Background technique

When a user is watching TV, the user is in different viewing positions and experiences different sound effects. The user can have the best sound effect only when the user is facing the center of the TV; when the user is in other areas, the pitch, timbre, loudness, etc. of the TV sound entering the left and right ears of the human will change, resulting in poor sound effect and affecting the sound experience.

SUMMARY OF THE INVENTION

The main purpose of the present application is to provide a TV sound adjustment method, a TV and a computer-readable storage medium, aiming to solve the problem of poor sound experience when existing users are not watching TV at the central point of the TV.

In order to achieve the above-mentioned purpose, the present application provides a TV sound adjustment method, comprising the steps of:

Control the camera to collect images of the target area at a preset sampling frequency;

Perform image recognition on the currently collected target area image to obtain the current recognition result;

According to the current recognition result, determine whether both the left ear area and the right ear area exist in the current target area image:

When it is determined that both the left ear area and the right ear area exist, according to the preset camera field angle, preset standard definition, preset standard vertical distance, preset left and right speaker horizontal spacing, preset coefficient, Ear area and right ear area to obtain left ear position information and right ear position information, where left ear position information includes left ear vertical distance, left ear horizontal distance and left ear horizontal angle, right ear position information includes right ear vertical distance, Right ear horizontal distance and right ear horizontal angle;

Obtain the left channel difference parameter and the right channel difference parameter according to the left ear position information and the right ear position information;

Adjust the current left channel signal according to the left channel difference parameter to obtain the adjusted left channel signal, and adjust the current right channel signal according to the right channel difference parameter to obtain the adjusted right channel signal channel signal;

Plays according to the adjusted left channel signal and the adjusted right channel signal.

In one embodiment, when it is determined that both the left ear area and the right ear area exist, the preset camera angle of view, the preset standard definition, the preset standard vertical distance, the preset horizontal distance between the left and right speakers, the preset coefficient, the left ear area and the right ear area in the current target area image, and the steps of obtaining the left ear position information and the right ear position information include:

When it is determined that both the left ear area and the right ear area exist, according to the left ear area, preset camera field angle, preset standard definition, preset standard vertical distance, preset left and right speaker horizontal spacing and preset in the current target area image. Set the coefficient to obtain the position information of the left ear;

The position information of the right ear is obtained according to the right ear area, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset horizontal distance between the left and right speakers, and the preset coefficient in the current target area image.

In one embodiment, after the step of judging whether both the left ear area and the right ear area in the current target area image exist according to the current recognition result, the step further includes:

When it is determined that only the left ear area exists in the current target area image, according to the left ear area in the current target area image, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset left and right speaker horizontal spacing and Preset coefficients to obtain left ear position information;

According to the left ear position information and the preset horizontal offset value, the right ear position information is obtained.

In one embodiment, after the step of judging whether both the left ear area and the right ear area in the current target area image exist according to the current recognition result, the step further includes:

When it is determined that only the right ear area exists in the current target area image, according to the right ear area in the current target area image, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset left and right speaker horizontal spacing and Preset coefficients to obtain right ear position information;

The left ear position information is obtained according to the right ear position information and the preset horizontal offset value.

In one embodiment, according to the left ear area in the current target area image, the preset camera angle of view, the preset standard definition, the preset standard vertical distance, the preset left and right speaker horizontal spacing and the preset coefficient, the The steps of left ear position information include:

Perform spatial spectrum analysis on the left ear area in the current target area image to obtain the clarity of the left ear area;

Obtain left ear vertical distance according to left ear area definition, preset standard definition, preset standard vertical distance and preset coefficient;

Obtain the left ear horizontal distance according to the abscissa value of at least one pixel in the left ear area, the preset left and right speaker horizontal distance, the left ear vertical distance, the total number of horizontal pixels of the current target area image, and the preset camera field of view;

Obtain the horizontal angle of the left ear according to the horizontal distance of the left ear, the vertical distance of the left ear, and the preset horizontal distance of the left and right speakers.

In one embodiment, according to the right ear area, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset left and right speaker horizontal distance, and the preset coefficient in the current target area image, the The steps of right ear position information include:

Perform spatial spectrum analysis on the right ear area in the current target area image to obtain the clarity of the right ear area;

Obtain the vertical distance of the right ear according to the area definition of the right ear, the preset standard definition, the preset standard vertical distance and the preset coefficient;

Obtain the horizontal distance of the right ear according to the abscissa value of at least one pixel in the right ear area, the preset horizontal distance between the left and right speakers, the vertical distance of the right ear, the total number of horizontal pixels of the current target area image, and the preset camera field angle;

The horizontal included angle of the right ear is obtained according to the horizontal distance of the right ear, the vertical distance of the right ear, and the preset horizontal distance between the left and right speakers.

In one embodiment, the step of judging whether the left ear region and the right ear region both exist in the current target region image according to the current recognition result includes:

Determine whether the current recognition result is the same as the recognition result corresponding to the previous sampling time;

If the current recognition result is different from the recognition result corresponding to the previous sampling time, then execute the step of judging whether both the left ear area and the right ear area in the current target area image exist according to the current recognition result;

The current recognition result is the same as the recognition result corresponding to the previous sampling time, then the current left channel signal is adjusted according to the left channel difference parameter obtained at the previous sampling time, and the adjusted left channel signal is obtained. Adjust the current right channel signal with the right channel difference parameter obtained at the moment to obtain the adjusted right channel signal;

Plays according to the adjusted left channel signal and the adjusted right channel signal.

