CN111612873A

CN111612873A - GIF picture generation method and device and electronic equipment

Info

Publication number: CN111612873A
Application number: CN202010478312.9A
Authority: CN
Inventors: 付玉迪
Original assignee: Vivo Mobile Communication Co Ltd
Current assignee: Vivo Mobile Communication Co Ltd
Priority date: 2020-05-29
Filing date: 2020-05-29
Publication date: 2020-09-01
Anticipated expiration: 2040-05-29
Also published as: CN111612873B; WO2021238943A1

Abstract

The embodiment of the application provides a GIF picture generation method, a GIF picture generation device and electronic equipment, belongs to the technical field of communication, and can solve the problems that the sharing of GIF pictures is long in time consumption and even fails. The method comprises the following steps: receiving a first input of a user, wherein the first input is used for selecting a target object in a target video frame of a target video; in response to a first input, matting image content of a target object in each of M first video frames in a target video to obtain M target video images; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame. The method can be applied to the process of generating the GIF picture by the video.

Description

GIF picture generation method and device and electronic equipment

Technical Field

The application belongs to the technical field of communication, and particularly relates to a GIF picture generation method, a GIF picture generation device and electronic equipment.

Background

The Graphic Interchange Format (GIF) picture (or GIF picture, such as GIF picture emoticon) is interesting, so that the GIF picture is widely used in instant messaging application programs and other chat tools. However, the data size of the current GIF picture is usually large, which results in long time consuming and even failure of the GIF picture sharing.

Disclosure of Invention

The embodiment of the application aims to provide a GIF picture generation method, a GIF picture generation device and electronic equipment, and the problem that the sharing of the GIF picture is long in time and even fails can be solved.

In order to solve the technical problem, the present application is implemented as follows:

in a first aspect, an embodiment of the present application provides a GIF picture generation method, including: receiving a first input of a user, wherein the first input is used for selecting a target object in a target video frame of a target video; in response to a first input, matting image content of a target object in each of M first video frames in a target video to obtain M target video images; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame.

In a second aspect, an embodiment of the present application provides a GIF picture generating device, including: the receiving module is used for receiving a first input of a user, wherein the first input is used for selecting a target object in a target video frame of a target video; the editing module is used for responding to the first input received by the receiving module, and scratching the image content of the target object in each of M first video frames in the target video to obtain M target video images; the generating module is used for generating a target GIF picture based on the M target video images obtained by the editing module; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame.

In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, where the program or instructions, when executed by the processor, implement the steps of the GIF picture generating method according to the first aspect.

In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a program or instructions are stored, and when executed by a processor, the program or instructions implement the steps of the GIF picture generation method according to the first aspect.

In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or an instruction to implement the GIF picture generating method according to the first aspect.

In the embodiment of the application, the image content of the target object in each of the M first video frames in the target video can be extracted through the first input of selecting the target object in the target video frame of the target video by the user to obtain the M target video images; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame. Specifically, each target video image is a part of content which is extracted from one first video frame according to the target video object or the object selection frame, but not the whole content of the first video frame, for example, the part of content required by the user in the first video frame, so that the data volume of the target GIF picture obtained by converting the target video is small, and the successful sharing of the GIF picture is facilitated.

Drawings

Fig. 1 is a schematic flowchart of a picture generation method according to an embodiment of the present application;

fig. 2 is an operation diagram of a process of a picture generation method according to an embodiment of the present application;

fig. 3 is a second operation diagram of a process of a picture generation method according to an embodiment of the present application;

fig. 4 is a third operation schematic diagram of a process of a picture generation method according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a possible image generating apparatus according to an embodiment of the present disclosure;

fig. 6 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present disclosure;

fig. 7 is a second schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, the character "/" in the specification and claims generally indicates that the former and latter related objects are in an "or" relationship.

The GIF picture generation method provided by the embodiment of the application can be applied to a scene for generating the GIF picture, for example, a scene for generating the GIF picture through a video.

According to the GIF picture generation method, the GIF picture generation device and the electronic equipment, the image content of the target object in each of M first video frames in the target video can be extracted through the first input of selecting the target object in the target video frame of the target video by a user, and M target video images are obtained; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame. Specifically, each target video image is a part of content which is extracted from one first video frame according to the target video object or the object selection frame, but not the whole content of the first video frame, for example, the part of content required by the user in the first video frame, so that the data volume of the target GIF picture obtained by converting the target video is small, and the successful sharing of the GIF picture is facilitated.

The method for generating a GIF picture provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.

For example, the GIF picture generation method provided in the embodiment of the present application is described in detail with reference to the flowchart of the GIF picture generation method shown in fig. 1. Wherein, although the logical order of the GIF picture generation method provided by the embodiments of the present application is shown in the method flowchart, in some cases, the steps shown or described may be performed in an order different from that here. For example, the GIF picture generation method shown in fig. 1 may include steps 101 to 103:

step 101, the GIF picture generating device receives a first input of a user, wherein the first input is used for selecting a target object in a target video frame of a target video.

For example, the terminal provided by the embodiment of the present application may include a display screen, and the display screen may support touch input or fingerprint input of a user. Specifically, the first input may be a touch screen input or a fingerprint input. The touch screen input may be touch input such as pressing input, long-pressing input, sliding input, clicking input, and hovering input (input by a user near the touch screen) of the terminal by the user; the fingerprint input can be fingerprint input such as sliding fingerprint, long-time pressing fingerprint, single-click fingerprint and double-click fingerprint of a fingerprint identifier of the terminal by a user.

Wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames all comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame. That is, the selection of the target object from the respective first video frames is realized by the target video object or the object selection box.

Step 102, the GIF picture generating device, in response to the first input, scratches the image content of the target object in each of the M first video frames in the target video to obtain M target video images.

Wherein the M first video frames comprise target video frames, and M is a positive integer.

It should be noted that, in the following embodiments, the GIF picture generation method in the embodiment of the present application is described by an application scenario 1 to an application scenario 3, respectively.

Specifically, in application scenario 1, target objects in different first video frames satisfy: the target objects in different first video frames each contain a target video object (denoted as condition 1).

Alternatively, the target video object may be a person, an animal, or a still object in the video frame. For example, the target video object may be a foreground object (i.e., foreground) such as a person or animal in the video frame, or a background object (i.e., background) such as a tree or a building in the video frame.

In application scenario 2, the target objects in different first video frames satisfy: the target objects in different first video frames are all the objects in the object marquee (denoted as condition 2).

In application scenario 2, the target objects in different first video frames satisfy: the target objects in different first video frames all contain target video objects, and the target objects in different first video frames are all objects in the object selection box (marked as condition 3).

