Subtitle display method and system

Abstract

The present invention proposes a subtitle display method and system. Based on the face positioning point data of the spokesperson, positioning and calibration are performed through a preset independent large-screen position verification coordinate system to obtain the first position coordinates of the spokesperson; based on the first position coordinates of the spokesperson, subtitle coordinate points are obtained and subtitles are displayed; the change value of the spokesperson's position coordinates is captured in real time, and when the change value of the spokesperson's position coordinates exceeds the preset change threshold, the first position coordinates of the spokesperson at the current moment are updated to obtain the second position coordinates of the spokesperson; the second position coordinates of the spokesperson are used as the updated first position coordinates, and the subtitles are displayed at the corresponding updated subtitle coordinate points. The present invention solves the problem in the prior art that the position of the spokesperson changes in real time during the explanation, and the subtitles are blocked, resulting in a poor experience for the audience. The method proposed in the present invention can achieve subtitle tracking, avoid the problem of occlusion, and improve the experience of the audience.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a subtitle display method and system. Background Art

[0002] When the spokesperson needs to explain the content of a certain module on the big screen in a targeted manner in scenarios such as tourism explanations, museum exhibit explanations, and exhibition hall product explanations, subtitles and translations are needed to assist in the expression, and the spokesperson needs to walk around to introduce the content of each module. Since the position of the subtitles is fixed, the audience will not be able to see all the subtitles, which seriously affects the viewer's big-screen viewing experience.

[0003] At present, the subtitle display method adopted by the existing technology is to obtain subtitle information and display the subtitles in a fixed interval, or to display the subtitles synchronously through multi-screen display. The subtitles cannot be adjusted according to the height of the speaker or the movement of the speaker. The subtitles are generally placed at the lowest or top of the large screen, which is easily blocked by the speaker or other objects. The existing technology cannot realize the subtitle tracking of the speaker's movement display, so it cannot be used for independent super-long long screens and independent large-area large screens and other explanation equipment, which seriously affects the viewer's large-screen viewing experience. Summary of the invention

[0004] Based on the above problems, the present invention proposes a subtitle display method and system to solve the problem in the prior art that the position of the speaker changes in real time during the explanation, resulting in subtitle obstruction and poor audience experience.

[0005] To achieve the above object, an embodiment of the present invention provides a subtitle display method, comprising:

[0006] Based on the face positioning point data of the speaker, positioning calibration is performed through the preset independent large screen position verification coordinate system to obtain the first position coordinates of the speaker;

[0007] Based on the first position coordinates of the speaker, obtaining subtitle coordinate points and displaying subtitles;

[0008] Capturing the change value of the speaker's position coordinate in real time, and when the change value of the speaker's position coordinate exceeds a preset change threshold, updating the speaker's first position coordinate at the current moment to obtain the speaker's second position coordinate;

[0009] The second position coordinates of the speaker are used as updated first position coordinates, and the subtitles are displayed at the corresponding updated subtitle coordinate points.

[0010] Furthermore, based on the face positioning point data of the spokesperson, positioning calibration is performed through a preset independent large screen position verification coordinate system to obtain the first position coordinates of the spokesperson, specifically:

[0011] Based on the preset independent large screen coordinate system, obtain the speaker's face positioning point data;

[0012] Based on a preset independent large-screen position verification coordinate system, the spokesperson's face positioning point data is calibrated and abnormal data values ​​are corrected to obtain the spokesperson's first position coordinates.

[0013] Furthermore, based on the first position coordinates of the speaker, obtaining the subtitle coordinate points and displaying the subtitles is specifically as follows:

[0014] Based on the position coordinates of the speaker, the horizontal coordinate value of the subtitle coordinate point is obtained by increasing or decreasing the horizontal coordinate value;

[0015] Based on the position coordinates of the speaker, the ordinate value of the subtitle coordinate point is obtained by increasing or decreasing the ordinate value;

[0016] The subtitles are displayed based on the abscissa value of the subtitle coordinate point and the ordinate value of the subtitle coordinate point.

