Image processing method and device, electronic equipment and storage medium

Abstract

The method comprises: determining a target torso model corresponding to a target object when it is detected that a special effect mounting condition is met; determining target special effect and target vertex information on the target torso model; determining a target mounting point corresponding to the target vertex information and determining a current offset angle of the target object; mounting the target special effect on the target object based on the target mounting point and the current offset angle to obtain a special effect video frame. The technical solution of the embodiment of the present disclosure can associate the added special effect with the user's limbs in the video picture, and the orientation of the special effect corresponds to the orientation of the user's limbs in the picture, so that the visual effect of the special effect video is more realistic.

Description

Technical Field

[0001] This disclosure relates to the field of image processing technology, and in particular to an image processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of internet technology, more and more applications have entered users' lives, especially a series of software that can shoot short videos, which are very popular among users.

[0003] To enhance the fun of video shooting, software developers can create a variety of special effects props. However, the special effects props currently provided to users are very limited, and the richness of video content needs to be further improved. At the same time, the special effects added by users cannot interact with the video content. For example, when the user's body is in the frame, the added special effects cannot be linked with the user's body, resulting in poor special effects video effects generated based on the relevant special effects props. Summary of the Invention

[0004] This disclosure provides an image processing method, apparatus, electronic device, and storage medium that enables added special effects to be associated with the user's limbs in a video frame, and the orientation of the special effects corresponds to the orientation of the user's limbs in the frame, thereby making the visual effect of the special effects video more realistic.

[0005] In a first aspect, embodiments of this disclosure provide an image processing method, including:

[0006] When the conditions for special effects mounting are met, the target torso model corresponding to the target object is determined.

[0007] Determine the target special effects and the target vertex information on the target torso model;

[0008] Determine the target mount point corresponding to the target vertex information, and determine the current offset angle of the target object;

[0009] Based on the target mounting point and the current offset angle, the target effect is mounted on the target object to obtain the effect video frame.

[0010] Secondly, embodiments of this disclosure also provide an image processing apparatus, comprising:

[0011] The target torso model determination module is used to determine the target torso model corresponding to the target object when the special effect mounting conditions are met.

[0012] The target vertex information determination module is used to determine the target effect and the target vertex information on the target torso model;

[0013] The target mount point determination module is used to determine the target mount point corresponding to the target vertex information and to determine the current offset angle of the target object;

[0014] The special effects video frame generation module is used to attach the target special effects to the target object based on the target mounting point and the current offset angle, thereby obtaining the special effects video frame.

[0015] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0016] One or more processors;

[0017] Storage device for storing one or more programs.

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the image processing method as described in any of the embodiments of this disclosure.

[0019] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the image processing method as described in any of the embodiments of this disclosure.

[0020] The technical solution of this disclosure, when detecting that the special effect mounting conditions are met, determines the target torso model corresponding to the target object, then determines the target special effect and the target vertex information on the target torso model, further determines the target mounting point corresponding to the target vertex information, and determines the current offset angle of the target object. Finally, based on the target mounting point and the current offset angle, the target special effect is mounted on the target object to obtain a special effect video frame, so that the added special effect can be associated with the user's limbs in the video screen. At the same time, the orientation of the special effect corresponds to the orientation of the user's limbs in the screen, so that the visual effect presented by the special effect video is more realistic and enhances the user experience. Attached Figure Description

[0021] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 This is a schematic flowchart of an image processing method provided in an embodiment of the present disclosure;

[0023] Figure 2 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of the present disclosure;

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0025] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0026] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0027] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0028] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependencies. It should also be noted that the modifications of "a" and "a plurality of" mentioned in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0029] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0030] Before introducing this technical solution, the application scenarios of the embodiments of this disclosure can be illustrated by example. For instance, when a user uploads a recorded multimedia data stream to the server corresponding to the application, or when a mobile terminal containing a camera captures video footage in real time, the application can detect the content of multiple video frames (i.e., multiple objects within the frame) and determine the target object. The target object within the video frame can be either dynamic or static, and the number of target objects can be one or more. Based on this, when the application detects the presence of a target object within the video frame, it can, according to the solution of the embodiments of this disclosure, attach pre-designed special effects selected by the user from a special effects package to the corresponding position on the target object's body, obtaining multiple special effects video frames. This allows interaction between the special effects and the screen content, and generates a more interesting special effects video based on the multiple special effects video frames.

[0031] Figure 1 This is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure. This embodiment is applicable to situations where application software processes the current video frame to generate a special effects video. For example, if a target object's body exists in the current video frame, and the application detects that a user has selected an effect from an effects package and touched the target object's body, the application can process each video frame according to the scheme of this embodiment, so that the user-selected effect is attached to the target object's body, and a corresponding special effects video is obtained. This method can be executed by an image processing device, which can be implemented in the form of software and / or hardware, and optionally, by an electronic device, such as a mobile terminal, a PC, or a server.

[0032] like Figure 1 As shown, the method includes:

[0033] S110. When the conditions for special effects mounting are met, determine the target torso model corresponding to the target object.

[0034] The apparatus for executing the image processing method provided in this embodiment can be integrated into application software that supports image processing functions, and this software can be installed on an electronic device, optionally a mobile terminal or a PC. The application software can be a type of software for image / video processing; specific application software will not be detailed here, as long as it can perform image / video processing. Alternatively, it can be a specially developed application program for adding and displaying special effects, or it can be integrated into a corresponding page, allowing users to process special effects videos through the integrated page on a PC.

