Method and system for automatically generating animation video

Abstract

The invention is suitable for the technical field of cartoon video generation, and provides a cartoon video automatic generation method and system. The method comprises the following steps: performing frame-by-frame processing and object recognition on an original shot video to construct a plurality of object drawing templates; receiving a partial coloring creation; determining a plurality of sample point color channel values, and calculating a plurality of target color channel values; performing supplementary coloring rendering; and cartoon processing is carried out to generate a basic cartoon video. The method comprises the following steps: constructing a plurality of object drawing templates, receiving partial coloring creation of a creator, determining a plurality of sample point color channel values according to RGB three-color channels, calculating a plurality of target color channel values, performing supplementary coloring rendering on a plurality of corresponding supplementary target points, and generating a basic animation video. Another more flexible semi-creation mode is provided for the cartoon video generation technology, coloring supplement and optimization of partial coloring creation of creators are realized, and the flexibility and application potential of the cartoon video generation technology are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of animation video generation, and in particular relates to an automatic generation method and system for animation videos. Background Art

[0002] Animation video generation is the process of automatically generating or assisting in the generation of animation videos using computer graphics and image technology, artificial intelligence technology, etc. Animation video generation technology can quickly generate animation characters, scenes, and animation effects, reduce production costs and time, and thus greatly improve the efficiency and quality of animation production. It has broad development prospects in the fields of entertainment, education, and scientific research.

[0003] In the existing animation video generation technology, the coloring process of animation videos mostly relies on automatic processing by computers, or completely follows the manual coloring processing of creators. This greatly limits the flexibility of animation video generation technology and cannot effectively support another more flexible semi-creation mode. It cannot perform intelligent coloring supplement and optimization based on the partial coloring creation of creators, thus hindering the application potential of animation video generation technology. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for automatically generating an animation video, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0005] The embodiment of the present invention is implemented as follows: A method for automatically generating an animation video, the method specifically comprising the following steps: Acquire an original captured video, perform frame-by-frame processing on the original captured video, acquire multiple frame-by-frame captured images, perform object recognition on the multiple frame-by-frame captured images, and construct multiple object drawing templates; Create and display a plurality of the object drawing templates, receive partial coloring creations from creators, and generate a plurality of partial coloring templates; Selecting a plurality of coloring sample points and a plurality of supplementary target points from the plurality of partial coloring templates, determining a plurality of sample point color channel values ​​according to the RGB three color channels, and calculating a plurality of target color channel values; According to the plurality of target color channel values, in the plurality of partial coloring templates, performing supplementary coloring rendering on a plurality of corresponding supplementary target points to generate a complete coloring template; Based on the multiple complete coloring templates, the original shot video is animated to generate a basic animation video.

[0006] As a further limitation of the technical solution of the embodiment of the present invention, the method further includes the following steps: Grayscale value distribution analysis is performed on the plurality of images captured frame by frame to obtain a plurality of grayscale value distribution data, and the brightness of the animation picture is adjusted according to the plurality of grayscale value distribution data to generate an optimized animation video.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, the obtaining of the original captured video, frame-by-frame processing of the original captured video, obtaining multiple frame-by-frame captured images, performing object recognition on the multiple frame-by-frame captured images, and constructing multiple object drawing templates specifically include the following steps: Get the original video. Processing the original captured video frame by frame to obtain a plurality of frame-by-frame captured images; Performing object recognition on the plurality of images captured frame by frame to determine a plurality of captured objects; Acquiring internal dimension data of a plurality of photographed objects; According to the plurality of internal dimension data, a plurality of object drawing templates of the photographed objects are constructed.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, the creation and display of the plurality of object drawing templates, receiving partial coloring creations of creators, and generating a plurality of partial coloring templates specifically include the following steps: Create an interactive interface for creation; In the creation interaction interface, a plurality of the object drawing templates are created and displayed; Receive some of the coloring works of the creators; Generate multiple partial coloring templates.

