A method and device for producing personalized three-dimensional animation

Abstract

The present invention discloses a method and device for producing personalized three-dimensional animation, which obtain dynamic acquisition data and preset feature data; establish an action database according to the dynamic acquisition data, cluster and integrate a weighted model constructed in the action database for optimization, and generate weighted optimization data; generate a position tag according to the weighted optimization data, match the position tag with the preset feature data, and proofread and construct a character model; match the constructed character model with the action database to generate a three-dimensional animation image, and a user wears a dynamic capture device and obtains facial expression information through a facial recognition device, and then matches the acquisition data with the preset data by establishing a preset action database, thereby reducing a large amount of rendering work and solving the problem that the three-dimensional animation cannot be created when the user changes the computer or the computer configuration is low.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for producing personalized three-dimensional animation. Background Art

[0002] The existing 3D animation production process usually adopts the method of first making a 3D animation model before continuing the work in the following links. The step of creating a model is usually called modeling. Secondly, after the modeling is completed, it is necessary to specify the material for the animation production to make the model more realistic. By using different materials for model production and achieving a variety of colorful mapping effects, it is possible to prepare for the subsequent animation production links. Models with added lights and shadows have a real sense of existence. Adding appropriate lights according to different animation scenes can make the model more realistic, and the addition of light and shadow adds a sense of atmosphere to the game. Finally, computer calculation is required to obtain the final 3D image, and this process is also called rendering.

[0003] With the development of the times, people now edit videos more through SaaS software built on cloud servers. Traditional 3D stereoscopic animation production requires local deployment software. Users need to install corresponding software on local computers and complete modeling and other operations. When users change computers or the computer configuration is low, they cannot create 3D animations. In order to solve this problem, a personalized 3D animation production method has been developed. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for producing personalized three-dimensional animation, which can solve the problem that the three-dimensional animation cannot be created when the user changes the computer or the computer configuration is low.

[0005] In a first aspect, the present invention provides a method for producing a personalized three-dimensional animation, comprising:

[0006] Obtain dynamic collection data and preset feature data;

[0007] Establishing an action database according to the dynamically collected data, clustering and integrating the weighted model constructed in the action database for optimization, and generating weighted optimization data;

[0008] Generating a position tag according to the weighted optimization data, matching the position tag with the preset feature data, and proofreading and constructing a character model;

[0009] The constructed character model is matched with the action database to generate a three-dimensional cartoon image.

[0010] Furthermore, the acquisition of dynamic collection data and preset feature data includes:

[0011] Acquiring dynamic data includes collecting data through dynamic capture devices, cameras, and somatosensory devices;

[0012] The preset feature data includes character graphic features and preset character standard action feature data, and the preset feature data matches the pre-examined character action feature data.

[0013] Furthermore, an action database is established based on the dynamic collected data, and a weighted model is clustered and integrated to be optimized in the action database to generate weighted optimization data, including:

[0014] Clustering the dynamically collected data in an action database, and constructing a weighted model clustering integration for optimization;

[0015] The weighted model is optimized according to the user's usage frequency and user time to generate weighted optimization data.

[0016] Furthermore, matching the constructed character model with the action database to generate a three-dimensional cartoon image includes:

[0017] The character model construction includes character dynamic capture data and character dynamic action movement time data;

[0018] Generate dynamic data tags from the character dynamic capture data and the character dynamic action movement time data;

[0019] The dynamic data tags are matched with the action database to generate a three-dimensional cartoon image.

[0020] In a second aspect, the present invention provides a device for producing personalized three-dimensional animation, comprising:

[0021] An acquisition unit, used for acquiring dynamic collection data and preset feature data;

[0022] A processing unit, used to establish an action database according to the dynamically collected data, cluster and integrate the weighted model constructed in the action database for optimization, and generate weighted optimization data;

[0023] An optimization unit, configured to generate a position tag according to the weighted optimization data, match the position tag with the preset feature data, and calibrate and construct a character model;

[0024] The image generation unit is used to match the constructed character model with the action database to generate a three-dimensional cartoon image.