[0035] It should be noted that the technical solution of this embodiment can be executed using existing video files as data foundation, or it can be executed during the user's video recording process. For example, when a user pre-records a video containing a target object and uses this video as the original video, the user can actively upload the video to the application's corresponding server. Furthermore, the user can select a target effect from the effect package provided by the application according to their own wishes. This allows the server to construct a 3D torso model for the target object in the video. Then, the server processes each video frame in the video according to the solution of this embodiment. That is, the user-selected target effect is attached to the torso of the target object in the video frame to obtain an effect video frame. Alternatively, the user can use a mobile terminal equipped with a camera to capture video of the target object in real time. When the application detects the target object in the real-time captured video frame, it can also construct a corresponding 3D torso model for the target object. Furthermore, when the application detects the user's touch operation on the torso of the target object, it can also process each video frame according to the solution of this embodiment based on its own image processing function to obtain the corresponding effect video frame.

[0036] In this embodiment, the special effect mounting conditions include at least one of the following: triggering the special effect mounting control; detecting the trigger target object; detecting voice information to trigger the special effect mounting wake word; detecting that the body movement information is consistent with the preset movement information. It can be understood that the special effect mounting conditions are the trigger conditions for mounting the special effect selected by the user onto the torso of the target object and displaying it.

[0037] Specifically, for the first type of special effect mounting condition mentioned above, a control can be developed in the application software in advance. At the same time, the special effect mounting related program can be associated with the control. Based on this, when the user triggers the control, the application software can call the relevant program to determine the special effect selected by the user and mount the special effect on the body of the target object. It can be understood that there are multiple ways for the user to trigger the control. For example, when the client is installed and deployed on a PC, the user can trigger the special effect mounting control by clicking with a mouse. When the client is installed and deployed on a mobile terminal, the user can trigger the special effect mounting control by touching with a finger. Those skilled in the art should understand that the specific special effect mounting touch method can be selected according to the actual situation. This disclosure does not make specific limitations in this regard.

[0038] Regarding the second type of effect attachment condition mentioned above, when the application receives images or videos actively uploaded by the user or captured in real time using a camera device, it can process the images or video frames based on a pre-trained image recognition model to determine whether the image contains a target object. Furthermore, when a target object is displayed in the image, the application needs to detect the user's trigger action in real time. If the application detects that the user has triggered the target object, it can attach the user-selected effect to the target object's body. For example, if the application detects a cat image as the target object in the currently displayed image, and if it detects that the user has clicked on the cat's head area via the touchscreen, it can attach a pre-selected effect to the cat's head.

[0039] For the third type of special effect attachment condition mentioned above, specific information can be pre-set in the application software as the special effect attachment wake-up word. For example, one or more of the words such as "attach", "special effect attachment", and "attach special effect" can be used as the special effect attachment wake-up word. Based on this, when the application software receives the voice information sent by the user, it can use a pre-trained speech recognition model to recognize the voice information and determine whether the recognition result contains one or more of the above-mentioned preset special effect attachment wake-up words. When the judgment result is yes, the application can attach the special effect selected by the user to the torso of the target object.

[0040] For the fourth type of special effect application, multiple human or animal motion information can be entered into the application software and used as preset motion information. For example, information reflecting the action of a person raising their hands can be used as preset motion information, or information reflecting the action of a cat standing up can be used as preset motion information. Based on this, when the application receives images or videos actively uploaded by the user or captured in real time by a camera device, it can identify the images or video frames based on a pre-trained limb motion information recognition algorithm. When the recognition result shows that the limb motion information of the target object in the current image is consistent with the preset motion information, the application can apply the special effect selected by the user to the torso of the target object.

[0041] It should be noted that the above-mentioned special effects loading conditions can be applied simultaneously in the application software, or only one or more of them can be selected to be applied in the application software. This disclosure embodiment does not make specific limitations in this regard.

[0042] In this embodiment, the target object can be a user displayed on the screen. For example, when a user's dance video is played based on an application for image processing, the dancing user displayed in the video is the target object. Of course, in practical applications, the target object can also be various dynamic or static creatures, such as a user's pet. This embodiment does not specifically limit this.

[0043] Specifically, there are two ways to identify target objects from raw video. The first way is that users can pre-mark one or more target objects in the video frame. Based on this, when the application obtains the raw video, it can determine the target objects according to the user's marking results. The second way is that after the raw video is uploaded to the server, or during the real-time video acquisition process, the application software can dynamically recognize the video frame and then determine one or more target objects based on the recognition results.