[0009] As a further limitation of the technical solution of the embodiment of the present invention, the step of selecting a plurality of coloring sample points and a plurality of supplementary target points from the plurality of partial coloring templates, determining a plurality of sample point color channel values ​​according to the RGB three-color channels, and calculating a plurality of target color channel values ​​specifically comprises the following steps: According to the preset sample point ratio, multiple coloring sample points are selected from multiple partial coloring templates; In multiple partial coloring templates, multiple supplementary target points are marked; According to the RGB three-color channels, hue analysis is performed on the plurality of colored sample points to obtain color channel values ​​of the plurality of sample points; In the plurality of partial coloring templates, calculating the internal relative distances between the plurality of supplementary target points and the plurality of coloring sample points; Based on the plurality of sample point color channel values ​​and the plurality of internal relative distances, target color channel values ​​of the plurality of supplementary target points are calculated.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the target color channel values ​​of the plurality of supplementary target points is: ; in, Representative color channels, To supplement the pixel coordinates of the target point, for The supplementary target point at The target color channel value for each color channel. Representative Colored points, total Colored points, is the pixel coordinate of the color sample point, for The first color sample point at The sample color channel values ​​of the color channels, for The additional target points at The internal relative distance between the colored sample points at is the preset distance decomposition factor.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the animation processing of the original shot video based on the multiple complete coloring templates to generate a basic animation video specifically includes the following steps: Based on the plurality of complete coloring templates, performing animation processing on the plurality of frame-by-frame captured images to generate a plurality of frame-by-frame animation images; Recording frame-by-frame order data of a plurality of the images captured frame by frame; According to the frame-by-frame sequence data, a plurality of the frame-by-frame animation images are processed into video form to generate a basic animation video.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the grayscale value distribution analysis of the plurality of frame-by-frame images is performed to obtain a plurality of grayscale value distribution data, and the brightness of the animation picture is adjusted according to the plurality of grayscale value distribution data to generate an optimized animation video, specifically comprising the following steps: Selecting a plurality of representative captured images from the plurality of frame-by-frame captured images according to a preset representative selection frequency; Performing grayscale value distribution analysis on a plurality of representative captured images to obtain a plurality of grayscale value distribution data; Generate a plurality of corresponding brightness distribution data according to the plurality of gray value distribution data; According to the plurality of brightness distribution data, brightness adjustment is performed on the plurality of frame-by-frame animation images to generate a plurality of optimized animation images; According to the frame-by-frame order data, multiple optimized animation images are processed into video to generate optimized animation videos.