Optionally, the M first video frames are part or all of the video frames in the target video.

Optionally, the M first video frames may be video frames in a target video manually selected by a user or video frames in a target video automatically selected by the electronic device.

Specifically, the process of intercepting the image content of the target object in one first video frame by the GIF picture generating device specifically includes: and identifying the target object from the first video frame, and performing matting operation on the image content of the target object so as to obtain all pixel points of the image content of the target object.

For example, the video content of the target object in one of the M first video frames may be an irregularly-shaped image content, or one or more video objects (e.g., a foreground such as a person or an animal) in the first video frame. Therefore, the generated target GIF picture is more interesting.

And 103, generating a target GIF picture by the GIF picture generating device based on the M target video images.

The frame rate (marked as the target frame rate) of the target GIF picture is the frame rate or the preset frame rate of the target video.

Optionally, the preset frame rate may be selected manually by a user or defaulted by an electronic device, which is not specifically limited in this embodiment of the application and may be set according to an actual requirement of the user.

It can be understood that the electronic device may sequentially arrange the corresponding target video images according to the frame sequence of the M first video frames, so as to synthesize the M intercepted target video images into the target GIF picture according to the target frame rate.

Optionally, the display sizes of different target video images in the M target video images are the same or different, and may be determined according to actual requirements of users, which is not described in detail in this embodiment of the application.

It is understood that the target GIF picture may be a dynamic emoticon or a sticker.

According to the GIF image generation method provided by the embodiment of the application, the image content of the target object in each of M first video frames in the target video can be extracted through the first input of the user selecting the target object in the target video frame of the target video, so that M target video images are obtained; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame. Specifically, each target video image is a part of content which is extracted from one first video frame according to the target video object or the object selection frame, but not the whole content of the first video frame, for example, the part of content required by the user in the first video frame, so that the data volume of the target GIF image obtained by converting the target video is small, the successful sharing of the GIF image is facilitated, and the interest of the GIF image is high.

Optionally, the electronic device may provide a human-machine interaction interface for converting the video into the GIF picture (e.g., converting the target video into the target GIF picture), so as to enable the user to control the electronic device to generate the target video into the target GIF picture through the human-machine interaction interface.

Optionally, in this embodiment of the application, the electronic device may provide a control (denoted as a GIF sticker) for triggering the conversion of the video into the GIF picture, and be used for triggering the electronic device to execute a process of producing the GIF picture from the video. After the user inputs the GIF sticker control, the electronic device may provide the first content in each first video frame of the target video according to any application scene from the application scenes 1 to 3. For example, after the user inputs the control for making the GIF sticker, the electronic device may display one or more function controls, where each function control is used to acquire the first content in each first video frame in the target video by using any one of the application scenes 1 to 3.

For example, as shown in fig. 2 (a), in the case that the electronic device displays the content of the target video 31 on the video playing interface, a "make GIF sticker" control 32 may also be included in the video playing interface, where the "make GIF sticker" 32 is used to trigger the electronic device to generate the target video 31 as a target GIF picture. After the user inputs "make GIF sticker" 32 shown in fig. 3 (a), the electronic device may display a "main body GIF sticker" functionality control 33 and a "region GIF sticker" functionality control 34, as shown in fig. 2 (b). The "main GIF sticker" function control 33 and the "area GIF sticker" function control 34 are respectively used for triggering the electronic device to acquire the image content of the target object of each first video frame in the target video 31 according to the application scene 1 and the application scene 2, so as to obtain the target GIF picture. Specifically, in the application scenario 1, for each first video frame, the electronic device may first identify a target object and determine image content of the target object, and then perform a matting operation on the image content of the target object, so as to obtain a target video image in each first video frame.

Similarly, for the control for triggering the electronic device to acquire the first content in the first video frame according to the application scenario 3, reference may be made to the "main GIF sticker" function control 33 and the "area GIF sticker" function control 34 shown in (b) in fig. 2, which are not described in detail in this embodiment of the present application.

In a possible implementation manner, in the application scenario 1 and the application scenario 2 in the embodiment of the present application, the target object in each of the M first video frames includes a target video object.

Optionally, in application scenario 1, in this embodiment of the application, step 101 may further include step 104 and step 105. Accordingly, the above step 101 may be through step 101 a. Before the step 102, the method may further include the step 106:

and step 104, the GIF picture generation device receives a second input of the user.

For the description of the input mode of the second input, reference may be made to the description of the input mode of the first input in the foregoing embodiment, and details are not repeated here.

Step 105, the GIF picture generation means displays at least one video object identifier in response to the second input, each video object identifier indicating one video object in the target video frame.

It is understood that multiple video objects, such as multiple people, animals, or still objects, may be included in the target video. At this time, one or more video frames may also be included in each first video frame. Some video objects are always in the picture of the target video, that is, all video frames in the target video include the image content of the video objects; while other video objects are in partial pictures of the target video, i.e. partial video frames in the target video comprise the image content of these video objects.

For example, in application scenario 1, the target object may comprise one or more video objects in the target video, and the image content of the target object is in some or all of the video frames in the target video.

For example, the electronic device may provide an identification control, and in a case where the electronic device displays a first video frame, the identification control may trigger the electronic device to identify and mark one or more video objects in the first video frame, such as generating a tag for each of the one or more video objects, and then selecting a target object from the one or more video objects by the user. For example, the second input may be a click input to the recognition control described above.

Step 101a, the GIF picture generating device receives a first input of a target video object identifier of at least one video object identifier from a user.

At this time, the first input may be a click input.

And step 106, the GIF picture generation device determines the video object indicated by the target video object identification as the target video object, wherein the target object comprises the target video object.

Referring to fig. 2, after the user inputs the "main body GIF sticker" function control 33 shown in (b) of fig. 2, the electronic device may display a first video frame 41 (i.e., one first video frame in the target video) in the target video and a recognition control 42 on the screen, as shown in (a) of fig. 3. Subsequently, after the user makes an input (e.g., a second input) to the recognition control 42, the electronic device may display a "cat" tab 43 and a "ball" tab 44 below the first video frame 41, as shown in fig. 3 (b). Here, the "cat" tag 43 is used to mark a camera object of a cat in the first video frame 41, and the "ball" tag 44 is used to mark a video object of a ball in the first video frame. At this time, the M first video frames of the target video 31 include two video objects of "cat" and "ball". Subsequently, after the user inputs (e.g., the first input) the "cat" tag 43 shown in (b) of fig. 3, the electronic device may determine that the video object of cat in the target video 31 is the target video object. Further, the electronic device may determine a first video frame of the target video that contains image content of all target objects of the cat.