[0017] Furthermore, the abscissa value of the subtitle coordinate point is obtained by increasing or decreasing the abscissa value based on the position coordinate of the speaker, specifically:

[0018] When the abscissa of the first position coordinate of the speaker is less than a preset first threshold, the abscissa of the position coordinate of the speaker is increased to obtain the abscissa value of the subtitle coordinate point;

[0019] When the abscissa of the first position coordinate of the speaker is greater than a preset first threshold, the abscissa of the position coordinate of the speaker is reduced to obtain the abscissa value of the subtitle coordinate point.

[0020] Furthermore, based on the position coordinates of the speaker, the ordinate value of the subtitle coordinate point is obtained by increasing or decreasing the ordinate value, specifically:

[0021] When the ordinate of the first position coordinate of the speaker is less than a preset second threshold, the ordinate value of the subtitle coordinate point is obtained by increasing the ordinate of the position coordinate of the speaker;

[0022] When the ordinate of the first position coordinate of the speaker is greater than a preset second threshold, the ordinate value of the subtitle coordinate point is obtained by reducing the ordinate of the position coordinate of the speaker.

[0023] Furthermore, the real-time capture of the speaker's position coordinate change value, when the speaker's position coordinate change value exceeds a preset change threshold, updates the speaker's first position coordinate at the current moment to obtain the speaker's second position coordinate, specifically:

[0024] Based on the change values ​​of the horizontal and vertical coordinates of the speaker's position coordinates, the change values ​​of the speaker's position coordinates are captured in real time;

[0025] When the change value of the position coordinate of the speaker exceeds the change threshold, the first position coordinate of the speaker at the current moment is updated based on the preset independent large-screen position verification coordinate system, and the second position coordinate of the speaker is obtained.

[0026] Furthermore, when the change value of the speaker's position coordinates does not exceed the change threshold or the speaker's position coordinates do not exist, the speaker's first position coordinates at the current moment are not updated and subtitles are displayed at the subtitle coordinate point corresponding to the first position coordinates.

[0027] Furthermore, the second position coordinate of the speaker is used as the updated first position coordinate, and the subtitle is displayed at the corresponding updated subtitle coordinate point, specifically:

[0028] Whenever the first position coordinate of the speaker is updated and the second position coordinate of the speaker is obtained, the second position coordinate of the speaker is iterated as the updated first position coordinate;

[0029] Based on the updated first position coordinates, the corresponding updated subtitle coordinate points are obtained and the subtitles are displayed.

[0030] Furthermore, the method further comprises the following steps:

[0031] Based on the spokesperson face recognition image acquired in real time, the spokesperson identity information is obtained by comparing it with a preset face verification image; wherein the spokesperson face recognition image includes face recognition images of several spokespersons;

[0032] According to the preset face verification images, the face recognition images of the spokesperson are verified one by one to obtain the identity verification result of the spokesperson;

[0033] Based on the speaker identity authentication result, matching the corresponding pre-stored speaker identity information;

[0034] Based on the speaker's position coordinates, the corresponding speaker identity information is bound and displayed at the subtitle coordinate point.

[0035] The embodiment of the present invention further provides a subtitle display system, comprising:

[0036] Independent large screen, face recognition module, server and voice processing module;

[0037] The independent large screen is divided into a number of equally spaced positioning intervals by a number of colored lights;

[0038] The face recognition module obtains a face image of the speaker by performing face recognition on the speaker, and sends the face image of the speaker to the server;

[0039] The face recognition module obtains the first position coordinates of the speaker by identifying the position of the speaker in the positioning interval and sends the coordinates to the server;

[0040] The voice processing module is used to convert the speaker's voice information into text information, and send the text information to the server;

[0041] The server verifies the identity of the speaker by receiving the speaker's facial image; the server generates subtitle coordinate points by receiving the speaker's position coordinates; and the server displays the received text information at a corresponding position on the independent large screen based on the subtitle coordinate points.