[0013] An automatic generation system for an animation video, the system comprises an object recognition processing module, a coloring creation receiving module, an RGB color channel analysis module, a supplementary coloring rendering module and an animation video generation module, wherein: An object recognition processing module is used to obtain an original captured video, perform frame-by-frame processing on the original captured video, obtain a plurality of frame-by-frame captured images, perform object recognition on the plurality of frame-by-frame captured images, and construct a plurality of object drawing templates; A coloring creation receiving module is used to create and display a plurality of the object drawing templates, receive partial coloring creations from creators, and generate a plurality of partial coloring templates; An RGB color channel analysis module is used to select a plurality of coloring sample points and a plurality of supplementary target points from the plurality of partial coloring templates, determine the color channel values ​​of the plurality of sample points according to the RGB three color channels, and calculate a plurality of target color channel values; A supplementary coloring rendering module, used to perform supplementary coloring rendering on a plurality of corresponding supplementary target points in a plurality of partial coloring templates according to a plurality of target color channel values, so as to generate a complete coloring template; The animation video generation module is used to perform animation processing on the original shot video based on the multiple complete coloring templates to generate a basic animation video.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the system also includes: The picture brightness adjustment module is used to perform grayscale value distribution analysis on the multiple frame-by-frame images, obtain multiple grayscale value distribution data, adjust the brightness of the animation picture according to the multiple grayscale value distribution data, and generate an optimized animation video.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The embodiment of the present invention constructs multiple object drawing templates by performing frame-by-frame processing and object recognition on the original shot video; receives partial coloring creations; determines multiple sample color channel values ​​and calculates multiple target color channel values; performs supplementary coloring rendering; performs animation processing to generate basic animation videos. It is possible to construct multiple object drawing templates, receive partial coloring creations of creators, determine multiple sample color channel values ​​according to the RGB three-color channels, calculate multiple target color channel values, perform supplementary coloring rendering on multiple corresponding supplementary target points, and generate basic animation videos, providing another more flexible semi-creation mode for animation video generation technology, realizing coloring supplementation and optimization of partial coloring creations of creators, and improving the flexibility and application potential of animation video generation technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for automatically generating an animated video provided by an embodiment of the present invention is shown; Figure 2 Another flow chart of the method for automatically generating an animated video provided by an embodiment of the present invention is shown; Figure 3 A flowchart of constructing multiple object drawing templates in a method provided by an embodiment of the present invention is shown; Figure 4 A flow chart showing the generation of multiple partial coloring templates in the method provided by an embodiment of the present invention; Figure 5 A flow chart showing the calculation of the target color channel value in the method provided by an embodiment of the present invention is shown; Figure 6 A flow chart of generating a basic cartoon video in a method provided by an embodiment of the present invention is shown; Figure 7 A flow chart of generating an optimized cartoon video in a method provided by an embodiment of the present invention is shown; Figure 8 An application architecture diagram of an automatic generation system for cartoon videos provided by an embodiment of the present invention is shown; Fig. 9 Another application architecture diagram of the automatic generation system of cartoon videos provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] It is understandable that in the existing animation video generation technology, the coloring process of the animation video mostly relies on automatic processing by computers, or completely follows the manual coloring processing of the creators. This greatly limits the flexibility of the animation video generation technology, and cannot effectively support another more flexible semi-creation mode. It cannot perform intelligent coloring supplement and optimization based on the partial coloring creation of the creators, thereby hindering the application potential of the animation video generation technology.

[0019] To solve the above problems, an embodiment of the present invention discloses an automatic generation method and system for an animated video, which obtains an original shot video, processes the original shot video frame by frame, obtains multiple frame-by-frame images, performs object recognition on the multiple frame-by-frame images, and constructs multiple object drawing templates; creates and displays the multiple object drawing templates, receives partial coloring creations from creators, and generates multiple partial coloring templates; selects multiple coloring sample points and multiple supplementary target points from the multiple partial coloring templates, determines multiple sample point color channel values ​​according to the RGB three-color channels, and calculates multiple target color channel values; performs supplementary coloring rendering on multiple corresponding supplementary target points in the multiple partial coloring templates according to the multiple target color channel values, and generates a complete coloring template; and performs animation processing on the original shot video based on the multiple complete coloring templates to generate a basic animated video. It is able to construct multiple object drawing templates, receive partial coloring creations of creators, determine multiple sample color channel values ​​according to the RGB three-color channels, calculate multiple target color channel values, perform supplementary coloring rendering on multiple corresponding supplementary target points, and generate basic animation videos, providing another more flexible semi-creative mode for animation video generation technology, realizing coloring supplementation and optimization of partial coloring creations of creators, and improving the flexibility and application potential of animation video generation technology.

[0020] Specifically, Figure 1 A flow chart of a method for automatically generating an animation video provided by an embodiment of the present invention is shown.

[0021] In a preferred embodiment of the present invention, a method for automatically generating an animation video comprises the following steps: Step S101: obtaining an original captured video, performing frame-by-frame processing on the original captured video, obtaining a plurality of frame-by-frame captured images, performing object recognition on the plurality of frame-by-frame captured images, and constructing a plurality of object drawing templates.