In addition, as shown in fig. 3 (a), the electronic device may further display video editing controls such as "cut", "text", and "music" for editing the target video.

Therefore, a user can intuitively and conveniently select the target video object meeting the requirement through at least one video object identifier, each target video image meets the requirement of the user, and the target GIF picture meets the requirement of the user. Therefore, the interest of the target GIF picture is improved.

In one possible implementation manner, in the application scene 2, the target object in each first video frame is an object in the object selection box; an object pick-up box is also included on a video frame (e.g., a target video frame) displayed on a screen (i.e., display screen).

Optionally, in the application scenario 2, the step 102 further includes a step 107 before, and the corresponding step 102 may be implemented by the step 102 b:

and step 107, the GIF picture generating device determines the object framed by the object selection frame as the target object.

It should be noted that, in the embodiment of the present application, the object selection box is used to select image content from video frames, such as to select image content of a target object in a first video frame. Specifically, the object framed by the object selection box may be an object in the object selection box in one video frame.

Alternatively, the shape of the object marquee may be any shape, such as a rectangle, a circle, a triangle, or an irregular shape, and may be determined according to the actual needs of the user, which is not specifically limited herein.

Optionally, the display size of the object selection and frame may be a preset size or a size manually selected by a user, and may be determined according to an actual requirement of the user, which is not specifically limited herein.

Optionally, the display positions and display sizes of the object frames in different first video frames are the same or different.

It is understood that the electronic device typically takes the area where the foreground (i.e., the subject such as the video object) in the first video frame is located as the display position of the object marquee in the first video frame. Wherein, since the foreground in a video frame is usually placed at the center of the video frame, the default object marquee may be set at the center of a video frame.

It should be noted that a picture (e.g., an image of a video frame) includes a foreground and a background, where the foreground is an image to be highlighted in the picture, and the background is image content except the foreground in the picture.

For example, the foreground of a person picture is the person image in the person picture, or the face image in the person picture. For another example, the foreground of a scene picture is the scene image in the scene picture.

Optionally, in the embodiment of the present application, the foreground in one video frame may be determined according to the pixel value of each pixel point of the image of the video frame. For example, the pixel value of the foreground in a video frame satisfies a certain value range, such as greater than a preset threshold.

Optionally, in the embodiment of the present application, the foreground in one video frame may be determined according to the contrast of an image of the video frame. For example, the difference between the contrast of the foreground in a video frame and the contrast of other image contents in the video frame satisfies a certain range of values.

And 102b, the GIF picture generating device scratches the image content framed by the object selection frame in each of the M first video frames to obtain M target video images.

Specifically, in step 102b, for each first video frame, the GIF picture generating device may first determine an object frame in the first video frame, and then perform a matting operation on image content in the object frame (i.e., image content of the target object), so as to obtain a target video image in each first video frame.

Illustratively, referring to FIG. 2, after a user input into the "region GIF Sticker" functionality control 34 shown in FIG. 2 (b), the electronic device may display a rectangular marquee 51 on the first video frame 31, as shown in FIG. 4. The user can trigger the electronic device to determine the display size and the display position of the selection frame 51 through the selection frame 51, and then extract the target video image in each first video frame.

Therefore, the user can intuitively and conveniently select the target object meeting the requirement through the object selection frame, each target video image meets the requirement of the user, and the target GIF image meets the requirement of the user. Therefore, the interest of the target GIF picture is improved.

Optionally, before the step 102b, the method further includes steps 108 and 109:

and step 108, the GIF picture generating device receives a third input of the object selection box from the user.

For the description of the input mode of the second input, reference may be made to the description of the input mode of the first input in the foregoing embodiment, and details are not repeated here. For example, the third input may be an input dragging the object marquee.

Step 109, the GIF picture generating means adjusts the display position and the display size of the object marquee in response to the third input.

Illustratively, referring to fig. 4, the user may trigger the electronic device to adjust the display size and display position of the marquee 51 via the marquee 51.

Optionally, the center of the default object selection box of the electronic device is the center of the picture of one first video frame. If the user does not manually select the display position and the display size of the object marquee in the first video frame, the electronic equipment determines that the default object marquee is the display size and the display area of the object marquee on the current first video frame. If the user manually selects the object selection frame from the first video frame, the electronic equipment determines the object selection frame manually selected by the user as the object selection frame of the first video frame.

Therefore, the user can adjust the display position and the display size of the object selection frame through the third input, so that the target object selected through the object selection frame meets the user requirement, each target video image further meets the user requirement, and the target GIF picture meets the user requirement. Therefore, the interest of the target GIF picture is improved.

Optionally, in application scenario 3 of the embodiment of the present application, in combination with application scenario 2, before step 102b, step 110 may further be included:

and step 110, the GIF picture generating device controls the object marquee to move along with the target video object in the K second video frames based on the display position and the display size of the object marquee on the target video frame, so that the objects framed by the object marquee in each second video frame are the same.

And K second video frames are video frames except the target video frame in the M first video frames, and K is a positive integer smaller than M.

Similarly, for the specific manner of acquiring the first content in each first video frame by the electronic device in the application scenario 3, reference may be made to the above-mentioned related descriptions of the application scenario 1 and the application scenario 2, and details thereof are not described here. For example, in application scenario 3, the user may trigger the electronic device to identify and select the target object through the identification control, and the electronic device may provide an object selection box that selects the target object in which the image content of the target object is located in each first video frame. Furthermore, the electronic equipment takes the image content of the target object in the object selection frame as the target video image in the first video frame.

It should be noted that, because the target video image in the first video frame acquired by the electronic device may be not only an image of the target object but also an image in the target area, the first content in each first video frame obtained by capturing is an image content meeting the user requirement, and the interest of generating the obtained target GIF picture is provided.

Optionally, in this embodiment of the application, before the step 102, a step 111 is further included:

and step 111, the GIF picture generation device acquires N third video frames of which the image quality parameters are within a preset numerical range in the target video frame.

The M first video frames are video frames in the N third video frames, and N is a positive integer greater than or equal to M.

Optionally, the M first video frames are: and video frames with image quality parameters in a preset value range in the target video.

It can be understood that the video frame of the target video with the image quality parameter within the preset numerical range is the video frame of the target video with better quality; on the contrary, the video frame of which the image quality parameter is out of the preset value range in the target video is the video frame of which the quality is poor in the target video. For example, the image quality parameter is the sharpness of an image of a video frame. The video frame with the image quality parameter in the preset numerical range is a video frame with better definition; on the contrary, the video frame with the image quality parameter outside the preset value range is the video frame with lower definition, namely the video frame with higher fuzziness.

