Target object expression synchronization method and device

Abstract

The invention belongs to the technical field of computer vision, and particularly discloses a target object expression synchronization method and device. According to the method and the device, the position relation of the feature points in the face of the target object in the real-time video data in different expressions is determined based on the first input, and the position relation of the feature points in the target model for simulating different expressions of the target object is adjusted, so that synchronous simulation of different expressions of the target object is realized; the virtual and real expression synchronization effect is achieved, and the purpose of capturing the facial expression of the target object in real time is achieved. The method is easy to operate, low in cost and free of site limitation, various complex backgrounds can be processed, expression capture of the target object is more convenient and intelligent, the method can be applied to the fields of computer animation, games, virtual reality and the like, and the problems that an existing target object expression capture technology is complex in process and high in cost are solved.

Description

Technical Field

[0001] The present application belongs to the field of computer vision technology, and more specifically, to a method and device for synchronizing expression of a target object. Background Art

[0002] The difficulty of capturing the target object's expression is crucial to whether the target object's expression can be simulated synchronously. Currently, there are the following problems in capturing the target object's expression: Editing facial expression animations by using preset expressions has the problem of not being able to collect expressions in real time and lacking certain flexibility; Using motion capture helmets and other hardware devices to capture the target object's expression is costly and cumbersome, and cannot meet the requirements of convenience. Using the Adaboost algorithm to detect facial features from facial images will affect the real-time performance of expression capture. Summary of the invention

[0003] In view of the defects of the prior art, the purpose of the present application is to provide a method and device for synchronizing the expression of a target object, aiming to solve the problems of the prior art in that the target object expression capture technology is complex, costly and has poor real-time performance.

[0004] To achieve the above objectives, in a first aspect, the present application provides a method for synchronizing expression of a target object, comprising: In the case where it is determined that the read real-time video data includes the face of the target object, receiving a first input from the user; In response to the first input, based on the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions, the positional relationship of each feature point in the target model is adjusted to simulate different expressions of the target object. The target model is a model for simulating different expressions of the target object.

[0005] In some embodiments, when it is determined that the read real-time video data includes the face of the target object, before receiving the first input from the user, the method further includes: receiving a second input from the user; In response to the second input, calling a preset algorithm to determine the positional relationship of each feature point in the face of the target object in the real-time video data when the target object is in the first expression; receiving a third input from the user; In response to the third input, a preset algorithm is called to determine the positional relationship between the various feature points on the face of the target object in the real-time video data when the target object is in the second expression.

[0006] In some embodiments, in response to the second input, calling a preset algorithm to determine the positional relationship of each feature point on the face of the target object when the target object is in the first expression includes: In response to the second input, calling a preset algorithm to determine the positions of each feature point on the face of the target object in the real-time video data when the target object is in the first expression; Determine a facial position area where positions of each feature point on the face of the target object in the real-time video data are located when the target object is in a first expression; Calculate the degree and angle of opening and closing of facial position areas; Calculating the distance relationship between each feature point in the face of the target object in the real-time video data contained in the face position area when the target object is in the first expression; The positional relationship of each feature point in the face of the target object in the real-time video data when the target object is in the first expression is determined according to the distance relationship, the opening and closing degree and the angle.

[0007] In some embodiments, the method further comprises: receiving a fourth input from the user; In response to the fourth input, a target model is created.

[0008] In some embodiments, the first expression and the second expression are any one of sadness, fear, disgust, happiness, anger, surprise and neutrality, and the second expression is different from the first expression.

[0009] In a second aspect, the present application provides a target object expression synchronization device, comprising: A first receiving module, configured to receive a first input from a user when it is determined that the read real-time video data includes a face of a target object; The first processing module is used to respond to the first input, adjust the positional relationship of each feature point in the target model based on the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions, and simulate different expressions of the target object. The target model is a model used to simulate different expressions of the target object.

[0010] In some embodiments, it also includes: A second receiving module, used to receive a second input from a user; A second processing module is used to call a preset algorithm in response to a second input to determine the position relationship of each feature point on the face of the target object in the real-time video data when the target object is in a first expression; A third receiving module, used to receive a third input from a user; The third processing module is used to call a preset algorithm in response to the third input to determine the position relationship of each feature point in the face of the target object in the real-time video data when the target object is in a second expression.