[0025] Furthermore, the acquisition unit includes:

[0026] The acquisition unit acquires dynamic data including collecting data through a dynamic capture device, a camera and a somatosensory device;

[0027] The action matching unit, the preset feature data includes character graphic features and preset character standard action feature data, and the preset feature data matches the pre-examined character action feature data.

[0028] Furthermore, the data analysis unit clusters the dynamically collected data in the action database and constructs a weighted model clustering integration for optimization;

[0029] The first data processing unit optimizes the weighted model according to the user's usage frequency and user time to generate weighted optimization data.

[0030] The image generation unit includes: a data construction unit, wherein the constructed character model includes character dynamic capture data and character dynamic action movement time data;

[0031] A second data processing unit generates a dynamic data tag from the character dynamic capture data and the character dynamic action movement time data;

[0032] The image generation unit matches the dynamic data tag with the action database to generate a three-dimensional cartoon image.

[0033] The beneficial effects of the present invention are as follows: a method and device for producing personalized three-dimensional animation provided by the present invention obtain dynamic acquisition data and preset feature data; establish an action database based on the dynamic acquisition data, cluster and integrate the weighted model constructed in the action database for optimization, and generate weighted optimization data; generate position tags based on the weighted optimization data, match the position tags with the preset feature data, and proofread and construct a character model; match the constructed character model with the action database to generate a three-dimensional animation image, and the user wears a dynamic capture device and obtains facial expression information through a facial recognition device, and then matches the acquisition data with the preset data by establishing a preset action database, thereby reducing a large amount of rendering work and solving the problem that the user cannot create and produce three-dimensional animation when the computer is replaced or the computer configuration is low. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 A flow chart of a method for producing personalized three-dimensional animation provided by an embodiment of the present invention;

[0036] Figure 2A flowchart of step S101 of the method for producing personalized three-dimensional animation provided by an embodiment of the present invention;

[0037] Figure 3 A flowchart of step S102 of the method for producing personalized three-dimensional animation provided by an embodiment of the present invention;

[0038] Figure 4 A flowchart of step S104 of the method for producing personalized three-dimensional animation provided by an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of a device for producing personalized three-dimensional animation provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0041] See also Figure 1 The present invention provides a method for producing a personalized three-dimensional animation, comprising:

[0042] S101, acquiring dynamic collection data and preset feature data.

[0043] The present application provides a method, in which a user wears a motion capture device and moves according to the movements designed by the user. The motion capture device generates corresponding movement data. After collecting the movement data, it is stored in a computer or other storage medium, and then preset standard movement parameters are collected in advance. For example, the parameters of basic movements such as leg raising and jumping are collected.

[0044] S102, establishing an action database according to the dynamically collected data, clustering and integrating the weighted model constructed in the action database for optimization, and generating weighted optimization data.

[0045] Since the data collected by the motion capture device will contain a lot of noise data, after uploading this data to the cloud server, there will be a large error with the preset standard action, so it is necessary to build a weighted model clustering integration in the action database for optimization and generate weighted optimization data.

[0046] S103, generating a position tag according to the weighted optimization data, matching the position tag with the preset feature data, and proofreading and constructing a character model.

[0047] Since the user's movement range cannot be standardized during the use of the dynamic capture device, for example, multiple jumps at very high heights cannot achieve the preset standard movements, so it is necessary to match the position tag with the preset feature data, proofread and construct the character model, and avoid large errors in the character model.

[0048] S104, matching the constructed character model with the action database to generate a three-dimensional cartoon image.

[0049] The proofread character model is matched with the action database to generate an animated image consistent with the user's movement trajectory. For example, the user performs actions such as jumping, running, and spinning. After collecting these data, a three-dimensional animated image matching the user's actions is generated.

[0050] For further information, see Figure 2 , the acquisition of dynamic collection data and preset feature data includes:

[0051] S201, acquiring dynamic collection data includes collecting data through a dynamic capture device, a camera, and a somatosensory device;

[0052] The motion capture device can be a somatosensory device, a skeletal dynamic motion acquisition device, and the camera can be a smartphone with facial recognition function.

[0053] S202, the preset feature data includes character graphic features and preset character standard action feature data, and the preset feature data matches the pre-examined character action feature data.

