AI-based real person digital duplicate mapping method and system

Abstract

The invention relates to an AI-based real person digital duplication mapping method and system, and the method comprises the steps: obtaining first image information of a target object at multiple angles, carrying out the feature extraction of the first image information, obtaining the type of clothes worn by the target object, and determining a preset clothes model of the clothes type, the method comprises the following steps: extracting a clothing map and a pattern of clothing of a target object, mapping the clothing map and the pattern to a corresponding preset clothing model to obtain a to-be-selected clothing model, obtaining video information of the target object moving according to a preset action, determining a wrinkle video of the clothing at each joint from the video information, and sending the wrinkle video to the target object. And obtaining a mapping video of the target object during real person mapping, and processing the to-be-selected clothes model based on the wrinkle video and the mapping video to obtain a final clothes model of the target object during real person mapping. According to the method and the device, changes such as wrinkles of clothes during activity of people in reality are more accurate than those in reality during virtual mapping, and the virtual mapping effect is improved.

Description

Technical Field

[0001] The present application relates to the field of digital twins, and in particular to an AI-based real-person digital avatar mapping method and system. Background Art

[0002] The metaverse will have a profound impact on the fields of office, games, medical care, social interaction, education, etc. Its most important feature is to integrate virtual and reality and map elements of real life into the virtual world. At present, the daily life image of people is mapped into the virtual world mainly by collecting images of people and generating corresponding virtual images in the virtual world based on the images. Since the actions of people in reality cause changes such as deformation of clothes, it is not easy to accurately render the changes consistent with real life in the virtual world, resulting in low realism of the image of people in the virtual world. Summary of the invention

[0003] In order to make the changes of clothing wrinkles and other changes when people move in reality closer to reality during virtual mapping and improve the virtual mapping effect, the present application provides an AI-based real-person digital avatar mapping method and system.

[0004] In the first aspect, the present application provides an AI-based real-person digital avatar mapping method, which adopts the following technical solutions: A real-person digital avatar mapping method based on AI, comprising: Acquire first image information of a target object at multiple angles; Extracting features of the first image information to obtain the type of clothing worn by the target object; Finding a preset clothing model of the clothing type from a preset database, and extracting a clothing map of the clothing of the target object and a pattern on the clothing from the first image information of the multiple angles; Mapping the clothing map and pattern onto a corresponding preset clothing model to obtain a clothing model to be selected; Acquire video information of the target object performing activities according to preset actions; Determining the wrinkle video of the clothing at each joint from the video information; A mapping video of the target object during real-person mapping is obtained, and a clothing model to be selected is processed based on the wrinkle video and the mapping video to obtain a final clothing model of the target object during real-person mapping.

[0005] By adopting the above technical solution, the first image information of the target object at multiple angles is obtained, which facilitates the subsequent feature extraction of the first image information to obtain the type of clothing worn by the target object, and then finds the predicted clothing model corresponding to the type of clothing from the preset database, and extracts the image on the target object's clothing from the first image information at multiple angles, maps the pattern to the preset clothing model to obtain a candidate clothing model that is consistent with the clothing worn by the target object in reality, and obtains video information of the target object performing activities according to preset actions. When the target object performs activities according to preset actions, deformations such as wrinkles will appear on the clothing at various joints, but deformations such as wrinkles at the joints in the virtual world cannot be accurately simulated. In order to achieve a consistent effect in reality, a wrinkle video of clothing at each joint is determined from the video information. The wrinkle video records the specific situation of wrinkles appearing when each joint moves. Therefore, a mapping video of the target object during real-person mapping is obtained, and the clothing model to be selected is processed according to the wrinkle video and the mapping video to obtain the final clothing model of the target object during real-person virtual space mapping, that is, according to the specific situation of the target object's actions and activities in the mapping video, the expression form of wrinkles at each joint is determined from the wrinkle video to obtain the final clothing model. The final clothing model is closer in each joint to the joints of the target object wearing clothes in reality, thereby making the virtual mapping effect better.

[0006] In another possible implementation, mapping the clothing map and pattern onto a corresponding preset clothing model to obtain a clothing model to be selected includes: Mapping the clothing map corresponding to each angle into a preset coordinate system to determine the coordinate point of each position on the pattern; Acquire second image information of the preset clothing model at the multiple angles, and overlap and map the first image information and the second image information at the same angle; Mapping the pattern to each second image information according to the coordinate point corresponding to each angle of the pattern to obtain mapped second image information; The mapped second image information is inversely mapped onto the preset clothing model to obtain the final clothing model.

[0007] In another possible implementation, determining the wrinkle video of clothing at each joint from the video information includes: Determine a preset range corresponding to each joint based on the position of the joint; Performing feature recognition on the video information to obtain feature points of each joint; A clipping area is obtained according to a preset range with the feature point as the center point, feature tracking is performed on each joint, and in the process of feature tracking, video information is clipped according to the clipping area to obtain a video of the wrinkles of the clothing at each joint.

[0008] In another possible implementation, the step of processing the clothing model to be selected based on the wrinkle video and the mapping video to obtain a final clothing model of the target object when performing real-person mapping includes: Determine the first wrinkle feature at each bending angle from the wrinkle video corresponding to each joint; Performing a rotation simulation on the first wrinkle feature at each bending angle to obtain a second wrinkle feature when the wrinkle feature at each bending angle is rotated to each angle, each second wrinkle feature corresponding to a bending angle and a rotation angle; Performing action recognition on each frame of the mapping video to obtain the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; Searching for a target wrinkle feature corresponding to each joint from the second wrinkle feature of each joint based on the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; The target wrinkle features corresponding to the joints are mapped to corresponding positions on the to-be-selected clothing model to obtain the final clothing model.