[0011] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the method described in the first aspect or any embodiments of the first aspect.

[0012] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any embodiments of the first aspect.

[0013] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any embodiments of the first aspect.

[0014] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art: The target object expression synchronization method and device provided by the present application determines the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions based on the first input, and adjusts the positional relationship of each feature point in the target model used to simulate the different expressions of the target object, so as to achieve the synchronous simulation of the different expressions of the target object, achieve the effect of synchronizing virtual and real expressions, and realize the purpose of real-time capture of the facial expression of the target object. The present application is simple to operate, low in cost, not limited by the venue, and can handle various complex backgrounds, making the expression capture of the target object more convenient and intelligent. It can be applied to computer animation, games, virtual reality and other fields, solving the problem of complex process and high cost of the current target object expression capture technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of a target object expression synchronization method provided in an embodiment of the present application; Figure 2 is a schematic diagram of the structure of a target object expression synchronization device provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0017] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0018] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of objects. For example, a first input and a second input are used to distinguish different inputs rather than to describe a specific order of inputs.

[0019] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0020] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more than two.

[0021] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0022] See also Figure 1 , an embodiment of the present application provides a method for synchronizing expression of a target object, including: step 110 and step 120.

[0023] Step 110: receiving a first input from a user when it is determined that the read real-time video data includes a face of the target object; Step 120 responds to the first input, and adjusts the positional relationship of each feature point in the target model based on the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions, so as to simulate different expressions of the target object. The target model is a model for simulating different expressions of the target object.

[0024] It should be noted that the execution subject of the above method may be a terminal, and more specifically, may be an expression synchronization application installed in the terminal.

[0025] The target object expression synchronization method provided in the embodiment of the present application is described in detail below by taking the expression synchronization application being Unity3D as an example.

[0026] Start Unity3D software, place the RawImage component on the display panel of Unity3D software, read the real-time video data captured by the imaging device, convert the real-time video data through Texture2D, obtain the image corresponding to the real-time video data, and carry the image to the RawImage component for display.

[0027] The display panel is also provided with a control component, which is used to receive user input.

[0028] When the read real-time video data contains the face of the target object, a first input from the user is received through the control component. The first input is used to characterize the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions. In the embodiment of the present application, the target object may be a person.

[0029] Exemplarily, different txt documents may be used to store the positional relationships of various feature points for different expressions. Each txt document stores the positional relationships of various feature points for one expression. Different txt documents are distinguished by different names, for example, they may be named after the expressions they store.

[0030] A txt document storing the positional relationship of each feature point during each of the above-mentioned expressions is used as the first input.

[0031] When the read real-time video data contains the face of the target object, the user can give an indication of the target object, and the target object gives different expression feedback according to the indication given by the user. At the same time, the user saves the position relationship of each feature point in the face of the target object with different expressions as the first input to the control component.

[0032] The Unity3D software adjusts the positional relationship of each feature point in the target model in the display panel of the Unity3D software according to the positional relationship of each feature point on the face of the target object in the real-time video data in the first input when the target object has different expressions, and adjusts the positional relationship of each feature point in the target model to be consistent with the positional relationship of each feature point on the face of the target object when the target object has different expressions. This achieves synchronous simulation of different expressions of the target object and achieves the effect of virtual expression synchronization.

[0033] In the embodiment of the present application, the target simulation can be a model for simulating different expressions of the target object, and the model is provided with various feature points in the face of the target object for simulating different expressions. The model can be built by 3D modeling software and then imported into Unity3D software.

[0034] Determine whether the real-time video data read contains the target object's face through the following steps: In the embodiment of the present application, the OpencvForUnity plug-in is imported into the Unity3D software to build a deep learning and video image processing environment; Get the image corresponding to the real-time video data displayed by the RawImage component, use the CvtColor function to convert the image into a grayscale image, use the fast guided filter to perform smoothing filtering on the grayscale image to obtain the processed image, which reduces noise while retaining the edge details of the face.

[0035] The processed image is transferred to the libfacedetectionV3 model to identify the facial area of ​​the target object in the processed image; The libfacedetectionV3 model is used to obtain the position coordinates of the facial area on the real-time video data, and then the position coordinates of the facial area are saved and returned to the RawImage component for display.