[0022] In an embodiment of the present invention, an original captured video is obtained, and the original captured video is processed frame by frame according to the video frame rate of the original captured video to obtain a plurality of frame-by-frame captured images. Object recognition is then performed on the plurality of frame-by-frame captured images to determine a plurality of captured objects in the original captured video, and object representative images corresponding to the plurality of captured objects are captured from the plurality of frame-by-frame captured images. By performing size analysis on the plurality of object representative images, internal size data of the plurality of captured objects is obtained, and then object drawing templates for the plurality of captured objects are constructed based on the plurality of internal size data.

[0023] It can be understood that the photographed object can be a real object existing in the original shot video, such as a person, a house, a tree, an animal, the sky, etc.; the object representative image is captured from multiple frame-by-frame images, and contains an image of the complete or largest photographed object, and each photographed object has one or more object representative images.

[0024] It can be understood that the internal dimension data is the size ratio data of the photographed object itself, which has nothing to do with other photographed objects and reflects the shape of the photographed object itself. For example, when there are two photographed objects, "box" and "person", the internal dimension data of the "box" is the size ratio of the length, width and height of the "box", which has nothing to do with the "person".

[0025] It is understandable that the object drawing template can be a two-dimensional image template or a three-dimensional model template. The object drawing template of each photographed object only shows its own shape and contour features, and does not show other features such as color and texture.

[0026] Specifically, Figure 3 A flow chart of constructing multiple object drawing templates in the method provided by an embodiment of the present invention is shown.

[0027] Among them, in the preferred embodiment provided by the present invention, the obtaining of the original shot video, performing frame-by-frame processing on the original shot video, obtaining a plurality of frame-by-frame shot images, performing object recognition on the plurality of frame-by-frame shot images, and constructing a plurality of object drawing templates specifically include the following steps: Step S1011: Obtain the original shot video.

[0028] Step S1012: performing frame-by-frame processing on the original captured video to obtain a plurality of frame-by-frame captured images.

[0029] Step S1013: performing object recognition on the plurality of images captured frame by frame to determine a plurality of captured objects.

[0030] Step S1014: Acquire internal dimension data of a plurality of the photographed objects.

[0031] Step S1015: constructing a plurality of object drawing templates of the photographed objects according to the plurality of internal dimension data.

[0032] Furthermore, the method for automatically generating an animated video also includes the following steps: Step S102: Create and display the plurality of object drawing templates, receive partial coloring creations from creators, and generate a plurality of partial coloring templates.

[0033] In an embodiment of the present invention, a creative interaction interface is created, and then multiple object drawing templates are sequentially displayed in the creative interaction interface. During the display process, the creator can call the creative tool to perform partial coloring creation on the corresponding object drawing template. By receiving the partial coloring creation of the creator, the multiple object drawing templates are subjected to corresponding partial coloring processing to generate multiple partial coloring templates.

[0034] It can be understood that the creation tools are virtual drawing tools set in the creation interaction interface, including a virtual palette, a virtual brush, a virtual eraser, etc.

[0035] Specifically, Figure 4 A flow chart of generating multiple partial coloring templates in the method provided by an embodiment of the present invention is shown.

[0036] Among them, in the preferred embodiment provided by the present invention, the creation and display of multiple object drawing templates, receiving partial coloring creations of creators, and generating multiple partial coloring templates specifically include the following steps: Step S1021, create a creative interactive interface.

[0037] Step S1022: In the creation interaction interface, a plurality of the object drawing templates are created and displayed.

[0038] Step S1023, receiving partial coloring creation from the creator.

[0039] Step S1024: Generate multiple partial coloring templates.

[0040] Furthermore, the method for automatically generating an animated video also includes the following steps: Step S103: Select multiple coloring sample points and multiple supplementary target points from the multiple partial coloring templates, determine multiple sample point color channel values ​​according to the RGB three color channels, and calculate multiple target color channel values.