[0009] In another possible implementation, the method further includes: Determine the third image information of each joint in each frame from the mapping video, each third image information corresponds to the bending angle formed at the joint and the relative rotation angle of the limbs on both sides of the joint; Find out the associated second wrinkle feature whose bending angle and rotation angle are consistent with the third image information; Calculating a first similarity between the associated second wrinkle feature and the third image information; If the first similarity does not reach a preset similarity threshold, the associated second wrinkle feature is adjusted based on the third image information.

[0010] In another possible implementation manner, adjusting the associated second wrinkle feature based on the third image information includes: Performing texture extraction on the third image information and the second wrinkle feature respectively to obtain a first texture map related to the third image information and a second texture map related to the second wrinkle feature; Overlapping the first texture map and the second texture map to determine a non-overlapping texture; Determine the grayscale value of the area corresponding to the non-overlapping texture from the third image information; The associated second wrinkle feature is adjusted according to the grayscale value and the non-overlapping texture to obtain an adjusted second wrinkle feature.

[0011] In another possible implementation, the method further includes: Determine from the mapping video to perform edge detection on each frame to obtain fourth image information of the clothing; Calculating a second similarity between the fourth image information and the final clothing model corresponding to each frame; averaging the second similarity of each frame of the mapped video to obtain a second similarity average value; The second similarity average value is output.

[0012] In the second aspect, the present application provides an AI-based real-person digital avatar mapping system, which adopts the following technical solutions: An AI-based real-person digital avatar mapping system, comprising: An image acquisition module, used to acquire first image information of a target object at multiple angles; A first extraction module, configured to extract features from the first image information to obtain the type of clothing worn by the target object; A second extraction module, configured to search a preset clothing model of the clothing type from a preset database, and extract a clothing map of the clothing of the target object and a pattern on the clothing from the first image information of the multiple angles; A mapping module, used for mapping the clothing map and pattern onto a corresponding preset clothing model to obtain a clothing model to be selected; A video acquisition module, used to acquire video information of the target object performing activities according to preset actions; A video determination module, used to determine the wrinkle video of the clothing at each joint from the video information; The processing module is used to obtain a mapping video of the target object when performing real-person mapping, and to process the clothing model to be selected based on the wrinkle video and the mapping video to obtain a final clothing model of the target object when performing real-person mapping.

[0013] By adopting the above technical solution, the image acquisition module acquires the first image information of the target object at multiple angles, so that the subsequent first extraction module can extract features from the first image information to obtain the type of clothing worn by the target object, and then find out the predicted clothing model corresponding to the type of clothing from the preset database, and the second extraction module extracts the image on the target object's clothing from the first image information at multiple angles, the mapping module maps the pattern to the preset clothing model to obtain a candidate clothing model that is consistent with the clothing worn by the target object in reality, and the video acquisition module acquires video information of the target object performing activities according to preset actions. When the target object performs activities according to preset actions, deformations such as wrinkles will appear on the clothing at each joint, but the wrinkles and other deformations at the joints will not appear in the virtual world. It can accurately simulate the effect consistent with reality, so the video determination module determines the wrinkle video of the clothes at each joint from the video information. The wrinkle video records the specific situation of wrinkles when each joint moves. Therefore, the processing module obtains the mapping video of the target object when performing real-person mapping, and processes the selected clothing model according to the wrinkle video and the mapping video to obtain the final clothing model of the target object when performing real-person virtual space mapping, that is, according to the specific situation of the target object's actions and activities in the mapping video, the expression form of wrinkles at each joint is determined from the wrinkle video to obtain the final clothing model. The final clothing model is closer to the joints of the target object wearing clothes in reality at each joint, thereby making the virtual mapping effect better.

[0014] In another possible implementation, when the mapping module maps the clothing map and pattern onto the corresponding preset clothing model to obtain the clothing model to be selected, it is specifically used to: Mapping the clothing map corresponding to each angle into a preset coordinate system to determine the coordinate point of each position on the pattern; Acquire second image information of the preset clothing model at the multiple angles, and overlap and map the first image information and the second image information at the same angle; Mapping the pattern to each second image information according to the coordinate point corresponding to each angle of the pattern to obtain mapped second image information; The mapped second image information is inversely mapped onto the preset clothing model to obtain the final clothing model.

[0015] In another possible implementation, when the video determination module determines the wrinkle video of the clothing at each joint from the video information, it is specifically used to: Determine a preset range corresponding to each joint based on the position of the joint; Performing feature recognition on the video information to obtain feature points of each joint; A clipping area is obtained according to a preset range with the feature point as the center point, feature tracking is performed on each joint, and in the process of feature tracking, video information is clipped according to the clipping area to obtain a video of the wrinkles of the clothing at each joint.

[0016] In another possible implementation, when the processing module processes the clothing model to be selected based on the wrinkle video and the mapping video to obtain the final clothing model of the target object when real-person mapping is performed, it is specifically used to: Determine the first wrinkle feature at each bending angle from the wrinkle video corresponding to each joint; Performing a rotation simulation on the first wrinkle feature at each bending angle to obtain a second wrinkle feature when the wrinkle feature at each bending angle is rotated to each angle, each second wrinkle feature corresponding to a bending angle and a rotation angle; Performing action recognition on each frame of the mapping video to obtain the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; Searching for a target wrinkle feature corresponding to each joint from the second wrinkle feature of each joint based on the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; The target wrinkle features corresponding to the joints are mapped to corresponding positions on the to-be-selected clothing model to obtain the final clothing model.