[0036] By observing the RawImage component, the user can determine whether the real-time video data includes the face of the target object.

[0037] The target object expression synchronization method provided in the embodiment of the present application determines the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions based on the first input, and adjusts the positional relationship of each feature point in the target model used to simulate the different expressions of the target object, so as to achieve the synchronous simulation of the different expressions of the target object, achieve the effect of synchronizing the virtual and real expressions, and realize the purpose of real-time capture of the facial expression of the target object. The present application is simple to operate, low in cost, not limited by the venue, and can handle various complex backgrounds, making the expression capture of the target object more convenient and intelligent. It can be applied to computer animation, games, virtual reality and other fields, solving the problem of complex process and high cost of the current target object expression capture technology.

[0038] Furthermore, in some embodiments, when it is determined that the read real-time video data includes the face of the target object, before receiving the first input from the user, the method further includes: receiving a second input from the user; In response to the second input, calling a preset algorithm to determine the positional relationship of each feature point in the face of the target object in the real-time video data when the target object is in the first expression; receiving a third input from the user; In response to the third input, a preset algorithm is called to determine the positional relationship between the various feature points in the face of the target object in the real-time video data when the target object is in the second expression.

[0039] In an embodiment of the present application, in order to achieve real-time capture of the target object in different expressions, when the user observes that the target object in the read real-time video data is in a first expression, a second input is input into Unity3D, and the second input can be used to characterize that the target object in the real-time video data is in the first expression.

[0040] The Unity3D software determines the positional relationship of each feature point of the target object in the real-time video data when the target object is in the first expression from the second input by calling a preset algorithm. If the target object is a person, the positional relationship of the above 68 feature points of the person in the first expression needs to be determined.

[0041] After determining the positional relationship of each feature point of the target object in the real-time video data when the target object is in the first expression, the feature point is saved in a txt document. The txt document is named in English corresponding to the first expression.

[0042] The user instructs the target object to adjust its expression. When the target object in the real-time video data is observed to be in the second expression, in order to be able to capture the target object's expression movements in real time, when it is determined that the expression of the target object in the real-time video data has changed, a third input is input into the Unity3D software. The third input can be used to characterize that the expression of the target object in the real-time video data has changed.

[0043] The Unity3D software continues to call the above preset algorithm, determines the positional relationship of each feature point of the target object in the real-time video data when it is in the second expression from the third input, and saves it in a txt document. The txt document is named in English corresponding to the second expression.

[0044] The target object expression synchronization method provided in the embodiment of the present application determines the positional relationship of each feature point of the target object when it is in a first expression through a second input, so as to realize the synchronous simulation of the first expression of the target object, and after the expression of the target object is adjusted to the second expression, timely adjusts the positional relationship of each feature point of the target object when it is in the second expression through a third input, thereby realizing dynamic adjustment of the positional relationship of each feature point in the face of the target object when it is in different expressions, thereby improving the accuracy and real-time performance of facial expression capture.

[0045] Further, in some embodiments, in response to the second input, calling a preset algorithm to determine the positional relationship of each feature point on the face of the target object when the target object is in the first expression includes: In response to the second input, calling a preset algorithm to determine the positions of each feature point in the face of the target object in the real-time video data when the target object is in the first expression; Determine a facial position area where positions of each feature point on the face of the target object in the real-time video data are located when the target object is in a first expression; Calculate the degree and angle of opening and closing of facial position areas; Calculating the distance relationship between each feature point in the face of the target object in the real-time video data contained in the face position area when the target object is in the first expression; The positional relationship of each feature point in the face of the target object in the real-time video data when the target object is in the first expression is determined according to the distance relationship, the opening and closing degree and the angle.

[0046] In the embodiment of the present application, the facial area of ​​the target object when it is in the first expression is detected by the libfacedetectionV3 model, and the facial area is returned to the RawImage component for display.

[0047] According to the facial area of ​​the target object when it is in the first expression, dlib is called to perform feature point detection to determine the positions of the various feature points of the target object in the real-time video data when it is in the first expression.