[0044] Correspondingly, when an application detects a target object in a video frame, it can retrieve a pre-generated or real-time target torso model corresponding to the target object. Specifically, when the first method is used to determine the target object (i.e., the object in the video frame is pre-labeled), the application can create a corresponding target torso model for one or more target objects in real time after acquiring the original video. When the second method is used to determine the target object (i.e., the application dynamically identifies the target object from the video frame), the application can construct a corresponding target torso model (3D mesh) for all objects in the video frame. Based on this, when the application identifies the target object again during subsequent video playback, it can directly call the pre-constructed target torso model (3D mesh) corresponding to that target object. It can be understood that the body of the target object is represented by the target torso model. For example, when an application detects a target object in a video frame, it can use multiple polygons to construct a 3D mesh in real time, reflecting various parts of the user's body. This 3D mesh can then be used as the target torso model corresponding to the user. After the target torso model is constructed, the application can annotate the model and associate it with the user as the target object. Based on this, if the application detects the user's body again in the video frame later, it can directly use the constructed 3D mesh as the target torso model. Those skilled in the art should understand that when the application determines the corresponding target torso model for the target object, the user can also edit and adjust the model according to actual needs, thereby further improving the accuracy of subsequently applying special effects to the target object's body.

[0045] It should be noted that once the application has built a corresponding target torso model for the target object, even if the target object appears multiple times in subsequent video frames, the application does not need to rebuild the model for the target object. Instead, it can directly call the target torso model corresponding to the target object.

[0046] It should also be noted that in practical applications, once the application software has determined the target torso model, it can determine one or more key points on the target torso model based on a pre-written key point determination program or algorithm. For example, the transformation matrix can be determined based on the key points on the target torso model and the points corresponding to the joints of the human body.

[0047] The transformation matrix is ​​a matrix that reflects the relationship between key points and joints on the human body. Specifically, the transformation matrix can include translation and rotation matrices. Using these two types of matrices, the application can determine how to translate or rotate the target torso model in the current video frame, and subsequently determine the target display position of each pixel of the target torso model in the current video frame. In other words, based on this transformation matrix, the binding or association between the target torso model and the actual human body can be achieved, ensuring that the target torso model remains aligned with the moving human body at all times; that is, ensuring that the movement of the target torso model always follows the actual movement of the human body.

[0048] S120. Determine the target vertex information on the target effect and target torso model.

[0049] Optionally, first determine the touch point corresponding to the target object, and then determine the target vertex information on the corresponding target torso model based on the touch point; or, determine the mounting part corresponding to the voice information, and then determine the target vertex information for the target torso based on the mounting part; or, determine the target vertex information according to the torso model corresponding to the limb movement information.

[0050] Specifically, when target vertex information is determined through touch points, the torso model corresponding to the target object can be determined when the target object is detected in the display interface. The vertex information of at least one facet is determined to obtain the target torso model corresponding to the target object, so that when a touch point is detected, the target vertex information corresponding to the touch point on the target torso model can be determined. It should be noted that the torso model to be processed consists of at least one facet; the vertex information of each facet is different. Here, a facet refers to a mesh in an application software or application that supports special effects image processing; it can be understood as an object used to carry images in the application software. Furthermore, each facet can consist of at least three vertices. Based on this, it can be understood that the vertex information of each facet is the position information of each vertex constituting the torso model to be processed.

[0051] In the actual process of determining the target torso model, the texture to be processed corresponding to the torso model can be determined first, and then the vertex information of each facet can be determined based on the texture to be processed. Since the target torso model is composed of multiple facets, the texture to be processed can be one or more textures created for the torso of the target object. Each texture corresponds to a specific 3D mesh. It can be understood that when the target object is a user, each 3D mesh is used to represent at least one region on the target torso model corresponding to that user, for example, representing the user's head region. This can be understood as each 3D mesh representing at least one of multiple regions, and multiple 3D meshes representing multiple different regions. Furthermore, since each texture to be processed consists of multiple vertices, once the application determines each texture to be processed, it can determine the corresponding vertex arrangement information from the facets corresponding to the texture to be processed, and then determine the vertex information of each facet based on the vertex arrangement information. It should be noted that in actual application, after associating each created texture with a 3D mesh, it is also possible to set the vertices determined from each 3D mesh, or adjust the UVs and general parameters of the vertices of each 3D mesh, so as to ensure that the UVs of each 3D mesh are not reused.

[0052] In this embodiment, when a target torso model is displayed on the screen, the application software can also detect the user's touch operation in real time. When a touch point is detected, it needs to determine whether the touch point is located on the target object. Furthermore, if it is determined that the touch point is located on the target object, the application can determine the target vertex information corresponding to the touch point on the target torso model. It can be understood that since the torso model is composed of at least one facet, and each facet is composed of at least three vertices, the target vertex information is the position information of each vertex that constitutes the target torso model, such as the coordinates of each vertex in the three-dimensional coordinate system. Continuing with the above example, when a user is dancing in the video, if another user touches the screen and the touch point is located on the body of the dancing user in the screen, the application can further determine the coordinate information of the three vertices corresponding to the touch point on the user's torso model, that is, the target vertex information.

[0053] In this embodiment, when determining the target vertex information through the attachment location corresponding to the voice information, specific information can be preset in the application software as the information for determining the attachment location by using preset effect attachment conditions. For example, one or more words such as "head," "shoulder," or "leg" can be used as the information for determining the effect attachment location. At the same time, the above information is also associated with the corresponding torso position. Based on this, when the application needs to attach the effect to the torso of the target object and receives the user's voice information, it can use a pre-trained speech recognition model to recognize the voice information. When it is determined that the recognition result contains the word "head," the application can determine the head region on the target torso model associated with that word, thereby determining the target vertex information of that region.