In one embodiment, the step of obtaining the left channel difference parameter and the right channel difference parameter according to the left ear position information and the right ear position information includes:

According to the horizontal included angle of the left ear and the horizontal included angle of the right ear, obtain the angle difference between the horizontal included angle of the left ear and the horizontal included angle of the right ear;

According to the angle difference, the left ear horizontal distance, and the left ear vertical distance, query the left channel difference parameters corresponding to the angle difference, the left ear horizontal distance, and the left ear vertical distance from the preset left channel difference parameters;

According to the angle difference, the right ear horizontal distance, and the right ear vertical distance, query the right channel difference parameters corresponding to the angle difference, right ear horizontal distance and right ear vertical distance from a preset right channel difference parameter table .

In order to achieve the above object, the present application also provides a television comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor When executed, it implements the steps of the TV sound adjustment method as described above.

In order to achieve the above object, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned TV sound adjustment method are realized. .

A TV sound adjustment method, a TV, and a computer-readable storage medium proposed in the present application collect user scenes through a smart TV camera, automatically identify the position of the user's head, locate the human ears, and calculate the regional positions where the ears are located, and the The angle difference between the ears, the pre-stored phase, frequency, and gain difference parameters are called according to the area position and the angle difference between the ears; then the difference parameters are used to adjust the decoded left channel signal and right channel signal The phase, frequency and gain of the speaker are obtained, and the adjusted left channel signal and right channel signal are obtained; the adjusted left channel signal and right channel signal are driven by the left and right speakers of the speaker after driving processing, so that the user can produce sound. When the user is located in different areas and the user's head is in different directions, the tone, timbre and loudness heard are always the same as when the user is at the center of the TV, so the sound the user hears is always the same as when the user is at the center of the TV The effect of the sound heard at the same time is the same, and the "sound moves with the ear" is realized, which provides the user with a good sound effect and improves the user experience.

Description of drawings

FIG. 1 is a schematic structural diagram of a hardware operating environment involved in a solution according to an embodiment of the present application;

FIG. 2 is a schematic flowchart of the first embodiment of the TV sound adjustment method of the application;

FIG. 3 is a schematic flow chart of the refinement of step S40 in the first embodiment of the TV sound adjustment method of the present application;

FIG. 4 is a schematic flowchart of the second embodiment of the TV sound adjustment method of the present application;

FIG. 5 is a schematic flowchart of the third embodiment of the TV sound adjustment method of the present application;

FIG. 6 is a schematic flowchart of the fourth embodiment of the TV sound adjustment method of the present application.

The realization, functional characteristics and advantages of the purpose of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.

detailed description

It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of a hardware structure of a TV provided in various embodiments of the present application. The TV includes components such as a communication module 01 , a memory 02 and a processor 03 . Those skilled in the art will understand that the television shown in FIG. 1 may also include more or less components than shown, or combine certain components, or arrange different components. The processor 03 is respectively connected to the memory 02 and the communication module 01 , the memory 02 stores a computer program, and the computer program is simultaneously executed by the processor 03 .

The communication module 01 can be connected with external devices through the network. The communication module 01 can receive data sent by an external device, and can also send data, instructions and information to the external device. The external device can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, and a desktop computer.

The memory 02 can be used to store software programs and various data. The memory 02 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function (according to the left ear position information and the right ear position information, the left channel difference parameters and Right channel difference parameter) etc.; the storage data area can store data or information etc. created according to the usage of the TV. Additionally, memory 02 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The processor 03 is the control center of the TV, and uses various interfaces and lines to connect various parts of the entire TV, by running or executing the software programs and/or modules stored in the memory 02, and calling the data stored in the memory 02, Perform various functions of the TV and process data to monitor the TV as a whole. The processor 03 may include one or more processing units; preferably, the processor 03 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc. The processor mainly handles wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may also not be integrated into the processor 03 .

Although not shown in FIG. 1 , the above-mentioned television may further include a circuit control module, which is used for connecting with the commercial power to realize power control and ensure the normal operation of other components.

Those skilled in the art can understand that the TV structure shown in FIG. 1 does not constitute a limitation on the TV, and may include more or less components than the one shown, or combine some components, or arrange different components.

According to the above hardware structure, various embodiments of the method of the present application are proposed.

Referring to FIG. 2, in the first embodiment of the TV sound adjustment method of the present application, the TV sound adjustment method includes the steps:

Step S10, controlling the camera to collect the image of the target area with a preset sampling frequency;

In this solution, the TV has two left and right speakers, namely the left speaker and the right speaker, and the two speakers are in the same horizontal direction. The camera can be built-in to the TV, or it can be an external device of the TV, and the camera is located on the vertical line of the connection between the left and right speakers. The TV will control the camera to collect the image of the target area at the preset sampling frequency. The sampling frequency can be preset by the manufacturer before leaving the factory, or can be preset by the user according to the actual needs, such as the sampling frequency is 5s, and the frequency is not used here. The specific value is limited. The target area image is the image of the target area in front of the TV that is captured by the camera.

