Video shooting method and device, terminal, storage medium and program product

By recognizing the content of the scene in real-time video streams and automatically adjusting shooting parameters, the problem of users having to make frequent manual adjustments when shooting concert or sports event videos is solved, improving video quality and efficiency, especially reducing moiré interference in audience seating and electronic screen scenarios.

CN118921553APending Publication Date: 2024-11-08REALME MOBILE TELECOMM SHENZHEN CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411140850.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

During concert or sporting event video recording, users need to frequently manually adjust shooting parameters when switching between different scenes, resulting in poor video quality and cumbersome operation. Moiré patterns are particularly common when switching to electronic screens, making it difficult for ordinary users to determine the optimal shooting parameters.

Method used

By identifying the type of content in the real-time video stream and automatically adjusting the corresponding shooting parameters, including focal length, aperture, and shutter speed, the system ensures that different content types use the most suitable shooting parameters and avoids moiré interference.

Benefits of technology

It improves video shooting quality, reduces manual operation by users, and increases shooting efficiency, especially significantly improving the picture quality in audience seating and electronic screen scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921553A_ABST
    Figure CN118921553A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a video shooting method and device, a terminal, a storage medium and a program product, and relates to the technical field of terminals. The method comprises the following steps: displaying a video shooting interface; identifying the content type of the picture content contained in the video picture based on the real-time video stream under the condition of the performance shooting scene; the shooting parameters corresponding to the content types are adopted for video shooting, and different content types correspond to different shooting parameters. By adopting the video shooting method provided by the invention, the shooting quality of picture contents of different content types can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of terminal technology, and in particular to a video shooting method, device, terminal, storage medium and program product. Background Art

[0002] Users can use the terminal to shoot videos in different scenes, for example, in concert scenes or event scenes. In the same scene, users may need to shoot different types of content. For example, in a concert scene, users need to shoot the stage when the star is performing, the audience seats when fans are cheering or singing, and the electronic screen when the electronic screen is playing content.

[0003] During video shooting, when the screen content switches, users usually need to manually adjust shooting parameters such as focal length, shutter, focus area, sensitivity, etc. to improve the video shooting quality. Summary of the invention

[0004] The embodiments of the present application provide a video shooting method, device, terminal, storage medium and program product. The technical solution is as follows:

[0005] On the one hand, an embodiment of the present application provides a video shooting method, the method comprising:

[0006] Display the video shooting interface;

[0007] In the case of a performance or event shooting scene, the content type of the video content contained in the video screen is identified based on the real-time video stream;

[0008] The video is shot using shooting parameters corresponding to the content type, wherein different content types correspond to different shooting parameters.

[0009] On the other hand, an embodiment of the present application provides a video shooting device, the device comprising:

[0010] Display module, used to display the video shooting interface;

[0011] An identification module is used to identify the content type of the picture content contained in the video picture based on the real-time video stream in the case of a performance or event shooting scene;

[0012] The shooting module is used to shoot the video using shooting parameters corresponding to the content type, wherein different content types correspond to different shooting parameters.

[0013] On the other hand, an embodiment of the present application provides a terminal, which includes a processor and a memory, wherein the memory stores at least one computer instruction, and the at least one computer instruction is loaded and executed by the processor to implement the method described in the above aspect.

[0014] On the other hand, an embodiment of the present application provides a computer-readable storage medium, in which at least one computer instruction is stored. The computer instruction is loaded and executed by a processor to implement the method described in the above aspects.

[0015] On the other hand, an embodiment of the present application provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a terminal reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the terminal executes the method provided in various optional implementations of the above aspects.

[0016] In an embodiment of the present application, in the case of a performance or event shooting scene, the content type of the video content contained in the video screen is identified based on the real-time video stream, and the video is shot using shooting parameters corresponding to the content type. Since different content types correspond to different shooting parameters, when shooting the current content type, the shooting parameters that are most suitable for the current content type can be used to maximize the quality of the current video screen. In the case of a switch in the content type, the video is shot using the switched shooting parameters, which can improve the shooting quality of the video on the one hand, and avoid frequent manual operations by the user on the other hand, thereby achieving high shooting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 is a flow chart of a video shooting method provided by an exemplary embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of an exemplary embodiment of the present application providing that a user triggers an option control corresponding to a performance event shooting mode to control a terminal to enter a performance event shooting scene;

[0020] Figure 3 It is a schematic diagram of a terminal using a first shooting parameter to shoot a video when the content type is a performance event venue type, provided by an exemplary embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of a terminal using a second shooting parameter to shoot a video when the content type is an auditorium type, provided by an exemplary embodiment of the present application;

[0022] Figure 5 It is a schematic diagram of using a third shooting parameter to shoot a video when the content type is an electronic screen type, provided by an exemplary embodiment of the present application;

[0023] Figure 6 is a flowchart of determining a third shooting parameter provided by an exemplary embodiment of the present application;

[0024] Figure 7 is a flow chart of a video shooting method provided by another exemplary embodiment of the present application;

[0025] Figure 8 is a structural block diagram of a video shooting device provided by an exemplary embodiment of the present application;

[0026] Fig. 9 It is a structural block diagram of a terminal device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0028] In the video shooting scenes of concerts or events, there may be many complex shooting factors, which may lead to problems such as poor video shooting effects, difficulty in post-processing, and inconvenience in adjusting parameters.

[0029] For example, when the content of the captured image switches, the user needs to frequently adjust the parameters manually so that the different image contents captured in the video can all have good shooting effects. Taking the concert scene as an example, for the stage, the video shooting needs to pay more attention to the stars; for the audience seats, it is necessary to ensure the atmosphere of the user's on-site support; for the electronic screen on the scene, the focus of the mobile phone shooting may cause moiré, so it is necessary to avoid moiré as much as possible to improve the quality of video shooting.

[0030] On the one hand, it is cumbersome for users to constantly make manual adjustments; on the other hand, users who lack shooting experience cannot directly determine the most suitable shooting parameters, resulting in poor video quality.