[0054] In this embodiment, when the target vertex information is determined by the torso model corresponding to the limb action information, the action of the target object in the picture can be detected in real time by the application. When the target object makes a specific action, the target area associated with the action can be determined on the target torso model of the target object, and then the vertex information of the area can be determined as the target vertex information.

[0055] Specifically, in determining the target vertex information, the pixel of the touch point on the display interface can be determined, or the pixel corresponding to the center of the mounting part can be determined, or the geometric center point can be determined based on the torso model corresponding to the limb action information, and the geometric center point can be used as the pixel to determine the target patch corresponding to the pixel; based on the three vertex information of the target patch, the target vertex information corresponding to the touch point can be determined. Specifically, when a video containing the torso of the target object is playing, if it is detected that the user clicks on the body of the target object in the screen with a mouse, the location of the mouse click is the touch point; or, when a video containing the torso of the target object is displayed on a touch screen, if it is detected that the user triggers the body of the target object in the screen with a finger or other device, the location where the finger or other device contacts the touch screen is the touch point.

[0056] In this embodiment, the application can also determine the center of the attachment part as a pixel. For example, when the attachment part of the special effect is determined to be the user's arm area, the pixel at the center of the arm area can be directly determined. When the attachment part of the special effect is determined to be the head, the pixel at the center of the head area can be directly determined. At the same time, since the target torso model can be either static or dynamic, a geometric center point can be determined on the torso model corresponding to the limb action information. For example, when the target torso model is a user's limb model, and one of the user's arms on the model is always swinging, the application can determine the geometric center point of the user's arm part on the model, and then use that point as a pixel.

[0057] For example, the application can first draw the corresponding render texture based on each video frame and output the UV value of each vertex. This can be understood as setting continuous and different UV values ​​for each vertex of the mesh. Based on this, when the user touches a part of the dancer's body in the display interface, the application can determine a script click event and parse it to determine the position (i.e., pixel) of the user's click on the screen. Further, based on the pixel, the UV of the corresponding triangle (i.e., target facet) on the target torso model is determined, and the three vertex information representing the position of the triangle is used as the target vertex information corresponding to the user's touch point.

[0058] Optionally, when determining the target vertex information based on the three vertex information of the target patch, the three vertex information can be interpolated based on the three vertex information of the target patch and the touch point to determine the target vertex information of the touch point. For example, when the application software determines that the target patch corresponds to a certain area on the torso of the target object, the three vertex information corresponding to the patch can be determined. Furthermore, combined with the determined touch point, the three vertex information can be interpolated to determine the target vertex as the attachment point of the special effect. It can be understood that image interpolation is the process of using the gray values ​​of known neighboring pixels (or the three color values ​​in an RGB image) to generate the gray value of an unknown pixel. This embodiment of the present disclosure will not elaborate further on this.

[0059] S130. Determine the target mount point corresponding to the target vertex information, and determine the current offset angle of the target object.

[0060] In this embodiment, after the target vertex information is determined on the target torso model, in order to associate the target effect selected by the user with the user's body in the video frame, it is also necessary to determine the target mounting point corresponding to the target vertex information. At the same time, in order to make the orientation of the effect consistent with the orientation of the user's torso in the video frame, the application also needs to determine the current offset angle of the target object.

[0061] The target mounting point can be a point on the face to which the target vertex belongs, used to indicate the mounting position of the target effect. For example, when it is determined that the face to which the target vertex belongs corresponds to the area of ​​the user's arm in the video frame, the vertex corresponding to that face can be determined as the target mounting point, or a point within that face can be used as the target mounting point.

[0062] In this embodiment, since the target object in the video frame may be in constant motion, the orientation of the target object will deflect at a certain angle relative to the virtual camera. Therefore, while determining the target mounting point, the application also needs to determine the current offset angle of the target object. The current offset angle represents the orientation of the user's body in the video frame at the current moment. For example, the user's spine in the video frame is associated with the z-axis of the spatial coordinate system. Furthermore, when the target object faces the virtual camera, a surface is determined from the target torso model of the target object, resulting in a normal line facing the virtual camera. Based on this, when the torso of the target object deflects, another normal line can be obtained from the target torso model. By calculating the angle between the two normal lines, the application can determine the deflection angle of the target torso model in the spatial coordinate system, and thus use this angle as the current offset angle.

[0063] Optionally, the target mounting point on the display interface is determined based on the target vertex information, and the current offset angle of the target object is determined based on the deflection angle of the target limb torso.

[0064] Specifically, once the target vertex information (e.g., the position coordinates of the three vertices) corresponding to the target facet is determined, a pre-created interpolation plugin can be used to determine one of the vertexes of the facet as the target mounting point, or a specific point within the facet as the target mounting point. Simultaneously, this plugin can be used to construct a spatial coordinate system in virtual 3D space, and any coordinate axis within this system can be arbitrarily associated with the target torso model of the target object.

[0065] S140. Based on the target mounting point and the current offset angle, mount the target effect onto the target object to obtain the effect video frame.

[0066] It should be noted that before attaching the special effect to the user's body in the video frame, the user first needs to select the corresponding target effect in the application software. The target effect can be an effect selected by the user from the effect package provided by the application. For example, the target effect can be an item, flower, or jewelry displayed on the display interface that can be attached to the target object's body.