[0017] In another possible implementation, the AI-based real-person digital avatar mapping system further includes: An image determination module, used to determine the third image information of each joint in each frame from the mapping video, each third image information corresponds to the bending angle formed at the joint and the relative rotation angle of the limbs on both sides of the joint; A search module, used to search for a second wrinkle feature associated with a bending angle and a rotation angle consistent with the third image information; A first calculation module, used for calculating a first similarity between the associated second wrinkle feature and the third image information; An adjustment module is used to adjust the associated second wrinkle feature based on the third image information when the first similarity does not reach a preset similarity threshold.

[0018] In another possible implementation manner, when the adjustment module adjusts the associated second wrinkle feature based on the third image information, it is specifically configured to: Performing texture extraction on the third image information and the second wrinkle feature respectively to obtain a first texture map related to the third image information and a second texture map related to the second wrinkle feature; Overlapping the first texture map and the second texture map to determine a non-overlapping texture; Determine the grayscale value of the area corresponding to the non-overlapping texture from the third image information; The associated second wrinkle feature is adjusted according to the grayscale value and the non-overlapping texture to obtain an adjusted second wrinkle feature.

[0019] In another possible implementation, the AI-based real-person digital avatar mapping system further includes: An edge detection module, used to determine each frame from the mapping video to perform edge detection to obtain fourth image information of the clothing; A second calculation module, used for calculating a second similarity between the fourth image information and a final clothing model corresponding to each frame; A third calculation module is used to average the second similarity of each frame of the mapping video to obtain a second similarity average value; An output module is used to output the second similarity average value.

[0020] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute an AI-based real-person digital avatar mapping method shown in any possible implementation of the first aspect.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute the AI-based real-person digital avatar mapping method described in any one of the first aspects.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: Acquiring the first image information of the target object at multiple angles facilitates subsequent feature extraction of the first image information to obtain the type of clothing worn by the target object, then searching the preset database for a predicted clothing model corresponding to the type of clothing, extracting the image on the target object's clothing from the first image information at multiple angles, mapping the pattern to the preset clothing model to obtain a candidate clothing model that is consistent with the clothing worn by the target object in reality, and acquiring video information of the target object performing activities according to preset actions. When the target object performs activities according to preset actions, deformations such as wrinkles will appear at the clothing at each joint, but in the virtual world, deformations such as wrinkles at the joints cannot be accurately simulated to be consistent with reality. Effect, therefore, a wrinkle video of clothing at each joint is determined from the video information, and the wrinkle video records the specific situation of wrinkles appearing when each joint moves. Therefore, a mapping video of the target object during real-person mapping is obtained, and the clothing model to be selected is processed according to the wrinkle video and the mapping video to obtain the final clothing model of the target object during real-person virtual space mapping, that is, according to the specific situation of the target object's actions and activities in the mapping video, the expression form of wrinkles at each joint is determined from the wrinkle video to obtain the final clothing model. The final clothing model is closer at each joint to the joints of the target object wearing clothes in reality, thereby making the virtual mapping effect better. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of an AI-based real-person digital avatar mapping method in an embodiment of the present application.

[0024] Figure 2 It is a structural diagram of an AI-based real-person digital avatar mapping system in an embodiment of the present application.

[0025] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application is further described in detail below in conjunction with the accompanying drawings.

[0027] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In addition, the term "and / or" in this article is only 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. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0030] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0031] The embodiment of the present application provides a method for mapping a real person's digital avatar based on AI, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104, step S105, step S106 and step S107, wherein: S101, obtaining first image information of a target object at multiple angles.

[0032] For the embodiment of the present application, the electronic device is connected to the camera device through a wire, and multiple preset voice instructions can be stored in the electronic device, each preset voice instruction represents the guidance of how much the target object rotates in situ, such as "rotate 45° clockwise in situ", "rotate 90° clockwise in situ", etc. The electronic device outputs the preset voice instruction, and the target object rotates under the guidance of the preset voice instruction, so that the camera device can collect the first image information of the target object at multiple angles, and then the electronic device obtains the first image information at multiple angles, and the multiple first image information records the relevant information of the target object's clothing, such as patterns, etc.

[0033] S102: Extract features from the first image information to obtain the type of clothing worn by the target object.

[0034] In the embodiment of the present application, the electronic device inputs the multi-angle first image information into the trained network model to identify the type of clothing, such as identifying the clothing worn by the target object as a hoodie, jeans, etc. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models, which are not limited here.

[0035] S103, searching for a preset clothing model of the clothing type from a preset database, and extracting a clothing map of the target object clothing and a pattern on the clothing from the first image information at multiple angles.

[0036] For the embodiment of the present application, preset clothing models of different types of clothing are stored in the preset database, and each preset clothing model is modeled and stored in advance by relevant personnel. Each preset clothing model corresponds to a type of clothing, so the electronic device can find the preset clothing model in the preset database according to the type of clothing of the target object. In order to make the clothing model in the virtual world more consistent with the clothing in reality, the electronic device extracts the clothing map and pattern of the target object clothing from the first image information of multiple angles. Specifically, the electronic device can perform edge detection on the first image information of multiple angles, first denoise the first image information, and then perform grayscale transformation on the denoised first image information to obtain a grayscale image, and then determine the edge of the clothing and the environment by determining the position where the grayscale value in the grayscale image has a step, and then determine the image within the edge range as a clothing map, and then perform edge detection on the foreign body map to obtain the pattern in the clothing map.

[0037] S104, mapping the clothing map and pattern to the corresponding preset clothing model to obtain a clothing model to be selected.

[0038] For the embodiment of the present application, after the electronic device determines the clothing map and pattern of the target object's clothing, it can map the clothing map and pattern to the corresponding preset clothing model, thereby obtaining the clothing model to be selected.