[0048] Taking a human face as an example, the 68 feature points of the person in the first expression obtained above are divided according to the facial position area where they are located, specifically: The 68 feature points are divided into four facial position areas according to the nose, eyes, mouth and eyebrows, or the facial area is divided into 6 facial position areas, namely upper left, middle left, lower left, upper right, middle right and lower right, and according to the positions of the above 68 feature points, they are divided into 6 facial position areas, namely upper left, middle left, lower left, upper right, middle right and lower right.

[0049] The opening and closing degrees and angles of the nose, eyes, mouth and eyebrows, which are divided into four facial position areas, of the target object in the real-time video data when the target object is in the first expression are calculated based on the positions of the 68 feature points.

[0050] The distance relationship between 68 feature points in the six facial position areas of upper left, left middle, lower left, upper right, right middle and lower right is calculated respectively.

[0051] According to the distance relationship, the opening and closing degree and the angle, the positional relationship of each feature point in the face of the target object in the real-time video data when the target object is in the first expression is determined.

[0052] In the embodiment of the present application, the libfacedetectionV3 model used plays a vital role in the face detection process. It can be combined with the fast guided filtering algorithm to quickly locate the face area, and then use dlib to extract the coordinates of 68 feature points of the face. The face model is driven by calculating the changes in the coordinates of the 68 feature points under various facial expressions and actions. Finally, the data is saved to drive the face model to achieve the effect of capturing facial expressions.

[0053] Further, in some embodiments, the first expression and the second expression are any one of sadness, fear, disgust, happiness, anger, surprise and neutrality, and the second expression is different from the first expression.

[0054] In the embodiment of the present application, the first expression and the second expression are any one of sadness, fear, disgust, happiness, anger, surprise and neutrality, and the second expression is different from the first expression.

[0055] The target object expression synchronization method provided in the embodiment of the present application uses the libfacedetectionV3 model to quickly locate the face area, divides the face into four facial position areas of nose, eyes, mouth, and eyebrows, and also divides the face into six facial position areas of upper left, middle left, lower left, upper right, middle right, and lower right. The feature point data in each facial position area when the target object is in different expressions is obtained through dlib. The real face makes various facial expressions, and the degree of opening and closing, the angle and the distance relationship between the feature points are synchronously calculated to simulate the different facial expressions of the real face, so as to obtain a more natural and practical expression capture effect.

[0056] Furthermore, in some embodiments, the method further comprises: receiving a fourth input from the user; In response to the fourth input, a target model is created.

[0057] In the embodiment of the present application, a target model is created by using 3D modeling software (such as 3DMax).

[0058] Exemplarily, 3DMax is opened, the fourth input of the user is received, and the subdivision modifier MeshSmooth and the edit polygon tool are applied to build a face model with 68 feature points. The face model is the target model, and it is imported into Unity3D and placed in the 3D space.

[0059] Specifically, firstly, in 3DMax, the fourth input of the user is received, a simple sphere is placed, and the basic outline of a face is shaped by stretching, squeezing, scaling and other operations; Secondly, apply the subdivision modifier MeshSmooth to increase the number of polygons of the facial contour, and then use the Edit Polygon tool to further adjust the points, edges and faces of the facial contour to make the contour more consistent with the real human face; Finally, the shapes of the facial features such as eyes, nose, mouth, ears and eyebrows are sculpted, and sculpting tools are used to fine-tune the contours and undulations of the facial features. Based on the distribution of 68 feature points in the human face, marker points are created at the corresponding positions of the model, so that the face model can respond to facial expressions and movements by adjusting the 68 feature points.

[0060] The target object expression synchronization device provided by the present application is described below. The target object expression synchronization device described below and the target object expression synchronization method described above can be referenced to each other.

[0061] See also Figure 2 An embodiment of the present application provides a target object expression synchronization device, including: a first receiving module 210 and a first processing module 220.

[0062] The first receiving module 210 is used to receive a first input from a user when it is determined that the read real-time video data includes a face of a target object; The first processing module 220 is used to respond to the first input, adjust the positional relationship of each feature point in the target model based on the positional relationship of each feature point in the face of the target object in different expressions in the real-time video data, and simulate different expressions of the target object. The target model is a model used to simulate different expressions of the target object.