Step S20, performing image recognition on the currently collected target area image to obtain a current recognition result;

Step S30, according to the current recognition result, determine whether the left ear area and the right ear area both exist in the current target area image;

When the camera collects the image of the target area at the current sampling time, it will use face recognition technology to identify the current target area image, which can directly identify the area where the human ear is located, but because the human ear is located on both sides of the face, If the head is slightly deflected or the hair is covered, the ears may not be captured by the camera, which makes it difficult to capture the ears in most cases. Therefore, face recognition can also be performed to obtain the face in the image of the target area. It is located at a fixed position of the human face, and then can be indirectly and automatically located to the ear area of the human face according to the human face, and the ear area includes the left ear area and the right ear area. After image recognition, the current recognition result will be obtained. The current recognition result may be the left ear area and the right ear area that exist in the image of the target area. It is also possible that in some cases, only the left ear area may exist in the image of the target area. area or the right ear area. After the recognition result is obtained, it is determined whether the left ear area and the right ear area exist in the current target area image.

Step S40: Obtain left ear position information and right ear position information according to the ear area in the current target area image, the preset camera angle of view, the preset standard definition, the preset standard vertical distance, the preset horizontal distance between the left and right speakers, and the preset coefficient. Ear position information, where the left ear position information includes the vertical distance of the left ear, the horizontal distance of the left ear and the horizontal angle of the left ear, and the position information of the right ear includes the vertical distance of the right ear, the horizontal distance of the right ear and the horizontal angle of the right ear;

When it is determined that both the left ear area and the right ear area in the current target area image exist, it will be determined according to the identified left ear area, right ear area, preset camera field angle, preset standard definition, preset standard vertical distance, Preset the horizontal distance and preset coefficient of the left and right speakers, and use a specific algorithm to obtain the left ear position information and the right ear position information. The left ear position information includes the vertical distance of the left ear, the horizontal distance of the left ear and the horizontal angle of the left ear, and the position of the right ear. The information includes the vertical distance of the right ear, the horizontal distance of the right ear, and the horizontal angle of the right ear. The vertical distance of the left ear and the vertical distance of the right ear refer to the distance between the left ear and the plane where the TV is located and the distance between the right ear and the plane where the TV is located; The horizontal distance refers to the distance from the left ear to the vertical line passing through the two speakers and is perpendicular to the plane of the TV; the horizontal distance of the right ear refers to the distance from the right ear to the vertical line passing through the two speakers and is perpendicular to the TV. The distance of the plane; the horizontal angle of the left ear refers to the projection point on the plane of the point determined by the horizontal distance of the left ear and the vertical distance of the left ear on the plane that is connected to the left and right speakers and perpendicular to the TV and the left speaker respectively. The angle formed by the connection of the right speaker and the connection of the right speaker; the horizontal angle of the right ear refers to the point determined by the horizontal distance of the right ear and the vertical distance of the right ear on the plane passing through the connection of the left and right speakers and perpendicular to the TV. The projection points on the plane are respectively the included angles formed by the connection line of the left speaker and the connection line of the right speaker.

It should be noted that in the scheme of recognizing the face and then locating the ear area, more than one face may be recognized. When this happens, the preset screening rules will be used first, such as the closest to the center of the image. For example, the face with the highest definition, select a face from the identified multiple faces, and then locate the ear area according to the selected face, and obtain the ear area as the recognition result.

Specifically, please refer to FIG. 3 . FIG. 3 is a schematic flow chart of the refinement of step S40 in the first embodiment of the TV sound adjustment method according to the present application. Step S40 includes:

Step S401, when it is determined that both the left ear area and the right ear area exist, according to the left ear area, the preset camera field of view, the preset standard definition, the preset standard vertical distance, and the preset left and right speaker levels in the current target area image. Spacing and preset coefficients to obtain left ear position information;

When it is determined that both the left ear area and the right ear area exist, according to the left ear area, preset camera field angle, preset standard definition, preset standard vertical distance, preset left and right speaker horizontal spacing and preset in the current target area image. Set the coefficient and use a specific algorithm to obtain the left ear position information.

Specifically, in step S401, according to the left ear area in the current target area image, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset horizontal distance between the left and right speakers, and the preset coefficient, obtain The steps of left ear position information include:

Step S4011, performing spatial spectrum analysis on the left ear region in the current target region image to obtain the clarity of the left ear region;

Step S4012, obtaining the left ear vertical distance according to the left ear area definition, the preset standard definition, the preset standard vertical distance and the preset coefficient;

Step S4013: Obtain the left ear horizontal distance according to the abscissa value of at least one pixel in the left ear area, the preset left and right speaker horizontal distance, the left ear vertical distance, the total number of horizontal pixels of the current target area image, and the preset camera field of view. ;

Step S4014: Obtain the horizontal included angle of the left ear according to the horizontal distance of the left ear, the vertical distance of the left ear, and the preset horizontal distance between the left and right speakers.

Firstly, spatial spectrum analysis is performed on the pixels of the left ear area in the current target area image to obtain the clarity of the left ear area.

Then input the left ear area definition, preset standard definition, preset standard vertical distance and preset coefficient into the preset left ear vertical distance calculation formula to obtain the left ear vertical distance. The left ear vertical distance calculation formula is:

D _{left vertical} = β × X _left × Ds/Xs, where D _left vertical distance is the left ear, β is a preset coefficient, X _left is the clarity of the left ear area, D _s is the preset standard vertical distance, X _s is Default standard definition.