[0039] S105, obtaining video information of the target object performing activities according to preset actions.

[0040] For the embodiment of the present application, the camera device is also used to collect video information when the target object performs activities according to preset actions. Multiple preset action videos can also be stored in the electronic device. The electronic device controls the display device to output and display the preset action videos, so that the target object performs corresponding actions according to the preset action videos, such as raising hands, bending over, turning arms, squatting, etc. The camera device collects video information when the target object performs the above activities and the electronic device obtains it.

[0041] S106, determining the wrinkle video of the clothing at each joint from the video information.

[0042] For the embodiment of the present application, after the electronic device obtains the video information, it determines the wrinkle video of the clothing at each joint from the video information, thereby facilitating the subsequent further rendering and adjustment of the clothing model to be selected based on the wrinkle video, thereby reducing the amount of data.

[0043] S107, obtaining a mapping video of the target object when performing real-person mapping, and processing the clothing model to be selected based on the wrinkle video and the mapping video to obtain a final clothing model of the target object when performing real-person mapping.

[0044] For the embodiment of the present application, when the target object starts to perform virtual mapping of the metaverse, the electronic device obtains a video of the target object captured by the camera device, namely, a mapping video. The mapping video records the specific circumstances of the target object's activities. Therefore, the electronic device can determine the activity of each joint from the mapping video, and then determine the wrinkles that need to be formed at each joint in the virtual world according to the wrinkle video, and then map the wrinkles that need to be formed onto the selected clothing model to obtain a final clothing model that is consistent with the performance of the clothing in reality. The final clothing model is closer in each joint to the joints of the target object wearing clothes in reality, thereby making the virtual mapping effect better.

[0045] In a possible implementation of the embodiment of the present application, in step S104, the clothing map and pattern are mapped to the corresponding preset clothing model to obtain the clothing model to be selected, which specifically includes step S1041 (not shown in the figure), step S1042 (not shown in the figure), step S1043 (not shown in the figure) and step S1044 (not shown in the figure), wherein: S1041, mapping the clothing map corresponding to each angle to a preset coordinate system to determine the coordinate point of each position on the pattern.

[0046] For the embodiment of the present application, the electronic device maps the clothing map at each angle to a preset coordinate system, which is a plane rectangular coordinate system, and then determines the coordinate points of the clothing map at each angle. Then the electronic device maps the pattern at each angle to the preset coordinate system to obtain the coordinate points of each position on the pattern.

[0047] S1042, obtaining second image information of a preset clothing model at multiple angles, and overlapping and mapping the first image information and the second image information at the same angle.

[0048] For the embodiment of the present application, the electronic device rotates and captures the preset clothing model through relevant simulation software to obtain the second image information of the preset clothing model at multiple angles, and the second image information is also the clothing map of the preset clothing model at multiple angles. The multiple angles of the second image information are consistent with the multiple angles of the first image information. Then the electronic device overlaps and maps the first image information and the second image information at the same angle to facilitate the subsequent more accurate determination of the position of the pattern on the preset clothing model.

[0049] S1043: Map the pattern to each second image information at a coordinate point corresponding to each angle of the pattern to obtain mapped second image information.

[0050] For the embodiment of the present application, the electronic device maps the pattern to the second image information of the corresponding angle according to the coordinate points corresponding to the pattern at each angle, so as to obtain the second image information after the pattern is mapped, that is, the clothing map after the pattern is mapped.

[0051] S1044, inversely mapping the mapped second image information onto a preset clothing model to obtain a final clothing model.

[0052] For the embodiment of the present application, the electronic device can obtain the final clothing model by reverse mapping the mapped second image information onto the preset clothing model. The final preset clothing model can be obtained more accurately by determining the coordinate points of the pattern and mapping the first image information and the second image information.

[0053] In a possible implementation of the embodiment of the present application, in step S106, the wrinkle video of the clothing at each joint is determined from the video information, which specifically includes step S1061, step S1062 and step S1063, wherein: S1061, determining a preset range corresponding to each joint based on the position of the joint.

[0054] For the embodiment of the present application, the electronic device determines the preset range corresponding to each joint based on the size and position of the joint. The preset range is a rectangle. For example, the volume area of ​​the elbow joint is smaller than that of the knee joint, so the preset range of the elbow joint is smaller than the preset range of the knee joint. The preset range corresponding to each joint is pre-stored in the electronic device. Therefore, after the electronic device determines the position of the joint, such as the elbow joint, it can find the preset range corresponding to the elbow joint.

[0055] S1062, performing feature recognition on the video information to obtain feature points of each joint.

[0056] For the embodiment of the present application, the electronic device inputs the video information into the trained network model for feature recognition to obtain the feature points of each joint, such as the bend of the elbow joint and the bend of the knee joint, which are all feature points. The network model can be a convolutional neural network model, a recurrent neural network model, or other network models.

[0057] S1063, taking the feature point as the center point, obtaining a clipping area according to a preset range, performing feature tracking on each joint, and in the process of feature tracking, clipping the video information according to the clipping area to obtain a video of the wrinkles of the clothing at each joint.

[0058] For the embodiment of the present application, the electronic device determines the center point of a preset range of feature points to form a video capture area. The electronic device performs feature tracking on the feature points of each joint and captures the video information according to the capture area during the tracking process to obtain a video recording the wrinkles of clothing at each joint.

[0059] In a possible implementation of the embodiment of the present application, in step S107, the clothing model to be selected is processed based on the wrinkle video and the mapping video to obtain the final clothing model of the target object when performing real-person mapping, which specifically includes step S1071 (not shown in the figure), step S1072 (not shown in the figure), step S1073 (not shown in the figure), step S1074 (not shown in the figure) and step S1075 (not shown in the figure), wherein: S1071, determining the first wrinkle feature at each bending angle from the wrinkle video corresponding to each joint.