[0042] Beneficial effects:

[0043] (1) The embodiment of the present invention proposes a subtitle display method, which can accurately obtain the speaker's position information by obtaining the speaker's face positioning point data and calibrating it based on the verification coordinate system, and adjust the subtitle generation position so that the subtitle is not blocked; at the same time, based on the preset change threshold, the speaker's position coordinates and subtitle display coordinates are updated in real time, so that the subtitles can be tracked during the speaker's actions, and the problem of blockage will not occur, thereby improving the audience's experience;

[0044] (2) The embodiment of the present invention provides a subtitle display method. Whenever the speaker position information is updated, the speaker position information is calibrated and corrected based on a preset independent large screen position verification coordinate system, thereby improving the accuracy of speaker position acquisition, so that the subtitle display will not be biased when the speaker position changes, reducing the problem of subtitles being blocked, and improving the viewer experience;

[0045] (3) The embodiment of the present invention provides a subtitle display method, which determines the size of the speaker's horizontal and vertical coordinates relative to a preset first threshold and a preset second threshold, and obtains subtitle coordinate values ​​based on the increase and decrease of the horizontal and vertical coordinate values ​​of the speaker's position, so that the subtitles are displayed as centered as possible, avoiding the problem of missing subtitles or subtitle obstruction when the speaker stands at the edge of the large screen, thereby improving the viewer's experience;

[0046] (4) The embodiment of the present invention proposes a subtitle display method, which also considers the problem that when the speaker's position moves slightly or his face rotates so that the face is not recognized, the subtitle display changes frequently or the subtitles are not displayed. By not updating the speaker's position when the change threshold is not exceeded or the speaker's position coordinates do not exist, the subtitles are displayed at the subtitle coordinate point corresponding to the position coordinates at the moment before the change occurs, thereby improving the audience's experience.

[0047] (5) The embodiment of the present invention proposes a subtitle display method, which also obtains the identity information of the speaker through face recognition and identity authentication matching. This is beneficial for accurately matching the speech subtitles of the corresponding speakers when multiple speakers appear during the large-screen explanation, and avoids the problem of frequent changes in subtitles due to multiple speakers explaining at the same time. In addition, when the heights of multiple speakers are different, the subtitle display will be adjusted according to the position information of the corresponding speaker, thereby reducing the problem of subtitles being blocked and improving the audience's experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic flow chart of subtitle display steps of a subtitle display method provided in one embodiment of the present invention;

[0049] Figure 2 A schematic flow chart of identity authentication steps of a subtitle display method provided in one embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the module structure of a subtitle display system provided by an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of an application example of a subtitle display method provided by a certain embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] At present, the existing large-screen subtitles can only be displayed in a fixed position on the large screen. When the speaker needs to explain the content of a certain module on the large screen in a targeted manner in scenarios such as tourism explanations, museum exhibits explanations, and exhibition hall product explanations, subtitles and translations are needed for auxiliary expression, and the speaker needs to walk around to introduce the content of each module. The existing technology cannot achieve subtitle tracking of the speaker's movement, so it cannot be used on products such as super-long screens and large-area screens. In addition, since the subtitles cannot be adjusted according to the height of the speaker, the subtitles are generally placed at the lowest or top of the large screen, which is easily blocked by the speaker or other objects, resulting in a poor viewing experience for the audience.

[0054] In order to solve the above problems, an embodiment of the present invention proposes a display method and system for solving the problem that the position of the speaker changes in real time during the explanation, resulting in subtitles being blocked and causing poor audience experience.

[0055] See also Figure 4 , Figure 4 Schematic diagram of an application example of a subtitle display method provided by a certain embodiment of the present invention; in this embodiment, the following Figure 4 The subtitle display example shown explains a subtitle display method proposed in an embodiment of the present invention.

[0056] Example 1

[0057] See also Figure 1 , Figure 1 A flowchart of subtitle display steps of a subtitle display method provided by an embodiment of the present invention. Figure 1 As shown, the present invention proposes a subtitle display method, including steps 101 to 104, each step is specifically as follows:

[0058] Step 101, based on the face positioning point data of the speaker, positioning calibration is performed through a preset independent large screen position verification coordinate system to obtain the first position coordinates of the speaker;

[0059] As an example of this embodiment, based on the preset independent large screen coordinate system, the spokesperson's face positioning point data is obtained; based on the preset independent large screen position verification coordinate system, the spokesperson's face positioning point data is calibrated and abnormal data values ​​are corrected to obtain the spokesperson's first position coordinates. Figure 4 In the figure, colored lights are installed on the top of the large screen. On the virtual large screen, vertical lines are drawn according to the colored lights to divide the large screen into multiple intervals, and the interval numbers are defined. The red light to the yellow light is the first interval, the yellow to the blue light is the second interval, and so on; the number of white lights between two colored lights is the interval subdivision accuracy. The more white lights, the more accurate the positioning; when the camera captures the large screen, it determines the specific interval number of the speaker by identifying between which two colored lights the speaker is, and then determines the precise position of the speaker according to the position of the white light in the interval, that is, the speaker’s first position coordinate (X1, Y1).

[0060] Step 102, based on the first position coordinates of the speaker, obtaining subtitle coordinate points and displaying subtitles;

[0061] As an example of this embodiment, based on the position coordinates of the speaker, the horizontal coordinate value of the subtitle coordinate point is obtained by increasing or decreasing the horizontal coordinate value; based on the position coordinates of the speaker, the vertical coordinate value of the subtitle coordinate point is obtained by increasing or decreasing the vertical coordinate value; based on the horizontal coordinate value of the subtitle coordinate point and the vertical coordinate value of the subtitle coordinate point, the subtitle is displayed. Specifically, through step 101, the first position coordinates (X1, Y1) of the speaker are obtained, and parameters a and b are introduced to obtain the horizontal and vertical coordinate values ​​(X1+a, Y1+b) of the subtitle to determine the position of the subtitle, and the position information of the speaker and the subtitle are associated to form subtitles that can be tracked and displayed in real time according to the speaker's face recognition position, and then the subtitle information of the corresponding position is sent to the large screen for display.

[0062] As another example of this embodiment, when the horizontal coordinate of the first position coordinate of the speaker is less than the preset first threshold, the horizontal coordinate of the speaker's position coordinate is increased to obtain the horizontal coordinate value of the subtitle coordinate point; when the horizontal coordinate of the first position coordinate of the speaker is greater than the preset first threshold, the horizontal coordinate of the speaker's position coordinate is reduced to obtain the horizontal coordinate value of the subtitle coordinate point. When the vertical coordinate of the first position coordinate of the speaker is less than the preset second threshold, the vertical coordinate of the speaker's position coordinate is increased to obtain the vertical coordinate value of the subtitle coordinate point; when the vertical coordinate of the first position coordinate of the speaker is greater than the preset second threshold, the vertical coordinate of the speaker's position coordinate is reduced to obtain the vertical coordinate value of the subtitle coordinate point. Specifically, an X2 coordinate information is set on the X-axis of the large screen, and the X2 can be adjusted according to the actual large-screen application. When 0≤X1≤X2, the (X1+a, Y1+b) coordinate point is generated on the right side of the (X1, Y1) coordinate point, and the subtitles are generated from the (X1+a, Y1+b) coordinate point; when X1>X2, the (X1-m, Y1-n) coordinate point is generated on the left side of the (X1, Y1) coordinate point, and the subtitles are generated from the (X1-m, Y1-n) coordinate point, where parameters a, b, m, and n are all values ​​that are increased or decreased according to the speaker's first position coordinates. Similarly, a Y2 coordinate information can be set at the Y coordinate of the large screen. When 0≤Y1≤Y2, a (X1+a, Y1+b) or (X1-m, Y1+b) coordinate point is generated above the (X1, Y1) coordinate point, and the subtitles are generated from the (X1+a, Y1+b) or (X1-m, Y1+b) coordinate point; when Y1>Y2, a (X1-m, Y1-n) or (X1+a, Y1-n) coordinate point is generated below the (X1, Y1) coordinate point, and the subtitles are generated from the (X1-m, Y1-n) or (X1+a, Y1-n) coordinate point. When determining the Y-axis coordinate, the determination of the X-axis coordinate needs to be synchronized. The ultimate goal is to make the subtitles displayed as centered as possible to avoid missing or blocking the subtitle display when the speaker is at the edge of the screen. The centering mentioned here means: as close to the middle of the screen as possible.