[0063] Furthermore, in some embodiments, it also includes: A second receiving module, used to receive a second input from a user; A second processing module is used to call a preset algorithm in response to a second input to determine the position relationship of each feature point on the face of the target object in the real-time video data when the target object is in a first expression; A third receiving module, used to receive a third input from a user; The third processing module is used to call a preset algorithm in response to the third input to determine the position relationship of each feature point in the face of the target object in the real-time video data when the target object is in a second expression.

[0064] The target object expression synchronization device provided in the embodiment of the present application determines the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions based on the first input, and adjusts the positional relationship of each feature point in the target model used to simulate the different expressions of the target object, so as to achieve the synchronous simulation of the different expressions of the target object, achieve the effect of synchronizing virtual and real expressions, and realize the purpose of real-time capture of the facial expression of the target object. The present application is simple to operate, low in cost, not limited by the venue, and can handle various complex backgrounds, making the expression capture of the target object more convenient and intelligent. It can be applied to computer animation, games, virtual reality and other fields, solving the problem of complex process and high cost of the current target object expression capture technology.

[0065] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0066] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0067] Based on the method in the above embodiment, the present application embodiment provides an electronic device, see Figure 3 The electronic device may include: a processor (Processor) 310, a communication interface (Communications Interface) 320, a memory (Memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the method in the above embodiment.

[0068] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0069] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0070] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0071] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0072] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0073] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0074] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0075] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for synchronizing expression of a target object, characterized in that: include: In the case where it is determined that the read real-time video data includes the face of the target object, receiving a first input from the user; In response to the first input, based on the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions, the positional relationship of each feature point in the target model is adjusted to simulate the different expressions of the target object. The target model is a model for simulating different expressions of the target object.

2. The target object expression synchronization method according to claim 1, characterized in that: In the case where it is determined that the read real-time video data includes the face of the target object, before receiving the first input from the user, the method further includes: receiving a second input from the user; In response to the second input, calling a preset algorithm to determine the positional relationship of each feature point on the face of the target object in the real-time video data when the target object is in the first expression; receiving a third input from the user; In response to the third input, the preset algorithm is called to determine the positional relationship between the various feature points on the face of the target object in the real-time video data when the target object is in a second expression.

3. The target object expression synchronization method as claimed in claim 2, characterized in that: In response to the second input, calling a preset algorithm to determine the positional relationship of each feature point on the face of the target object when the target object is in the first expression includes: In response to the second input, calling the preset algorithm to determine the positions of each feature point on the face of the target object in the real-time video data when the target object is in a first expression; Determine a facial position area where positions of each feature point on the face of the target object in the real-time video data when the target object is in the first expression; Calculating the degree and angle of opening and closing of the facial position area; Calculating the distance relationship between each feature point in the face of the target object in the real-time video data contained in the facial position area when the target object is in the first expression; The positional relationship of each feature point in the face of the target object in the real-time video data when the target object is in the first expression is determined according to the distance relationship, the opening and closing degree and the angle.

4. The target object expression synchronization method according to claim 1, characterized in that: The method further comprises: receiving a fourth input from the user; In response to the fourth input, the target model is created.

5. The target object expression synchronization method as claimed in claim 2, characterized in that: The first expression and the second expression are any one of sadness, fear, disgust, happiness, anger, surprise and neutrality, and the second expression is different from the first expression.

6. A target object expression synchronization device, characterized in that: include: A first receiving module, configured to receive a first input from a user when it is determined that the read real-time video data includes a face of a target object; The first processing module is used to respond to the first input, adjust the positional relationship of each feature point in the target model based on the positional relationship of each feature point in the face of the target object in the real-time video data when the target object has different expressions, and simulate different expressions of the target object. The target model is a model for simulating different expressions of the target object.

7. The target object expression synchronization device as claimed in claim 6, characterized in that: Also includes: A second receiving module, used to receive a second input from a user; A second processing module, configured to call a preset algorithm in response to the second input to determine a positional relationship between each feature point on the face of the target object in the real-time video data when the target object is in a first expression; A third receiving module, used to receive a third input from a user; The third processing module is used to call the preset algorithm in response to the third input to determine the position relationship of each feature point in the face of the target object in the real-time video data when the target object is in a second expression.

8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 5.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 5.

10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 5.

Images