For example, "acquiring N third video frames of the target video frame whose image quality parameter is within the preset value range" may exclude blurred and unclear main objects (i.e., video objects) (video frames) according to a preferred algorithm of the pictures, select a high-score video frame from composition and aesthetic scores to display in the video, and simultaneously, display all the preferred video frames in a thumbnail (detailed in the following embodiments).

Optionally, with reference to the application scenes 1 to 3, the electronic device may obtain, through an intelligent algorithm, video frames in the target video where the image quality parameter is within the preset numerical range, so that the N third video frames are video frames in the target video where the image quality parameter is within the preset numerical range.

It can be understood that, in the application scenario 1, the electronic device may obtain, through an intelligent algorithm, video frames in the target video where the image quality parameter is in a preset numerical range, and then recognize video frames containing image content of the target object in the video frames as M first video frames. In the application scenario 2, the electronic device may obtain, through an intelligent algorithm, video frames in a target video where the image quality parameter is within a preset numerical range, and use the video frames as M first video frames.

It should be noted that the video frames with poor quality in the target video can be removed, so that the M first video frames in the target video are video frames with good quality, thereby being beneficial to improving the quality of the target GIF picture obtained by the M first video frames.

Optionally, in this embodiment of the present application, step 103 includes step 103a and step 103 b:

step 103a, the GIF picture generating device sets the transparency of the target area in each target video image to be a preset transparency, and M first images are obtained.

Illustratively, the above-mentioned predetermined transparency value is 100%, i.e., transparent throughout. At this time, setting the transparency of the target region to the preset transparency may be to set the pixel points in the target region to be transparent pixels.

Optionally, the frame of each target video image may be transparent or opaque, and may be set according to the actual needs of the user.

And 103b, synthesizing the M first images by the GIF image generating device to generate a target GIF image.

And the target area in each target video image is an image area except the area where the target object is located.

The transparency of the image area except the area where the target object is located in the target area in each target video image is set as the preset transparency, so that the interestingness of each target video image can be improved, and the interestingness of the target GIF image is further improved.

Optionally, in this embodiment of the present application, step 103 may be implemented by steps 103c to 103 e:

step 103c, the GIF picture generating means determines the first image size based on the image size of each target video image.

Wherein the image size of each target video image is less than or equal to the first image size.

And 103b, adding preset pixels around each target video image by the GIF image generation device to obtain M second images, wherein the image size of each second image is the first image size.

Optionally, the preset pixel may be a pixel with preset parameters such as a preset color and a preset transparency. For example, the preset pixel may be a white pixel with a transparency value of 100%, which is not specifically limited in this embodiment of the application and may be determined according to an actual requirement of a user.

And step 103e, the GIF picture generating device generates the M second images into the target GIF picture.

Alternatively, for target video images (such as the second image) whose image sizes are different, the target GIF picture may be synthesized with the center of each image as a reference, i.e., such that the center points of each image coincide.

Alternatively, the target GIF picture may be synthesized at a specific point (default or user-selected, such as the point at which the upper left corner of each target video image is located) of each target video image, i.e., such that the points at which the upper left corners of each target video image are located coincide.

It should be noted that, since the target video images in the plurality of video frames (i.e., M first video frames) in the target video can be synthesized into the target GIF picture according to the same first display size, the display effect of the generated target GIF picture is better.

Optionally, in this embodiment of the present application, the step 103c may be implemented by the step 103 c-1:

step 103c-1, the GIF picture generating means determines the first width or the second width as an image width of the first image size and sets the first height or the second height as an image height of the first image size.

Wherein the first width is: the image width of the target object with the largest image width in all the M target video images; the first height is: the image height of the target object with the largest image height in the M target video images; the second width is the first width plus a first preset value, and the second height is the first height plus a second preset value.

Optionally, the first preset value is the same as or different from the second preset value, for example, the first preset value is equal to the second preset value (for example, the value is 5).

In example 1, the image width of the first image size is the second width, and the image height of the first image size is the second height. At this time, it is explained that the GIF picture generating apparatus increases the first preset number of pixels to the edge of the target display size and the second preset number of pixels to the edge of the target display size. I.e. it is equivalent to adding a complete border to the target GIF picture.

In addition, the image width for the first image size is a first width, and the image height for the first image size is a second height; and the two scenes that the image width of the first image size is the second width and the image height of the first image size is the first height show that the GIF picture generation device adds partial borders to the target GIF picture.

For example, when the image content of the target object is at different positions and different sizes in different first video frames, the image content of the target object can be displayed in a size of 5 pixels increased according to the maximum length and width of the image content of the target object. The 5 pixels are added to avoid the target object from being displayed at the edge of the picture, and the display effect is not good.

Therefore, the target GIF picture is obtained according to the first image size, a main body (such as a target object or a target video object contained in the target object) in the target GIF picture can be prevented from being displayed at the edge of the target GIF picture, and the display effect of the target GIF picture is improved.

Optionally, in this embodiment of the application, in the case of one first video frame in the target video on the screen, the electronic device may further display the video frame of the target video or a thumbnail of the video frame, so that a user can conveniently view each first video frame in the target video through the thumbnail. Illustratively, before the step 101, steps 112 to 114 may be further included:

and step 112, the GIF picture generation device displays the video frame indicated by the first thumbnail on the first area of the screen, and displays the P thumbnails on the second area of the screen according to the first frame rate.

Wherein the first frame rate is less than the frame rate of the target video. Each thumbnail is used for indicating one video frame in the target video, and the first thumbnail is one thumbnail in the P thumbnails. P is a positive integer less than or equal to M.

It can be understood that the above-mentioned P thumbnails are thumbnails of partial video frames in the target video. For example, the thumbnails shown in fig. 3 or fig. 4 are the above-described P thumbnails.

Illustratively, referring to fig. 3, the electronic device in fig. 3 may display a plurality of thumbnails, such as thumbnail 35, while displaying the first video frame 31. At this time, the thumbnail 35 is a first thumbnail, and the video frame indicated by the thumbnail 35 is the first video frame 31 shown in fig. 3.

Referring to fig. 4, while the electronic device of fig. 4 displays the first video frame 31, a plurality of thumbnails, such as thumbnail 52, may also be displayed. At this time, the thumbnail 52 is the first thumbnail, and the video frame indicated by the thumbnail 52 is the first video frame 31 shown in fig. 4.