[0054] For further information, see Figure 3 , establishing an action database according to the dynamically collected data, optimizing the weighted model clustering integration constructed in the action database, and generating weighted optimization data, including:

[0055] S301, clustering the dynamically collected data in an action database, and constructing a weighted model clustering integration for optimization;

[0056] S302, optimizing the weighted model according to the user's usage frequency and user's usage time to generate weighted optimization data.

[0057] In order to improve the matching speed, the dynamically collected data is clustered and classified, and the frequently occurring dynamically collected data is aggregated together to generate weighted optimized data and speed up the operation and loading speed.

[0058] For further information, see Figure 4 , matching the constructed character model with the action database to generate a three-dimensional cartoon image, including:

[0059] S401, constructing a character model including character motion capture data and character dynamic motion movement time data;

[0060] S402, generating a dynamic data tag from the character dynamic capture data and the character dynamic action movement time data;

[0061] S403, matching the dynamic data tag with the action database to generate a three-dimensional cartoon image.

[0062] The character model constructed includes character motion capture data and character dynamic action movement time data; the user is equipped with a motion capture device, and the data generated during the user's movement will be collected, and the character motion capture data and the character dynamic action movement time data will be generated into dynamic data tags, and the generated dynamic data tags are easy to modify and query; the dynamic data tags are matched with the action database to generate a three-dimensional cartoon image.

[0063] See also Figure 5 The embodiment of the present invention further provides a device for producing personalized three-dimensional animation, including:

[0064] An acquisition unit 501 is used to acquire dynamic collection data and preset feature data;

[0065] The processing unit 502 is used to establish an action database according to the dynamic collection data, cluster and integrate the weighted model constructed in the action database for optimization, and generate weighted optimization data;

[0066] The optimization unit 503 is used to generate a position tag according to the weighted optimization data, match the position tag with the preset feature data, and calibrate and construct a character model.

[0067] The image generation unit 504 is used to match the constructed character model with the action database to generate a three-dimensional cartoon image.

[0068] Since the user's movement range cannot be standardized during the use of the dynamic capture device, for example, multiple jumps at very high heights cannot achieve the preset standard movements, so it is necessary to match the position tag with the preset feature data, proofread and construct the character model, and avoid large errors in the character model.

[0069] The proofread character model is matched with the action database to generate an animated image consistent with the user's movement trajectory. For example, the user performs actions such as jumping, running, and spinning. After collecting these data, a three-dimensional animated image matching the user's actions is generated.

[0070] Furthermore, the acquisition unit includes:

[0071] The acquisition unit acquires dynamic data including collecting data through a dynamic capture device, a camera and a somatosensory device;

[0072] The action matching unit, the preset feature data includes character graphic features and preset character standard action feature data, and the preset feature data matches the pre-examined character action feature data.

[0073] Acquiring dynamic acquisition data includes acquiring data through a dynamic capture device, a camera, and a somatosensory device; the dynamic capture device may be a somatosensory device, a skeletal dynamic motion acquisition device, and the camera may be a smart phone with a facial recognition function. The preset feature data includes character graphic features and preset character standard motion feature data, and the preset feature data matches the pre-examination character motion feature data.

[0074] Furthermore, the data analysis unit clusters the dynamically collected data in the action database and constructs a weighted model clustering integration for optimization;

[0075] The first data processing unit optimizes the weighted model according to the user's usage frequency and user time to generate weighted optimization data. In order to improve the matching speed, the dynamic collection data is clustered and classified, and the high-frequency dynamic collection data is aggregated together to generate weighted optimization data and speed up the operation and loading speed.

[0076] The image generation unit includes: a data construction unit, wherein the constructed character model includes character dynamic capture data and character dynamic action movement time data;

[0077] A second data processing unit generates a dynamic data tag from the character dynamic capture data and the character dynamic action movement time data;

[0078] The image generation unit matches the dynamic data tag with the action database to generate a three-dimensional cartoon image.

[0079] Since the user's movement range cannot be standardized during the use of the dynamic capture device, for example, multiple jumps at very high heights cannot achieve the preset standard movements, so it is necessary to match the position tag with the preset feature data, proofread and construct the character model, and avoid large errors in the character model.