After obtaining the vertical distance of the left ear, select the pixel horizontal coordinate value of any pixel in the left ear area or obtain the average value of the pixel horizontal coordinate values of all pixels in the left ear area as the reference pixel horizontal coordinate value of the left ear area, Then input the horizontal coordinate value of the reference pixel of the left ear area, the vertical distance of the left ear, the preset horizontal distance between the left and right speakers, the total number of horizontal pixels of the current target area image and the preset camera field angle into the preset left ear horizontal distance calculation formula , obtain the horizontal distance of the left ear, where the calculation formula of the horizontal distance of the left ear is:

Among them, D _{left water} is the horizontal distance of the left ear, β is the preset coefficient, X _left is the clarity of the left ear area, D _s is the preset standard vertical distance, X _s is the preset standard definition, and θ ₀ is the preset camera. Field of view, N is the total number of horizontal pixels in the current target area image, and Nleftwater is the horizontal coordinate value of the reference pixel in the _left ear area.

After obtaining the vertical distance and horizontal distance of the left ear, finally input the horizontal distance of the left ear, the vertical distance of the left ear and the preset horizontal distance of the left and right speakers into the formula of the preset horizontal angle of the left ear, and calculate to obtain the horizontal angle of the left ear, The formula for the preset left ear horizontal angle is:

Among them, αleft is the horizontal angle of the _left ear, D _{left water} is the horizontal distance of the left ear, D _{left drop} is the vertical distance of the left ear, and D _x is the preset horizontal distance between the left and right speakers.

Step S402: Obtain right ear position information according to the right ear area, preset camera field angle, preset standard definition, preset standard vertical distance, preset horizontal distance between left and right speakers, and preset coefficients in the current target area image.

According to the right ear area, preset camera field angle, preset standard definition, preset standard vertical distance, preset left and right speaker horizontal distance and preset coefficient in the current target area image, use a specific algorithm to obtain the right ear position information .

Specifically, step S402 includes:

Step S4021, performing spatial spectrum analysis on the right ear region in the current target region image to obtain the clarity of the right ear region;

Step S4022, obtain the vertical distance of the right ear according to the area definition of the right ear, the preset standard definition, the preset standard vertical distance and the preset coefficient;

Step S4023: Obtain the horizontal distance of the right ear according to the abscissa value of at least one pixel in the right ear area, the preset horizontal distance between the left and right speakers, the vertical distance of the right ear, the total number of horizontal pixels of the current target area image, and the preset camera field of view. ;

Step S4024: Obtain the horizontal included angle of the right ear according to the horizontal distance of the right ear, the vertical distance of the right ear, and the preset horizontal distance between the left and right speakers.

Firstly, spatial spectrum analysis is performed on the pixels of the right ear area in the current target area image to obtain the clarity of the right ear area.

Then input the right ear area definition, preset standard definition, preset standard vertical distance and preset coefficient into the preset right ear vertical distance calculation formula to obtain the right ear vertical distance. The right ear vertical distance calculation formula is:

D _{right vertical} = β × X _right × Ds/Xs, where D _right vertical distance is the right ear, β is a preset coefficient, X _right is the clarity of the right ear area, D _s is the preset standard vertical distance, X _s is Default standard definition.

After obtaining the vertical distance of the right ear, select the pixel horizontal coordinate value of any pixel in the right ear area or obtain the average value of the pixel horizontal coordinate values of all pixels in the right ear area as the reference pixel horizontal coordinate value of the right ear area, Then input the horizontal coordinate value of the reference pixel of the right ear area, the vertical distance of the right ear, the preset horizontal distance between the left and right speakers, the total number of horizontal pixels of the current target area image and the preset camera field angle into the preset right ear horizontal distance calculation formula , obtain the horizontal distance of the right ear, where the calculation formula of the horizontal distance of the right ear is:

Among them, D _{right water} is the horizontal distance of the right ear, β is the preset coefficient, X _right is the definition of the right ear area, Ds is the preset standard vertical distance, Xs is the preset standard definition, and θ ₀ is the preset camera field of view angle, N is the total number of horizontal pixels in the current target area image, and N is the horizontal coordinate value of the reference pixel in the _right ear area.

After obtaining the vertical distance and horizontal distance of the right ear, finally input the horizontal distance of the right ear, the vertical distance of the right ear and the preset horizontal distance of the left and right speakers into the formula of the preset horizontal angle of the right ear, and calculate the horizontal angle of the right ear, The formula for the preset horizontal angle of the right ear is:

Among them, α _right is the horizontal angle of the right ear, D _{right water} is the horizontal distance of the right ear, D _{right drop} is the vertical distance of the right ear, and D _x is the preset horizontal distance between the left and right speakers.

Step S50, obtaining the left channel difference parameter and the right channel difference parameter according to the left ear position information and the right ear position information;

After the left ear position information and the right ear position information are obtained, the left channel difference parameter and the right channel difference parameter are obtained according to the left ear position information and the right ear position information. The left channel difference parameter includes the left channel difference phase ΔP_L , left channel difference frequency ΔF_L and left channel difference gain ΔA_L, right channel difference parameters include right channel difference phase ΔP_R, right channel difference frequency ΔF_R, right channel difference gain ΔA_R.

Specifically, step S50 includes:

Step S51, according to the horizontal angle of the left ear and the horizontal angle of the right ear, obtain the angle difference between the horizontal angle of the left ear and the horizontal angle of the right ear;

Step S52, according to the angle difference, the left ear horizontal distance and the left ear vertical distance, from the preset left channel difference parameter table, look up the angle difference, the left ear horizontal distance and the left ear vertical distance corresponding to the left sound. Road difference parameter;

Step S53, according to the angle difference, the horizontal distance of the right ear and the vertical distance of the right ear, from the preset right channel difference parameter table, query the angle difference, the horizontal distance of the right ear and the vertical distance of the right ear corresponding to the right sound. track difference parameters.