[0031] Therefore, the present application proposes a video shooting method for improving the video shooting quality in performance and event shooting scenarios.

[0032] See also Figure 1, Figure 1 1 is a flow chart of a video shooting method provided by an exemplary embodiment of the present application. In some embodiments, the method is performed by a terminal equipped with a camera. The method includes the following steps.

[0033] Step 101, display the video shooting interface.

[0034] Optionally, the video shooting interface may be a video shooting interface corresponding to a camera application that comes with the terminal system, or may be a video shooting interface launched by a third-party application on the terminal, for example, a short video shooting interface launched by a social application, or a long video shooting interface launched by a video application.

[0035] Optionally, when a trigger operation for the video shooting interface is received, the terminal displays the video shooting interface. For example, when the user clicks the application icon corresponding to the camera application on the terminal desktop and triggers the video shooting mode, the terminal displays the video shooting interface.

[0036] Step 102: in the case of a performance or event shooting scene, identifying the content type of the picture content contained in the video picture based on the real-time video stream.

[0037] The terminal can determine whether it is currently in a performance or event shooting scene in different ways.

[0038] In a possible implementation, the video shooting interface includes an option control corresponding to the performance event shooting mode. When the user triggers the option control corresponding to the performance event shooting mode, the terminal determines that it is in the performance event shooting scene.

[0039] See also Figure 2 , Figure 2 It is a schematic diagram of an exemplary embodiment of the present application providing a user triggering an option control corresponding to a performance event shooting mode to control a terminal to enter a performance event shooting scene.

[0040] like Figure 2 As shown, the video shooting interface includes two option controls corresponding to performance and event shooting modes, namely, option control 201 corresponding to the concert mode, and option control 202 corresponding to the sports game mode. When the user triggers option control 201, the terminal determines that it is in the performance shooting scene; when the user triggers option control 202, the terminal determines that it is in the event shooting scene.

[0041] It should be noted that Figure 2This is only an example of the option control corresponding to the performance event shooting mode, and does not constitute any limitation on determining that the performance event shooting mode is in place. For example, the terminal may combine option control 201 and option control 202 into one control, or may further distinguish option controls corresponding to different categories of performance event shooting modes (e.g., different controls for football matches, gymnastics matches, and table tennis matches), or may enter the performance event shooting mode not by setting the option control, but by entering the performance event shooting mode through a specific gesture, function button, or any other possible method, without limitation.

[0042] In a possible implementation, the terminal may also determine whether it is currently in a performance or event shooting scene based on the real-time video stream captured by the camera.

[0043] In some embodiments, the terminal is deployed with an AI content recognition model, and the AI ​​content recognition model can be used to perform content analysis on the real-time video stream to determine whether the current scene is a performance or event shooting scene.

[0044] In some embodiments, the terminal's backend server is deployed with an AI content recognition model, and the terminal can upload the real-time video stream to the backend server. The backend server uses the AI ​​content recognition model to perform content analysis on the real-time video stream to determine whether it is currently in a performance or event shooting scene, and returns the result to the terminal.

[0045] It should be noted that in the process of collecting relevant data of the user (such as real-time video stream collected by the camera), the present application may display a prompt interface, a pop-up window or output a voice prompt information, and the prompt interface, pop-up window or voice prompt information is used to prompt the user that the relevant data is currently being collected, so that the present application only starts to execute the relevant steps of obtaining the relevant data of the user after obtaining the confirmation operation issued by the user to the prompt interface or pop-up window, otherwise (that is, when the confirmation operation issued by the user to the prompt interface or pop-up window is not obtained), the relevant steps of obtaining the relevant data of the user are terminated, that is, the relevant data of the user is not obtained. In other words, the information involved in this application (including but not limited to user device information, user personal information, user's real-time location), data (including but not limited to data for analysis, data for storage, data for display, etc.) and signals are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the real-time video streams involved in this application are all obtained with full authorization.

[0046] The video images may contain images of different content types.

[0047] For example, in a video shot at a concert, there are three video frames. The first video frame shows a star dancing and singing on the stage, the second video frame shows a cheering sign in the auditorium, and the third video frame shows lyrics displayed on an electronic screen. The first video frame has a content type corresponding to the performance venue type; the second video frame has a content type corresponding to the auditorium type; and the third video frame has a content type corresponding to the electronic screen type.

[0048] In some embodiments, for the same performance event scene, the terminal may be pre-configured with different candidate content types for the performance event scene. For example, the terminal is pre-configured with five candidate content types for a diving competition scene, namely, diving platform type, swimming pool type, auditorium type, waiting room type, and electronic screen type.

[0049] Regarding the specific method of identifying the content type of the picture content contained in the video screen based on the real-time video stream, in some embodiments, in the case of a performance or event shooting scene, the video content recognition technology can be used to identify the picture content contained in the video screen based on the real-time video stream, and determine the most matching content type from at least two candidate content types in the performance or event scene based on the picture content.

[0050] Regarding the specific method of identifying the content type of the picture content contained in the video screen based on the real-time video stream, in other embodiments, the pre-trained content recognition model can also be deployed in the terminal or the background server to be used for identifying the content type of the picture content contained in the video screen based on the real-time video stream.

[0051] Step 103: Use shooting parameters corresponding to the content type to shoot the video, where different content types correspond to different shooting parameters.

[0052] Different content types may require different shooting parameters to achieve the most suitable shooting effect. For example, the performance venue type uses an ISO of 640 to achieve a good lighting effect, while the auditorium type requires an ISO of 1000 to achieve a good lighting effect; or the focal length used in the auditorium type is different from the focal length used in the electronic screen type, etc.

[0053] Optionally, shooting parameters include but are not limited to focal length, aperture size, shutter speed, sensitivity, focus, exposure, metering, white balance, shooting mode, etc.

[0054] Optionally, the shooting mode may be a mode of a camera application, such as a face focus mode, a tracking focus mode, a depth of field optimization mode, a wide-angle shooting mode, etc., and there is no limitation on this.