[0060] For the embodiment of the present application, the electronic device determines the joint bend in the wrinkle video corresponding to each joint as the vertex of the bending angle, and then simplifies the limbs on both sides of the bend into straight lines and connects the vertices to obtain an angle. Since the wrinkle video is a dynamic expression of the target object performing an action, the electronic device determines the angle value of the obtained angle, thereby determining the display effect of the wrinkles of each joint at each bending angle, that is, the first wrinkle feature.

[0061] S1072, performing a rotation simulation on the first wrinkle feature at each bending angle to obtain a second wrinkle feature when the wrinkle feature at each bending angle is rotated to each angle.

[0062] Each second wrinkle feature corresponds to a bending angle and a rotation angle.

[0063] With respect to the embodiments of the present application, since when the target object moves in reality, relative rotation may occur between the limbs on both sides of the bend during the bending process of each joint, and the relative rotation of the limbs on both sides will produce deformation effects such as stretching on the wrinkles at the current angle. Therefore, the electronic device performs a rotation simulation on the first wrinkle feature at each bending angle through a convolutional neural network or related analysis software to obtain the second wrinkle feature at each bending angle when the wrinkle feature is rotated to each angle. The rotation simulation can make the wrinkles more realistic.

[0064] S1073, performing action recognition on each frame in the mapped video to obtain the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint.

[0065] For the embodiment of the present application, the electronic device extracts each frame from the mapped video, and then extracts the posture of the target object in each frame. Specifically, the electronic device inputs each frame into a trained network model for motion recognition to obtain the bending angle formed at each joint in each frame and the relative rotation angle on both sides of the joint.

[0066] S1074, searching for a target wrinkle feature corresponding to each joint from the second wrinkle features of each joint based on the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint.

[0067] For the embodiment of the present application, after the electronic device determines the bending angle and relative rotation angle formed at each joint, it can find the consistent target wrinkle feature from the second wrinkle feature of each joint based on these two angle values.

[0068] S1075, mapping the target wrinkle features corresponding to each joint to the corresponding position on the clothing model to be selected to obtain the final clothing model.

[0069] For the embodiment of the present application, after the electronic device determines the target wrinkle features of each joint, it maps the target wrinkle features to the corresponding positions on the selected clothing model to obtain the final clothing model corresponding to each frame of the picture, thereby achieving a more realistic mapping of the metaverse reality and virtuality.

[0070] In a possible implementation of the embodiment of the present application, step S107 further includes step Sa (not shown in the figure), step Sb (not shown in the figure), step Sc (not shown in the figure) and step Sd (not shown in the figure), wherein: Sa, the third image information of each joint in each frame is determined from the mapped video, and each third image information corresponds to the bending angle formed at the joint and the relative rotation angle of the limbs on both sides of the joint.

[0071] For the embodiment of the present application, the electronic device can intercept the images of each joint in reality from each frame of the mapped video according to the interception area recorded in step S1063, that is, the third image information. Then the electronic device performs feature recognition on the third image information to obtain the bending angle of each joint and the relative rotation angle of the limbs on both sides of the joint. The way in which the electronic device determines the bending angle and the relative rotation angle can be determined by referring to the method recorded in steps S1071 and S1072.

[0072] Sb, find out the associated second wrinkle feature whose bending angle and rotation angle are consistent with the third image information.

[0073] For the embodiment of the present application, the electronic device searches for a consistent associated second wrinkle feature from the second wrinkle features corresponding to each joint based on the bending angle and the relative rotation angle corresponding to the third image information at each joint.

[0074] Sc, calculate the first similarity between the associated second wrinkle feature and the third image information.

[0075] For the embodiment of the present application, the electronic device can calculate the cosine distance value between the associated second wrinkle feature and the third image information, and characterize the first similarity through the cosine distance value, that is, the picture is represented as a vector, and the similarity of the two pictures is characterized by calculating the cosine distance between the vectors. The first similarity can also be calculated through a histogram, or the first similarity can be calculated through other methods, or the electronic device inputs the second wrinkle feature and the third image information into a trained network model to perform similarity calculation to obtain the first similarity. This is not limited here.

[0076] Sd: if the first similarity does not reach a preset similarity threshold, adjusting the associated second wrinkle feature based on the third image information.

[0077] For the embodiment of the present application, the preset similarity threshold serves as the dividing point between the associated second wrinkle feature and the third image information as to whether they are relatively close. The electronic device compares the determined first similarity with the preset similarity threshold. If the first similarity does not reach the preset similarity threshold, it means that the simulated associated second feature is quite different from the actual joint bending performance and the simulation effect is poor. Therefore, the associated second wrinkle feature is adjusted according to the third image information representing the actual joint bending, so that the second wrinkle feature used in the subsequent virtual simulation of each joint is more realistic.

[0078] In a possible implementation of the embodiment of the present application, in step Sd, the associated second wrinkle feature is adjusted based on the third image information, specifically including step S1 (not shown in the figure), step S2 (not shown in the figure), step S3 (not shown in the figure) and step S4 (not shown in the figure), wherein: S1, performing texture extraction on the third image information and the second wrinkle feature respectively to obtain a first texture map related to the third image information and a second texture map related to the second wrinkle feature.