[0063] Step 103, capturing the change value of the speaker's position coordinate in real time, and when the change value of the speaker's position coordinate exceeds a preset change threshold, updating the speaker's first position coordinate at the current moment to obtain the speaker's second position coordinate;

[0064] As an example of this embodiment, based on the change value of the horizontal and vertical coordinates of the speaker's position coordinates, the speaker's position coordinate change value is captured in real time; when the speaker's position coordinate change value exceeds the change threshold, the speaker's first position coordinate at the current moment is updated based on the preset independent large screen position verification coordinate system, and the speaker's second position coordinate is obtained. When the speaker's position coordinate change value does not exceed the change threshold or the speaker's position coordinate does not exist, the speaker's first position coordinate at the current moment is not updated and the subtitles are displayed at the subtitle coordinate point corresponding to the first position coordinate. Specifically, when performing face recognition, a dotted frame (a dotted frame constructed according to a preset change threshold) is generated on the face part. When the speaker's face recognition position exceeds the dotted frame (that is, when the speaker's position coordinate change value exceeds the change threshold), the speaker's (X1, Y1) coordinate point value is updated to obtain the speaker's second position coordinate; when the speaker's face position does not exceed the dotted frame or turns his head and disappears in the dotted frame (that is, when the speaker's position coordinate change value does not exceed the change threshold or the speaker's position coordinate does not exist), the speaker's first position information (X1, Y1) coordinate point remains unchanged and the corresponding subtitles are still displayed according to the speaker's first position information (X1, Y1) coordinate point.

[0065] Step 104: Use the second position coordinates of the speaker as updated first position coordinates, and display the subtitles at the corresponding updated subtitle coordinate points.

[0066] As an example of this embodiment, whenever the speaker's first position coordinates are updated and the speaker's second position coordinates are obtained, the speaker's second position coordinates are iterated as the updated first position coordinates; based on the updated first position coordinates, the corresponding updated subtitle coordinate points are obtained and the subtitles are displayed. Specifically, when the speaker's face recognition position exceeds the dotted box (that is, when the speaker's position coordinate change value exceeds the change threshold), the speaker's (X1, Y1) coordinate point value is updated to obtain the speaker's second position coordinates (X1', Y1'), and the obtained speaker's second position coordinates (X1', Y1') are used as the updated first position coordinates (X1', Y1'), and the subtitles are also displayed at the corresponding position according to the updated first position coordinates (X1', Y1'). After obtaining the updated first position coordinates, the updated first position coordinates are continuously monitored to see if they exceed the change threshold.

[0067] See also Figure 2 , Figure 2 A flowchart of identity authentication steps of a subtitle display method provided by an embodiment of the present invention; Figure 2 As shown, a subtitle display method proposed in an embodiment of the present invention further includes: Step 105 to Step 108, each step is specifically as follows:

[0068] Step 105, based on the spokesperson face recognition image acquired in real time, by comparing it with a preset face verification image, the spokesperson identity information is acquired; wherein the spokesperson face recognition image includes face recognition images of several spokespersons;

[0069] Step 106, verifying the spokesperson's facial recognition images one by one according to the preset facial verification images to obtain a spokesperson's identity verification result;

[0070] Step 107, matching the corresponding pre-stored speaker identity information based on the speaker identity authentication result;

[0071] Step 108: Based on the speaker's position coordinates, the corresponding speaker identity information is bound and displayed at the subtitle coordinate point.