[0055] Optionally, the shooting mode also includes a mode corresponding to a specific shooting style, such as documentary style, artistic style, black and white style, pop style, etc., without limitation.

[0056] In a possible implementation, the terminal is pre-configured with a correspondence between at least two candidate content types and candidate shooting parameters in a performance event scenario, and determines the shooting parameters corresponding to the real-time content type based on the correspondence.

[0057] In another possible implementation, a shooting parameter recommendation model is deployed in the terminal or the backend server to recommend appropriate shooting parameters to the terminal based on the real-time video stream and the content type.

[0058] To sum up, in the case of shooting scenes of performances and events, the content type of the video content contained in the video screen is identified based on the real-time video stream, and the video is shot using the shooting parameters corresponding to the content type. Since different content types correspond to different shooting parameters, when shooting the current content type, the shooting parameters that are most suitable for the current content type can be used to maximize the quality of the current video screen. In the case of switching of the content type, the video is shot using the switched shooting parameters, which can improve the shooting quality of the video on the one hand, and avoid frequent manual operations by the user on the other hand, thereby achieving high shooting efficiency.

[0059] In some embodiments, the content type in the performance event scenario includes at least one of a performance event venue type, an auditorium type, and an electronic screen type.

[0060] Among them, when the picture content in the video screen of the real-time video stream is a performance or event venue such as a stage or a competition venue, the content type is the performance or event venue type; when the picture content in the video screen of the real-time video stream is an auditorium, the content type is the auditorium type; when the picture content in the video screen of the real-time video stream is an electronic screen, the content type is the electronic screen type.

[0061] In some embodiments, when the content type is a performance event venue type, the terminal uses a first shooting parameter to shoot the video.

[0062] Among them, the first shooting parameter is used to focus on the core elements in the performance and event venue.

[0063] For example, in a concert scene, the core element is the face of a celebrity; in a sports game, the core element is an element related to the sports game, such as football or basketball.

[0064] Optionally, the first shooting parameter is used to implement focusing on a core element, or to track a focusing core element.

[0065] Exemplarily, the first shooting parameter may include a focus position parameter and a focus mode parameter (eg, single focus AF-S or continuous auto focus AF-C).

[0066] See also Figure 3 , Figure 3 It is a schematic diagram of a terminal using a first shooting parameter to shoot a video when the content type is a performance event venue type, provided by an exemplary embodiment of the present application.

[0067] like Figure 3 As shown, the terminal determines that the content type corresponding to the screen content of the video screen is a performance event venue type based on the real-time video stream, so the first shooting parameter is used for video shooting. The first shooting parameter can achieve a focus effect on the face of the celebrity, so the part of the video shooting the stage can more clearly highlight the face of the celebrity, thereby improving the quality of video shooting.

[0068] Regarding the specific way in which the terminal uses the first shooting parameter to shoot video, in some embodiments, when the performance event shooting scene is a concert scene and the content type is a performance event venue type, the terminal performs face recognition on the video screen to obtain a face recognition result; when the face recognition result indicates that the video screen contains a target face, the first shooting parameter is used to focus on the target face and shoot the video.

[0069] Regarding the method of determining the target face, in one possible implementation, when the content type is a performance event venue type, the terminal determines the performer information of the concert scene based on the geographic location information and time information, and obtains the target face based on the performer information.

[0070] Exemplarily, when the user turns on the option control corresponding to the concert mode, the terminal obtains the current geographic location coordinates and the current time and sends them to the background server. The background server queries the performers information of the current concert from the pre-configured concert information, and returns the facial image of the leading actor as the target face to the terminal.

[0071] In some embodiments, the terminal determines the face recognition result based on the similarity between the face recognized from the video screen and the target face.

[0072] Exemplarily, when the similarity is greater than 40%, it is determined that the face recognition result indicates that the video screen contains the target face; when the similarity is less than or equal to 40%, it is determined that the face recognition result indicates that the video screen does not contain the target face.

[0073] In some embodiments, when the face recognition result indicates that the video screen does not contain the target face, if the video screen contains other faces, the terminal can use the first shooting parameter to focus on the other faces in the video screen and shoot the video.

[0074] In another possible implementation manner, the target face may also be specified and determined by the user.

[0075] In some embodiments, when the content type is a performance event venue type, in response to a face designation operation, the terminal obtains the target face indicated by the face designation operation, and determines the face recognition result based on the similarity between the face recognized from the video screen and the target face.

[0076] Optionally, the face designation operation can be a user's selection operation on a face in the video screen, or the face designation operation can also be a user's pre-input operation on a person's name. The terminal can extract the target face corresponding to the person's name from the video screen based on face recognition technology, and there is no restriction on this.

[0077] In some embodiments, the performance event shooting scene is an event scene, such as a football game scene, a dragon boat race scene, a gymnastics game scene, etc.

[0078] In some embodiments, when the content type is a performance event venue type, the terminal identifies event elements contained in the video screen, and uses the first shooting parameter to focus on the event elements and perform video shooting.

[0079] For example, in a football match, the event element is a football; in a dragon boat race scene, the event element is a dragon boat; in a gymnastics competition scene, the event element is a ribbon, and so on.

[0080] Exemplarily, the event element may also be a facial image corresponding to a person participating in the event, or a screen element specified by a user, without limitation.

[0081] Regarding the specific method by which the terminal identifies event elements contained in the video screen, in some embodiments, when the content type is a performance event venue type, the terminal determines the event type of the event scene based on geographic location information and time information, and determines a reference picture corresponding to the event element based on the event type, and identifies the event elements contained in the video screen based on the reference picture.

[0082] Exemplarily, when the user turns on the option control corresponding to the sports game mode, the terminal obtains the current geographic location coordinates and the current time and sends them to the background server. The background server queries the event information of the current sports game from the pre-configured sports game information to determine the event type (for example, the football game type) according to the event information. The background server can also determine the reference picture corresponding to the current event type based on the pre-configured different reference pictures corresponding to different event types and different event elements, so as to identify the event elements contained in the video screen according to the reference picture. For example, when the similarity between the reference picture and the screen element in the video screen exceeds a threshold, the screen element is determined as a game element.

[0083] In this embodiment, when the content type is a performance event venue type, the terminal can focus on the core elements in the performance event venue by adopting the first shooting parameter to shoot the video, thereby improving the video shooting quality under the performance event venue type.

[0084] In a possible scenario, when the content type is an auditorium type, the terminal uses the second shooting parameter to shoot the video.

[0085] The second shooting parameter is used to achieve at least one shooting effect of wide-angle shooting and depth of field optimization.

[0086] Optionally, the second shooting parameter includes but is not limited to a focal length parameter in the wide-angle focal length segment, a depth of field parameter, an aperture size, and the like.

[0087] Regarding the type of auditorium, to ensure good video shooting quality, it is not necessary to focus on each audience member's face. Instead, wide-angle shooting and depth of field optimization can be used to highlight the overall cheering atmosphere. Therefore, the second shooting parameter corresponding to the auditorium type is different from the first shooting parameter corresponding to the performance venue type.

[0088] See also Figure 4 , Figure 4 It is a schematic diagram of a terminal using a second shooting parameter to shoot a video when the content type is an auditorium type, provided by an exemplary embodiment of the present application.

[0089] like Figure 4 As shown, the terminal determines that the content type corresponding to the screen content of the video screen is the audience type based on the real-time video stream, so the second shooting parameter is used for video shooting. Under the second shooting parameter, at least one shooting effect of wide-angle shooting and depth of field optimization can be achieved, so that the part of the video shooting the audience seats can highlight the cheering atmosphere of the audience seats as a whole, thereby improving the quality of video shooting.

[0090] Regarding the specific determination method of the second shooting parameter, in some embodiments, the second shooting parameter is a fixed value determined in advance by the terminal for the performance event scene; in other embodiments, it can also be a value predicted by the terminal based on the real-time video stream through a pre-trained parameter recommendation model. Among them, the parameter recommendation model can be trained based on a sample video set, the picture content of the sample video in the sample video set includes the picture content of the auditorium type, the label corresponding to the sample video is the actual shooting parameter for shooting the auditorium, and the sample video is a video whose shooting effect meets the quality requirements (for example, a video shot by a professional photographer).

[0091] In this embodiment, when the content type is the auditorium type, the terminal uses the second shooting parameter to perform video shooting, which can achieve at least one of the shooting effects of wide-angle shooting and depth of field optimization for the auditorium, highlighting the cheering atmosphere of the auditorium, thereby improving the video shooting quality under the auditorium type.

[0092] In some embodiments, when the content type is an electronic screen type, a third shooting parameter is used for video shooting.

[0093] The third shooting parameter is used to reduce the interference degree of the moiré phenomenon on the shooting effect of the electronic screen.

[0094] Moiré pattern refers to an interference stripe or wavy pattern that appears when photographing certain fine-textured objects (such as cloth, screens, grids, etc.). Moiré is usually caused by the interference of two similar but not completely overlapping patterns, especially when interference occurs between high-frequency details and the pixel arrangement of the camera sensor. Moiré occurs when the fine pattern of the photographed object forms a certain periodic interference with the pixel array of the camera sensor. By adjusting the focal length or aperture of the lens, the resolution and depth of field of the image can be changed, thereby reducing or avoiding moiré.

[0095] When the content type is an electronic screen type, if inappropriate shooting parameters are used, moiré patterns may be displayed in the captured screen image. Therefore, by adopting the third shooting parameter for video shooting, the prominence of the moiré patterns can be reduced, thereby reducing the degree of interference of the moiré pattern phenomenon on the electronic screen shooting effect and improving the quality of video shooting.

[0096] See also Figure 5 , Figure 5 It is a schematic diagram of using a third shooting parameter to shoot a video when the content type is an electronic screen type, provided by an exemplary embodiment of the present application.

[0097] like Figure 5As shown, the terminal determines that the content type corresponding to the screen content of the video screen is the electronic screen type based on the real-time video stream, so the third shooting parameter is used for video shooting. The third shooting parameter can reduce the interference degree of the moiré phenomenon on the electronic screen shooting effect, so the electronic screen obtained by video shooting shows no moiré or only a small amount of moiré, thereby improving the quality of video shooting. For example Figure 5 In the video captured, the text or pattern on the electronic screen can be displayed clearly, and no moiré pattern appears on the electronic screen.

[0098] Regarding the specific determination method of the third shooting parameter, in some embodiments, the third shooting parameter is a fixed value predetermined by the terminal. For example only, when the content type is an electronic screen type, the focal length is 45 mm.

[0099] In other embodiments, the third shooting parameter may also be a value predicted by the terminal based on the real-time video stream through a pre-trained parameter recommendation model. The parameter recommendation model may be trained based on a sample video set, wherein the screen content of the sample video in the sample video set includes the screen content of the electronic screen type, the label corresponding to the sample video is the actual shooting parameter for shooting the electronic screen, and the sample video is a video that avoids the moiré phenomenon (e.g., a video shot by a professional photographer).

[0100] In some other embodiments, the third shooting parameter may also be a value obtained by the terminal through at least one adjustment according to the prominence of the moiré phenomenon.

[0101] See also Figure 6 , Figure 6 FIG. 1 is a flow chart of determining a third shooting parameter provided by an exemplary embodiment of the present application. The flow chart includes the following steps.

[0102] Step 601: Adjust the shooting parameters within the adjustable range of the shooting parameters.

[0103] Exemplarily, the adjustable range of focal length is 25 mm to 70 mm.

[0104] In a possible implementation, the terminal shoots the sampled video segments according to gradually increasing shooting parameters during the first time period, and the shooting parameters dynamically change from a minimum value to a maximum value of an adjustable range of the shooting parameters.

[0105] Exemplarily, after the terminal identifies that the content type of the picture content is an electronic screen type based on the real-time video stream, the terminal gradually increases the focal length from 25 mm to 70 mm within a time period of 0 to 1 second.

[0106] Step 602, performing moiré recognition on the video image after the shooting parameters are adjusted to obtain a moiré recognition result, where the moiré recognition result is used to indicate the prominence of the moiré in the video image.

[0107] Exemplarily, if the frame rate of the captured video is 60fps, the terminal will capture 60 frames of video in a time period of 0 to 1s. The terminal can perform moiré recognition on the video after adjusting the shooting parameters through a pre-trained moiré recognition model to determine the moiré significance of each frame of the 60 frames.

[0108] Exemplarily, the moiré recognition result may be a value between 0 and 1. A larger moiré recognition result indicates a greater prominence of the moiré in the video image.

[0109] Step 603: Determine a third shooting parameter based on the moiré recognition results under different shooting parameters, where the moiré prominence under the third shooting parameter is lower than the moiré prominence under other shooting parameters.

[0110] In some embodiments, the terminal determines the shooting parameter corresponding to the video picture with the smallest moiré recognition result as the third shooting parameter.

[0111] For example, among 60 frames of video, the prominence of the moiré in the 31st frame of video is lower than that in other frames of video. Therefore, the terminal determines the shooting parameters corresponding to the 31st frame of video as the third shooting parameters, and subsequently uses the third shooting parameters to shoot the electronic screen, thereby reducing the prominence of the moiré in the electronic screen and improving the video shooting quality.

[0112] In one possible implementation, in order to improve the efficiency of determining the third shooting parameter, the moiré recognition results may not be determined for all 60 frames of video. Instead, the 60 frames of video may be divided into multiple groups, and one frame of video may be extracted from each group to determine the moiré recognition results.

[0113] In some embodiments, moiré recognition is performed on the video images after the shooting parameters are adjusted, including: grouping the video images after the shooting parameters are adjusted to obtain at least two video image groups, wherein different video image groups correspond to different focal length intervals; extracting a video image frame from each video image group, and performing moiré recognition on each video image frame to obtain a moiré recognition result for each video image frame.

[0114] In some embodiments, based on the moiré recognition results under different shooting parameters, determining the third shooting parameter includes: determining a target video frame from each video frame, wherein the moiré in the target video frame is less significant than the moiré in other video frames; and determining the third shooting parameter based on the target video frame.

[0115] In some embodiments, determining the third shooting parameter based on the target video frame includes at least one of the following: determining the focal length corresponding to the target video frame as the third shooting parameter; determining the average of the focal lengths corresponding to each video frame in the video frame group where the target video frame is located as the third shooting parameter; performing moiré recognition on each video frame in the video frame group where the target video frame is located to obtain a moiré recognition result for each video frame in the video frame group, and determining the third shooting parameter based on the moiré recognition result in the focal length interval corresponding to the video frame group, wherein the significance of the moiré under the third shooting parameter is lower than the significance of the moiré under other focal lengths.

[0116] In this embodiment, by grouping the video pictures after adjusting the shooting parameters, at least two video picture groups are obtained, and the third shooting parameters are determined according to the video picture groups. Compared with directly determining the third shooting parameters through each video picture, the amount of calculation can be reduced, the efficiency of determining the third shooting parameters can be improved, and the appropriate third shooting parameters can be screened out more quickly from coarse to fine, thereby reducing or avoiding moiré patterns earlier, and further improving the quality of video shooting.

[0117] See also Figure 7 , Figure 7 FIG. 1 is a flow chart of a video shooting method provided by another exemplary embodiment of the present application. The flow chart includes the following steps.

[0118] Step 711: The terminal displays a video shooting interface and is in a performance event shooting scene.

[0119] In some embodiments, after the user starts the video shooting interface of the camera application, the terminal displays the video shooting interface; when the user triggers the option control corresponding to the concert mode, the terminal determines that it is in the performance event shooting scene.

[0120] Step 721, obtaining real-time video stream and sensor data.

[0121] Optionally, the terminal obtains a real-time video stream through a camera and obtains sensor data through a sensor.

[0122] Optionally, the sensor data includes an acceleration sensor, an angular velocity sensor (such as a gyroscope), an angle sensor (such as a level), an acoustic sensor (such as a microphone), or other types of sensors.

[0123] Step 731 , in response to a video shooting instruction, identifying the content type of the picture content contained in the video picture based on the real-time video stream.

[0124] When the video is just beginning to be shot, when the user clicks the video shooting control in the video shooting interface, the terminal receives the video shooting instruction, and the terminal identifies the content type of the screen content contained in the video screen according to the acquired real-time video stream.

[0125] Step 732: When it is determined based on the sensor data that the picture content has changed, identify the content type of the picture content included in the video picture.

[0126] In the case where the video is being shot, when the terminal determines based on the sensor data that the picture content has changed, the content type of the picture content included in the video picture is identified.

[0127] In some embodiments, the terminal determines the acceleration of the terminal's displacement based on the acceleration sensor data, and identifies the content type of the picture content contained in the video picture when the acceleration is greater than an acceleration threshold.

[0128] Exemplarily, the acceleration sensor measures the acceleration of the terminal displacement to be 10 cm / s, which is greater than the acceleration threshold of 5 cm / s. Then, the picture content may change, and the terminal re-identifies the content type of the picture content contained in the video picture.

[0129] In some embodiments, the angular velocity of the terminal displacement is determined based on the angular velocity sensor data, and when the angular velocity is greater than an angular velocity threshold, the content type of the picture content contained in the video picture is identified.

[0130] Exemplarily, the angular velocity sensor measures the terminal displacement to be 5 cm / s, which is greater than the angular velocity threshold of 3 cm / s. Then, the picture content may change, and the terminal re-identifies the content type of the picture content contained in the video picture.

[0131] In some embodiments, an environmental volume change is determined based on acoustic sensor data, and when the environmental volume change is greater than a volume change threshold, a content type of the picture content contained in the video picture is identified.

[0132] For example, when the acoustic sensor measures an ambient volume change of 20db, which is greater than the volume change threshold of 10db, or when the acoustic sensor measures an ambient volume change of 20%, which is greater than the volume change threshold of 10%, the picture content may change, and the terminal re-identifies the content type of the picture content contained in the video picture.

[0133] Since the terminal can determine whether the picture content is likely to change through sensor data, the terminal avoids continuous recognition of the real-time video stream, thereby reducing the power consumption of the terminal.

[0134] Regarding the method for a terminal to identify the content type of the screen content contained in a video screen, in some embodiments, the terminal identifies the content type of the screen content contained in the video screen based on the real-time video stream through a content recognition model, and the content type is one of at least two candidate content types in a performance event shooting scene. The content recognition model is trained based on sample videos in a performance event shooting scene, and the sample videos include sample video screens corresponding to at least two candidate content types.

[0135] In one possible implementation, the terminal is deployed with a content recognition model; in another possible implementation, the background server corresponding to the terminal is deployed with a content recognition model, the terminal sends a real-time video stream to the background server, and receives the content type returned by the background server.

[0136] In some embodiments, the actual content type corresponding to the sample video screen in the sample video can be used as a label, and the sample video screen in the sample video can be used as a training sample to train the content recognition model so that the content recognition model has the ability to recognize the content type corresponding to the screen content in the video screen. For example, the training can be performed by the gradient descent method and the back propagation method, which is not limited.

[0137] Step 741, when the content type is a performance event venue type, a first shooting parameter is used to perform video shooting, and the first shooting parameter is used to achieve focusing on the core elements in the performance event venue.

[0138] Step 742, when the content type is an auditorium type, use a second shooting parameter to shoot a video, where the second shooting parameter is used to achieve at least one shooting effect of wide-angle shooting and depth of field optimization;

[0139] Step 743: When the content type is an electronic screen type, a third shooting parameter is used to shoot a video, where the third shooting parameter is used to reduce the degree of interference of the moiré phenomenon on the shooting effect of the electronic screen.

[0140] For more information about steps 741-743, see Figure 3-5 And the related description will not be repeated here.

[0141] In addition to adjusting the shooting parameters of the video, you can also adjust the audio in performance and event scenarios.

[0142] Step 722: Based on the original audio collected during the video shooting, the ambient sound and noise are identified through a sound recognition model.

[0143] By way of example only, the ambient sound may include the cheering of the audience, the chorus, the singing of stars, and the like.

[0144] By way of example only, noise may include crowd noise, wind noise, etc.

[0145] In some embodiments, when the performance event shooting scene is a concert scene, the sound recognition model is trained based on performance sound samples corresponding to the concert type to which the concert scene belongs.

[0146] In some embodiments, when the performance event shooting scene is an event scene, the sound recognition model is trained based on event sound samples corresponding to the event type to which the event scene belongs.

[0147] Step 733, the ambient sound in the original audio is enhanced, and the noise in the original audio is eliminated to obtain the target audio.

[0148] The target audio is used to be synthesized with the captured video.

[0149] In one possible implementation, the terminal enhances the ambient sound in the original audio and eliminates the noise in the original audio to obtain the target audio during the video shooting process; in another possible implementation, the terminal processes the original audio of the entire video after the video shooting is completed, enhances the ambient sound in the original audio, eliminates the noise in the original audio to obtain the target audio, and there is no restriction on this.

[0150] Step 751, turn on automatic exposure, adjust the sensitivity, and turn on 3D sound effects to shoot the video.

[0151] The specific parameters of the automatic exposure and sensitivity may be fixed values ​​preset by the terminal or recommended values ​​calculated by the terminal based on the current video picture, and there is no limitation on this.

[0152] When not in a performance or event scene, the user needs to manually turn on automatic exposure, adjust sensitivity, and turn on 3D sound effects. However, when in a performance or event scene, the terminal can automatically achieve the above effects, reducing the difficulty and complexity of video shooting and improving the user experience.

[0153] Step 761, identify highlight moments.

[0154] In some embodiments, the terminal can identify the highlight moments in the performance or event shooting scene based on the real-time video stream through a highlight moment recognition model, and store the highlight node marks corresponding to the highlight moments in association with the captured video.

[0155] For example, the highlight moment may be the moment when fans cheer, sing-along or propose on the spot, or it may be the moment when the song reaches its climax.

[0156] In one possible implementation, the terminal may identify the rhythm of the music through a highlight moment recognition model to determine the moment when the song reaches its climax.

[0157] Optionally, the highlight node mark corresponding to the highlight moment may be a timestamp mark or a highlight content mark, and there is no limitation on this.

[0158] Step 771, save the video file.

[0159] See also Figure 8 , Figure 8 : is a structural block diagram of a video shooting device provided by an exemplary embodiment of the present application. The device includes:

[0160] Display module 801, used to display the video shooting interface;

[0161] An identification module 802 is used to identify the content type of the picture content contained in the video picture based on the real-time video stream in the case of a performance or event shooting scene;

[0162] The shooting module 803 is used to shoot the video using shooting parameters corresponding to the content type, wherein different content types correspond to different shooting parameters.

[0163] Optionally, the shooting module 803 is used to:

[0164] In the case where the content type is a performance event venue type, a first shooting parameter is used to shoot the video, where the first shooting parameter is used to focus on the core elements in the performance event venue;

[0165] In the case where the content type is an auditorium type, a second shooting parameter is used to shoot the video, where the second shooting parameter is used to achieve at least one shooting effect of wide-angle shooting and depth of field optimization;

[0166] In the case that the content type is an electronic screen type, a third shooting parameter is used for video shooting, and the third shooting parameter is used to reduce the interference degree of the moiré phenomenon on the electronic screen shooting effect.

[0167] Optionally, the shooting module 803 is used to:

[0168] In the case where the content type is the performance event venue type, performing face recognition on the video screen to obtain a face recognition result;

[0169] When the face recognition result indicates that the video image includes the target face, the first shooting parameter is used to focus on the target face and perform video shooting.

[0170] Optionally, the shooting module 803 is used to:

[0171] In the case where the content type is the performance event venue type, determining performer information of the concert scene based on the geographic location information and time information;

[0172] Acquire the target face according to the performer information;

[0173] The face recognition result is determined based on the similarity between the face recognized from the video image and the target face.

[0174] Optionally, the shooting module 803 is used to:

[0175] In a case where the content type is the performance event venue type, in response to a face designation operation, obtaining the target face indicated by the face designation operation;

[0176] The face recognition result is determined based on the similarity between the face recognized from the video image and the target face.

[0177] Optionally, the shooting module 803 is used to:

[0178] In the case where the content type is the performance event venue type, identifying event elements contained in the video screen;

[0179] The first shooting parameters are used to focus on the event elements and perform video shooting.

[0180] Optionally, the shooting module 803 is used to:

[0181] In the case where the content type is the performance event venue type, determining the event type of the event scene based on the geographic location information and the time information;

[0182] Determining, according to the event type, a reference picture corresponding to the event element;

[0183] The event element contained in the video screen is identified according to the reference image.

[0184] Optionally, the shooting module 803 is used to:

[0185] Adjust the shooting parameters within the adjustable range of shooting parameters;

[0186] Performing moiré recognition on the video image after adjusting the shooting parameters to obtain a moiré recognition result, wherein the moiré recognition result is used to indicate the prominence of the moiré in the video image;

[0187] The third shooting parameter is determined based on the moiré recognition results under different shooting parameters, and the moiré prominence under the third shooting parameter is lower than the moiré prominence under other shooting parameters.

[0188] Optionally, the identification module 802 is used to:

[0189] In response to a video shooting instruction, identifying the content type of the picture content contained in the video picture based on the real-time video stream; or,

[0190] In the case where it is determined based on the sensor data that the picture content has changed, the content type of the picture content included in the video picture is identified.

[0191] Optionally, the identification module 802 is configured to:

[0192] Determine the acceleration of the terminal displacement based on the acceleration sensor data, and identify the content type of the picture content included in the video picture when the acceleration is greater than the acceleration threshold;

[0193] Determine the angular velocity of the terminal displacement based on the angular velocity sensor data, and identify the content type of the picture content included in the video picture when the angular velocity is greater than the angular velocity threshold;

[0194] An environmental volume change is determined based on the acoustic sensor data, and when the environmental volume change is greater than a volume change threshold, the content type of the picture content included in the video picture is identified.

[0195] Optionally, the device further includes an audio processing module, configured to:

[0196] Based on the original audio collected during video shooting, the ambient sound and noise in the original audio are identified by a sound recognition model;

[0197] The ambient sound in the original audio is enhanced, and the noise in the original audio is eliminated to obtain a target audio, and the target audio is used to be synthesized with the captured video.

[0198] Optionally, when the performance event shooting scene is a concert scene, the sound recognition model is trained based on performance sound samples corresponding to the concert type to which the concert scene belongs; when the performance event shooting scene is an event scene, the sound recognition model is trained based on event sound samples corresponding to the event type to which the event scene belongs.

[0199] Optionally, the device further includes a highlight recognition module, which is used to:

[0200] Based on the real-time video stream, identifying the highlight moments in the performance or event shooting scene by using a highlight moment recognition model;

[0201] The highlight node mark corresponding to the highlight moment is associated with the captured video and stored.

[0202] Optionally, the identification module 802 is used to:

[0203] Identifying the content type of the screen content contained in the video screen based on the real-time video stream by a content recognition model, wherein the content type is one of at least two candidate content types in the performance event shooting scene;

[0204] The content recognition model is trained based on sample videos in the performance and event shooting scene, and the sample videos include sample video pictures corresponding to the at least two candidate content types.

[0205] See also Fig. 9 , Fig. 9 It is a structural block diagram of a terminal device provided by an exemplary embodiment of the present application.

[0206] The terminal may execute the video shooting method of the above embodiment. The terminal may be a terminal device with a camera, such as a smart phone, a laptop, a tablet computer, a smart watch, etc. The terminal may also be called a user equipment, a portable terminal, etc. The terminal may include one or more of the following components: a processor 910 and a memory 920.

[0207] Optionally, the processor 910 uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 920, and calling data stored in the memory 920. Optionally, the processor 910 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 910 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a neural network processor (NPU), and a baseband chip. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content that needs to be displayed on the touch display; the NPU is used to implement artificial intelligence (AI) functions; and the baseband chip is used to process wireless communications. It is understandable that the above baseband chip may not be integrated into the processor 910, but may be implemented by a separate chip.

[0208] The memory 920 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 920 includes a non-transitory computer-readable storage medium. The memory 920 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 920 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc.; the data storage area may store data created according to the use of the electronic device (such as audio data, a phone book), etc.

[0209] In addition, those skilled in the art will appreciate that the structure of the electronic device shown in the above figures does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figures, or a combination of certain components, or a different arrangement of components.

[0210] The embodiment of the present application also provides a computer-readable storage medium, in which at least one computer instruction is stored, and at least one computer instruction is loaded and executed by a processor to implement the method described in the above embodiment. Optionally, the computer-readable storage medium may include: ROM, RAM, solid state drives (SSD, Solid State Drives) or optical disks, etc. Among them, RAM may include resistance random access memory (ReRAM, Resistance Random Access Memory) and dynamic random access memory (DRAM, Dynamic Random Access Memory).

[0211] The embodiment of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in various optional implementations of the above aspects.

[0212] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A video shooting method, characterized in that: The method comprises: Display the video shooting interface; In the case of a performance or event shooting scene, the content type of the video content contained in the video screen is identified based on the real-time video stream; The video is shot using shooting parameters corresponding to the content type, wherein different content types correspond to different shooting parameters.

2. The method according to claim 1, characterized in that The adopting the shooting parameters corresponding to the content type to shoot the video includes: In the case where the content type is a performance event venue type, a first shooting parameter is used to shoot the video, where the first shooting parameter is used to focus on the core elements in the performance event venue; In the case where the content type is an auditorium type, a second shooting parameter is used to shoot the video, where the second shooting parameter is used to achieve at least one shooting effect of wide-angle shooting and depth of field optimization; In the case that the content type is an electronic screen type, a third shooting parameter is used for video shooting, and the third shooting parameter is used to reduce the interference degree of the moiré phenomenon on the electronic screen shooting effect.

3. The method according to claim 2, characterized in that The performance event shooting scene is a concert scene, and when the content type is a performance event venue type, the first shooting parameter is used to shoot the video, including: In the case where the content type is the performance event venue type, performing face recognition on the video screen to obtain a face recognition result; When the face recognition result indicates that the video image includes the target face, the first shooting parameter is used to focus on the target face and perform video shooting.

4. The method according to claim 3, characterized in that When the content type is the performance event venue type, performing face recognition on the video screen to obtain a face recognition result includes: In the case where the content type is the performance event venue type, determining performer information of the concert scene based on the geographic location information and time information; Acquire the target face according to the performer information; The face recognition result is determined based on the similarity between the face recognized from the video image and the target face.

5. The method according to claim 3, characterized in that: When the content type is the performance event venue type, performing face recognition on the video screen to obtain a face recognition result includes: In a case where the content type is the performance event venue type, in response to a face designation operation, obtaining the target face indicated by the face designation operation; The face recognition result is determined based on the similarity between the face recognized from the video image and the target face.

6. The method according to claim 2, characterized in that The performance event shooting scene is an event scene, and when the content type is a performance event venue type, the first shooting parameter is used to shoot the video, including: In the case where the content type is the performance event venue type, identifying event elements contained in the video screen; The first shooting parameters are used to focus on the event elements and perform video shooting.

7. The method according to claim 6, characterized in that When the content type is the performance event venue type, identifying the event elements contained in the video screen includes: In the case where the content type is the performance event venue type, determining the event type of the event scene based on the geographic location information and the time information; Determining, according to the event type, a reference picture corresponding to the event element; The event element contained in the video screen is identified according to the reference image.

8. The method according to claim 2, characterized in that: When the content type is an electronic screen type, a third shooting parameter is used to shoot the video, and the third shooting parameter is used to reduce the interference degree of the moiré phenomenon on the shooting effect of the electronic screen, including: Adjust the shooting parameters within the adjustable range of shooting parameters; Performing moiré recognition on the video image after adjusting the shooting parameters to obtain a moiré recognition result, wherein the moiré recognition result is used to indicate the prominence of the moiré in the video image; The third shooting parameter is determined based on the moiré recognition results under different shooting parameters, and the moiré prominence under the third shooting parameter is lower than the moiré prominence under other shooting parameters.

9. The method according to claim 1, characterized in that: The method of identifying the content type of the picture content contained in the video picture based on the real-time video stream includes: In response to a video shooting instruction, identifying the content type of the picture content contained in the video picture based on the real-time video stream; or, In the case where it is determined based on the sensor data that the picture content has changed, the content type of the picture content included in the video picture is identified.

10. The method according to claim 9, characterized in that In the case where it is determined based on the sensor data that the picture content has changed, identifying the content type of the picture content included in the video picture includes at least one of the following: Determine the acceleration of the terminal displacement based on the acceleration sensor data, and identify the content type of the picture content included in the video picture when the acceleration is greater than the acceleration threshold; Determine the angular velocity of the terminal displacement based on the angular velocity sensor data, and identify the content type of the picture content included in the video picture when the angular velocity is greater than the angular velocity threshold; An environmental volume change is determined based on the acoustic sensor data, and when the environmental volume change is greater than a volume change threshold, the content type of the picture content included in the video picture is identified.

11. The method according to claim 1, characterized in that: The method further comprises: Based on the original audio collected during video shooting, the ambient sound and noise in the original audio are identified by a sound recognition model; The ambient sound in the original audio is enhanced, and the noise in the original audio is eliminated to obtain a target audio, and the target audio is used to be synthesized with the captured video.

12. The method according to claim 11, characterized in that In the case where the performance event shooting scene is a concert scene, the sound recognition model is trained based on performance sound samples corresponding to the concert type to which the concert scene belongs; In the case where the performance event shooting scene is an event scene, the sound recognition model is trained based on event sound samples corresponding to the event type to which the event scene belongs.

13. The method according to claim 1, characterized in that The method further comprises: Based on the real-time video stream, identifying the highlight moments in the performance or event shooting scene by using a highlight moment recognition model; The highlight node mark corresponding to the highlight moment is associated with the captured video and stored.

14. The method according to claim 1, characterized in that The method of identifying the content type of the picture content contained in the video picture based on the real-time video stream includes: Identifying the content type of the screen content contained in the video screen based on the real-time video stream by a content recognition model, wherein the content type is one of at least two candidate content types in the performance event shooting scene; The content recognition model is trained based on sample videos in the performance and event shooting scene, and the sample videos include sample video pictures corresponding to the at least two candidate content types.

15. A video shooting device, characterized in that: The device comprises: Display module, used to display the video shooting interface; An identification module is used to identify the content type of the picture content contained in the video picture based on the real-time video stream in the case of a performance or event shooting scene; The shooting module is used to shoot the video using shooting parameters corresponding to the content type, wherein different content types correspond to different shooting parameters.

16. A terminal, characterized in that: The terminal includes a processor and a memory; the memory stores at least one computer instruction, and the at least one computer instruction is used to be executed by the processor to implement the video shooting method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer instruction, and the computer instruction is loaded and executed by a processor to implement the video shooting method according to any one of claims 1 to 14.

18. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium; a processor of the terminal reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the terminal executes the video shooting method as described in any one of claims 1 to 14.