A left channel difference parameter table and a right channel difference parameter table are preset in the TV. After obtaining the position information of the left ear and the right ear, obtain the angle difference between the horizontal angle of the left ear and the horizontal angle of the right ear according to the horizontal angle of the left ear and the horizontal angle of the right ear. The difference here is the absolute difference of the values. value. A plurality of left channel difference parameters are stored in the left channel difference parameter table, and each left channel difference parameter corresponds to a different angle difference value, left ear horizontal distance and left ear vertical distance. A plurality of right channel difference parameters are stored in the right channel difference parameter table, and each right channel difference parameter corresponds to a different angle difference value, right ear horizontal distance and right ear vertical distance.

Then according to the angle difference, the left ear horizontal distance and the left ear vertical distance, the left channel difference parameters corresponding to the angle difference, the left ear horizontal distance and the left ear vertical distance are queried from the preset left channel difference parameter table. And according to the angle difference, the horizontal distance of the right ear and the vertical distance of the right ear, the right channel difference parameters corresponding to the angle difference, the horizontal distance of the right ear and the vertical distance of the right ear are inquired from the preset right channel difference parameter table.

It should be noted that the execution of step S52 and the execution of step S53 may be performed simultaneously, or step S52 may be performed first and then step S53 may be performed, or step S53 may be performed first and then step S52 may be performed, and the execution order of step S52 and step S53 is not performed here. limited.

Step S60, adjust the current left channel signal according to the left channel difference parameter, obtain the adjusted left channel signal, and adjust the current right channel signal according to the right channel difference parameter, and obtain the adjusted signal. the right channel signal;

Step S70, playing according to the adjusted left channel signal and the adjusted right channel signal.

Decoding the currently received audio signal to obtain the current left channel signal L_S and the current right channel signal R_S, the phase, frequency and gain of the current left channel signal L_S are P_L, F_L and A_L respectively, the current right channel The phase, frequency and gain of the signal R_S are P_R, F_R and A_R, respectively. The signal function of the current left channel signal L_S is expressed as:

L_S=∑H(P_L, F_L, A_L),

The signal function of the current right channel signal R_S is expressed as:

R_S=ΣH(P_R, F_R, A_R).

According to the left channel difference phase ΔP_L, left channel difference frequency ΔF_L and left channel difference gain ΔA_L in the left channel difference parameters, adjust the phase P_L, frequency F_L and gain A_L in the current left channel signal respectively, and finally output The adjusted left channel signal, the signal function of the adjusted channel signal L_C is expressed as:

L_C=∑H(P_L+ΔP_L, F_L+ΔF_L, A_L×ΔA_L),

According to the right channel difference phase ΔP_R, right channel difference frequency ΔF_R and right channel difference gain ΔA_R in the right channel difference parameter, respectively adjust the phase P_R, frequency F_R and gain A_R in the current right channel signal, and finally output The adjusted right channel signal, the signal function of the adjusted channel signal R_C is expressed as:

R_C=∑H(P_R+ΔP_R, F_R+ΔF_R, A_R×ΔA_R),

After the adjusted left channel signal L_C and right channel signal R_C are processed by signal amplification, amplitude limiting, etc., the left speaker driving signal L_D and the right speaker driving signal R_D are obtained, and finally the left speaker is driven according to the left speaker driving signal L_D for playback. , and at the same time drive the right speaker to play according to the right speaker driving signal R_D.

It should be noted that, when the determination result in step S30 is that neither the left ear region nor the right ear region exists in the current region image, the decoded left and right channel signals will not be adjusted.

In this example, the smart TV camera captures the user scene, automatically identifies the user's head position and locates the human ear, calculates the regional position where the two ears are located, and the angle difference between the two ears, according to the regional position and the angle between the two ears. Then use the difference parameters to adjust the phase, frequency and gain of the decoded left channel signal and right channel signal, and obtain the adjusted left channel signal and right channel signal. Channel signal; after the adjusted left channel signal and right channel signal are processed, the left speaker and right speaker of the speaker are driven to emit sound, so that when the user is in different areas and the user's head is in different directions, the tones heard , timbre, and loudness are always the same as when the user is at the center of the TV, so the sound that the user hears is always the same as the sound when the user is at the center of the TV. Provide users with good sound effects and improve user experience.

Further, please refer to FIG. 4. FIG. 4 is a second embodiment of the TV sound adjustment method of the present application according to the first embodiment of the television sound adjustment method of the present application. After step S30, the method further includes:

Step S41, when it is determined that only the left ear area exists in the current target area image, according to the left ear area in the current target area image, the preset camera field of view, the preset standard definition, the preset standard vertical distance, and the preset left and right speakers. Horizontal spacing and preset coefficients to obtain left ear position information;

In step S42, the position information of the right ear is obtained according to the position information of the left ear and the preset horizontal offset value.

Since the user may be in the edge area of the scene that the camera can capture or the user's face is partially covered, the camera only captures part of the user's face, so when performing image recognition on the current area image, it may only be determined that the left ear area exists. . When it is determined that there is only one left ear area in the current image of the current area, the left ear area, preset camera field of view, preset standard definition, preset standard vertical distance, preset left and right speakers in the current target area image The horizontal distance and the preset coefficient are used to obtain left ear position information. The specific algorithm and specific steps involved in the process of obtaining the left ear position information are the same as those in steps S4011 to S4013, and will not be described in detail here.