[0041] In an embodiment of the present invention, according to a preset sample point ratio, multiple coloring sample points are selected in multiple partial coloring templates, and the areas other than the partial coloring by the creators in the multiple partial coloring templates are marked as supplementary coloring areas, and the pixel points in the supplementary coloring areas are marked as supplementary target points, so that the corresponding multiple supplementary target points in each partial coloring template can be obtained, and then the multiple coloring sample points are subjected to hue analysis according to the RGB three-color channels to obtain multiple sample point color channel values, and the internal relative distances between the multiple supplementary target points and the multiple coloring sample points are calculated in the multiple partial coloring templates, and then the target color channel values ​​corresponding to the multiple supplementary target points are calculated based on the multiple sample point color channel values ​​and the multiple internal relative distances. Specifically, the calculation formula of the target color channel values ​​of the multiple supplementary target points is: ; in, Representative color channels, To supplement the pixel coordinates of the target point, for The supplementary target point at The target color channel value for each color channel. Representative Colored points, total Colored points, is the pixel coordinate of the color sample point, for The first color sample point at The sample color channel values ​​of the color channels, for The additional target points at The internal relative distance between the colored sample points at is the preset distance decomposition factor.

[0042] It is understandable that, since the screen size of each partial coloring template is different, after the coloring samples are selected according to the sample ratio, the number of coloring samples obtained is also different.

[0043] It can be understood that, according to the RGB three-color channels, each colored sample has three sample color channel values ​​of R, G and B.

[0044] It can be understood that, according to the RGB three-color channels, each supplementary target point has three target color channel values ​​of R, G and B.

[0045] Specifically, Figure 5 A flow chart of calculating a target color channel value in a method provided by an embodiment of the present invention is shown.

[0046] Among them, in the preferred embodiment provided by the present invention, the selecting of multiple coloring sample points and multiple supplementary target points from the multiple partial coloring templates, determining multiple sample point color channel values ​​according to the RGB three-color channels, and calculating multiple target color channel values ​​specifically includes the following steps: Step S1031 : Select multiple coloring sample points from multiple partial coloring templates according to a preset sample point ratio.

[0047] Step S1032: Mark multiple supplementary target points in multiple partial coloring templates.

[0048] Step S1033: performing hue analysis on the plurality of colored sample points according to the RGB three-color channels to obtain color channel values ​​of the plurality of sample points.

[0049] Step S1034: Calculate the internal relative distances between the plurality of supplementary target points and the plurality of colored sample points in the plurality of partial colored templates.

[0050] Step S1035 : Calculate target color channel values ​​of a plurality of the supplementary target points based on the plurality of sample point color channel values ​​and the plurality of internal relative distances.

[0051] Furthermore, the method for automatically generating an animated video also includes the following steps: Step S104: According to the plurality of target color channel values, in the plurality of partial coloring templates, a plurality of corresponding supplementary target points are subjected to supplementary coloring rendering to generate a complete coloring template.

[0052] In an embodiment of the present invention, according to the three target color channel values ​​of R, G and B corresponding to the multiple supplementary target points, multiple corresponding supplementary target points are automatically supplemented and rendered in multiple partial coloring templates to generate multiple complete coloring templates.

[0053] It is understandable that the colors in the complete coloring template are composed of partial coloring creation by the creator and automatic supplementary coloring rendering.

[0054] Step S105: Based on the multiple complete coloring templates, the original shot video is animated to generate a basic animation video.

[0055] In an embodiment of the present invention, based on multiple complete coloring templates, the photographed objects in the multiple frame-by-frame images are animated to generate multiple frame-by-frame animation images, and the frame-by-frame order data of the multiple frame-by-frame images are recorded. Then, according to the frame-by-frame order data, the multiple frame-by-frame animation images are processed into video form to generate a basic animation video.

[0056] Specifically, Figure 6 A flow chart of generating a basic animation video in the method provided by an embodiment of the present invention is shown.

[0057] Among them, in the preferred embodiment provided by the present invention, the animation processing of the original shot video based on the multiple complete coloring templates to generate a basic animation video specifically includes the following steps: Step S1051: Based on the multiple complete coloring templates, the multiple frame-by-frame captured images are animated to generate multiple frame-by-frame animated images.