[0067] In this embodiment, the target effect also includes static effects and dynamic effects; wherein, static effects are effects fixed at the target mounting point, and dynamic effects are motion effects associated with the target mounting point. For example, when a 3D balloon model is pre-generated as a static effect using any image processing software, and a control associated with the static effect is generated, if the user clicks the control, it can be determined that the user has currently selected the balloon effect. Furthermore, based on the user's touch point, the application can fix the 3D balloon model corresponding to the static effect at a certain position on the user's body displayed on the display interface. When a colored light strip is pre-generated as a dynamic effect, and a control associated with the dynamic effect is generated, if the user clicks the control, it can be determined that the user has currently selected the light strip effect. Furthermore, based on the user's touch point, the application can associate the light strip corresponding to the dynamic effect with a certain area on the user's body displayed on the display interface, so that the light strip produces adaptive motion as the user's body moves in the interface, presenting the user with a richer visual effect.

[0068] In this embodiment, once the application determines the target attachment point and the current offset angle, the user-selected target effect can be attached to the target object. For example, the 3D balloon model corresponding to the user-selected effect can be attached to the body of a user dancing in a video. It should be noted that in practical applications, a pre-created interpolation plugin can still be used to perform the operation of attaching the target effect to the target object. That is, this plugin can treat each part of the target object as a single entity, thereby attaching the effect to the UV points of the target object's mesh. Furthermore, the lerp function can be used to adjust the specific position of the effect attached to the target torso model.

[0069] In practical applications, target objects can be divided into two categories: dynamic target objects and static target objects. Based on this, when the target object is static, after the application attaches the special effects selected by the user from the special effects package to the body of the target object, the special effects will remain statically displayed. When the target object is dynamic, after the application attaches the special effects selected by the user from the special effects package to the body of the target object, the special effects will also move adaptively with the movement of the target object. The following is a detailed explanation of this process.

[0070] Specifically, when the target effect is a dynamic effect, in order to obtain the corresponding effect video frame, it is also necessary to determine the display style, motion rate, and motion path of the dynamic effect. The display style can be information representing parameters such as the pattern, color, and texture of the dynamic effect; the motion rate is a parameter reflecting how fast the 2D texture or 3D model corresponding to the target effect moves in the display interface; and the motion path represents the trajectory of the 2D texture or 3D model corresponding to the target effect in the display interface. Of course, in practical applications, the display style, motion rate, and motion path of the dynamic effect can be adjusted according to actual needs, and this disclosure does not impose specific limitations on them.

[0071] Optionally, the target mounting point can be used as the starting point for the dynamic effect, and the effect can be generated by moving according to the motion path and speed. Each effect video frame is the original video frame after the target effect is added. Furthermore, each effect video frame carries the same timestamp as the original video frame. Therefore, by stitching the effect video frames together based on the timestamps, the corresponding effect video is obtained. In essence, in the effect video, the 2D texture or 3D model corresponding to the dynamic effect will use the target mounting point as the starting point and move according to the motion path and speed determined by the application.

[0072] For example, when the user selects a target effect that corresponds to a specific object, the application can first determine the display style corresponding to the effect, that is, the object model associated with the effect. At the same time, it determines that the movement speed of the object model in the display interface is 1, which means that the model moves one unit length per second in the display interface. It also determines that the movement path of the object model in the display interface is a horizontal line of a specific length. Based on this, when the target attachment point is the left shoulder of the target object, it means that the model is added to the video to obtain an effect video frame. After generating an effect video based on multiple effect video frames, the object model displayed in the effect video will move from the left shoulder to the right shoulder of the target object according to the preset movement speed.

[0073] In practical applications, the application can also determine at least one path vertex of the target effect on the target torso model based on the target vertex information, motion path, and motion rate of the target mount point; and determine the effect video frames of the target effect moving on the target torso model based on the target vertex information and at least one path vertex. Specifically, in the process of generating effect videos based on target effects, since the target mount point has been determined as the starting point of the 2D texture or 3D model associated with the target effect, and the motion path and motion rate of the model in the video have also been determined, the application can calculate multiple path vertices of the target effect on the target torso model through a pre-edited program. For example, after determining the starting point of the 3D balloon's movement in the video frame, as well as the 3D balloon's motion rate and trajectory, the application can call and run the pre-edited path point determination program to determine multiple path vertices. It can be understood that these vertices can directly reflect the motion path of the 2D texture or 3D model associated with the target effect.

[0074] Furthermore, based on the target vertex information serving as the starting point of the special effects motion, and multiple path vertices, the application can control the 2D texture or 3D model corresponding to the target special effects to move within the original video frame, thereby obtaining multiple special effects video frames. Those skilled in the art should understand that once multiple special effects video frames are obtained, the application can write the information of each pixel in the special effects video frame into the rendering engine, thereby enabling the rendering engine to render the image corresponding to the current special effects video frame on the display interface. The rendering engine can be a program that controls the graphics processing unit (GPU) to render relevant images; that is, it can enable the computer to complete the drawing task of multiple special effects video frames. Further details are omitted here.

[0075] It should also be noted that in practical applications, a pre-written script can be used to read the mesh corresponding to the user's body in the video frame in real time, driven by the algorithm, and test whether the 2D texture or 3D model corresponding to the attached target effect can correctly follow the movement of the specific mesh. At the same time, it can also test whether each mesh can be aligned with the torso of the target object in the display interface.