After determining the position information of the left ear, in most cases, the right ear and the left ear are in the same horizontal direction and at the same height, but the distance between the left ear and the right ear in the horizontal direction is the width of the face. According to big data analysis, the average width value of a face is obtained as the preset horizontal offset value. After the TV determines the position information of the left ear, the vertical distance of the right ear is equal to the vertical distance of the left ear.

For calculating the horizontal distance of the right ear, first, according to the position of the left ear area in the image of the current target area, you can determine whether the point projected by the left ear on the TV is in the area where the camera to the left speaker is located in the TV, or is in the area where the camera and the right speaker are located in the TV area. Then input the left ear horizontal distance and the horizontal offset value into the second preset right ear horizontal distance formula, and calculate the right ear horizontal distance. The preset right ear horizontal distance second formula is:

D _{right water} = | D _{left water} + λ ₁ D _offset |,

Among them, D _{right water} is the horizontal distance of the right ear, D _{left water} is the horizontal distance of the left ear, and D _offset is the horizontal offset value. When the point projected by the left ear on the TV is in the area between the camera and the left speaker in the TV, then λ ₁ =-1; when the point projected by the left ear on the TV is in the area where the camera to the right speaker is located in the TV, then λ ₁ =1.

The horizontal angle of the right ear is calculated by inputting the horizontal distance of the right ear, the vertical distance of the right ear and the preset horizontal distance of the left and right speakers into the formula of the preset horizontal angle of the right ear, and the preset right ear horizontal angle is calculated. The formula for the included angle is:

Among them, α _right is the horizontal angle of the right ear, D _{right water} is the horizontal distance of the right ear, D _{right drop} is the vertical distance of the right ear, and D _x is the preset horizontal distance between the left and right speakers.

This embodiment provides a strategy for obtaining left ear position information and right ear position information only according to the left ear region under the condition that only the left ear region can be obtained in the target region image.

Further, please refer to FIG. 5. FIG. 5 is a third embodiment of the TV sound adjustment method of the present application according to the first embodiment and the second embodiment of the television sound adjustment method of the present application. After step S30, the method further includes:

Step S43, when it is determined that only the right ear area exists in the current target area image, according to the right ear area, preset camera field of view, preset standard definition, preset standard vertical distance, preset left and right speakers in the current target area image Horizontal spacing and preset coefficients to obtain right ear position information;

Step S44: Obtain left ear position information according to the right ear position information and the preset horizontal offset value.

Since the user may be in the edge area of the scene that the camera can capture or the user's face is partially covered, the camera only captures part of the user's face, so when performing image recognition on the current area image, it may only be determined that the left ear area exists. . When it is determined that there is only one right ear area in the current image of the current area, the current target area image will be based on the right ear area, the preset camera field of view, the preset standard definition, the preset standard vertical distance, and the preset left and right speakers. The horizontal distance and the preset coefficient are used to obtain the position information of the right ear. The specific algorithm and specific steps involved in the process of obtaining the position information of the right ear are the same as those in steps S4021 to S4023, and will not be described in detail here.

After determining the position information of the right ear, in most cases, the right ear and the left ear are in the same horizontal direction and at the same height, but the distance between the left ear and the right ear in the horizontal direction is the width of the face. According to big data analysis, the average width value of a face is obtained as the preset horizontal offset value. After the TV determines the position information of the right ear, the vertical distance of the left ear is equal to the vertical distance of the right ear.

For calculating the horizontal distance of the left ear, first, according to the position of the image of the current target area of the right ear, it can be determined whether the point projected by the right ear on the TV is in the area where the camera and the left speaker are located in the TV, or in the TV where the camera and the right speaker are located. area. Then input the right ear horizontal distance and the horizontal offset value into the second preset left ear horizontal distance formula, and calculate the left ear horizontal distance. The preset left ear horizontal distance second formula is:

D _{left water} = |D _{right water} + λ ₂ D _offset |,

Among them, D _{left water} is the horizontal distance of the left ear, D _{right water} is the horizontal distance of the right ear, and D _offset is the horizontal offset value. When the point where the right ear is projected on the TV is in the area between the camera and the left speaker in the TV, then λ ₂ =1; when the point projected by the right ear on the TV is in the area where the camera to the right speaker is located in the TV, then λ ₂ ==-1.

The horizontal angle of the left ear is calculated by inputting the horizontal distance of the left ear, the vertical distance of the left ear and the preset horizontal distance of the left and right speakers into the formula of the preset horizontal angle of the left ear, and the preset left ear horizontal angle is calculated. The formula for the included angle is:

Among them, αleft is the horizontal angle of the _left ear, D _{left water} is the horizontal distance of the left ear, D _{left drop} is the vertical distance of the left ear, and D _x is the preset horizontal distance between the left and right speakers.

This embodiment provides a strategy for obtaining left ear position information and right ear position information only according to the right ear region when only the right ear region can be obtained in the target region image.