[0058] Step S1052: Record the frame-by-frame sequence data of the plurality of images captured frame by frame.

[0059] Step S1053: Perform video processing on the plurality of frame-by-frame animation images according to the frame-by-frame sequence data to generate a basic animation video.

[0060] Furthermore, Figure 2 Another flow chart of the method for automatically generating cartoon videos provided by an embodiment of the present invention is shown.

[0061] Specifically, in another preferred embodiment provided by the present invention, the method further comprises the following steps: Step S106: performing grayscale value distribution analysis on the plurality of images captured frame by frame, obtaining a plurality of grayscale value distribution data, adjusting the brightness of the animation picture according to the plurality of grayscale value distribution data, and generating an optimized animation video.

[0062] In an embodiment of the present invention, according to a preset representative selection frequency, a plurality of representative captured images are selected from a plurality of frame-by-frame captured images, and image representative intervals of the plurality of representative captured images are determined, and grayscale value distribution data corresponding to the plurality of representative captured images are obtained by performing grayscale value distribution analysis on the plurality of representative captured images, and then corresponding brightness distribution matching is performed based on the plurality of grayscale value distribution data to generate a plurality of brightness distribution data, and then, according to the image representative interval and the plurality of brightness distribution data, the brightness of the plurality of frame-by-frame animated images is adjusted to generate a plurality of optimized animated images, and then, according to the frame-by-frame order data, the plurality of optimized animated images are converted into videos to generate optimized animation videos.

[0063] It can be understood that the image representative interval is the number of images representing the captured image in the brightness adjustment. For example, when the image representative interval is 12, it means that in the brightness adjustment, the representative captured image can represent itself and the next 11 frame-by-frame captured images. Therefore, according to the brightness distribution data corresponding to the grayscale value distribution data representing the captured image, the 12 frame-by-frame animated images corresponding to itself and the next 11 frame-by-frame captured images can be adjusted accordingly to generate an optimized animated image.

[0064] It is understandable that by finely adjusting the brightness distribution of animated images frame by frame, not only can the visual level of the picture be enhanced under different lighting angles and intensities, but the surface gloss changes of the animated objects can also be delicately displayed, which can significantly improve the expression of animated details of the objects, making them more vivid, natural and three-dimensional.

[0065] Specifically, Figure 7 A flow chart of generating an optimized animation video in the method provided by an embodiment of the present invention is shown.

[0066] Among them, in the preferred embodiment provided by the present invention, the gray value distribution analysis is performed on the multiple frame-by-frame images to obtain multiple gray value distribution data, and the animation screen brightness is adjusted according to the multiple gray value distribution data to generate an optimized animation video, which specifically includes the following steps: Step S1061 : selecting a plurality of representative captured images from the plurality of frame-by-frame captured images according to a preset representative selection frequency.

[0067] Step S1062: performing grayscale value distribution analysis on a plurality of representative captured images to obtain a plurality of grayscale value distribution data.

[0068] Step S1063: Generate a plurality of corresponding brightness distribution data according to the plurality of gray value distribution data.

[0069] Step S1064: adjusting the brightness of the plurality of frame-by-frame animation images according to the plurality of brightness distribution data to generate a plurality of optimized animation images.

[0070] Step S1065: Perform video processing on the plurality of optimized animation images according to the frame-by-frame order data to generate an optimized animation video.

[0071] Furthermore, Figure 8 The application architecture diagram of the automatic generation system of cartoon videos provided by an embodiment of the present invention is shown.

[0072] In another preferred embodiment of the present invention, a system for automatically generating an animated video includes: The object recognition processing module 101 is used to obtain an original captured video, perform frame-by-frame processing on the original captured video, obtain multiple frame-by-frame captured images, perform object recognition on the multiple frame-by-frame captured images, and construct multiple object drawing templates.