Optionally, the GIF picture generation apparatus may provide a control for selecting the first frame rate, for enabling a user to manually set the first frame rate.

For example, the GIF picture generation apparatus may provide an interface for adjusting the FPS (i.e., the frame rate), where the interface includes controls such as "5", "10", "15", "20", and "24", which are respectively used to trigger the electronic device to set the first frame rate to the value represented by the corresponding control. In addition, the interface can also comprise prompt information' FPS: FPS refers to the number of pictures extracted in 1 s. The higher the FPS value is, the smoother the picture is, the larger the generated GIF is, and the situation that the picture cannot be shared may occur. ". And an indication of "suggested value" for "10" flag, for prompting the user that the first frame rate can be set to 10 frames per second so that the generated target GIF picture can be normally shared.

And step 113, the GIF picture generation device receives a third input of the second thumbnail from the user.

Optionally, the third input may be used to trigger the electronic device to update thumbnails of the P thumbnails.

And step 114, the GIF picture generation device responds to the third input, and updates and displays the content on the first area as the target video frame indicated by the second thumbnail and updates and displays the content on the second area as the Q thumbnails displayed according to the first frame rate.

The P thumbnails are different from the Q thumbnails, the second thumbnail is one of the Q thumbnails, and P is a positive integer smaller than or equal to M.

For example, if the first input is a sliding input on P thumbnails, the electronic device is triggered to update the P thumbnails, for example, the P thumbnails are updated according to the sliding direction of the first input.

For example, if the first input is a long-press input on a thumbnail of P thumbnails, the first input is used to trigger the electronic device to expand and display all video frames in the target video.

Further, in the embodiment of the application, the thumbnail also supports a user to select whether to delete some video frames in the target video. For example, a user's swipe in on a thumbnail of a video frame, or a long press and swipe in, is used to trigger the electronic device to delete the video frame. Therefore, the user can quickly trigger and delete some video frames in the target video through the thumbnails, for example, the user does not need to generate the video frame of the target GIF picture or the video frame with lower definition.

It is understood that deleting a video frame in a target video in the embodiment of the present application refers to deleting a video frame other than the video frame used for generating the target GIF picture, rather than deleting an original video frame in the target video file. Namely, the M first video frames are video frames in the target video for which the user has not performed the deletion operation.

It is understood that the M first video frames in the target video do not include video frames that are manually deleted by the user.

It should be noted that, by displaying the thumbnail of the video frame in the target video, the user can conveniently view each video frame in the target video, and further, the user can conveniently trigger the selection of the target object from each video frame.

Optionally, in this embodiment of the present application, after the step 103, the method further includes steps 115 to 117:

and step 115, the GIF picture generating device stores the target GIF picture and the identifier corresponding to the target GIF picture in a target storage area.

And the identifier corresponding to the target GIF picture is used for indicating the target video object contained in the target GIF picture. For example, the identifier corresponding to the target GIF picture is the identification information of the target video object contained therein, such as when the target video object is "dog", the identifier is the text of dog.

For example, the electronic device may provide a save control, such as a display save control on a screen, to trigger the electronic device to save the target GIF picture.

Optionally, the target storage area may be an area used for storing media files such as pictures in the local area of the electronic device, such as a storage area corresponding to a local album application. Alternatively, the target storage area may be an area for storing media files such as pictures in a server interacting with the GIF picture generation apparatus.

Step 116, the GIF picture generating device acquires the target information input by the user in the content input area in the target application program.

In step 117, the GIF picture generating means displays the target GIF picture when the target information is the same as the information indicated by the identifier of the target GIF picture.

For example, in implementation mode 1, in a scene of video editing, picture editing, and the like, a GIF picture (or GIF sticker, such as a target GIF picture) may be added to a video or a picture as a resource, the content of the edited picture or video is identified, and a material is intelligently recommended. For example, if there is an element of a pet in the edited video screen content and in the music theme, the user is recommended to use the GIF picture containing the video object of the pet when editing. For example, the target application is an application for video editing and picture editing, the content input area is a search box of the target application, and the target information is identification information (such as a name) of the pet.

For example, in implementation 2, when the user sends the emoticon in the instant messaging chat tool (i.e., the target application), the created target GIF picture may be sent as the emoticon. The target GIF picture can also be sent according to the content of the subject of the cutout (i.e., the target video object in the target GIF picture). For example, when a target GIF picture including a target video object is made, the selected subject (i.e., the target video object) is a "dog", and the user inputs the text "dog" into a chat interface of the instant messaging chat tool, so that the GIF expression (i.e., the GIF picture) of the subject of the dog can be displayed and transmitted.

For example, in implementation 3, when the user inputs "dog" in the input method, the expression of the subject GIF of the dog (i.e., the GIF picture) may also be displayed on the edited content (e.g., edited text). At this time, the target application is an input method application.

In an exemplary implementation manner 4, during a video call, a user inputs text content of a main body through voice, and sends a corresponding main body gif expression package to an opposite side. For example, if the user says "dog", the gif emoticon mainly comprising the dog can be sent to the opposite side, and the gif emoticon can be popped up and displayed on the chat interface of the opposite side, so that the interest of video chat is increased. At this time, the chat interface of the native user may also display the gif emoticon.

Therefore, under the condition that the target GIF picture and the identifier corresponding to the target GIF picture are stored in the target storage area, the target GIF picture can be rapidly and conveniently triggered and displayed under the condition that the target information is the same as the information indicated by the identifier of the target GIF picture by acquiring the target information input by the user in the content input area in the target application program. Therefore, the interest and the convenience of the target GIF picture are improved.

It should be noted that, in the GIF picture generating method provided in the embodiment of the present application, the executing subject may be a GIF picture generating device, or a control module in the GIF picture generating device for executing the GIF picture generating method. The embodiment of the present application takes the GIF picture generation apparatus as an example to execute the GIF picture generation method, and the GIF picture generation apparatus provided in the embodiment of the present application is described.

Fig. 5 is a schematic structural diagram of a GIF picture generating device according to an embodiment of the present application. As shown in fig. 5, the GIF picture generating apparatus 50 includes a receiving module 501, configured to receive a first input from a user, where the first input is used to select a target object in a target video frame of a target video; an editing module 502, configured to, in response to the first input received by the receiving module 501, scratch image content of a target object in each of M first video frames in a target video, to obtain M target video images; a generating module 503, configured to generate a target GIF picture based on the M target video images obtained by the editing module 502; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame.