Further, please refer to FIG. 6 . FIG. 6 is a fourth embodiment of the TV sound adjustment method of the present application according to the aforementioned embodiment of the television sound adjustment method of the present application. In this embodiment, the steps before step S30 include:

Step S80, judging whether the current recognition result is the same as the recognition result corresponding to the previous sampling moment; the current recognition result is not the same as the recognition result corresponding to the previous sampling moment, then step S30 is performed; the current recognition result and the recognition corresponding to the previous sampling moment If the result is the same, step S81 is executed;

Step S81, adjust the current left channel signal according to the left channel difference parameter obtained at the previous sampling time, obtain the adjusted left channel signal, and adjust the current right channel signal according to the right channel difference parameter obtained at the previous sampling time. Adjust the channel signal to obtain the adjusted right channel signal;

Step S82, playing according to the adjusted left channel signal and the adjusted right channel signal.

In this embodiment, before obtaining the left ear position information and the right ear position information according to the ear area, it is first judged whether the position of the ear area in the current target area image collected at the current sampling time is the same as the ear area in the target area image sampled at the previous sampling time. Whether the positions of the regions are the same, and the current recognition result is different from the recognition result corresponding to the previous sampling time, step S30 is executed, that is, according to the current recognition result, it is judged whether both the left ear region and the right ear region exist in the current target region image.

The current recognition result is the same as the recognition result corresponding to the previous sampling time, then the currently received audio signal is decoded to obtain the current left channel signal and the current right channel signal, according to the difference of the left channel obtained at the previous sampling time The parameter adjusts the current left channel signal to obtain the adjusted left channel signal, and adjusts the current right channel signal according to the right channel difference parameter obtained at the previous sampling moment to obtain the adjusted right channel signal. Then the adjusted left channel signal and right channel signal are processed by signal amplification, amplitude limiting, etc., to obtain the left speaker drive signal and the right speaker drive signal, and finally drive the left speaker according to the left speaker drive signal for playback, and at the same time according to The right speaker drive signal drives the right speaker for playback.

In this embodiment, before determining the left ear position information and the right ear position information at each sampling moment, it is first determined whether the position of the left ear area and the position of the right ear area in the target area image collected at the current sampling moment are the same as those collected at the previous sampling moment. Whether the position of the left ear area and the position of the right ear area in the target area image are the same, in the same case, you do not need to determine the ear position information, and directly use the channel difference parameter obtained last time as the current channel difference parameter, which can reduce Calculation process, improve processing speed.

The present application also proposes a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be the memory 02 in the television of FIG. 1, or may be, for example, ROM (Read-Only Memory, read-only memory)/RAM (Random Access Memory, random access memory), magnetic disk, optical disk At least one of the computer-readable storage medium includes several pieces of information to enable the television to perform the methods described in the various embodiments of the present application.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or system comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or system. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system that includes the element.

The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course hardware can also be used, but in many cases the former is better implementation.

The above are only the preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the contents of the description and drawings of the present application, or directly or indirectly applied in other related technical fields , are similarly included within the scope of patent protection of this application.

Claims (14)

1. A TV sound adjustment method, applied to a TV, includes the steps:

   Control the camera to collect images of the target area at a preset sampling frequency;

   Perform image recognition on the currently collected target area image to obtain the current recognition result;

   According to the current recognition result, determine whether both the left ear area and the right ear area exist in the current target area image:

   When it is determined that both the left ear area and the right ear area exist, according to the preset camera field angle, preset standard definition, preset standard vertical distance, preset left and right speaker horizontal spacing, preset coefficient, Ear area and right ear area to obtain left ear position information and right ear position information, where left ear position information includes left ear vertical distance, left ear horizontal distance and left ear horizontal angle, right ear position information includes right ear vertical distance, Right ear horizontal distance and right ear horizontal angle;

   Obtain the left channel difference parameter and the right channel difference parameter according to the left ear position information and the right ear position information;

   Adjust the current left channel signal according to the left channel difference parameter to obtain the adjusted left channel signal, and adjust the current right channel signal according to the right channel difference parameter to obtain the adjusted right channel signal channel signal;

   Plays according to the adjusted left channel signal and the adjusted right channel signal.
2. The TV sound adjustment method according to claim 1, wherein when it is determined that both the left ear area and the right ear area exist, the method is based on a preset camera field angle, preset standard definition, preset standard vertical distance, preset The horizontal distance between the left and right speakers, the preset coefficient, the left ear area and the right ear area in the current target area image, and the steps of obtaining the left ear position information and the right ear position information include:

   When it is determined that both the left ear area and the right ear area exist, according to the left ear area, preset camera field angle, preset standard definition, preset standard vertical distance, preset left and right speaker horizontal spacing and preset in the current target area image. Set the coefficient to obtain the position information of the left ear;

   The position information of the right ear is obtained according to the right ear area, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset horizontal distance between the left and right speakers, and the preset coefficient in the current target area image.
3. The TV sound adjustment method according to claim 2, wherein after the step of judging whether the left ear area and the right ear area in the current target area image exist according to the current recognition result, the step further comprises:

   When it is determined that only the left ear area exists in the current target area image, according to the left ear area in the current target area image, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset left and right speaker horizontal spacing and Preset coefficients to obtain left ear position information;

   According to the left ear position information and the preset horizontal offset value, the right ear position information is obtained.
4. The TV sound adjustment method according to claim 3, wherein after the step of judging whether the left ear area and the right ear area in the current target area image exist according to the current recognition result, the step further comprises:

   When it is determined that only the right ear area exists in the current target area image, according to the right ear area in the current target area image, the preset camera field angle, the preset standard definition, the preset standard vertical distance, the preset left and right speaker horizontal spacing and Preset coefficients to obtain right ear position information;