[0073] In the embodiment of the present invention, the object recognition processing module 101 obtains the original captured video, performs frame-by-frame processing on the original captured video according to the video frame rate of the original captured video, obtains multiple frame-by-frame captured images, and then performs object recognition on the multiple frame-by-frame captured images to determine multiple captured objects in the original captured video, and intercepts object representative images corresponding to the multiple captured objects from the multiple frame-by-frame captured images, obtains internal size data of the multiple captured objects by performing size analysis on the multiple object representative images, and then constructs object drawing templates for the multiple captured objects based on the multiple internal size data.

[0074] The coloring creation receiving module 102 is used to create and display multiple object drawing templates, receive partial coloring creations from creators, and generate multiple partial coloring templates.

[0075] In an embodiment of the present invention, the coloring creation receiving module 102 creates a creation interaction interface, and then displays multiple object drawing templates in sequence in the creation interaction interface. During the display process, the creator can call the creation tool to perform partial coloring creation on the corresponding object drawing template. By receiving the partial coloring creation of the creator, the multiple object drawing templates are subjected to corresponding partial coloring processing to generate multiple partial coloring templates.

[0076] The RGB color channel analysis module 103 is used to select multiple coloring sample points and multiple supplementary target points from the multiple partial coloring templates, determine multiple sample point color channel values ​​according to the RGB three color channels, and calculate multiple target color channel values.

[0077] In the embodiment of the present invention, the RGB color channel analysis module 103 selects multiple coloring sample points in multiple partial coloring templates according to a preset sample point ratio, marks the areas other than the partial coloring by the creators in the multiple partial coloring templates as supplementary coloring areas, and marks the pixels in the supplementary coloring areas as supplementary target points, so that the corresponding multiple supplementary target points in each partial coloring template can be obtained, and then the multiple coloring sample points are analyzed according to the RGB three-color channels to obtain multiple sample point color channel values, and the internal relative distances between the multiple supplementary target points and the multiple coloring sample points are calculated in the multiple partial coloring templates, and then the target color channel values ​​corresponding to the multiple supplementary target points are calculated based on the multiple sample point color channel values ​​and the multiple internal relative distances. Specifically, the calculation formula of the target color channel values ​​of the multiple supplementary target points is: ; in, Representative color channels, To supplement the pixel coordinates of the target point, for The supplementary target point at The target color channel value for each color channel. Representative Colored points, total Colored points, is the pixel coordinate of the color sample point, for The first color sample point at The sample color channel values ​​of the color channels, for The additional target points at The internal relative distance between the colored sample points at is the preset distance decomposition factor.

[0078] The supplementary coloring rendering module 104 is used to perform supplementary coloring rendering on a plurality of corresponding supplementary target points in a plurality of partial coloring templates according to the plurality of target color channel values ​​to generate a complete coloring template.

[0079] In the embodiment of the present invention, the supplementary color rendering module 104 automatically performs supplementary color rendering on multiple corresponding supplementary target points in multiple partial coloring templates according to the three target color channel values ​​of R, G and B corresponding to the multiple supplementary target points, and generates multiple complete coloring templates.

[0080] The animation video generation module 105 is used to perform animation processing on the original shot video based on the multiple complete coloring templates to generate a basic animation video.

[0081] In an embodiment of the present invention, the animation video generation module 105 performs animation processing on the photographed objects in the multiple frame-by-frame images based on multiple complete coloring templates, generates multiple frame-by-frame animation images, and records the frame-by-frame sequence data of the multiple frame-by-frame images, and then performs video processing on the multiple frame-by-frame animation images according to the frame-by-frame sequence data to generate a basic animation video.

[0082] Furthermore, Fig. 9 Another application architecture diagram of the automatic generation system of cartoon videos provided by an embodiment of the present invention is shown.