[0076] The technical solution of this disclosure, when detecting that the special effect mounting conditions are met, determines the target torso model corresponding to the target object, then determines the target special effect and the target vertex information on the target torso model, further determines the target mounting point corresponding to the target vertex information, and determines the current offset angle of the target object. Finally, based on the target mounting point and the current offset angle, the target special effect is mounted on the target object to obtain a special effect video frame, so that the added special effect can be associated with the user's limbs in the video screen. At the same time, the orientation of the special effect corresponds to the orientation of the user's limbs in the screen, so that the visual effect presented by the special effect video is more realistic and enhances the user experience.

[0077] Figure 2 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, the device includes: a target torso model determination module 210, a target vertex information determination module 220, a target mounting point determination module 230, and a special effects video frame generation module 240.

[0078] The target torso model determination module 210 is used to determine the target torso model corresponding to the target object when the special effect mounting conditions are detected.

[0079] The target vertex information determination module 220 is used to determine the target effect and the target vertex information on the target torso model.

[0080] The target mount point determination module 230 is used to determine the target mount point corresponding to the target vertex information and to determine the current offset angle of the target object.

[0081] The special effects video frame generation module 240 is used to attach the target special effects to the target object based on the target mounting point and the current offset angle to obtain the special effects video frame.

[0082] Based on the above technical solutions, the image processing device also includes a to-be-processed torso model determination module and a target torso model determination module.

[0083] The torso model determination module is used to determine the torso model corresponding to the target object when the display interface detects that the target object is included; wherein the torso model is composed of at least one facet.

[0084] The target torso model determination module is used to determine the vertex information of the at least one facet to obtain a target torso model corresponding to the target object, so as to determine the target vertex information corresponding to the touch point on the target torso model when a touch point is detected; wherein, the vertex information of each facet is different.

[0085] Based on the above technical solutions, the target torso model determination module includes a texture determination unit and a vertex information determination unit.

[0086] The texture determination unit is used to determine the texture to be processed corresponding to the body torso model to be processed.

[0087] Vertex information determination form, used to determine the vertex information of each facet based on the texture to be processed.

[0088] Based on the above technical solutions, the special effects mounting conditions include at least one of the following: triggering the special effects mounting control; detecting the trigger target object; detecting voice information triggering the special effects mounting wake-up word; detecting that the body movement information is consistent with the preset movement information.

[0089] Optionally, the target vertex information determination module 220 is further configured to determine the touch point of the target object, and determine the target vertex information corresponding to the target torso model based on the touch point; or, determine the mounting part corresponding to the voice information, and determine the target vertex information corresponding to the target torso based on the mounting part; or determine the target vertex information according to the torso model corresponding to the limb movement information.

[0090] Based on the above technical solutions, the target vertex information determination module 220 includes a pixel point determination unit and a target vertex information determination unit.

[0091] A pixel determination unit is used to determine the pixel of the touch point on the display interface; or, determine the pixel corresponding to the center of the mounting part; or, determine the geometric center point based on the torso model corresponding to the limb movement information, and use the geometric center point as the pixel.

[0092] The target vertex information determination unit is used to determine the target patch corresponding to the pixel and, based on the three vertex information of the target patch, determine the target vertex information corresponding to the touch point.

[0093] Optionally, the target vertex information determination unit is further configured to perform interpolation processing on the three vertex information of the target patch and the touch point to determine the target vertex information of the touch point.

[0094] Optionally, the target mounting point determination module 230 is further configured to determine the target mounting point on the display interface based on the target vertex information, and to determine the current offset angle of the target object based on the deflection angle of the target limb torso.

[0095] Based on the above technical solutions, the target special effects are static special effects and dynamic special effects; wherein, the static special effects are special effects fixed at the target mounting point, and the dynamic special effects are motion special effects associated with the target mounting point.

[0096] Based on the above technical solutions, the image processing device also includes a display style determination module.

[0097] The display style determination module is used to determine the display style, motion rate, and motion path of dynamic effects.

[0098] Optionally, the special effects video frame generation module 240 is further configured to use the target mounting point as the starting point of the dynamic special effects, and move according to the motion path and motion rate to obtain the special effects video frame.

[0099] Optionally, the special effects video frame generation module 240 is further configured to determine at least one path vertex of the target effect on the target torso model based on the target vertex information, motion path and motion rate of the target mounting point; and to determine the special effects video frame of the target effect moving on the target torso model based on the target vertex information and the at least one path vertex.

[0100] The technical solution provided in this embodiment, when detecting that the special effect mounting conditions are met, determines the target torso model corresponding to the target object, then determines the target special effect and the target vertex information on the target torso model, further determines the target mounting point corresponding to the target vertex information, and determines the current offset angle of the target object. Finally, based on the target mounting point and the current offset angle, the target special effect is mounted on the target object to obtain the special effect video frame, so that the added special effect can be associated with the user's limbs in the video screen. At the same time, the orientation of the special effect corresponds to the orientation of the user's limbs in the screen, so that the visual effect presented by the special effect video is more realistic and enhances the user experience.