[0072] As an example of this embodiment, by uploading multiple photos and names or business card information of speakers, the positions of multiple speakers can be identified based on facial recognition, and multiple subtitles can be displayed at the same time. The subtitles are displayed based on the speaker's lip shape to determine whether the speaker is speaking, and the speaker's name can be displayed in the front part of the subtitles or the content of the speaker's business card can be displayed above the speaker's head. The specific implementation method of facial recognition verification can be achieved by technical means commonly used in the field, which will not be repeated here.

[0073] As another example of this embodiment, for the method of generating subtitles, the specific implementation method is: converting the content spoken by the speaker into subtitle text through voice conversion, and then matching the corresponding speaker identity information. When the subtitles are displayed, the speaker identity information and the subtitle text are displayed at the same time; the embodiment of the present invention can also add a translation function to translate the corresponding subtitle text into the language required by the viewer, and finally realize the display of the speaker identity information, subtitle text and the corresponding translation of the subtitle text on the large screen.

[0074] The embodiment of the present invention proposes a subtitle display method, which can accurately obtain the speaker's position information by acquiring the speaker's face positioning point data and calibrating it based on the verification coordinate system, and adjust the subtitle generation position so that the subtitles are not blocked; at the same time, based on the preset change threshold, the speaker's position coordinates and subtitle display coordinates are updated in real time, so that the subtitles can be tracked during the speaker's actions, and there will be no problem of obstruction, thereby improving the audience's experience; whenever the speaker's position information is updated, the speaker's position information is calibrated and corrected based on the preset independent large-screen position verification coordinate system, thereby improving the accuracy of speaker position acquisition, so that the subtitle display will not be biased due to the change of the speaker's position, reducing the problem of subtitles being blocked, and improving the viewer's experience; by judging the size of the speaker's horizontal and vertical coordinates relative to the preset first threshold and the preset second threshold, the subtitle coordinates are obtained based on the increase and decrease of the horizontal and vertical coordinate values ​​of the speaker's position. The value is set so that the subtitles are displayed in the center as much as possible, avoiding the problem of missing subtitles or subtitle obstruction when the speaker stands at the edge of the large screen, thereby improving the viewer's experience; the problem of frequent changes in subtitle display or no subtitle display when the speaker's position moves slightly or his face rotates so that the face is not recognized is also considered. By not updating the speaker's position when it does not exceed the change threshold or the speaker's position coordinates do not exist, the subtitles are displayed at the subtitle coordinate point corresponding to the position coordinates at the moment before the change occurs, thereby improving the audience's experience; the speaker's identity information is obtained through face recognition identity authentication matching, which is conducive to accurately matching the corresponding speaker's speech subtitles when multiple speakers appear during the large-screen explanation, and there will be no problem of frequent changes in subtitles due to multiple people explaining at the same time. When the heights of multiple speakers are different, the subtitle display will be adjusted according to the corresponding speaker's position information, reducing the problem of subtitles being blocked and improving the audience's experience.

[0075] Example 2

[0076] See also Figure 3 , Figure 3 A schematic diagram of the module structure of a subtitle display system provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides a subtitle display system, including:

[0077] Independent large screen 301, face recognition module 302, server 303 and voice processing module 304;

[0078] The independent large screen 301 is divided into a number of equally spaced positioning intervals by a number of colored lights;

[0079] The face recognition module 302 obtains a face image of the speaker by performing face recognition on the speaker, and sends the face image of the speaker to the server 303;

[0080] The face recognition module 302 obtains the first position coordinates of the speaker by identifying the position of the speaker in the positioning interval and sends the coordinates to the server 303;

[0081] The voice processing module 304 is used to convert the speaker's voice information into text information, and send the text information to the server 303;

[0082] The server 303 verifies the identity of the speaker by receiving the speaker's facial image; the server 303 generates subtitle coordinate points by receiving the speaker's position coordinates; and the server 303 displays the received text information at the corresponding position of the independent large screen 301 based on the subtitle coordinate points.

[0083] As an example of this embodiment, the subtitle display system also includes: a management platform 305 and a sound receiving and amplifying device 306; the management platform 305 is used to construct the preset independent large screen position verification coordinate system and to set the horizontal and vertical coordinate values ​​of the subtitle display; the sound receiving and amplifying device 306 is used to pick up the speaker's voice through a microphone, send the audio signal to the sound reinforcement host for processing, send an audio signal to the speaker for amplification, and send another audio signal to the voice processing module 304 for voice transcription.