[0079] For the embodiment of the present application, the electronic device performs preprocessing operations on the third image information and the second wrinkle feature, such as grayscale, denoising, etc. Texture features are extracted from the preprocessed image. For example, spatial filters such as Gabor filters and Laws filters are used to extract the texture information of the image. Statistical methods (such as grayscale co-occurrence matrix GLCM, grayscale gradient histogram GLDH), frequency-based methods (such as Fourier transform, wavelet transform), etc. The extracted texture features are quantized and encoded into vector or matrix form as needed. For example, a histogram or vector can be used to represent texture features. Images are classified or identified based on the extracted texture features. Various machine learning algorithms (such as support vector machine SVM, K nearest neighbor algorithm KNN, neural network, etc.) can be used to implement texture classification and recognition tasks. After completing texture extraction and classification, the results can be post-processed as needed (such as smoothing, threshold segmentation, etc.), and the results can be displayed in a visual manner.

[0080] S2, performing overlapping mapping on the first texture map and the second texture map to determine a non-overlapping texture.

[0081] For the embodiment of the present application, the electronic device overlaps and maps the first texture map and the second texture map to a preset coordinate system, thereby determining the coordinates of each pixel point, and then determining the pixel points whose coordinate points do not overlap, and the pixel points whose coordinate points do not overlap constitute non-overlapping textures. Non-overlapping textures are areas where the wrinkles are inconsistent.

[0082] S3, determining the grayscale value of the area corresponding to the non-overlapping texture from the third image information.

[0083] For the embodiment of the present application, the electronic device performs grayscale transformation on the preprocessed third image information to obtain a grayscale image, and then maps the non-overlapping texture to the grayscale image to obtain the grayscale value of the area corresponding to the non-overlapping texture, and the size of the grayscale value represents the bright display effect of light and shadow at the folds.

[0084] S4, adjusting the associated second wrinkle feature according to the gray value and the non-overlapping texture to obtain an adjusted second wrinkle feature.

[0085] For the embodiment of the present application, the electronic device replaces the grayscale value of the area corresponding to the associated second feature with the grayscale value of the non-overlapping area, and then replaces the grayscale value of the area corresponding to the associated second feature with the non-overlapping texture to obtain the adjusted second wrinkle feature. The associated second wrinkle feature is adjusted by the third image information representing the real wrinkles in reality, thereby optimizing the second wrinkle feature, so that the simulation of the second wrinkle feature is more accurate.

[0086] In a possible implementation of the embodiment of the present application, step S107 further includes step S108 (not shown in the figure), step S109 (not shown in the figure), step S110 (not shown in the figure), and step S111 (not shown in the figure), wherein: S108, determining each frame in the mapped video to perform edge detection to obtain fourth image information of the clothing.

[0087] In the embodiment of the present application, the electronic device performs edge detection on each frame to obtain fourth image information of the clothing in each frame. Specifically, the electronic device performs denoising on each frame and then performs grayscale transformation on each denoised frame to obtain a grayscale image, and performs segmentation at the place where the grayscale value of the grayscale image has a step to obtain the fourth image information of the clothing area.

[0088] S109, calculating a second similarity between the fourth image information and the final clothing model corresponding to each frame.

[0089] For the embodiment of the present application, the electronic device determines the final clothing model corresponding to the same time point in the virtual simulation based on the time point of the fourth image information, and takes a screenshot of the final clothing model at that moment and other operations to obtain a picture of the final clothing model at that moment, and then the electronic device calculates the second similarity in the manner recorded in step S1. The higher the second similarity, the closer the simulation is to the actual clothing performance.

[0090] S110, calculating an average value of the second similarity of each frame of the mapped video to obtain a second similarity average value.

[0091] For the embodiment of the present application, after the electronic device determines the second similarity of each frame of the mapped video during the entire mapping process, it uses the average value calculation formula to calculate the second similarity average value, and the second similarity average value is used to represent the overall closeness level between the virtual simulation and the actual clothing performance during the entire mapping process. The larger the second similarity average value, the more realistic the virtual simulation during the entire process.

[0092] S111, output a second similarity average value.

[0093] For the embodiment of the present application, after the electronic device determines the second similarity average value, it can send the second similarity average value in the form of a text message to the terminal device of the target object or the terminal device of the manager, so that the target object and the manager can know the effect of the virtual simulation in a timely and intuitive manner, which is convenient for subsequent improvements.

[0094] The above embodiment introduces an AI-based real-person digital twin mapping method from the perspective of method flow, and the following embodiment introduces an AI-based real-person digital twin mapping system 20 from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0095] The present application embodiment provides an AI-based real-person digital avatar mapping system 20, such as Figure 2 As shown, an AI-based real-person digital avatar mapping system 20 may specifically include: An image acquisition module 201 is used to acquire first image information of a target object at multiple angles; A first extraction module 202 is used to extract features from the first image information to obtain the type of clothing worn by the target object; The second extraction module 203 is used to find a preset clothing model of a clothing type from a preset database, and extract a clothing map of the target object clothing and a pattern on the clothing from the first image information of multiple angles; A mapping module 204, used for mapping clothing images and patterns to corresponding preset clothing models to obtain clothing models to be selected; The video acquisition module 205 is used to acquire video information of the target object performing activities according to preset actions; A video determination module 206, for determining a video of wrinkles of clothing at each joint from the video information; The processing module 207 is used to obtain a mapping video of the target object when performing real-person mapping, and to process the clothing model to be selected based on the wrinkle video and the mapping video to obtain a final clothing model of the target object when performing real-person mapping.