[0101] The image processing apparatus provided in this disclosure can execute the image processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0102] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0103] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Reference is made below. Figure 3It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 3 The diagram below shows the structure of the terminal device or server 300. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0104] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, pattern processor, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 306 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An edit / output (I / O) interface 305 is also connected to the bus 304.

[0105] Typically, the following devices can be connected to I / O interface 305: editing devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0106] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 306, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of embodiments of this disclosure.

[0107] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0108] The electronic device provided in this embodiment and the image processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0109] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the image processing method provided in the above embodiments.

[0110] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but 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 may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0111] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0112] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0113] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to:

[0114] When the conditions for special effects mounting are met, the target torso model corresponding to the target object is determined.

[0115] Determine the target special effects and the target vertex information on the target torso model;

[0116] Determine the target mount point corresponding to the target vertex information, and determine the current offset angle of the target object;

[0117] Based on the target mounting point and the current offset angle, the target effect is mounted on the target object to obtain the effect video frame.

[0118] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can 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 can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0120] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0121] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0122] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0123] According to one or more embodiments of this disclosure, [Example 1] provides an image processing method, the method comprising:

[0124] When the conditions for special effects mounting are met, the target torso model corresponding to the target object is determined.

[0125] Determine the target special effects and the target vertex information on the target torso model;

[0126] Determine the target mount point corresponding to the target vertex information, and determine the current offset angle of the target object;

[0127] Based on the target mounting point and the current offset angle, the target effect is mounted on the target object to obtain the effect video frame.

[0128] According to one or more embodiments of this disclosure, [Example 2] provides an image processing method, which further includes:

[0129] Optionally, when a target object is detected in the display interface, a torso model to be processed corresponding to the target object is determined; wherein the torso model to be processed is composed of at least one facet.

[0130] Determine the vertex information of the at least one facet to obtain a target torso model corresponding to the target object, so that when a touch point is detected, the target vertex information corresponding to the touch point on the target torso model can be determined;

[0131] The vertex information of each facet is different.

[0132] According to one or more embodiments of this disclosure, [Example 3] provides an image processing method, which further includes:

[0133] Optionally, determine the texture to be processed corresponding to the body torso model to be processed;

[0134] Based on the texture to be processed, the vertex information of each facet is determined.

[0135] According to one or more embodiments of this disclosure, [Example 4] provides an image processing method, which further includes:

[0136] Optionally, the special effects mounting conditions include at least one of the following:

[0137] Trigger special effects to mount controls;

[0138] The target object that triggered the attack was detected;

[0139] Voice information was detected, triggering an effect to attach a wake word;

[0140] The detected limb movement information matches the preset movement information.

[0141] According to one or more embodiments of this disclosure, [Example 5] provides an image processing method, which further includes:

[0142] Optionally, a touch point on the target object is determined, and target vertex information on the corresponding target torso model is determined based on the touch point; or,

[0143] Determine the mounting location corresponding to the voice information, and based on the mounting location, determine the target vertex information corresponding to the target torso; or

[0144] The target vertex information is determined based on the torso model corresponding to the limb movement information.

[0145] According to one or more embodiments of this disclosure, [Example Six] provides an image processing method, which further includes:

[0146] Optionally, the pixel of the touch point on the display interface is determined, or the pixel corresponding to the center of the mounting part is determined; or, the geometric center point is determined according to the torso model corresponding to the limb movement information, and the geometric center point is used as the pixel.

[0147] The target patch corresponding to the pixel is determined, and the target vertex information corresponding to the touch point is determined based on the three vertex information of the target patch.

[0148] According to one or more embodiments of this disclosure, [Example Seven] provides an image processing method, which further includes:

[0149] Optionally, based on the three vertex information of the target patch and the touch point, the three vertex information is interpolated to determine the target vertex information of the touch point.

[0150] According to one or more embodiments of this disclosure, [Example Eight] provides an image processing method, which further includes:

[0151] Optionally, the target mounting point on the display interface is determined based on the target vertex information, and the current offset angle of the target object is determined based on the deflection angle of the target limb torso.

[0152] According to one or more embodiments of this disclosure, [Example Nine] provides an image processing method, which further includes:

[0153] Optionally, the target effect can be a static effect or a dynamic effect;

[0154] The static special effects are those fixed at the target mounting point, and the dynamic special effects are those motion effects associated with the target mounting point.

[0155] According to one or more embodiments of this disclosure, [Example 10] provides an image processing method, which further includes:

[0156] Optionally, you can determine the display style, motion rate, and motion path of the dynamic effects.

[0157] According to one or more embodiments of this disclosure, [Example 11] provides an image processing method, which further includes:

[0158] Optionally, the target mounting point can be used as the starting point of the dynamic effect, and the motion can be performed according to the motion path and motion rate to obtain the effect video frame.

[0159] According to one or more embodiments of this disclosure, [Example Twelve] provides an image processing method, which further includes:

[0160] Optionally, based on the target vertex information, motion path, and motion rate of the target mounting point, at least one path vertex of the target effect on the target torso model is determined;

[0161] Based on the target vertex information and the at least one path vertex, determine the special effect video frame in which the target effect moves on the target torso model.

[0162] According to one or more embodiments of this disclosure, [Example Thirteen] provides an image processing apparatus, the apparatus comprising:

[0163] The target torso model determination module is used to determine the target torso model corresponding to the target object when the special effect mounting conditions are met.