[0084] A subtitle display system described in an embodiment of the present invention can be used to execute a subtitle display method proposed in an embodiment of the present invention. By acquiring the face positioning point data of the spokesperson and calibrating it based on a verification coordinate system, the spokesperson position information can be accurately acquired, and the subtitle generation position can be adjusted so that the subtitles are not blocked; at the same time, based on a preset change threshold, the spokesperson position coordinates and subtitle display coordinates are updated in real time, so that the subtitles can be tracked during the spokesperson's actions, and there will be no problem of blockage, thereby improving the audience's experience; whenever the spokesperson position information is updated, the spokesperson position information is calibrated and corrected based on a preset independent large-screen position verification coordinate system, thereby improving the accuracy of the spokesperson position acquisition, so that the subtitle display will not be biased due to the change of the spokesperson position, reducing the problem of subtitles being blocked, and improving the viewer's experience; by judging the size of the spokesperson's horizontal and vertical coordinates relative to the preset first threshold and the preset second threshold, based on the horizontal and vertical coordinate values ​​of the spokesperson's position The subtitle coordinate value is obtained by increasing and decreasing the subtitle coordinate value, so that the subtitles are displayed in the center as much as possible, avoiding the problem of missing subtitles or subtitle obstruction when the speaker stands at the edge of the large screen, thereby improving the viewer's experience; the problem of frequent changes in subtitle display or non-display of subtitles when the speaker's position moves a small range or the face rotates so that the face is not recognized is also considered. By not updating the speaker's position when it does not exceed the change threshold or the speaker's position coordinates do not exist, the subtitles are displayed at the subtitle coordinate point corresponding to the position coordinates at the moment before the change occurs, thereby improving the audience's experience; the speaker's identity information is obtained through face recognition identity authentication matching, which is conducive to accurately matching the corresponding speaker's speech subtitles when multiple speakers appear during the large-screen explanation, and there will be no problem of frequent changes in subtitles due to multiple people explaining at the same time. When the heights of multiple speakers are different, the subtitle display will be adjusted according to the position information of the corresponding speaker, thereby reducing the problem of subtitles being blocked and improving the audience's experience.

[0085] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0086] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0087] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

Claims

1. A subtitle display method, characterized in that: The following steps are involved: Based on the face positioning point data of the spokesperson, positioning calibration is performed through the preset independent large screen position verification coordinate system to obtain the spokesperson's first position coordinates; specifically, colored lights are installed on the top of the large screen, and vertical lines are drawn on the virtual large screen according to the colored lights to divide the large screen into multiple intervals, and the interval numbers are defined. The number of white lights between two colored lights is the interval subdivision accuracy. When the camera captures the large screen, the specific interval number of the spokesperson is determined by identifying between which two colored lights the spokesperson is, and then the spokesperson's first position coordinates are determined according to the position of the white light in the interval; Based on the first position coordinates of the speaker, obtaining subtitle coordinate points and displaying subtitles; Capturing the change value of the speaker's position coordinate in real time, and when the change value of the speaker's position coordinate exceeds a preset change threshold, updating the speaker's first position coordinate at the current moment to obtain the speaker's second position coordinate; Using the second position coordinates of the speaker as updated first position coordinates, and displaying the subtitles at the corresponding updated subtitle coordinate points; The subtitle display method also includes the following steps: based on the real-time acquired spokesperson face recognition image, by comparing it with a preset face verification image, obtaining the spokesperson identity information; wherein the spokesperson face recognition image includes face recognition images of several spokespersons; according to the preset face verification image, verifying the spokesperson face recognition images one by one to obtain the spokesperson identity verification result; based on the spokesperson identity verification result, matching the corresponding pre-stored spokesperson identity information; based on the spokesperson's position coordinates, binding the corresponding spokesperson identity information and displaying it at the subtitle coordinate point.