[0096] The embodiment of the present application discloses an AI-based real-person digital avatar mapping system 20, wherein an image acquisition module 201 acquires first image information of a target object at multiple angles, so that a subsequent first extraction module 202 performs feature extraction on the first image information to obtain the type of clothing worn by the target object, and then searches a preset database for a predicted clothing model corresponding to the type of clothing, and a second extraction module 203 extracts an image on the target object's clothing from the multi-angle first image information, a mapping module 204 maps the pattern to a preset clothing model to obtain a candidate clothing model consistent with the clothing actually worn by the target object, and a video acquisition module 205 acquires video information of the target object performing an activity according to a preset action. When the target object performs an activity according to the preset action, the clothing at each joint will be deformed, such as wrinkles, but in the The deformations such as wrinkles at the joints in the virtual world cannot accurately simulate the effects consistent with those in reality, so the video determination module 206 determines the wrinkle video of the clothes at each joint from the video information. The wrinkle video records the specific situation of wrinkles appearing when each joint moves. Therefore, the processing module 207 obtains the mapping video of the target object when performing real-person mapping, and processes the selected clothing model according to the wrinkle video and the mapping video to obtain the final clothing model of the target object when performing real-person virtual space mapping, that is, according to the specific situation of the target object's actions and activities in the mapping video, the expression form of wrinkles at each joint is determined from the wrinkle video to obtain the final clothing model. The final clothing model is closer at each joint to the joints of the target object wearing clothes in reality, thereby making the virtual mapping effect better.

[0097] In a possible implementation of the embodiment of the present application, when the mapping module 204 maps the clothing map and pattern to the corresponding preset clothing model to obtain the clothing model to be selected, it is specifically used to: Map the clothing map corresponding to each angle to a preset coordinate system to determine the coordinate point of each position on the pattern; Acquire second image information of a preset clothing model at multiple angles, and overlap and map the first image information and the second image information at the same angle; Mapping the pattern to each second image information according to the coordinate point corresponding to each angle of the pattern to obtain the mapped second image information; The mapped second image information is inversely mapped onto a preset clothing model to obtain a final clothing model.

[0098] In a possible implementation of the embodiment of the present application, when the video determination module 206 determines the wrinkle video of the clothing at each joint from the video information, it is specifically used to: Determine a preset range corresponding to each joint based on the position of the joint; Perform feature recognition on the video information to obtain the feature points of each joint; A capture area is obtained according to a preset range with the feature point as the center point, and feature tracking is performed on each joint. During the feature tracking process, video information is captured according to the capture area to obtain a video of clothing wrinkles at each joint.

[0099] In a possible implementation of the embodiment of the present application, when the processing module 207 processes the clothing model to be selected based on the wrinkle video and the mapping video to obtain the final clothing model of the target object when performing real-person mapping, it is specifically used to: Determine the first wrinkle feature at each bending angle from the wrinkle video corresponding to each joint; Performing a rotation simulation on the first wrinkle feature at each bending angle to obtain a second wrinkle feature when the wrinkle feature at each bending angle is rotated to each angle, each second wrinkle feature corresponding to a bending angle and a rotation angle; Perform action recognition on each frame in the mapped video to obtain the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; Based on the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint, the target wrinkle feature corresponding to each joint is found from the second wrinkle feature of each joint; The target wrinkle features corresponding to each joint are mapped to the corresponding positions on the candidate clothing model to obtain the final clothing model.

[0100] In a possible implementation of the embodiment of the present application, an AI-based real-person digital avatar mapping system 20 further includes: An image determination module is used to determine the third image information of each joint in each frame from the mapped video, each third image information corresponds to the bending angle formed at the joint and the relative rotation angle of the limbs on both sides of the joint; A search module, used to search for a second wrinkle feature associated with a bending angle and a rotation angle consistent with the third image information; A first calculation module, used for calculating a first similarity between the associated second wrinkle feature and the third image information; The adjustment module is used to adjust the associated second wrinkle feature based on the third image information when the first similarity does not reach a preset similarity threshold.

[0101] In a possible implementation manner of the embodiment of the present application, when the adjustment module adjusts the associated second wrinkle feature based on the third image information, it is specifically used to: Performing texture extraction on the third image information and the second wrinkle feature respectively to obtain a first texture map related to the third image information and a second texture map related to the second wrinkle feature; Overlapping the first texture map and the second texture map to determine a non-overlapping texture; Determine the grayscale value of the area corresponding to the non-overlapping texture from the third image information; The associated second wrinkle feature is adjusted according to the grayscale value and the non-overlapping texture to obtain the adjusted second wrinkle feature.

[0102] In a possible implementation of the embodiment of the present application, an AI-based real-person digital avatar mapping system 20 further includes: An edge detection module, used to determine each frame from the mapped video and perform edge detection to obtain fourth image information of the clothing; A second calculation module, used for calculating a second similarity between the fourth image information and a final clothing model corresponding to each frame; A third calculation module is used to average the second similarity of each frame of the mapped video to obtain a second similarity average value; The output module is used to output the second similarity average value.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the AI-based real-person digital avatar mapping system 20 described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0104] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0105] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0106] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0107] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0108] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0109] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0110] The embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed on a computer, enables the computer to execute the corresponding contents of the aforementioned method embodiment. Compared with the related art, the embodiment of the present application obtains first image information of a target object at multiple angles to facilitate subsequent feature extraction of the first image information to obtain the type of clothing worn by the target object, and then finds the predicted clothing model corresponding to the type of clothing from the preset database, extracts the image on the target object's clothing from the first image information at multiple angles, maps the pattern to the preset clothing model to obtain a candidate clothing model that is consistent with the clothing worn by the target object in reality, obtains video information of the target object performing activities according to preset actions, and when the target object performs activities according to preset actions, the clothing at each joint will be deformed by wrinkles and other deformations, but wrinkles and other deformations at the joints cannot be accurately simulated in the virtual world. In order to produce an effect consistent with reality, a wrinkle video of clothing at each joint is determined from the video information. The wrinkle video records the specific situation of wrinkles appearing when each joint moves. Therefore, a mapping video of the target object during real-person mapping is obtained, and the clothing model to be selected is processed according to the wrinkle video and the mapping video to obtain the final clothing model of the target object during real-person virtual space mapping, that is, according to the specific situation of the target object's actions and activities in the mapping video, the expression form of wrinkles at each joint is determined from the wrinkle video to obtain the final clothing model. The final clothing model is closer at each joint to the joints of the target object wearing clothes in reality, thereby making the virtual mapping effect better.

[0111] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0112] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A real-person digital avatar mapping method based on AI, characterized in that: include: Acquire first image information of a target object at multiple angles; Extracting features of the first image information to obtain the type of clothing worn by the target object; Finding a preset clothing model of the clothing type from a preset database, and extracting a clothing map of the clothing of the target object and a pattern on the clothing from the first image information of the multiple angles; Mapping the clothing map and pattern onto a corresponding preset clothing model to obtain a clothing model to be selected; Acquire video information of the target object performing activities according to preset actions; Determining the wrinkle video of the clothing at each joint from the video information; A mapping video of the target object during real-person mapping is obtained, and a clothing model to be selected is processed based on the wrinkle video and the mapping video to obtain a final clothing model of the target object during real-person mapping.

2. The AI-based real-person digital avatar mapping method according to claim 1, characterized in that: The step of mapping the clothing map and pattern onto a corresponding preset clothing model to obtain a clothing model to be selected includes: Mapping the clothing map corresponding to each angle into a preset coordinate system to determine the coordinate point of each position on the pattern; Acquire second image information of the preset clothing model at the multiple angles, and overlap and map the first image information and the second image information at the same angle; Mapping the pattern to each second image information according to the coordinate point corresponding to each angle of the pattern to obtain mapped second image information; The mapped second image information is inversely mapped onto the preset clothing model to obtain the final clothing model.

3. The AI-based real-person digital avatar mapping method according to claim 1, characterized in that: Determining the wrinkle video of the clothing at each joint from the video information includes: Determine a preset range corresponding to each joint based on the position of the joint; Performing feature recognition on the video information to obtain feature points of each joint; A clipping area is obtained according to a preset range with the feature point as the center point, feature tracking is performed on each joint, and in the process of feature tracking, video information is clipped according to the clipping area to obtain a video of the wrinkles of the clothing at each joint.

4. The AI-based real-person digital avatar mapping method according to claim 1, characterized in that: The step of processing the clothing model to be selected based on the wrinkle video and the mapping video to obtain a final clothing model of the target object when performing real-person mapping includes: Determine the first wrinkle feature at each bending angle from the wrinkle video corresponding to each joint; Performing a rotation simulation on the first wrinkle feature at each bending angle to obtain a second wrinkle feature when the wrinkle feature at each bending angle is rotated to each angle, each second wrinkle feature corresponding to a bending angle and a rotation angle; Performing action recognition on each frame of the mapping video to obtain the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; Searching for a target wrinkle feature corresponding to each joint from the second wrinkle feature of each joint based on the bending angle formed at each joint in each frame and the relative rotation angle of the limbs on both sides of the joint; The target wrinkle features corresponding to the joints are mapped to corresponding positions on the to-be-selected clothing model to obtain the final clothing model.

5. The AI-based real-person digital avatar mapping method according to claim 1, characterized in that: The method further comprises: Determine the third image information of each joint in each frame from the mapping video, each third image information corresponds to the bending angle formed at the joint and the relative rotation angle of the limbs on both sides of the joint; Find out the associated second wrinkle feature whose bending angle and rotation angle are consistent with the third image information; Calculating a first similarity between the associated second wrinkle feature and the third image information; If the first similarity does not reach a preset similarity threshold, the associated second wrinkle feature is adjusted based on the third image information.

6. The AI-based real-person digital avatar mapping method according to claim 5, characterized in that: The adjusting the associated second wrinkle feature based on the third image information includes: Performing texture extraction on the third image information and the second wrinkle feature respectively to obtain a first texture map related to the third image information and a second texture map related to the second wrinkle feature; Overlapping the first texture map and the second texture map to determine a non-overlapping texture; Determine the grayscale value of the area corresponding to the non-overlapping texture from the third image information; The associated second wrinkle feature is adjusted according to the grayscale value and the non-overlapping texture to obtain an adjusted second wrinkle feature.

7. The AI-based real-person digital avatar mapping method according to claim 1, characterized in that: The method further comprises: Determine from the mapping video to perform edge detection on each frame to obtain fourth image information of the clothing; Calculating a second similarity between the fourth image information and the final clothing model corresponding to each frame; averaging the second similarity of each frame of the mapped video to obtain a second similarity average value; The second similarity average value is output.

8. An AI-based real-person digital avatar mapping system, characterized in that: include: An image acquisition module, used to acquire first image information of a target object at multiple angles; A first extraction module, configured to extract features from the first image information to obtain the type of clothing worn by the target object; A second extraction module, configured to search a preset clothing model of the clothing type from a preset database, and extract a clothing map of the clothing of the target object and a pattern on the clothing from the first image information of the multiple angles; A mapping module, used for mapping the clothing map and pattern onto a corresponding preset clothing model to obtain a clothing model to be selected; A video acquisition module, used to acquire video information of the target object performing activities according to preset actions; A video determination module, used to determine the wrinkle video of the clothing at each joint from the video information; The processing module is used to obtain a mapping video of the target object when performing real-person mapping, and to process the clothing model to be selected based on the wrinkle video and the mapping video to obtain a final clothing model of the target object when performing real-person mapping.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, and the at least one application is used to execute an AI-based real-person digital avatar mapping method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the AI-based real-person digital avatar mapping method described in any one of claims 1 to 7.

Images