[0083] Specifically, in another preferred embodiment provided by the present invention, the system further includes: The picture brightness adjustment module 106 is used to perform grayscale value distribution analysis on the multiple frame-by-frame images, obtain multiple grayscale value distribution data, adjust the animation picture brightness according to the multiple grayscale value distribution data, and generate an optimized animation video.

[0084] In an embodiment of the present invention, the screen brightness adjustment module 106 selects multiple representative captured images from multiple frame-by-frame captured images according to a preset representative selection frequency, and determines the image representative intervals of the multiple representative captured images, obtains the grayscale value distribution data corresponding to the multiple representative captured images by performing grayscale value distribution analysis on the multiple representative captured images, and then performs corresponding brightness distribution matching based on the multiple grayscale value distribution data to generate multiple brightness distribution data, and then adjusts the brightness of the multiple frame-by-frame animation images according to the image representative intervals and the multiple brightness distribution data to generate multiple optimized animation images, and then performs video processing on the multiple optimized animation images according to the frame-by-frame order data to generate optimized animation videos.

[0085] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0086] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0087] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for automatically generating an animation video, characterized in that: The method specifically comprises the following steps: Acquire an original captured video, perform frame-by-frame processing on the original captured video, acquire multiple frame-by-frame captured images, perform object recognition on the multiple frame-by-frame captured images, and construct multiple object drawing templates; Create and display a plurality of the object drawing templates, receive partial coloring creations from creators, and generate a plurality of partial coloring templates; Selecting a plurality of coloring sample points and a plurality of supplementary target points from the plurality of partial coloring templates, determining a plurality of sample point color channel values ​​according to the RGB three color channels, and calculating a plurality of target color channel values; According to the plurality of target color channel values, in the plurality of partial coloring templates, performing supplementary coloring rendering on a plurality of corresponding supplementary target points to generate a complete coloring template; Based on the multiple complete coloring templates, the original shot video is animated to generate a basic animation video.

2. The method for automatically generating an animation video according to claim 1, characterized in that: The method further comprises the following steps: Grayscale value distribution analysis is performed on the plurality of images captured frame by frame to obtain a plurality of grayscale value distribution data, and the brightness of the animation picture is adjusted according to the plurality of grayscale value distribution data to generate an optimized animation video.

3. The method for automatically generating an animation video according to claim 1, characterized in that: The steps of obtaining the original captured video, performing frame-by-frame processing on the original captured video, obtaining multiple frame-by-frame captured images, performing object recognition on the multiple frame-by-frame captured images, and constructing multiple object drawing templates specifically include the following steps: Get the original video. Processing the original captured video frame by frame to obtain a plurality of frame-by-frame captured images; Performing object recognition on the plurality of images captured frame by frame to determine a plurality of captured objects; Acquiring internal dimension data of a plurality of photographed objects; According to the plurality of internal dimension data, a plurality of object drawing templates of the photographed objects are constructed.

4. The method for automatically generating an animation video according to claim 1, characterized in that: The step of creating and displaying a plurality of object drawing templates, receiving partial coloring creations by creators, and generating a plurality of partial coloring templates specifically comprises the following steps: Create an interactive interface for creation; In the creation interaction interface, a plurality of the object drawing templates are created and displayed; Receive some of the coloring works of the creators; Generate multiple partial coloring templates.

5. The method for automatically generating an animation video according to claim 1, characterized in that: The method of selecting a plurality of coloring sample points and a plurality of supplementary target points from the plurality of partial coloring templates, determining a plurality of sample point color channel values ​​according to the RGB three-color channels, and calculating a plurality of target color channel values ​​specifically comprises the following steps: According to the preset sample point ratio, multiple coloring sample points are selected from multiple partial coloring templates; In multiple partial coloring templates, multiple supplementary target points are marked; According to the RGB three-color channels, hue analysis is performed on the plurality of colored sample points to obtain color channel values ​​of the plurality of sample points; In the plurality of partial coloring templates, calculating the internal relative distances between the plurality of supplementary target points and the plurality of coloring sample points; