VIDEO PROCESSING METHOD, APPARATUS, DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM PRODUCT

Abstract

[0009] The present disclosure provides a video processing method, apparatus, device, storage medium, and computer program product. The method includes: playing audio during video capture; performing variable-speed playback of a first portion of the audio according to a first speed change pattern in response to recognizing that a target object exhibits a target state in the captured video images; obtaining a target video based on the captured video images and audio; and playing back, in the target video, video images captured before the target object exhibits the target state at a normal speed, video images captured after the target object exhibits the target state at a second speed change pattern, and playing back the audio at a normal speed, wherein the first speed change pattern and the second speed change pattern have opposite speed change directions and the same speed change rate. The present disclosure provides a user with convenient operation, a simple processing process, and meets user needs and improves the user's operation experience.

Description

[Technical Field]

[0001] TECHNICAL FIELD Embodiments of the present disclosure relate to the field of computer technology, and in particular to video processing methods, devices, equipment, storage media, and computer program products. [Background technology]

[0002] Video recording function 、 It is a commonly used function of the client's video shooting device or video recording application program. With the development of science and technology, video recording function is becoming more and more widely used. attitude do.

[0003] Currently, the video recording function is e.g. 、 It is possible to create multiple types of videos, such as creating slow-motion videos or fast-motion videos. However, in order to create multiple types of videos, the captured video must be imported into video editing software or an editing page to perform the corresponding slow-motion playback or fast-motion playback process before the creation of a video that can be played in slow motion or fast motion can be completed.

[0004] Therefore, conventionally, the operation steps for variable speed video recording are complicated, and 、 The processing process is complicated, which does not provide users with convenient operations and further affects the user experience. Summary of the Invention [Problem to be solved by the invention]

[0005] The embodiments of the present disclosure can provide users with convenient operation, the processing process is simple, and 、 Meet user needs and improve user experience 、 Video processing method, device, equipment, and storage medium 、 and computer program products. [Means for solving the problem]

[0006] In a first aspect, an embodiment of the present disclosure provides a video processing method, the method comprising: playing audio while capturing video; In response to recognizing that the target object exhibits a target state in the captured video image, Object indicates the target state, performing variable speed playback on a first portion of the audio representing an unplayed portion of the audio according to a first speed change form; obtaining a target video based on the captured video image and the audio; In the target video, playing back at a normal speed a video image taken before the target object exhibits the target state, playing back at a variable speed a video image taken after the target object exhibits the target state according to a second variable speed format, and playing back the audio at a normal speed; The first and second speed change modes have opposite speed change directions. and and 、 The shift speed is the same.

[0007] In a second aspect, an embodiment of the present disclosure provides a video processing device, the device comprising: a recording module for playing audio while recording video; In response to recognizing that the target object exhibits a target state in the captured video image, Object indicates the target state, the processing module for performing variable speed playback on a first portion of the audio representing an unplayed portion of the audio according to a first speed variation form, a processing module for obtaining a target video based on the captured video image and the audio; a playback module for playing back, in the target video, video images taken before the target object exhibits the target state at a normal speed, playing back video images taken after the target object exhibits the target state at a variable speed according to a second variable speed format, and playing back the audio at a normal speed; The first and second speed change modes have opposite speed change directions. and and 、 The shift speed is the same.

[0008] In a third aspect, an embodiment of the present disclosure is an electronic device, comprising: at least one processor and a memory; the memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, thereby causing the at least one processor to implement the first aspect. Like An electronic device is provided for carrying out the described video processing method.

[0009] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having computer-executable instructions stored thereon, the computer-executable instructions being executed by a processor to perform the first aspect. Like The video processing method described is implemented.

[0010] In a fifth aspect, embodiments of the present disclosure include 、 There is provided a computer program product comprising a computer program, which, when executed by a processor, implements the video processing method according to the first aspect above.

[0011] In a sixth aspect, an embodiment of the present disclosure provides a computer program, the computer program comprising: 、 When executed by a processor, it is used to implement the video processing method according to the first aspect above. [Effects of the Invention]

[0012] Video processing method, device, apparatus, and storage medium provided in the embodiments of the present disclosure 、 and a computer program product for playing audio while shooting video, followed by 、 In response to recognizing that the target object exhibits the target state in the captured video image, displaying an unplayed portion of the audio when recognizing that the target object exhibits the target state in the captured video image. 、 A first portion of the audio is played back at a variable speed according to a first speed variation form, and a target video is obtained based on the captured video images and the audio. In the target video, the video images captured before the target object exhibits the target state are played back at a normal speed, and the video images captured after the target object exhibits the target state are played back at a variable speed according to a second speed variation form, and the audio is played back at a normal speed. do. Here, the first and second shift modes are 、 Shift direction is opposite and and 、 The speed of the shift is the same, so that the target video 、 It is guaranteed that audio is played at normal speed, and that some video images are played at normal speed and some at variable speed, thereby realizing variable speed recording and playback of the video being shot. 、 By recognizing the target state of the target object, it is possible to initiate the operation to control the variable speed recording of the video, without needing to input the captured video into video editing software or editing page to perform the corresponding slow playback or quick playback process, thereby improving the user experience. do. To give users a strong sense of variable speed recording, after triggering variable speed recording while shooting a video, in , the audio to be played is played at a variable speed according to a first variable speed mode, and in the process of playing back the target video generated after the shooting is completed, the video to be shot after the speed change is triggered is played at a variable speed according to a second variable speed mode. 、It can play video images at different speeds and audio at normal speeds to meet the personalized needs of users, and the processing process is simple. 、 The operation steps are simplified, allowing users to easily edit videos. gear shifting processing can be realized, and 、 Improve the user's experience. [Brief explanation of the drawings]

[0013] In order to more clearly describe the embodiments or conventional technical solutions of the present disclosure, the following briefly introduces drawings that may be used to describe the embodiments or conventional technical solutions. do. Obviously, the drawings in the following description 、 These are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without any creative effort. [Figure 1] 1 is a schematic diagram of a photographing interface provided in an embodiment of the present disclosure. [Figure 2] 1 is a scene schematic diagram of a video processing method provided in an embodiment of the present disclosure; [Figure 3] FIG. 2 is a scene schematic diagram of a video processing method provided in another embodiment of the present disclosure. [Figure 4] 10 is a flowchart of a video processing method provided in yet another embodiment of the present disclosure. [Figure 5] 1 is a flowchart of a video processing method provided in an embodiment of the present disclosure. [Figure 6] FIG. 10 is a scene schematic diagram of a video processing method provided in yet another embodiment of the present disclosure. [Figure 7] FIG. 1 is a structural block diagram of a video processing device provided in an embodiment of the present disclosure. [Figure 8] FIG. 1 is a schematic diagram of a hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014]

[0023] The present disclosure will now be described in more detail with reference to the drawings. While certain embodiments of the present disclosure are illustrated in the drawings, the present disclosure may be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather as being intended to provide a more thorough understanding of the present disclosure. 、 and 、 To fully understand 、 It should be understood that these examples are provided. 、 It should be understood that it serves only as an example and does not limit the scope of protection of the present disclosure.

[0015] The steps described in the method embodiments of the present disclosure may be performed in different orders. And also teeth 、 It should be understood that the methods may be performed in parallel. and / or The steps shown may be omitted. teeth, Not limited.

[0016] As used herein, the term "comprises" and variations thereof are open-ended, i.e. 、 The term "in one embodiment" means "at least one embodiment," "in another embodiment" means "at least one other embodiment," and "in some embodiments" means "at least some embodiments." Relevant definitions of other terms are provided below.

[0017] In addition, the concepts of "first", "second", etc., which refer to this disclosure, 、 It is only to distinguish between different devices, modules or units, and these devices, modules 、 It should be noted that this is not intended to limit the order or interdependence of the functions performed by the units.

[0018] The modifiers "one" and "multiple" refer to this disclosure. 、It should be noted that this is intended to be illustrative rather than limiting, and as will be understood by those skilled in the art, "one or more" should be understood unless the context clearly indicates otherwise.

[0019] The names of messages or information exchanged between devices or modules in the embodiments of the present disclosure are for illustrative purposes only. Tei , and are not intended to limit the scope of these messages or information.

[0020] Currently, the video recording function is e.g. 、 It is possible to create various types of videos, such as slow-motion videos or fast-motion videos. However, in order to create various types of videos, the shot video must be imported into video editing software or an editing page and subjected to the corresponding slow-motion or fast-motion playback process before the creation of a video with slow-motion or fast-motion playback can be completed. In addition, some platforms have previously included a slow-motion or fast-motion function in their shooting functions, but the slow-motion or fast-motion is processed in real time during shooting and displayed to the user, and the conditions required for real-time processing are relatively difficult. 、 and 、 Recording time is relatively short hand , which is usually 1s. Therefore, in the past, gear shifting The recording format is 、 The operation steps are complicated, and 、 The processing process is complicated, and it is not convenient for users to operate. 、 Affects the user's experience.

[0021] In order to solve the above problem, the technical idea of ​​the present invention is to configure the speed change trigger operation, and recognize the speed change trigger operation; 、 The second variable speed recording format obtained is 、 Based on the second shifting mode, a first shifting mode matching the second shifting mode is obtained. do.That is, the first and second shift modes have opposite shift directions. and and 、 The shift speed is the same do. Next 、 After the target object recognized in the captured video image shows a target state, the captured video image is played back at a variable speed according to a second speed change form, and a user is notified that the speed change process is started. Then, a part of the video images in the target video generated by the video images and audio is played back at a normal speed and a part of the video images is played back according to the second speed change form, and the audio in the target video is ensured to be played back at a normal speed, thereby completing the video speed change process, and the processing process is simple; and 、 The operation steps have been simplified to further improve the user experience by allowing users to achieve variable speed recording with just convenient operations.

[0022] The technical solutions of this disclosure are as follows: 、 These specific examples will be described in more detail below. teeth, The same or similar concepts or processes may be combined with one another and may not be described in some embodiments.

[0023] In actual use, the embodiments of the present disclosure are implemented by, for example, 、 The terminal equipment can be a mobile terminal, a computer device (e.g., a desktop computer, a laptop computer, an all-in-one computer, etc.), etc., and the mobile terminal can be 、 This includes mobile devices with playback capabilities, such as smartphones, palmtop computers, tablets, and wearable devices with display screens. 、 The shooting interface can be used to shoot or record a target object, which can be a person, a scene, etc., and the playback interface can be used to play the target video, which can be a variable speed recorded audio-video. 、 There is no specific limitation to this.

[0024] In a certain scene, as shown in FIG. 1, which is a schematic diagram of a photography interface provided in an embodiment of the present disclosure, a terminal device can display a photography interface 10 for photographing a target object, and the photography interface 10 is provided with a photography button 101, a photography time switching button 102, a special effect editing button 103, a music selection button 104, and an album button 105, and may further include another photography function display area 106. Here, by clicking the photography button 101, the target object can be photographed. to Those skilled in the art will be able to easily recognize the functions of the shooting button 101, the shooting time switching button 102, the special effect editing button 103, the music selection button 104, and other shooting function display areas. 106 It should be understood that the location and size of the buttons can be set according to actual needs. Among them, the shooting button 101 is used to provide the user with a shooting start function, the shooting time switching button 102 is used to provide the user with a shooting time switching function, and the special effect editing button 103 is used to provide the user with special effects. do. However, the special effects can be equipped with default music as standard, and the shooting object, i.e. the target object, can be edited by special effect editing. to can recognize the target state, i.e. 、 A speed change processing operation can be triggered, a music selection button 104 can provide the user with a music library, and an album button 105 is used to provide the user with filmed material.

[0025] A video processing method according to an embodiment of the present disclosure 、 It can be applied to shooting or recording scenes, specifically 、It can be a video variable speed recording scene, for example, supporting the triggering of any arranged special effect editing effect, and this special effect editing effect is used to support the function of controlling video variable speed recording, and it recognizes whether the captured video image shows a target state, and when this target state is recognized during shooting or recording, i.e. 、 When a trigger operation is detected to control variable speed video recording, for example, 、 This allows for variable speed processing of video images or variable speed playback of audio during shooting, without requiring complicated operation steps. 、 There are no restrictions on the application scenario.

[0026] The technical solutions of the present disclosure will be described in detail below through specific examples. teeth, The same or similar concepts or processes may be combined with each other, and may not be described in some embodiments. 、 In the function display area of ​​this photographing interface 10, for example, 、 It can display multiple functions, such as invert, filter, beautify, countdown, special effect editing effect, album, music selection, shooting time, etc., and the special effect editing effect here is 、 It can also include special effects and editing effects to support video variable speed recording. 、 Predefined stickers are provided, which can include a variable speed processing rate for special effects, and recording at the required rate can achieve variable speed recording. do. And the target object to indicates the target state, the speed change form (including the speed change direction and the speed change speed) arranged in this special effect editing effect is obtained, and the speed change processing speed and the speed change direction (fast or slow) that can be selected by the user may be provided through the shooting interface, and then 、Based on the speed change form selected by the user, the target state shown by the target object is recognized in accordance with the recognizable speed change trigger form arranged in the special effect in the special effect editing effect.

[0027] The special effects editing effects arranged in the embodiments of the present disclosure can control variable speed recording by recognizing trigger actions or specific objects. Take stickers as an example, the stickers can be arranged as follows: time the speed change rate corresponding to this sticker is placed in the resource packet; the speed change playback event and the speed change rate are transmitted to the Video Expression (VE) Software Development Kit (SDK) and client in real time; a speed change recording message interface is added and required to be controlled within 10 frames at the latest; when creating a sticker, appropriate acceleration and appropriate frame addition are required; after entering the editing page, the speed returns to normal after slow playback; if an effect that slows down with the screen is required, a normal speed sticker can be placed, and particle effects and physical effects (fabric, feathers, etc.) can only be slowed down; a new interface may be set to transmit the speed change playback event and the speed change rate to the VE and client in real time; this sticker prohibits collaborative filming; this sticker does not record original sound; this sticker requires the rate adjustment function to be disabled. 、 There is no limitation on this.

[0028] Specifically, a person is used as the object of photography, and 、The special effect editing effect itself may include a speed-change trigger special effect and a speed-change form (one special effect editing effect may correspond to one speed-change trigger special effect, and one special effect may correspond to one speed-change form, one special effect editing effect may correspond to multiple speed-change trigger special effects, and one special effect may correspond to one speed-change form, one special effect editing effect may correspond to multiple speed-change trigger special effects, and multiple special effects may correspond to one speed-change form, or multiple special effects editing effects may correspond to one speed-change trigger special effect, and one special effect may correspond to one speed-change form, etc. There is a mapping relationship between the special effect and the speed-change form, and here 、 For example, a person (not particularly limited) is placed in the image capture interface 10, and this person is displayed on the image capture interface 10. In the image capture interface 10, the user can select the capture time, for example, 、 The 15 seconds shown in Figure 1 is the maximum time allowed for a photo shoot in the current photo shoot interface. time By clicking the special effect editing button 103 (see FIG. 2(a)), the user can display a special effect editing display field 1031 including a plurality of stickers (see FIG. 2(b)). The user can then select a predefined sticker, such as a sticker, in the special effect editing field. 、 Select Sticker 1, replace the location of the special effect editing button with Sticker 1 (see Figure 2 (c)), display the background image corresponding to Sticker 1 on the shooting interface, and also enable the above other functions. time You can click on it, for example 、 By clicking the music selection button 104 (see FIG. 3(a)), a music selection display interface 1041 (see FIG. 3(b)) is displayed, and the user 、 Search for your target music, e.g. 、 Search for Music 1 (see Figure 3 (c)) 、 You can check the use.

[0029] The order of operations shown in (a) of FIG. 2 and (a) of FIG. 3 is not particularly limited. In addition to (c) of FIG. 2 and (c) of FIG. 3, the user may 、The photographing function can be turned on by clicking the photographing button 101 in the photographing interface (see FIG. 4(a)). After the photographing function is turned on, the terminal device starts photographing the target object and displays the current photographing interface. 、 The progress bar 110 of the shooting time and the shooting end button 107 are displayed, the function module is hidden, and the shooting button 101 is updated to the shooting state. do. That is, 、 When the shooting button 101 is switched to the shooting pause button 1011 (see FIG. 4(b)), and when it is detected that a special effect (e.g., a smile) appears during shooting, a variable speed recording function can be triggered (see FIG. 4(c) for slow recording), and the video images are played back at a normal speed during shooting, and the audio is played back at a speed opposite to the speed required for the special effect. When the video is played back after shooting is completed, the video images shot after the acquired speed change trigger operation are played back according to the speed change required for the special effect, and the audio is played back at the normal speed. 、 To ensure that the audio played back at a normal speed when playing back a video that has been shot.

[0030] For example, if the special effect of the special effect editing effect is a smile, when a smile action is detected during shooting, an operation for controlling the video variable speed recording is triggered, and the variable speed recording rate required for this smile special effect, e.g. 、 To capture 2x slow motion, and also to play back the audio after the special effect is triggered at 2x quick speed, the audio is processed at 2x quick speed in the background (here on the audio-video side). In this case, when playing back after recording is completed, the audio is processed to ensure that it is played back without being interfered with by the original sound played back before the speed-shift recording and / or randomly appearing. 、Original sounds captured, such as ambient sounds and the original sounds of the music being played, are not recorded. Furthermore, during shooting, video images and audio may be played back at normal speed without the user noticing that variable speed recording is being performed. To satisfy the user's experience, for variable speed recording, the video images captured during shooting may be played back at normal speed, and after a variable speed trigger operation is turned on, the unplayed portion of the audio may be played back in a second variable speed mode that matches the first variable speed mode required for the special effect. After shooting is completed, the audio and video recorded before the special effect appears may be played back at normal speed, and after a special effect trigger operation (i.e., a variable speed trigger operation) is detected, the video may be played back at the speed required for the special effect, and 、 By playing audio at normal speed, it can realize variable speed video recording process, which is convenient for users and the process is simple. 、 Meet user needs and improve user experience.

[0031] The normal speed of the video here is the speed at which it was shot, and the normal speed of the audio is the speed of the audio itself. 、 There are no restrictions on the application scenario.

[0032] Furthermore, those skilled in the art will understand that the "trigger" operation can be a click trigger, which is realized by a user clicking a corresponding button or any position on the interface; a gesture trigger, which is realized by a user performing a corresponding gesture; an audio trigger, which is realized by a user issuing a corresponding audio command; an expression trigger, which is realized by a user issuing a corresponding audio command; The user To realize trigger operation by making corresponding facial expressions 、 The present disclosure may include, but is not limited to, 、 It should be understood that there is no limitation on trigger operations.

[0033] In one embodiment, the video processing method can be implemented in the following manner.

[0034] As shown in Figure 5, Figure 5 is a flowchart of a video processing method provided in an embodiment of the present disclosure. 、 The following steps S101 to S104 may be included.

[0035] In S101, audio is played while video is being captured.

[0036] In S102, in response to recognizing that a target object in the captured video image exhibits a target state, the target object in the captured video image is to indicates the target state 、 for a first portion of the audio representing an unplayed portion of the audio, 、 Variable speed reproduction is performed in accordance with the first variable speed mode.

[0037] The first shifting mode is 、 It may match the recognized target state. stomach. For example, a smile triggers a gear change operation, and 、 If the speed change mode is 2x slow playback, the first speed change mode is 2x quick playback, and the user may select and input the speed change mode before shooting the video, and there is no particular limitation here.

[0038] The method of the embodiment of the present disclosure 、 The present invention is applicable to a terminal device, and can display a photographing interface, which is a user interface for photographing a target object, on the terminal device. The photographing interface includes a photographing area, a function display area, and a photographing button. The function display area includes: 、 You can view the special effect editing modules by clicking the corresponding special effect editing button. 、 A plurality of special effect editing effects can be displayed to the user in the shooting interface, where the plurality of special effect editing effects are: 、Special effects editing effects to support video variable speed recording may be included. However, the display format of multiple special effects editing effects may differ. 、 There are no particular restrictions.

[0039] Specifically, the user 、 The recording function can be turned on by clicking the recording button on the device, and the default audio, the audio that comes standard with the special effects editing effect, or the audio selected by the user will be played while recording the video. 、 Detecting in real time whether there is an operation for controlling the speed change process of the video during shooting, i.e. 、 It recognizes whether the target object exhibits a target state, and if detected, responds to this recognized target state. 、 When recognizing that a target object exhibits a target state in a captured video image, 、 A first speed change form, which is a speed change form required for speed-change playback of the unplayed portion of the audio, is obtained. This first speed change form may be a form that matches a recording form required for special effects, for example. 、 If the recording / playback mode required for the special effect is 2x slow playback, the first speed change mode is 2x quick playback, and this first speed change mode may also be a mode input by the user. This target state is 、 The interaction actions may include preset objects included in the captured video and / or interaction actions may include facial and limb actions, such as smiling, blinking, raising a hand, and raising a leg. 、 The recognized target object is 、 for example 、 The preset objects may be clothing, cars, architecture, etc., although the present disclosure is not limited in this respect.

[0040] When actually using it, before the speed change trigger, the shooting interface should be displayed and 、 The recording function must be turned on, and before this, users can select special effects that correspond to variable speed recording, such as 、It is necessary to pre-select certain special effects editing effects. Specifically, the terminal device 、 The following steps a1 to a3 can be used to display the photography interface and turn on the photography function.

[0041] In step a1, the photographing interface for photographing a target object is displayed, and the photographing interface 、 Includes special effect editing buttons to support controlling video variable speed recording.

[0042] In step a2, when receiving a command to instruct to perform a photographing operation in a photographing interface in response to a first trigger operation acting on the special effect editing button, perform a first photographing operation, photograph a target object in the photographing interface, and detect whether the target object shows a target state, and the target state is 、 The state includes the target object performing a target action and / or a preset object appearing on the target object.

[0043] In step a3, if it is recognized that the target object exhibits a target state during video shooting, an operation for controlling variable speed video recording is performed.

[0044] In the embodiment of the present disclosure, when a user (hereinafter referred to as a user) who shoots / records a video starts an application program, the terminal device 、 Multiple switching interfaces can be displayed, allowing users to 、 Click the corresponding switch key to switch to the shooting interface 、 The user can jump to the photography interface 10 and display it. Here, the photography interface is 、A special effect editing button for controlling variable speed video recording may be included, specifically, in the form of a sticker. One sticker may activate a single speed recording function, or one sticker may support multiple speed recording functions. Therefore, a corresponding speed recording function can be triggered depending on the target object's behavior or the specific identity of the target object. For example, a smile may correspond to 2x slow-motion recording, and a hand gesture may correspond to 2x quick-motion recording. The special effect action on the sticker may be used to trigger a speed-shifting operation. A user can select another special effect editing effect, such as a speed-shifting special effect, before recording a video. When the target state indicated during recording is recognized, the corresponding speed-shifting operation can be performed based on the acquired speed-shifting pattern input by the user. This disclosure is not limited in this respect.

[0045] For example, in the special effect editing process, a speed change mode is configured in the special effect. In the shooting interface, before starting shooting, the user 、 By clicking the Special Effects button, you can select special effects to control the video speed in the special effects display area. do. Here, if there are multiple special effects editing effects for supporting the control of video variable speed recording, a target special effect editing effect corresponding to the rate at which the video is to be recorded can be selected from the special effects editing effects, and then 、 According to the special effect in the special effect editing effect, a corresponding target trigger operation is performed, and if there is one special effect editing effect to support the control of video variable speed recording, according to the recognizable special effect in the special effect editing effect. 、 The corresponding target trigger operation can be performed.

[0046] Specifically, after the user selects the special effect editing effect, the terminal device 、In response to a first trigger operation acting on the special effect editing button, the background environment of the special effect editing effect is displayed in the shooting interface, and when the user clicks the shooting button to turn on shooting, a command is generated to instruct the shooting interface to perform a shooting operation, and the terminal device receives the command and starts to perform the first shooting operation, which is a shooting operation. During shooting, a target trigger operation, for example, 、 The presence or absence of an interaction action such as a smile, a hand gesture, or a target construction and / or a target object is detected in real time, and if present, the client in the terminal device transmits a variable speed recording message corresponding to this target trigger operation to the audio / video side in the terminal device to record and save the current music at variable speed.

[0047] In S103, a target video is obtained based on the captured video image and the audio.

[0048] In S104, in the target video, the video image taken before the target object exhibits the target state is played at a normal speed, the video image taken after the target object exhibits the target state is played at a variable speed according to a second variable speed form, and the audio is played at a normal speed.

[0049] The first and second speed change modes have opposite speed change directions. and and 、 The shift speed is the same.

[0050] In this embodiment, the captured video image and audio are synthesized to obtain the audio-video to be played, i.e., the target video. 、 Playing a target video, during the target video playback process, playing back at normal speed the video images captured before the target object exhibits the target state; and 、The video image captured after the target object exhibits the target state is played back at a variable speed according to a second variable speed mode, and the audio is played back at a normal speed.

[0051] The normal speed of the video is the shooting speed, and the normal speed of the audio is the speed of the audio itself. The second speed change mode is opposite to the first speed change mode. and For example, if the first speed change mode is 2x slow, the second speed change mode is 2x fast, and when the target video is played back after shooting is completed, the music is played at normal speed, aiming to improve the user's viewing experience.To ensure that the audio played back when shooting is completed is not interfered with by the original sound played back and / or randomly appearing before the speed change recording, the audio is processed and the original sound recorded is not recorded.

[0052] In one possible design, there is a mapping relationship between the target state and the first gear shift configuration, or the second gear shift configuration is determined in response to a user setting operation, and the first gear shift configuration is determined based on the second gear shift configuration.

[0053] In this embodiment, the target state and the first speed change mode have a mapping relationship, and the special effect editing effect is 、 The type and / or speed of the speed change itself can be default, so that the target state recognizable by the special effect editing effect can determine the corresponding type and / or speed of the speed change. Furthermore, the special effect editing effect may recognize the special effect, and different actions in the special effect may trigger different types of speed changes and even different speed changes, and 、 The target condition determines the type and / or speed of the shift.

[0054] Here, how to speed-change and play back the unplayed portion of the audio in accordance with the first speed-change form in response to recognizing that the target object indicates the target state in the captured video image is as follows: 、 This can be achieved by the following steps b1 and b2.

[0055] In step b1, in response to recognizing that a target object exhibits a target state in a captured video image, a first speed change form having a mapping relationship with the target state is determined.

[0056] In step b2, the first portion of the audio is reproduced at a variable speed in accordance with the first variable speed mode.

[0057] In this embodiment, in response to the recognized target state, a first shift configuration matching the target state is obtained according to the mapping relationship; and then 、 A first portion of the audio is reproduced at a variable speed based on a first speed variation form.

[0058] The second transmission mode is 、 The first shift mode is determined in response to a setting operation by a user. 、 The speed is determined based on the second shifting mode, and the user can set different speeds by pressing the slide rod, and can select and determine different types of shifting with a button. Here, there is no particular limitation on how the user selects or sets various shifting modes including the type and / or speed of shifting.

[0059] Specifically, this second shifting mode is 、The speed change mode may be a speed change mode required for a special effect, for example, if the speed change mode required for the special effect is 2x slow playback, the first speed change mode is 2x quick playback, and the second speed change mode is 2x slow playback, or may be a mode input by the user. Specifically, after the shooting is completed, the playback interface is displayed and a target video, which is a video that has been speed-changed by the playback interface, is played back. The target video here is a combination of a video image shot before the target object indicates the target state and changes speed, and a second video image. 2 The video image captured after the target object exhibits the target state is played back according to the speed-varying format of the video image captured after the target object exhibits the target state, and the audio is played back at normal speed. 2 The video image played back according to the speed change format is 、 It can be processed by frame addition or frame subtraction operations.

[0060] In addition, when you turn on the shooting function, the terminal device 、 Start shooting the target object, and play the currently shot video, where the content played includes the video image when shooting the target object and music played during shooting, and when a speed change is triggered, start a speed change process, and the target object in the shot video image is played. to indicates the target state, a first portion of the audio representing an unplayed portion of the audio is played back in a first speed-changing manner, where the start time of the first portion of the audio is 、 The time at which the photographing interface photographs the target object in response to recognizing that the target object exhibits the target state in the photographed video image (i.e. 、 The time when the speed change process is turned on is the end time of the first part of the audio. 、 This is the time to respond to the end of shooting, and this end time is 、It can be triggered by the user or the time when the shooting time is reached. For example, if the start time of the first part in the audio is the time when the shooting is turned on, it indicates that the target state is detected immediately when the shooting function is turned on, so that the video image to be played after the shooting is completed is 、 This is a video image that has been speed-shifted from the beginning.

[0061] Here, how to display the playback interface is as shown in Figure 6. 、 Yet another embodiment of the present disclosure provides Video processing methods 1 is a scene schematic diagram. Before playing the target object, the method includes: In response to a second trigger operation for instructing to end the shooting, jump to and display the playback interface for playing the target video; or The method may further include a step of jumping to the playback interface and displaying the playback interface after the shooting time in the shooting interface has ended.

[0062] In an embodiment of the present disclosure, when a user clicks the end shooting button 107 (shown in (a) of FIG. 6) during shooting, the terminal device responds to this click operation, which is a second trigger operation, and jumps from the shooting interface 10 to the playback interface 20 and displays it (see (b) of FIG. 6). If the user does not detect an operation to trigger the end shooting button 107 during shooting, after the shooting time in the shooting interface has ended, for example, the shooting progress bar in the shooting interface has reached the end position (see (c) of FIG. 6), and the shooting interface 10 automatically jumps to the playback interface 20 and displays it (see (b) of FIG. 6). The present disclosure 、 The manner of switching and jumping between the shooting interface and the playback interface is not specifically limited.

[0063] For example, if a smiling action is the target trigger operation (i.e., the target state), and the smiling action represents the trigger operation of double slow motion video recording, a special effect editing effect corresponding to the smiling action can be added first, and music can be selected, or the background music of the special effect editing effect corresponding to the smiling action can be used as the music for the video recording, and the terminal device will start to detect the target trigger operation. Specifically, whether there is a smiling action or not Determine , if there is a smile action, determine whether the current smile action occurs during shooting, and if so, determine whether to trigger a speed change state, and if so, send a message corresponding to the rate required for this smile action, i.e. 、 A message to record at 2x slow speed is sent to the audio / video VE, and the VE will quickly record the default music (the music currently playing in the recording interface). 、 (High-speed recording here can be 2x quick recording) and the original sound is not recorded. 、 The recorded target audio is sent to the client, and the client plays it back at double slow speed to shorten the total time, and then the recording and playback are completed.

[0064] This disclosure 、 The user does not need to operate the screen, but can control the shooting speed by simply smiling at the camera. In addition, there is no need to import the captured video into other editing pages or software, making the processing process simple and improving the user experience. In order to clearly explain the variable speed recording trigger and processing process, smile recognition is used as an example. 、 does not restrict interaction behaviors, including raising hands, covering mouths, shaking heads, etc.

[0065] The video processing method provided in the embodiment of the present disclosure plays audio while shooting video, and then 、In response to recognizing that the target object exhibits a target state in the captured video image, performing variable speed playback according to a first variable speed configuration on a first portion of the audio representing an unplayed portion of the audio when the target object exhibits the target state in the captured video image. cormorant. Then, a target video is obtained based on the captured video images and audio, and in the target video, the video images captured before the target object exhibits the target state are played at a normal speed, and the video images captured after the target object exhibits the target state are played at a variable speed according to a second variable speed mode; and 、 The audio is played at normal speed, and the first and second speed modes are in opposite speed directions. and and 、 The variable speed is the same, so that the audio in the target video is played at normal speed, and part of the video image is played at normal speed and part is played at variable speed, thereby realizing variable speed recording and playback for the video to be shot. 、 By recognizing the target state of the target object, an operation for controlling variable speed video recording can be initiated, and there is no need to input the shot video into video editing software or an editing page for corresponding slow playback or quick playback processing. In order to improve the user experience and make the user feel the variable speed recording strongly, after triggering variable speed recording during video shooting, the audio to be played back is played at variable speed according to a first speed change form. In the process of playing the generated target video after shooting is completed, the video to be shot after triggering speed change is played at variable speed according to a second speed change form, and the audio is played back at normal speed, thereby meeting the user's personalized needs and the processing process is simple. 、 The operation steps are simplified, allowing users to easily edit videos. gear shifting processing can be realized, and 、 Improve the user's experience.

[0066] Based on the above example, one embodiment of the present disclosure is , in at least two forms: Get the target video Ruko This can be done.

[0067] In the first embodiment, after the video image is subjected to speed change processing, 、 The audio will be played at normal speed and composited into the target video.

[0068] In step c1, the captured video images are recorded at a normal speed to obtain a first video.

[0069] In step c2, the first video is divided into a first video segment representing a segment of the first video before the target object exhibits the target state, and a second video segment representing a segment of the second video after the target object exhibits the target state.

[0070] In step c3, the second video segment is subjected to speed change processing in accordance with the second speed change mode to obtain a third video segment.

[0071] In step c4, the audio is synthesized into the stitched video of the first video segment and the third video segment to obtain the target video.

[0072] In this example teeth First, the captured video images are recorded at a normal speed to obtain the first video, and then 、 The first video is divided into a first video segment, which is a segment before the target object exhibits the target state, and a second video segment, which is a segment after the target object exhibits the target state. The first video segment is stored as is, and the second video segment is changed according to a second speed change form. 、The second video segment is subjected to a frame addition or frame subtraction process to obtain a third video segment, where the third video segment is a video image after the speed change process. 、 The first video segment stored and the third video segment obtained by the speed change process are stitched together to obtain a stitched video, and the audio is played, recorded, and stored at normal speed. 、 The stitched video is then composited to obtain the target video. Since it is a background process rather than a real-time process, it can support variable speed processing that differs from the time of the conventional technology, and is easy to operate, eliminating the need for additional editing software, improving the user experience.

[0073] In the second embodiment, the target video is generated by stitching the time-shifted video image and the time-shifted audio.

[0074] In step d1, during the video shooting, the reproduced video image and audio are recorded to obtain a second video, and in the second video, the audio is reproduced at a normal speed before the target object exhibits the target state, and after the target object exhibits the target state, 、 The audio is played back at a first variable speed mode, and the captured video images are played back at a normal speed.

[0075] In step d2, the second video is divided into a third video segment representing a segment of the second video before the target object exhibits the target state, and a fourth video segment representing a segment of the second video after the target object exhibits the target state.

[0076] In step d3, the fourth video segment is speed-shifted according to the second speed-shifting manner to obtain a fifth video segment, and the third video segment and the fifth video segment are stitched together to obtain the target video.

[0077] In this embodiment, during the video shooting, the played video images and audio are recorded to obtain a second video, and the audio recorded before the target object exhibits the target state is played at a normal speed, and the audio recorded after the target object exhibits the target state is played at a variable speed according to a first variable speed mode, and the recorded video images are played at a normal speed. Here, the second video is 、 The video is divided into a third video segment, which is a segment before the target object exhibits the target state, and a fourth video segment, which is a segment after the target object exhibits the target state.

[0078] Specifically, the third video segment is stored, and the fourth video segment is subjected to the second speed change process, i.e. 、 The image video in the fourth video segment is subjected to frame addition or frame subtraction processing, and the audio in the fourth video segment, i.e. 、 The audio that has been speed-shifted and played back according to the first speed-shift format is then played back according to the second speed-shift format, so that the audio is played back at normal speed. The saved third video segment and the speed-shifted fifth video segment are stitched together to obtain the target video. Because this is a background process rather than a real-time process, it can support speed-shifting processes that are different from those of conventional technologies, is easy to operate, and does not require the introduction of additional editing software, improving the user experience.

[0079] Here, in order to ensure that the audio played in the first speed change mode is played at a normal speed, the speed change direction is opposite to that of the first speed change mode. and and 、 First, a variable speed recording is performed using a second variable speed mode with the same speed to obtain audio processed using the first variable speed mode. For example, if the first variable speed mode is 2x slow speed, then the second variable speed mode is 2x quick speed. 、The audio processed by the first speed change format is then subjected to speed change processing according to the second speed change format to obtain audio that is played at normal speed, i.e., audio that is played in the target video.

[0080] Specifically, the terminal equipment 、 Get the currently playing target music when triggering variable speed recording during shooting, then 、 The audio after the target state is displayed is recorded at a variable speed in accordance with the determined second variable speed mode, and variable speed audio that does not include the original sound when shooting in the shooting interface is generated.

[0081] Here, the start time of the audio recorded at the first speed change mode is 、 The end time of the audio recorded at variable speed using the first variable speed mode is the time corresponding to the progress of the music played when the shooting interface shoots the target object at the end of shooting (i.e., the time when variable speed recording ends).

[0082] Here, the rate of change is 、 The speed includes slow, quick, and normal speeds, and the speed is any value between 0.333 and 3. The speed change can be expressed by a speed multiplier. For example, the first speed change is 2 times slow, for example: 、 The video image recorded at the normal rate is 30 frames / s, and according to the rate of 2 times slower, the video image undergoes a corresponding frame reduction operation, for example: 、 The recorded video images are recorded at 30 frames in 2 seconds, and when played back, the playback rate of each frame of the video image is slow.

[0083] Based on the above embodiment, as an embodiment of the present disclosure, after turning on the shooting function, the video processing method: In response to a second trigger operation for instructing the end of shooting, the first speed change mode, the second speed change mode, and the special effect editing effect state are changed. 、 and resetting at least one of the states of the photography interface.

[0084] In an embodiment of the present disclosure, the user 、 The user can click the end button in the shooting interface to end the shooting, and the terminal device 、 When a second trigger operation acting on the end button is detected, a message to reset the recording speed is sent in response to the second trigger operation, the VE state is reset, the client state is reset, and the shooting state is updated. Specifically, the first speed change mode and / or the second speed change mode and / or the state of the special effect editing effect and / or the state of the shooting interface are reset.

[0085] Specifically, the specific flow when the user clicks Start Shooting / Stop Special Effects Editing is as follows: 、 First, it determines whether to start recording or not. If it starts recording, it updates the recording state and ends the recording start state. If it does not start recording, it determines whether to end recording or not. If it ends recording, it sends a message to reset the recording speed, controls the VE state reset and the client state reset, and then 、 Update the capture state and end the capture state.

[0086] Based on the above embodiment, one embodiment of the present disclosure will describe in detail a video processing method. After jumping to display the playback interface, the video processing method is as follows: 、 Furthermore, this can be achieved by the following steps e1 and e2.

[0087] In step e1, in response to a first return trigger operation, the playback interface is controlled to return to the photographing interface including the photographed target object.

[0088] In step e2, when a command to instruct re-photographing is received, the content of the photography interface including the photographed target object is reset based on the command to instruct re-photographing, and the photography interface is terminated.

[0089] In the embodiment of the present disclosure, after jumping to the playback interface and displaying, the target video, which is the recorded video, is played in the playback interface, and the user can return to the shooting interface to re-edit, re-shoot, or 、 If you want to continue shooting, you can click the first back button on the playback interface, and the terminal device will 、 In response to a first return trigger operation acting on the first return button, the playback interface returns to a shooting interface including the photographed target object, i.e. 、 The camera jumps to the shooting interface in the shooting pause state and displays it. 、 In the current shooting interface, you can choose to cancel the content you are currently shooting, i.e. 、 The user 、 Click the second back button on the current shooting interface to generate a command to instruct re-shooting and send it to the terminal device. The terminal device will 、 Upon receiving this command, reset the content of this photography interface based on this command and exit the current photography interface, making it easier for users to re-photograph; 、 The interaction is easy.

[0090] Based on the above embodiment, one embodiment of the present disclosure will describe in detail a video processing method, which includes: 、 The following steps f1 and f2 may be further included.

[0091] In step f1, after controlling the playback interface to return to the photographing interface including the photographed target object, or 、When a command to instruct to temporarily stop photographing is received when photographing a target object on the photographing interface, it is detected whether or not a progress bar of photographing time on the current photographing interface reaches an end position.

[0092] In step f2, if the end position is not reached and a command to instruct to execute a photographing operation in the photographing interface is received, control is performed to continue executing the photographing operation in the photographing interface.

[0093] In the embodiment of the present disclosure, if the shooting time in the shooting interface has not yet ended, the user 、 In the current shooting interface, it is possible to continue shooting following the original shooting content. This can be achieved by at least two types of scenes:

[0094] In scene 1, the current interface is the playback interface, and the user clicks the first return button on the playback interface, so that the terminal device returns the playback interface to the shooting interface in the shooting pause state, and the shooting interface in this state displays the shooting time progress bar, and detects whether the shooting time progress bar on the shooting interface in this state reaches the end position. 、 It is determined whether or not photography can be continued, and if the end position is not reached, the user can click the photography button in the photography interface in this state, and the terminal device receives a command to instruct the user to perform a photography operation in the photography interface, and continues to perform the photography operation in the photography interface based on this command.

[0095] In scene 2, the current interface is the shooting interface, and 、The photographing interface is in a photographing pause state in response to a command input by the user to instruct to pause photographing. A photographing time progress bar is displayed on the photographing interface in this state, and whether photographing can be continued is determined by detecting whether the photographing time progress bar on the photographing interface in this state reaches an end position. If the end position is not reached, the user can click the photographing button on the photographing interface in this state, and the terminal device receives a command to instruct to perform a photographing operation on the photographing interface, and continues to perform the photographing operation on the photographing interface based on this command.

[0096] Therefore, the present disclosure 、 To solve the problem of audio and video mismatch caused by slowing down users' ability to shoot videos such as "slow motion transformation" and forcing users to record slow motion videos for more than 1 second or fast motion videos for special effect editing, a logic of "recognizing a certain trigger condition and changing the recording speed" is added to the special effect packet; 、 Special effects can transmit variable speed playback events between the audio-video side and the client side in real time, and perform variable speed recording on the audio-video side, helping users to create higher quality slow-motion or fast-motion videos more easily and improving the user experience.

[0097] Corresponding to the video processing method of the embodiment disclosed above, FIG. 、 7 is a structural block diagram of a video processing device provided in an embodiment of the present disclosure, where the video processing device can be a terminal device. For convenience of explanation, only the parts related to the embodiment of the present disclosure are shown. As shown in FIG. 7, the video processing device 70 、 The imaging module 701 includes a processing module 702 and a playback module 703. 701is used to play audio while the video is being captured, and the processing module 702, in response to recognizing that the target object exhibits a target state in the captured video image, Object indicates the target state, the processing module is used to perform variable speed playback on a first portion of the audio representing an unplayed portion of the audio according to a first speed variation form, 702 a playback module for obtaining a target video based on the captured video image and the audio; 703 is used to play back, in the target video, a video image taken before the target object exhibits the target state at a normal speed, to play back, in a second speed-changing manner, a video image taken after the target object exhibits the target state, and to play back the audio at a normal speed. do. Here, the first speed change mode and the second speed change mode are 、 Shift direction is opposite and and 、 The shift speed is the same.

[0098] The imaging module 701 and the processing module 702 provided in the embodiment of the present disclosure 、 and the playback module 703 plays back the video while the video is being captured, and subsequently, in response to recognizing that the target object exhibits the target state in the captured video image, 、 performing variable speed playback of a first portion of the audio representing an unplayed portion of the audio according to a first speed variation form; obtaining a target video based on the captured video images and the audio; playing back, in the target video, the video images captured before the target object exhibits the target state at a normal speed; and playing back, in the target video, the video images captured after the target object exhibits the target state according to a second speed variation form; and 、 Play audio at normal speed do.Here, the first and second shift modes are 、 Shift direction is opposite and and 、 The speed of the shift is the same, so that the target video 、 It is guaranteed that audio is played at normal speed, and that some video images are played at normal speed and some at variable speed, thereby realizing variable speed recording and playback of the video being shot. 、 By recognizing the target state indicated by the target object, an operation for controlling variable speed video recording can be initiated, and there is no need to input the shot video into video editing software or an editing page for corresponding slow playback or quick playback processing. In order to improve the user experience and make the user feel the variable speed recording strongly, after triggering variable speed recording during video shooting, the audio to be played back is played at a variable speed according to a first variable speed mode, and in the process of playing the generated target video after shooting is completed, the video to be shot after triggering the variable speed mode is played at a variable speed according to a second variable speed mode, and the audio is played back at a normal speed, thereby meeting the user's personalized needs and the processing process is simple; 、 The operation steps are simplified, allowing users to easily edit videos. gear shifting processing can be realized, and 、 Improve the user's experience.

[0099] The device provided in the embodiment of the present disclosure is the first embodiment. Like It can be used to implement the technical solutions of the embodiments of the described video processing method, and its realization principles and technical effects are similar, and the embodiments of the present disclosure 、 Here, overlapping explanations will be omitted.

[0100] In an embodiment of the present disclosure, based on the above embodiment, an embodiment of the present disclosure will now be described in detail with respect to a video processing device, in which the target state and the first speed variation form have a mapping relationship, and the processing module 702 is specifically used to determine the first speed variation form having a mapping relationship with the target state in response to recognizing that the target object indicates the target state in the captured video image, and perform speed variation playback on the first portion of the audio according to the first speed variation form.

[0101] In one embodiment of the present disclosure, the target state includes a state in which the target object is performing a target action and / or a state in which a preset object appears on the target object.

[0102] In one embodiment of the present disclosure, the processing module 702 is specifically used to record the captured video images at a normal speed to obtain a first video, divide the first video into a first video segment representing a segment of the first video before the target object exhibits the target state and a second video segment representing a segment of the second video after the target object exhibits the target state, speed-shift the second video segment according to the second speed-shift form to obtain a third video segment, and synthesize the audio into the stitched video of the first video segment and the third video segment to obtain the target video.

[0103] In one embodiment of the present disclosure, the processing module 702 is more specifically used to record the played video images and audio during video shooting, obtain a second video, play the audio in the second video at a normal speed before the target object exhibits the target state, play the audio at a first speed-shifted form after the target object exhibits the target state, play the captured video images at a normal speed, divide the second video into a third video segment representing a segment of the second video before the target object exhibits the target state and a fourth video segment representing a segment of the second video after the target object exhibits the target state, speed-shift process the fourth video segment according to the second speed-shifted form, obtain a fifth video segment, stitch the third video segment and the fifth video segment together, and obtain the target video.

[0104] In one embodiment of the present disclosure, the second gear shifting mode is determined in response to a setting operation by a user, and the first gear shifting mode is determined based on the second gear shifting mode.

[0105] In one embodiment of the present disclosure, the processing module 702 、 Furthermore, in response to a second trigger operation for instructing the end of shooting, the first speed change mode, the second speed change mode, and the special effect editing effect state are changed. 、 and is used to reset at least one of the states of the capture interface.

[0106] In one embodiment of the present disclosure, the playback module 703 、 Furthermore, before playing back the target video, in response to a second trigger operation for instructing the end of shooting, the trigger is used to jump to and display a playback interface for playing back the target video.

[0107] In one embodiment of the present disclosure, the processing module 702、 Furthermore, after jumping to and displaying the playback interface, in response to a first return trigger operation, the playback interface is controlled to return to the shooting interface including the photographed target object, and when a command to instruct re-shooting is received, the content of the shooting interface including the photographed target object is reset based on the command to instruct re-shooting, and the shooting interface is used to terminate the shooting interface.

[0108] In one embodiment of the present disclosure, the processing module 702 、 and then controlling the playback interface to return to the photographing interface including the photographed target object; or 、 When receiving a command to instruct to temporarily stop photographing when photographing a target object on the photographing interface, the progress bar of the photographing time on the current photographing interface is detected to reach an end position, and if the progress bar does not reach the end position, when receiving a command to instruct to execute a photographing operation on the photographing interface, the control unit is used to control to continue executing the photographing operation on the photographing interface.

[0109] In one embodiment of the present disclosure, the playback module 703 、 Furthermore, before playing the target video, it is used to jump to the playback interface for display after the shooting time in the shooting interface is over.

[0110] The modules may be implemented as software components running on one or more general-purpose processors, or as hardware performing certain functions or a combination thereof, such as programmable logic devices and / or application-specific integrated circuits. In some embodiments, the modules may be embodied in the form of a software product, which may be stored on a non-volatile storage medium, and the non-volatile storage medium may include instructions that cause a computing device (e.g., a personal computer, a server, a network device, a mobile terminal, etc.) to implement the methods described in the embodiments of the present invention. In one embodiment, the modules may be implemented in a single device or distributed across multiple devices. The modules may be functionally merged with each other or further divided into multiple sub-modules.

[0111] As will be apparent to those skilled in the art, for convenience and brevity, the above-described video For the specific operation process of the module of the processing device, reference can be made to the corresponding process in the method embodiment, and the duplicated description will be omitted here.

[0112] Based on the same inventive concept as the method, an embodiment of the present application is an electronic device, including a processor and a memory, There is further provided an electronic device in which a memory is used to store a program for carrying out the method according to each of the method embodiments above, and a processor is configured to execute the program stored in the memory.

[0113] This electronic device is 、 This electronic device can be a terminal device. 、The electronic device includes a processor and a memory, the memory being used to store a program for executing the method according to each of the above method embodiments, and the processor being configured to execute the program stored in the memory. The processor may be a central processing unit (CPU) or other form of processing device having data processing capability and / or instruction execution capability, and may also control other components in the electronic device to perform desired functions. The memory may 、 It may include one or more computer program products, such as 、 The computer-readable storage medium may include various forms of volatile and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache). The non-volatile memory may include, for example, read-only memory (ROM), hard disk, etc. 、 and flash memory. 、 One or more computer program instructions may be stored and executed by a processor to implement the functionality of the embodiments of the present disclosure described above and / or other desired functionality.

[0114] The terminal device is 、 The devices may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (abbreviated as PDAs), tablets, portable media players (abbreviated as PMPs), in-vehicle terminals (e.g., in-vehicle navigation terminals), and wearable electronic devices, as well as fixed terminals such as digital TVs and desktop computers. The electronic devices shown in FIG. 8 are merely examples and do not limit the functions and scope of use of the embodiments of the present disclosure.

[0115] Figure 8 is a book8 shows a structural schematic diagram of an electronic device for implementing the disclosed embodiments. As shown in FIG. 8, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 801 that can execute various appropriate operations and processes based on a program stored in a read only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. The RAM 803 contains 、 The processor 801 and the ROM 802 also store various programs and data necessary for the operation of the electronic device. 、 and RAM803 、 They are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0116] Generally, the device 806 includes, for example, a touch panel, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; the output device 807 includes, for example, a liquid crystal display (abbreviated as LCD), a speaker, a vibrator, etc.; the storage device 808 includes, for example, a magnetic tape, a hard disk, etc.; 、 A communication device 809 can be connected to the I / O interface 805. The communication device 809 allows the electronic device to communicate wirelessly or via wires with other devices to exchange data. Although FIG. 8 shows an electronic device with various devices, it is not necessary to implement all of the devices shown. 、 It should be understood that it is not necessary to provide more or 、 Implement fewer devices, or 、 It can be prepared.

[0117] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as a computer software program. TaThe computer program product may include a computer program loaded onto a readable medium, the computer program including program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication device 809, or 、 Installed from storage device 808, or 、 The computer program can be installed from the ROM 802. When executed by the processing unit 801, the computer program performs the functions defined in the method of the embodiment of the present disclosure. The embodiment of the present disclosure further includes a computer program, which, when executed by the processor, is used to perform the functions defined in the method of the embodiment of the present disclosure.

[0118] It should be noted that the computer-readable medium of the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. 、 It may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium include an electrical connection having one or more leads, a portable computer magnetic disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, optical fiber, a compact disc-read-only memory (CD-ROM), an optical storage element, a magnetic storage element, or 、It may include, but is not limited to, any suitable combination of the above. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used in or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may be a data signal that has computer-readable program code loaded thereon, in baseband or 、 It may include a data signal propagated as part of a carrier wave. Such propagated data signals may be electromagnetic, optical, or 、 The computer-readable signal medium may take a variety of forms, including, but not limited to, any suitable combination of the above. 、 The computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, and may transmit, propagate, or transmit a program for use in or in conjunction with an instruction execution system, device, or element. The program code contained in the computer-readable medium may be transmitted over a wire, optical cable, radio frequency (RF), or the like, or 、 It may be transmitted over any suitable medium, including, but not limited to, any suitable combination thereof.

[0119] The computer-readable medium may be included in the electronic device, or may exist independently of the electronic device.

[0120] The computer-readable medium has loaded thereon one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the disclosed embodiments.

[0121] Computer program code for carrying out the operations of the present disclosure may be written in one or more programming languages, or any combination thereof, such as Java (registered trademark), Smalltalk, C++, and other object-oriented programming languages, as well as conventional process-oriented programming languages ​​such as "C" or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, and partially on the user's computer. 、 and 、 It may be partially executed on a remote computer or may be executed entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to the user's computer via a network (e.g., 、 It may be connected to an external computer (via the Internet by an Internet Service Provider).

[0122] The flowcharts and block diagrams in the drawings illustrate systems, methods, and methods according to various embodiments of the present disclosure. 、 and executable system architectures and functions of computer program products 、 In this regard, each block in the flowchart or block diagram represents a 、 It can represent a module, program segment, or part of code, and the module, program segment, 、 Alternatively, a portion of code may include one or more executable instructions for implementing a specified logical function. It should also be noted that in alternative embodiments, the functions noted in the blocks may be implemented out of the order noted in the figures. For example, two successively shown blocks may be executed substantially in parallel, or may be executed in reverse order depending on the functionality. Each block in the block diagrams and / or flowcharts, and 、It should also be noted that combinations of blocks in the block diagrams and / or flowcharts may be implemented by dedicated hardware-based systems that perform the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0123] The unit according to the embodiment of the present disclosure is 、 It may be implemented in the form of software or hardware. Here, the name of the unit is 、 Without limiting the unit itself in some cases, for example, the first obtaining unit may be described as "a unit for obtaining at least two Internet Protocol addresses."

[0124] The functionality described herein above may be performed, at least in part, by one or more hardware logic components, including, for example, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logic Devices (CPLDs), etc. 、 Exemplary hardware logic components may be used, but are not limited to these.

[0125] In the context of this disclosure, a machine-readable medium may be a tangible medium, such as an instruction execution system, a device, 、 or used in equipment, instruction execution systems, devices 、 or includes a program used in conjunction with the equipment; or 、The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may be electronic, magnetic, optical, electromagnetic, infrared, or 、 semiconductor systems, devices or equipment; 、 This may include, but is not limited to, any suitable combination of the above. Reading medium A more specific example of the body is 、 Electrical connections made by one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fibers, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or 、 includes any suitable combination of the above.

[0126] An embodiment of the present disclosure provides a computer program product including a computer program that, when executed by a processor, causes the computer program to implement the video processing method described in the first aspect above.

[0127] In a first aspect, embodiments of the present disclosure include: playing audio while capturing video; In response to recognizing a target object in the captured video image exhibiting a target state, to indicates the target state, performing variable speed playback on a first portion of the audio representing an unplayed portion of the audio according to a first speed change form; obtaining a target video based on the captured video image and the audio; In the target video, playing back at a normal speed a video image taken before the target object exhibits the target state, playing back at a variable speed a video image taken after the target object exhibits the target state according to a second variable speed format, and playing back the audio at a normal speed; The first and second speed change modes have opposite speed change directions. and and 、 To provide a video processing method in which the speed change rate is the same.

[0128] According to one or more embodiments of the present disclosure, the target state and the first shifting configuration to There is a mapping relationship.

[0129] In response to recognizing that the target object exhibits a target state in the captured video image, the unplayed portion of the audio is played back at a variable speed in accordance with a first speed change form. Rusu Tep is determining a first speed change configuration having a mapping relationship with a target state in response to recognizing that the target object exhibits a target state in the captured video image; and playing back the first portion of the audio at a variable speed according to the first speed variation format.

[0130] According to one or more embodiments of the present disclosure, the target state includes a state in which the target object is performing a target action and / or a preset object appears on the target object.

[0131] According to one or more embodiments of the present disclosure, the step of obtaining a target video based on the captured video image and the audio includes: recording the captured video images at a normal speed to obtain a first video; dividing the first video into a first video segment representing a segment of the first video before the target object exhibits the target state and a second video segment representing a segment of the second video after the target object exhibits the target state; a step of speed-changing the second video segment according to the second speed-changing pattern to obtain a third video segment; and combining the audio with a stitched video of the first video segment and the third video segment to obtain the target video.

[0132] According to one or more embodiments of the present disclosure, the step of obtaining a target video based on the captured video image and the audio includes: During the shooting of the video, recording the played video images and audio to obtain a second video, in which the audio is played at a normal speed before the target object exhibits the target state, and the audio is played at a first variable speed form after the target object exhibits the target state, and the shot video images are played at a normal speed; dividing the second video into a third video segment representing a segment of the second video before the target object exhibits the target state and a fourth video segment representing a segment of the second video after the target object exhibits the target state; The method includes a step of: speed-changing the fourth video segment according to the second speed-changing form to obtain a fifth video segment; and stitching the third video segment and the fifth video segment to obtain the target video.

[0133] According to one or more embodiments of the present disclosure, the second gear shifting configuration is determined in response to a user's setting operation, and the first gear shifting configuration is determined based on the second gear shifting configuration.

[0134] In a second aspect, embodiments of the present disclosure include 、 There is provided a video processing device, the device comprising: a recording module for playing audio while recording video; In response to recognizing that the target object exhibits a target state in the captured video image, Object indicates the target state, the processing module for performing variable speed playback on a first portion of the audio representing an unplayed portion of the audio according to a first speed variation form, a processing module for obtaining a target video based on the captured video image and the audio; a playback module for playing back, in the target video, video images taken before the target object exhibits the target state at a normal speed, playing back video images taken after the target object exhibits the target state at a variable speed according to a second variable speed format, and playing back the audio at a normal speed; The first speed change mode and the second speed change mode and teeth 、 Shift direction is opposite and and 、 The shift speed is the same.

[0135] According to one or more embodiments of the present disclosure, there is a mapping relationship between the target state and the first speed variation form, and the processing module is specifically used to determine a first speed variation form having a mapping relationship with the target state in response to recognizing that the target object exhibits the target state in the captured video image, and perform speed variation playback on the first portion of the audio according to the first speed variation form.

[0136] According to one or more embodiments of the present disclosure, the target state includes a state in which the target object is performing a target action and / or a preset object appears on the target object.

[0137] According to one or more embodiments of the present disclosure, a processing module Lu is Specifically, the captured video image is recorded at a normal speed to obtain a first video, the first video is divided into a first video segment representing a segment of the first video before the target object exhibits the target state and a second video segment representing a segment of the second video after the target object exhibits the target state, the second video segment is speed-shifted according to the second speed-shifting form to obtain a third video segment, and the audio is synthesized into the stitched video of the first video segment and the third video segment to obtain the target video.

[0138] According to one or more embodiments of the present disclosure, the processing module 702 is more specifically used to record the played video images and audio during video shooting, obtain a second video, play the audio in the second video at a normal speed before the target object exhibits the target state, play the audio at a first speed-shifted form after the target object exhibits the target state, play the captured video images at a normal speed, divide the second video into a third video segment representing a segment of the second video before the target object exhibits the target state and a fourth video segment representing a segment of the second video after the target object exhibits the target state, speed-shift process the fourth video segment according to the second speed-shifted form, obtain a fifth video segment, stitch the third video segment and the fifth video segment together, and obtain the target video.

[0139] According to one or more embodiments of the present disclosure, the second transmission configuration is 、 The first shift mode is determined in response to a setting operation by a user. 、 This is determined based on the second shift mode.

[0140] In a third aspect, an embodiment of the present disclosure is an electronic device, comprising: at least one processor and a memory; the memory stores computer-executable instructions; The at least one processor executes computer-executable instructions stored in the memory, thereby causing the at least one processor to perform the video processing method according to any one of the first aspects.

[0141] In a fourth aspect, embodiments of the present disclosure include 、 A computer-readable storage medium is provided, the computer-readable storage medium storing computer-executable instructions, and a processor 、 The computer-executable instructions, when executed, effect the video processing method according to any one of the first aspects above.

[0142] In a fifth aspect, embodiments of the present disclosure include 、 A computer program product including a computer program, which when executed by a processor, performs the first aspect of the present invention. Either The present invention provides a computer program product in which the video processing method according to the present invention is implemented.

[0143] In a sixth aspect, an embodiment of the present disclosure comprises 、 A computer program is provided, which, when executed by a processor, performs the method according to the first aspect. Either This is used to implement the video processing method described in

[0144] The above description is merely a description of the preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art will understand that the scope of the present disclosure is not limited to the technical solutions based on the specific combinations of the above technical features, 、 It should cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the spirit of the above disclosure, including, for example, technical solutions formed by replacing the above features with technical features having similar functions disclosed in this disclosure (but not limited to).

[0145] Additionally, although operations have been described in a particular order, it should not be understood that these operations are required to be performed in the particular order or sequential order shown. In certain situations, multitasking and parallel processing may be advantageous. Similarly, although the above description includes details of several specific embodiments, these should not be construed as limiting the scope of the disclosure. Certain features described in the context of separate examples may be used interchangeably. 、 Conversely, various features that are described in the context of a single embodiment may also be implemented in combination in a single embodiment. 、 In multiple embodiments, the features may be implemented singly or in any suitable subcombination.

[0146] Although the present subject matter has been described using language specific to structural features and / or logical operations of methods, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or operations described above. Rather, the specific features and operations described above are merely example methods for implementing the claims.

[0147] This application is a Chinese patent application filed on December 18, 2020, with application number 202011508607.2 and an invention title of "Video processing method, device, equipment, storage medium, and computer program product." About Priority is claimed, the contents of which are incorporated herein by reference.

Claims

1. 1. A video processing method comprising the steps of: playing audio during the video capture, without recording the original sound captured during the video capture; in response to recognizing that a target object in a captured video image exhibits a target state, performing variable speed playback in accordance with a first speed variation form on a first portion of the audio representing an unplayed portion of the audio when the target object in the captured video image exhibits the target state; obtaining a target video based on the captured video images and the audio; playing back, in the target video, a video image taken before the target object exhibits the target state at a normal speed, playing back, in a second speed change manner, a video image taken after the target object exhibits the target state, and playing back the audio at a normal speed; The first shift mode and the second shift mode have opposite shift directions and the same shift speed. A method comprising:

2. There is a mapping relationship between the target state and the first shift mode, The step of playing back the unplayed portion of the audio in accordance with a first speed variation form in response to recognizing that the target object indicates a target state in the captured video image includes: determining the first speed change configuration having a mapping relationship with the target state in response to recognizing that the target object exhibits the target state in the captured video image; and playing back the first portion of the audio at a variable speed in accordance with the first speed variation form.

2. The method according to claim 1 .

3. The target state includes a state in which the target object is performing a target action and / or a preset object appears on the target object.

3. The method according to claim 1 or 2.

4. The step of obtaining a target video based on the captured video image and the audio includes: recording the captured video images at a normal speed to obtain a first video; dividing the first video into a first video segment representing a segment of the first video before the target object exhibits the target state and a second video segment representing a segment of the second video after the target object exhibits the target state; speed-changing the second video segment according to the second speed-changing format to obtain a third video segment; synthesizing the audio into a stitched video of the first video segment and the third video segment to obtain the target video; The method according to any one of claims 1 to 3, characterized in that

5. The step of obtaining a target video based on the captured video image and the audio includes: During the shooting of the video, recording the played video images and audio to obtain a second video, in which the audio is played at a normal speed before the target object exhibits the target state, and the audio is played in a first speed variation form after the target object exhibits the target state, and the shot video images are played at a normal speed; dividing the second video into a third video segment representing a segment of the second video before the target object exhibits the target state and a fourth video segment representing a segment of the second video after the target object exhibits the target state; speed-shifting the fourth video segment according to the second speed-shifting manner to obtain a fifth video segment, and stitching the third video segment and the fifth video segment to obtain the target video. The method according to any one of claims 1 to 3, characterized in that

6. The second gear shift mode is determined in response to a setting operation by a user, and the first gear shift mode is determined based on the second gear shift mode. The method according to any one of claims 1 to 5, characterized in that

7. Before the step of capturing a video, the method includes the steps of displaying a capture interface and turning on a capture function; Displaying a photography interface and turning on a photography function includes: displaying the photographing interface for photographing the target object, the photographing interface including a special effect editing button for supporting control of video variable speed recording; when receiving a command to instruct to perform a photographing operation in the photographing interface in response to a first trigger operation acting on the special effect editing button, performing a first photographing operation, photographing the target object in the photographing interface, and recognizing whether the target object shows the target state; The method according to any one of claims 1 to 6, characterized in that

8. The method further comprises: jumping to a playback interface for playing the target video in response to a second trigger operation for instructing an end of shooting, or jumping to the playback interface after a shooting time in the shooting interface ends; and playing the target video.

8. The method of claim 7.

9. After turning on the capture function, the method further comprises: resetting at least one of the first speed change mode, the second speed change mode, a state of a special effect editing effect, and a state of a shooting interface in response to the second trigger operation for instructing an end of shooting; 9. The method according to claim 8.

10. After the step of jumping to and displaying the playback interface, the method further comprises: In response to a first return trigger operation, controlling the playback interface to return to the photographing interface including the photographed target object; 9. The method according to claim 8.

11. A video processing device comprising: a recording module for playing audio during video recording, the recording module not recording the original sound recorded during video recording; a processing module for, in response to recognizing that a target object in a captured video image exhibits a target state, performing variable speed playback according to a first speed variation form on a first portion of the audio representing an unplayed portion of the audio when recognizing that the target object in the captured video image exhibits the target state; and a processing module for obtaining a target video based on the captured video images and the audio; a playback module for playing back, in the target video, a video image taken before the target object exhibits the target state at a normal speed, playing back a video image taken after the target object exhibits the target state at a variable speed according to a second variable speed format, and playing back the audio at a normal speed; The first shift mode and the second shift mode have opposite shift directions and the same shift speed. A video processing device comprising:

12. At least one processor; A memory, the memory storing computer executable instructions; Executing the computer-executable instructions stored in the memory by the at least one processor, thereby causing the at least one processor to perform the method according to any one of claims 1 to 10. An electronic device comprising:

13. A computer-readable storage medium having computer-executable instructions stored thereon, the computer-executable instructions being operable, when executed by a processor, to perform the method of any one of claims 1 to 10. A computer-readable storage medium comprising:

14. A computer program, which when executed by a processor performs the method according to any one of claims 1 to 10. A computer program comprising:

Images