[0080] The proofread character model is matched with the action database to generate an animated image consistent with the user's movement trajectory. For example, the user performs actions such as jumping, running, and spinning. After collecting these data, a three-dimensional animated image matching the user's actions is generated.

[0081] It can be seen from the above embodiments that the method and device for producing personalized three-dimensional animation provided by the present invention obtain dynamic acquisition data and preset feature data; establish an action database according to the dynamic acquisition data, cluster and integrate the weighted model constructed in the action database for optimization, and generate weighted optimization data; generate a position tag according to the weighted optimization data, match the position tag with the preset feature data, and proofread and construct a character model;

[0082] The constructed character model is matched with the action database to generate a three-dimensional cartoon image. The user wears a motion capture device and uses a facial recognition device or facial expression information to transmit basic preset action data to a cloud service platform. By establishing a preset action database, the collected data is matched with the preset data, thereby reducing a large amount of rendering work and solving the problem of being unable to create and produce three-dimensional animation when the user changes the computer or the computer configuration is low.

[0083] The embodiment of the present invention further provides a storage medium, and the embodiment of the present invention further provides a storage medium, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, some or all of the steps in each embodiment of the method for producing personalized three-dimensional animation provided by the present invention are implemented. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0084] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention or some parts of the embodiments.

[0085] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the personalized three-dimensional animation production device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0086] The above-described embodiments of the present invention do not limit the protection scope of the present invention.

Claims

1. A method for producing personalized three-dimensional animation, characterized in that: The method comprises a motion capture device and a face image capture device, wherein the method comprises: Obtain dynamic collection data and preset feature data; Establishing an action database according to the dynamically collected data, clustering and integrating the weighted model constructed in the action database for optimization, and generating weighted optimization data; Generating a position tag according to the weighted optimization data, matching the position tag with the preset feature data, and proofreading and constructing a character model; Matching the constructed character model with the action database to generate a three-dimensional cartoon image; The obtaining of dynamic collection data and preset characteristic data includes: Acquiring dynamic data includes collecting data through dynamic capture devices, cameras, and somatosensory devices; The preset feature data includes character graphic features and preset character standard action feature data, and the preset feature data matches the pre-examination character action feature data; Establishing an action database according to the dynamically collected data, clustering and integrating the weighted model constructed in the action database for optimization, and generating weighted optimization data, including: Clustering the dynamically collected data in an action database, and constructing a weighted model clustering integration for optimization; Optimizing the weighted model according to the user's usage frequency and user's usage time to generate weighted optimization data; The constructed character model is matched with the action database to generate a three-dimensional cartoon image, including: The character model construction includes character dynamic capture data and character dynamic action movement time data; Generate dynamic data tags from the character dynamic capture data and the character dynamic action movement time data; The dynamic data tags are matched with the action database to generate a three-dimensional cartoon image.

2. A device for producing personalized three-dimensional animation, characterized in that: include: An acquisition unit, used for acquiring dynamic collection data and preset feature data; A processing unit, used to establish an action database according to the dynamically collected data, cluster and integrate the weighted model constructed in the action database for optimization, and generate weighted optimization data; An optimization unit, configured to generate a position tag according to the weighted optimization data, match the position tag with the preset feature data, and calibrate and construct a character model; An image generation unit, used for matching the constructed character model with the action database to generate a three-dimensional cartoon image; The acquisition unit comprises: The acquisition unit acquires dynamic data including collecting data through a dynamic capture device, a camera and a somatosensory device; The action matching unit, the preset feature data includes character graphic features and preset character standard action feature data, and the preset feature data matches the pre-examined character action feature data; The processing unit comprises: A data analysis unit, clustering the dynamically collected data in an action database, and constructing a weighted model clustering integration for optimization; A first data processing unit optimizes the weighted model according to the user's usage frequency and user time to generate weighted optimization data; The image generation unit comprises: A data construction unit, wherein the character model construction includes character dynamic capture data and character dynamic action movement time data; A second data processing unit generates a dynamic data tag from the character dynamic capture data and the character dynamic action movement time data; The image generation unit matches the dynamic data tag with the action database to generate a three-dimensional cartoon image.

Images