[0164] The target vertex information determination module is used to determine the target effect and the target vertex information on the target torso model;

[0165] The target mount point determination module is used to determine the target mount point corresponding to the target vertex information and to determine the current offset angle of the target object;

[0166] The special effects video frame generation module is used to attach the target special effects to the target object based on the target mounting point and the current offset angle, thereby obtaining the special effects video frame.

[0167] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0168] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0169] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An image processing method, characterized in that, include: When the conditions for special effects mounting are met, the target torso model corresponding to the target object is determined. Determine the target effect and the target vertex information on the target torso model; wherein, the target torso model is composed of at least one facet, each facet is composed of at least three vertices, and the target vertex information is the position information of each vertex that constitutes the target torso model; Determine the target mount point corresponding to the target vertex information, and determine the current offset angle of the target object; Based on the target mounting point and the current offset angle, the target effect is mounted on the target object to obtain the effect video frame; The determination of the target effect and the target vertex information on the target torso model includes: Determine the touch point of the target object, and based on the touch point, determine the target vertex information on the corresponding target torso model; or, Determine the mounting location corresponding to the voice information, and based on the mounting location, determine the target vertex information corresponding to the target torso; or, The target vertex information is determined based on the torso model corresponding to the limb movement information.

2. The method according to claim 1, characterized in that, Before determining the target effect and the target vertex information on the target torso model, the method further includes: When a target object is detected in the display interface, a torso model to be processed corresponding to the target object is determined; wherein the torso model to be processed is composed of at least one facet. Determine the vertex information of the at least one facet to obtain a target torso model corresponding to the target object, so that when a touch point is detected, the target vertex information corresponding to the touch point on the target torso model can be determined; The vertex information of each facet is different.

3. The method according to claim 2, characterized in that, The step of determining the vertex information of the at least one facet to obtain a target torso model corresponding to the target object includes: Determine the texture to be processed corresponding to the body torso model to be processed; Based on the texture to be processed, the vertex information of each facet is determined.

4. The method according to claim 1, characterized in that, The conditions for attaching the special effects include at least one of the following: Trigger special effects to mount controls; The triggering target object has been detected; Voice information was detected, triggering an effect to attach a wake word; The detected limb movement information matches the preset movement information.

5. The method according to claim 1, characterized in that, The determination of the target effect and the target vertex information on the target torso model includes: Determine the pixel location of the touch point on the display interface; or, Determine the pixel point corresponding to the center of the mounting location; or, Based on the torso model corresponding to the limb movement information, the geometric center point is determined and the geometric center point is used as the pixel point; The target patch corresponding to the pixel is determined, and the target vertex information corresponding to the touch point is determined based on the three vertex information of the target patch.

6. The method according to claim 5, characterized in that, The step of determining the target vertex information corresponding to the touch point based on the three vertex information of the target patch includes: Based on the three vertex information of the target patch and the touch point, the three vertex information is interpolated to determine the target vertex information of the touch point.

7. The method according to claim 1, characterized in that, Determining the target mount point corresponding to the target vertex information and determining the current offset angle of the target object includes: Based on the target vertex information, the target mounting point on the display interface is determined, and based on the deflection angle of the target limb torso, the current offset angle of the target object is determined.

8. The method according to claim 1, characterized in that, The target special effects are relatively static special effects and / or relatively dynamic special effects; The relative static effect is an effect fixed at the target mounting point, and the relative dynamic effect is a motion effect associated with the target mounting point.

9. The method according to claim 1, characterized in that, Also includes: Determine the display style, motion speed, and motion path of the dynamic effects.

10. The method according to claim 9, characterized in that, The process of attaching the target effect to the target object to obtain the effect video frame includes: Using the target mounting point as the starting point of the dynamic effect, the motion is performed according to the motion path and motion rate to obtain the video frame of the effect.

11. The method according to claim 10, characterized in that, The step of using the target mounting point as the starting point of the dynamic effect, and moving according to the motion path and motion rate to obtain the effect video frame includes: Based on the target vertex information, motion path and motion rate of the target mounting point, at least one path vertex of the target effect on the target torso model is determined; Based on the target vertex information and the at least one path vertex, determine the special effect video frame in which the target effect moves on the target torso model.

12. An image processing apparatus, characterized in that, include: The target torso model determination module is used to determine the target torso model corresponding to the target object when the special effect mounting conditions are met. The target vertex information determination module is used to determine the target effect and the target vertex information on the target torso model; wherein, the target torso model is composed of at least one facet, each facet is composed of at least three vertices, and the target vertex information is the position information of each vertex that constitutes the target torso model; The target mount point determination module is used to determine the target mount point corresponding to the target vertex information and to determine the current offset angle of the target object; The special effects video frame generation module is used to attach the target special effects to the target object based on the target mounting point and the current offset angle to obtain the special effects video frame; The target vertex information determination module is further configured to determine the touch point of the target object and determine the target vertex information on the target torso model based on the touch point; or, determine the mounting part corresponding to the voice information and determine the target vertex information corresponding to the target torso based on the mounting part; or, determine the target vertex information according to the torso model corresponding to the limb movement information.

13. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the image processing method as described in any one of claims 1-11.

14. A storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to perform the image processing method as described in any one of claims 1-11.

Images