The GIF picture generation device provided by the embodiment of the application can extract the image content of the target object in each of the M first video frames in the target video through the first input of the target object in the target video frame of the target video selected by the user, so as to obtain M target video images; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame. Specifically, each target video image is a part of content which is extracted from one first video frame according to the target video object or the object selection frame, but not the whole content of the first video frame, for example, the part of content required by the user in the first video frame, so that the data volume of the target GIF picture obtained by converting the target video is small, and the successful sharing of the GIF picture is facilitated.

Optionally, the target object in each first video frame comprises a target video object; the receiving module 501 is further configured to receive a second input of the user before receiving the first input of the user; the apparatus 50 further comprises: a first display module for displaying at least one video object identifier in response to the second input received by the receiving module 501, each video object identifier indicating one video object in the target video frame; a receiving module 501, configured to receive a first input of a target video object identifier in at least one video object identifier from a user; the editing module 502 is further configured to scratch image content of a target object in each of M first video frames in the target video, and determine a video object indicated by the target video object identifier as the target video object before obtaining the M target video images, where the target object includes the target video object.

Optionally, the target object in each first video frame is an object in the object selection box; the video frame displayed on the screen also comprises an object selection frame; the editing module 502 is further configured to scratch image content of a target object in each of M first video frames in the target video, and before the M target video images are obtained, determine an object framed by the object selection frame as a target object; the editing module 502 is specifically configured to scratch image content framed by the object selection frame in each of the M first video frames to obtain M target video images.

Optionally, the receiving module 501 is configured to receive a third input of the object selection box from the user before the editing module 502 determines the object selected by the object selection box as the target object; the apparatus 50 further comprises: and an adjusting module, configured to adjust a display position and a display size of the object selection box in response to the third input received by the receiving module 501.

Optionally, the GIF picture generating apparatus 50 further includes: a control module, configured to, before the editing module 502 extracts the image content framed by the object extraction frame in each of the M first video frames to obtain M target video images, control the object extraction frame to move in the K second video frames following the target video object based on the display position and the display size of the object extraction frame on the target video frame, so that the objects framed by the object extraction frame in each second video frame are the same; and K second video frames are video frames except the target video frame in the M first video frames, and K is a positive integer smaller than M.

Optionally, the GIF picture generating apparatus 50 further includes: the acquisition module is used for matting the image content of the target object in each of M first video frames in the target video and acquiring N third video frames with image quality parameters in a preset value range in the target video frames before the M target video images are obtained; the M first video frames are video frames in the N third video frames, and N is a positive integer greater than or equal to M.

Optionally, the generating module 503 is specifically configured to set the transparency of the target area in each target video image to a preset transparency, so as to obtain M first images; synthesizing the M first images to generate a target GIF picture; and the target area in each target video image is an image area except the area where the target object is located.

Optionally, the generating module 503 is specifically configured to determine a first image size based on the image size of each target video image; adding preset pixels around each target video image to obtain M second images, wherein the image size of each second image is the first image size; generating M second images into a target GIF picture; wherein the image size of each target video image is less than or equal to the first image size.

Optionally, the generating module 503 is specifically configured to determine the first width or the second width as an image width of the first image size, and set the first height or the second height as an image height of the first image size; wherein the first width is: the image width of the target object with the largest image width in all the M target video images; the first height is: the image height of the target object with the largest image height in the M target video images; the second width is the first width plus a first preset value, and the second height is the first height plus a second preset value.

Optionally, the GIF picture generating apparatus 50 further includes: a second display module, configured to display, before the receiving module 501 receives the first input of the user, a video frame indicated by the first thumbnail on the first area of the screen, and display P thumbnails on the second area of the screen at the first frame rate; the receiving module 501 is further configured to receive a third input of the user to a second thumbnail of the P thumbnails; a second display module, configured to update and display the content on the first area as the target video frame indicated by the second thumbnail and update and display the content on the second area as Q thumbnails displayed at the first frame rate in response to a third input received by the receiving module 501; the P thumbnails are different from the Q thumbnails, the first frame rate is smaller than that of the target video, each thumbnail is used for indicating one video frame in the target video, the first thumbnail is one thumbnail in the P thumbnails, the second thumbnail is one thumbnail in the Q thumbnails, and both P and Q are positive integers smaller than or equal to M.

Optionally, the GIF picture generating apparatus 50 further includes: the storage module is configured to, after the generation module 503 generates the target GIF picture based on the M target video images, store the target GIF picture and an identifier corresponding to the target GIF picture in a target storage area, where the identifier corresponding to the target GIF picture is used to indicate a target video object included in the target GIF picture; the user input module is used for acquiring target information input by a user in a content input area in a target application program; and the third display module is also used for displaying the target GIF picture under the condition that the target information obtained by the user input module is the same as the information indicated by the identifier of the target GIF picture stored by the storage module.

The GIF picture generating device in the embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The device can be mobile electronic equipment or non-mobile electronic equipment. By way of example, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm top computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a Television (TV), a teller machine or a kiosk, and the like, and the embodiments of the present application are not particularly limited.

The GIF picture generation apparatus in the embodiment of the present application may be an apparatus having an operating system. The operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, and embodiments of the present application are not limited specifically.

The GIF picture generation apparatus provided in the embodiment of the present application can implement each process implemented in the method embodiment of fig. 1, and is not described here again to avoid repetition.

Optionally, as shown in fig. 6, an electronic device 600 is further provided in this embodiment of the present application, and includes a processor 601, a memory 602, and a program or an instruction stored in the memory 602 and executable on the processor 601, where the program or the instruction is executed by the processor 601 to implement each process of the foregoing GIF picture generation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

It should be noted that the electronic device in the embodiment of the present application includes the mobile electronic device and the non-mobile electronic device described above.

Fig. 7 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

The electronic device 1000 includes, but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010.

Those skilled in the art will appreciate that the electronic device 100 may further comprise a power source (e.g., a battery) for supplying power to various components, and the power source may be logically connected to the processor 1010 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The electronic device structure shown in fig. 7 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than those shown, or combine some components, or arrange different components, and thus, the description is omitted here.

The user input unit 1007 is configured to receive a first input of a user, where the first input is used to select a target object in a target video frame of a target video; a processor 1010, configured to, in response to a first input received by the user input unit 1007, scratch the image content of the target object in each of M first video frames in the target video, resulting in M target video images; generating a target GIF picture based on the M target video images obtained by the processor 1010; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame.

According to the electronic device provided by the embodiment of the application, the image content of the target object in each of the M first video frames in the target video can be scratched through the first input of the user selecting the target object in the target video frame of the target video, so that the M target video images are obtained; generating a target GIF picture based on the M target video images; wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames include a target video frame. Specifically, each target video image is a part of content which is extracted from one first video frame according to the target video object or the object selection frame, but not the whole content of the first video frame, for example, the part of content required by the user in the first video frame, so that the data volume of the target GIF picture obtained by converting the target video is small, and the successful sharing of the GIF picture is facilitated.