2. A subtitle display method as claimed in claim 1, characterized in that: The acquiring of the subtitle coordinate points and displaying of the subtitles based on the first position coordinates of the speaker is specifically as follows: Based on the position coordinates of the speaker, the horizontal coordinate value of the subtitle coordinate point is obtained by increasing or decreasing the horizontal coordinate value; Based on the position coordinates of the speaker, the ordinate value of the subtitle coordinate point is obtained by increasing or decreasing the ordinate value; The subtitles are displayed based on the abscissa value of the subtitle coordinate point and the ordinate value of the subtitle coordinate point.

3. A subtitle display method as claimed in claim 2, characterized in that: The abscissa value of the subtitle coordinate point is obtained by increasing or decreasing the abscissa value based on the position coordinate of the speaker, specifically: When the abscissa of the first position coordinate of the speaker is less than a preset first threshold, the abscissa of the position coordinate of the speaker is increased to obtain the abscissa value of the subtitle coordinate point; When the abscissa of the first position coordinate of the speaker is greater than a preset first threshold, the abscissa of the position coordinate of the speaker is reduced to obtain the abscissa value of the subtitle coordinate point.

4. A subtitle display method as claimed in claim 2, characterized in that: Based on the position coordinates of the speaker, the ordinate value of the subtitle coordinate point is obtained by increasing or decreasing the ordinate value, specifically: When the ordinate of the first position coordinate of the speaker is less than a preset second threshold, the ordinate value of the subtitle coordinate point is obtained by increasing the ordinate of the position coordinate of the speaker; When the ordinate of the first position coordinate of the speaker is greater than a preset second threshold, the ordinate value of the subtitle coordinate point is obtained by reducing the ordinate of the position coordinate of the speaker.

5. A subtitle display method as claimed in claim 1, characterized in that: The real-time capture of the speaker's position coordinate change value, when the speaker's position coordinate change value exceeds a preset change threshold, updates the speaker's first position coordinate at the current moment to obtain the speaker's second position coordinate, specifically: Based on the change values ​​of the horizontal and vertical coordinates of the speaker's position coordinates, the change values ​​of the speaker's position coordinates are captured in real time; When the change value of the position coordinate of the speaker exceeds the change threshold, the first position coordinate of the speaker at the current moment is updated based on the preset independent large-screen position verification coordinate system, and the second position coordinate of the speaker is obtained.

6. A subtitle display method as claimed in claim 5, characterized in that: Also includes: When the change value of the speaker's position coordinate does not exceed the change threshold or the speaker's position coordinate does not exist, the speaker's first position coordinate is not updated at the current moment and subtitles are displayed at the subtitle coordinate point corresponding to the first position coordinate.

7. A subtitle display method as claimed in claim 1, characterized in that: The second position coordinate of the speaker is used as the updated first position coordinate, and the subtitle is displayed at the corresponding updated subtitle coordinate point, specifically: Whenever the first position coordinate of the speaker is updated and the second position coordinate of the speaker is obtained, the second position coordinate of the speaker is iterated as the updated first position coordinate; Based on the updated first position coordinates, the corresponding updated subtitle coordinate points are obtained and the subtitles are displayed.

8. A subtitle display system, characterized in that: A subtitle display method as claimed in any one of claims 1 to 7 may be performed, comprising: Independent large screen, face recognition module, server and voice processing module; The independent large screen is divided into a number of equally spaced positioning intervals by a number of colored lights; The face recognition module obtains a face image of the speaker by performing face recognition on the speaker, and sends the face image of the speaker to the server; The face recognition module obtains the first position coordinates of the speaker by identifying the position of the speaker in the positioning interval and sends the coordinates to the server; The voice processing module is used to convert the speaker's voice information into text information, and send the text information to the server; The server verifies the identity of the speaker by receiving the speaker's facial image; the server generates subtitle coordinate points by receiving the speaker's position coordinates; and the server displays the received text information at a corresponding position on the independent large screen based on the subtitle coordinate points.

Images