   The left ear position information is obtained according to the right ear position information and the preset horizontal offset value.
5. The TV sound adjustment method according to any one of claims 2 to 4, wherein the method is based on the left ear area in the current target area image, the preset camera angle of view, the preset standard definition, the preset standard vertical distance, preset left and right speaker horizontal spacing and preset coefficient, and the steps of obtaining left ear position information include:

   Perform spatial spectrum analysis on the left ear area in the current target area image to obtain the clarity of the left ear area;

   Obtain left ear vertical distance according to left ear area definition, preset standard definition, preset standard vertical distance and preset coefficient;

   Obtain the left ear horizontal distance according to the abscissa value of at least one pixel in the left ear area, the preset left and right speaker horizontal distance, the left ear vertical distance, the total number of horizontal pixels of the current target area image, and the preset camera field of view;

   Obtain the horizontal angle of the left ear according to the horizontal distance of the left ear, the vertical distance of the left ear, and the preset horizontal distance of the left and right speakers.
6. The TV sound adjustment method according to any one of claims 2 to 4, wherein the method is based on the right ear area in the current target area image, the preset camera angle of view, the preset standard definition, the preset standard vertical The steps of obtaining the position information of the right ear include:

   Perform spatial spectrum analysis on the right ear area in the current target area image to obtain the clarity of the right ear area;

   Obtain the vertical distance of the right ear according to the area definition of the right ear, the preset standard definition, the preset standard vertical distance and the preset coefficient;

   Obtain the horizontal distance of the right ear according to the abscissa value of at least one pixel in the right ear area, the preset horizontal distance between the left and right speakers, the vertical distance of the right ear, the total number of horizontal pixels of the current target area image, and the preset camera field angle;

   The horizontal included angle of the right ear is obtained according to the horizontal distance of the right ear, the vertical distance of the right ear, and the preset horizontal distance between the left and right speakers.
7. The TV sound adjustment method according to claim 4, wherein the step of judging whether both the left ear area and the right ear area in the current target area image according to the current recognition result include:

   Determine whether the current recognition result is the same as the recognition result corresponding to the previous sampling time;

   If the current recognition result is different from the recognition result corresponding to the previous sampling time, the step of judging whether both the left ear area and the right ear area exist in the current target area image according to the current recognition result are performed; or

   The current recognition result is the same as the recognition result corresponding to the previous sampling time, then the current left channel signal is adjusted according to the left channel difference parameter obtained at the previous sampling time, and the adjusted left channel signal is obtained. Adjust the current right channel signal with the right channel difference parameter obtained at the moment to obtain the adjusted right channel signal;

   Plays according to the adjusted left channel signal and the adjusted right channel signal.
8. The TV sound adjustment method according to claim 4, wherein the step of obtaining the left channel difference parameter and the right channel difference parameter according to the left ear position information and the right ear position information comprises:

   According to the horizontal included angle of the left ear and the horizontal included angle of the right ear, obtain the angle difference between the horizontal included angle of the left ear and the horizontal included angle of the right ear;

   According to the angle difference, the left ear horizontal distance, and the left ear vertical distance, query the left channel difference parameters corresponding to the angle difference, the left ear horizontal distance, and the left ear vertical distance from the preset left channel difference parameters;

   According to the angle difference, the right ear horizontal distance, and the right ear vertical distance, query the right channel difference parameters corresponding to the angle difference, right ear horizontal distance and right ear vertical distance from a preset right channel difference parameter table .
9. The TV sound adjustment method according to claim 1, wherein the vertical distance of the left ear and the vertical distance of the right ear respectively refer to the distance between the left ear and the right ear from the plane where the TV is located; the horizontal distance of the left ear and the horizontal distance of the right ear respectively refer to The distance from the left ear and the right ear to the plane perpendicular to the TV through the line connecting the two speakers; the horizontal angle between the left ear refers to the distance between the left ear The projection point of the point determined by the distance and the vertical distance of the left ear on the plane is the angle formed by the connection of the left speaker and the connection of the right speaker; On the plane of the TV, the projection point of the point determined by the horizontal distance of the right ear and the vertical distance of the right ear on the plane is the angle formed by the connection line of the left speaker and the connection line of the right speaker respectively.
10. The TV sound adjustment method according to claim 5, wherein the calculation formula of the vertical distance of the left ear is:

    D _{left vertical} = β × X _left × Ds/Xs, where D _left vertical distance is the left ear, β is a preset coefficient, X _left is the clarity of the left ear area, D _s is the preset standard vertical distance, X _s is Default standard definition.
11. The TV sound adjustment method according to claim 5, wherein the left ear horizontal distance calculation formula is:

    

    Among them, D _{left water} is the horizontal distance of the left ear, β is the preset coefficient, X _left is the clarity of the left ear area, D _s is the preset standard vertical distance, X _s is the preset standard definition, and θ ₀ is the preset camera. Field of view, N is the total number of horizontal pixels in the current target area image, and Nleftwater is the horizontal coordinate value of the reference pixel in the _left ear area.
12. The TV sound adjustment method according to claim 1, wherein the formula of the horizontal angle of the left ear is:

    

    Among them, αleft is the horizontal angle of the _left ear, D _{left water} is the horizontal distance of the left ear, D _{left drop} is the vertical distance of the left ear, and D _x is the preset horizontal distance between the left and right speakers.
13. A television, wherein the television comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implements the method of claim 1 Steps of the television sound adjustment method described in any one of to 12.
14. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the television sound adjustment method according to any one of claims 1 to 12 is realized A step of.

Images