Optionally, the target object in each first video frame comprises a target video object; the user input unit 1007 is further configured to receive a second input from the user before receiving the first input from the user; a display unit 1006 for displaying at least one video object identifier in response to a second input received by the user input unit 1007, each video object identifier indicating one video object in the target video frame; a user input unit 1007, specifically configured to receive a first input of a target video object identifier in at least one video object identifier by a user; the processor 1010 is further configured to scratch image content of a target object in each of M first video frames in the target video, and determine a video object indicated by the target video object identifier as the target video object before obtaining the M target video images, where the target object includes the target video object.

Optionally, the target object in each first video frame is an object in the object selection box; the video frame displayed on the screen also comprises an object selection frame; the processor 1010 is further configured to scratch image content of a target object in each of M first video frames in the target video, and determine an object framed by the object selection frame as the target object before obtaining the M target video images; the processor 1010 is specifically configured to scratch image content framed by the object selection frame in each of the M first video frames to obtain M target video images.

Optionally, the user input unit 1007 is configured to receive a third input to the object selection box from the user before the processor 1010 determines the object selected by the object selection box as the target object; a processor 1010, configured to adjust a display position and a display size of the object selection box in response to a third input received by the user input unit 1007.

Optionally, the processor 1010 is configured to scratch out image content framed by an object selection frame in each of the M first video frames, and before obtaining the M target video images, based on a display position and a display size of the object selection frame on the target video frame, control the object selection frame to move in the K second video frames following the target video object, so that an object framed by the object selection frame in each second video frame is the same; and K second video frames are video frames except the target video frame in the M first video frames, and K is a positive integer smaller than M.

Optionally, the processor 1010 is configured to scratch image content of a target object in each of M first video frames in a target video, and before obtaining the M target video images, obtain N third video frames in the target video frames, where an image quality parameter is within a preset value range; the M first video frames are video frames in the N third video frames, and N is a positive integer greater than or equal to M.

Optionally, the processor 1010 is specifically configured to set the transparency of the target area in each target video image to a preset transparency, so as to obtain M first images; synthesizing the M first images to generate a target GIF picture; and the target area in each target video image is an image area except the area where the target object is located.

Optionally, the processor 1010 is specifically configured to determine a first image size based on an image size of each target video image; adding preset pixels around each target video image to obtain M second images, wherein the image size of each second image is the first image size; generating M second images into a target GIF picture; wherein the image size of each target video image is less than or equal to the first image size.

Optionally, the processor 1010 is specifically configured to determine the first width or the second width as an image width of the first image size, and set the first height or the second height as an image height of the first image size; wherein the first width is: the image width of the target object with the largest image width in all the M target video images; the first height is: the image height of the target object with the largest image height in the M target video images; the second width is the first width plus a first preset value, and the second height is the first height plus a second preset value.

Optionally, a display unit 1006, configured to display, before the user input unit 1007 receives the first input from the user, a video frame indicated by the first thumbnail on the first area of the screen, and display P thumbnails on the second area of the screen at the first frame rate; a user input unit 1007, further configured to receive a third input by the user to a second thumbnail of the P thumbnails; a second display module, configured to update and display the content on the first area as the target video frame indicated by the second thumbnail and update and display the content on the second area as Q thumbnails displayed at the first frame rate in response to a third input received by the user input unit 1007; the P thumbnails are different from the Q thumbnails, the first frame rate is smaller than that of the target video, each thumbnail is used for indicating one video frame in the target video, the first thumbnail is one thumbnail in the P thumbnails, the second thumbnail is one thumbnail in the Q thumbnails, and both P and Q are positive integers smaller than or equal to M.

Optionally, the memory 1009 is configured to, after the processor 1010 generates the target GIF picture based on the M target video images, store the target GIF picture and an identifier corresponding to the target GIF picture in a target storage area, where the identifier corresponding to the target GIF picture is used to indicate a target video object included in the target GIF picture; a user input unit 1007 for acquiring target information input by a user in a content input area in a target application; the display unit 1006 is further configured to display the target GIF picture if the target information obtained by the user input unit 1007 is the same as the information indicated by the identifier of the target GIF picture stored in the memory 1009.

Alternatively, the respective modules in the GIF picture generation apparatus 50 described above may be implemented by respective units in the electronic device 1000. For example, the editing module 502, the generating module 503, and the control module in the GIF picture generating device 50 may be implemented by the processor 1010. The first display module and the second display in the GIF picture generating apparatus 50 are implemented by the above-described display unit 1006, and the receiving module 501 and the user input module in the GIF picture generating apparatus 50 are implemented by the above-described user input unit 1007. The saving module in the GIF picture generating apparatus 50 is realized by the above-described memory 1009.

It should be understood that in the embodiment of the present application, the input Unit 1004 may include a Graphics Processing Unit (GPU) 1041 and a microphone 10042, and the graphics processing Unit 10041 processes image data of still pictures or videos obtained by an image capturing device (such as a camera) in a video capturing mode or an image capturing mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1007 includes a touch panel 10071 and other input devices 10072. The touch panel 10071 is also referred to as a touch screen. The touch panel 1071 may include two parts of a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein. The memory 1009 may be used to store software programs as well as various data, including but not limited to application programs and operating systems. Processor 1010 may integrate an application processor that handles primarily operating systems, user interfaces, applications, etc. and a modem processor that handles primarily wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 1010.

An embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the above-mentioned embodiment of the GIF picture generating method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and so on.

The embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement each process of the above-mentioned GIF picture generation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, the details are not repeated here.

It should be understood that the chips mentioned in the embodiments of the present application may also be referred to as system-on-chip, system-on-chip or system-on-chip, etc.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. A GIF picture generation method, comprising:

receiving a first input of a user, wherein the first input is used for selecting a target object in a target video frame of a target video;

in response to the first input, matting image content of a target object in each of M first video frames in the target video to obtain M target video images;

generating a target GIF picture based on the M target video images;

wherein the target objects in different first video frames satisfy at least one of: the target objects in different first video frames comprise target video objects, and the target objects in different first video frames are all objects in the object selection frame; m is a positive integer; the M first video frames comprise the target video frame.

2. The method of claim 1, wherein the target object in each of the first video frames comprises the target video object;

before the receiving the first input of the user, the method further comprises:

receiving a second input of the user;

in response to the second input, displaying at least one video object identification, each video object identification indicating one video object in the target video frame;

the receiving a first input of a user comprises:

receiving the first input of a user to a target video object identification in the at least one video object identification;

before the matting the image content of the target object in each of the M first video frames in the target video to obtain the M target video images, the method further includes:

and determining the video object indicated by the target video object identification as the target video object, wherein the target object contains the target video object.

3. The method according to claim 1, wherein the target object in each of the first video frames is an object in the object culling box; the video frame displayed on the screen also comprises the object selection frame;

determining the object framed by the object selection frame as the target object;

the matting of image content of a target object in each of M first video frames in the target video to obtain M target video images includes:

and matting the image content framed by the object selection frame in each of the M first video frames to obtain the M target video images.

4. The method of claim 3, wherein before determining the object framed by the object marquee as the target object, the method further comprises:

receiving a third input of the object selection box from the user;

and responding to the third input, and adjusting the display position and the display size of the object selection frame.

5. The method of claim 3,

before the matting the image content framed by the object selection frame in each of the M first video frames to obtain the M target video images, the method further includes:

controlling the object marquee to move following the target video object in the K second video frames based on the display position and the display size of the object marquee on the target video frame, so that the object marquee is the same in each second video frame;

and the K second video frames are video frames except the target video frame in the M first video frames, and K is a positive integer smaller than M.

6. The method as claimed in claim 1, wherein before said matting the image content of the target object in each of the M first video frames in the target video to obtain M target video images, the method further comprises:

obtaining N third video frames of which the image quality parameters are within a preset numerical range in the target video frame;

7. The method of claim 1, wherein generating a target GIF picture based on the M target video images comprises:

setting the transparency of a target area in each target video image as a preset transparency to obtain M first images;

synthesizing the M first images to generate the target GIF picture;

8. The method of claim 1, wherein generating a target GIF picture based on the M target video images comprises:

determining a first image size based on the image size of each target video image;

adding preset pixels around each target video image to obtain M second images, wherein the image size of each second image is the first image size;

generating the M second images into the target GIF picture;

9. The method of claim 8, wherein determining the first image size based on the image size of each target video image comprises:

determining a first width or a second width as an image width of the first image size, and setting a first height or a second height as an image height of the first image size;

wherein the first width is: the image width of the target object with the largest image width in all the M target video images; the first height is: the image height of a target object with the largest image height in the M target video images;

the second width is the first width plus a first preset value, and the second height is the first height plus a second preset value.

10. The method of claim 1, wherein prior to receiving the first input from the user, the method further comprises:

displaying a video frame indicated by a first thumbnail on a first area of a screen, and displaying P thumbnails on a second area of the screen at a first frame rate;

receiving a third input of a user to a second thumbnail of the P thumbnails;

in response to the third input, updating and displaying the content on the first area as the target video frame indicated by the second thumbnail and updating and displaying the content on the second area as Q thumbnails displayed at the first frame rate;

the P thumbnails are different from the Q thumbnails, the first frame rate is lower than the frame rate of the target video, each thumbnail is used to indicate one video frame in the target video, the first thumbnail is one of the P thumbnails, the second thumbnail is one of the Q thumbnails, and P and Q are both positive integers smaller than or equal to M.

11. The method of any one of claims 1 to 10, wherein after generating a target GIF picture based on the M target video images, the method further comprises:

storing the target GIF picture and an identifier corresponding to the target GIF picture into a target storage area, wherein the identifier corresponding to the target GIF picture is used for indicating the target video object contained in the target GIF picture;

acquiring target information input by a user in a content input area in a target application program;

and displaying the target GIF picture under the condition that the target information is the same as the information indicated by the identifier of the target GIF picture.

12. A GIF picture generation apparatus, comprising:

the receiving module is used for receiving a first input of a user, wherein the first input is used for selecting a target object in a target video frame of a target video;

the editing module is used for responding to the first input received by the receiving module, and scratching the image content of the target object in each of M first video frames in the target video to obtain M target video images;

the generating module is used for generating a target GIF picture based on the M target video images obtained by the editing module;

13. The apparatus of claim 12, wherein the target object in each of the first video frames comprises the target video object;

the receiving module is further configured to receive a second input of the user before receiving the first input of the user;

the device further comprises:

a first display module for displaying at least one video object identifier in response to the second input received by the receiving module, each video object identifier indicating one video object in the target video frame;

the receiving module is specifically configured to receive the first input of a target video object identifier in the at least one video object identifier from a user;

the editing module is further configured to scratch image content of a target object in each of the M first video frames in the target video, and before the M target video images are obtained, determine a video object indicated by the target video object identifier as the target video object, where the target object includes the target video object.

14. The apparatus according to claim 12, wherein the target object in each of the first video frames is an object in the object culling box; the video frame displayed on the screen also comprises the object selection frame;

the editing module is further configured to scratch image content of a target object in each of the M first video frames in the target video, and determine an object framed by the object selection frame as the target object before the M target video images are obtained;

the editing module is specifically configured to scratch image content framed by the object selection frame in each of the M first video frames to obtain the M target video images.

15. The apparatus of claim 14,

the device further comprises:

a control module, configured to, before the editing module scratches image content framed by the object selection frame in each of the M first video frames to obtain the M target video images, control the object selection frame to move along with the target video object in the K second video frames based on a display position and a display size of the object selection frame on the target video frame, so that an object framed by the object selection frame in each second video frame is the same;

16. The apparatus of claim 12,

the generating module is specifically configured to set the transparency of the target region in each target video image to a preset transparency, so as to obtain M first images; synthesizing the M first images to generate the target GIF picture;

17. The apparatus of claim 12,

the generating module is specifically configured to determine a first image size based on an image size of each target video image;

generating the M second images into the target GIF picture;

18. The apparatus of claim 17,

the generating module is specifically configured to determine a first width or a second width as an image width of the first image size, and set a first height or a second height as an image height of the first image size;

19. The apparatus of any one of claims 12 to 18,

the device further comprises:

a storage module, configured to store, after the generation module generates the target GIF picture based on the M target video images, the target GIF picture and an identifier corresponding to the target GIF picture in a target storage area, where the identifier corresponding to the target GIF picture is used to indicate the target video object included in the target GIF picture;

the user input module is used for acquiring target information input by a user in a content input area in a target application program;

and the third display module is further configured to display the target GIF picture under the condition that the target information obtained by the user input module is the same as the information indicated by the identifier of the target GIF picture stored by the storage module.

20. An electronic device comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the GIF picture generation method as claimed in any one of claims 1-11.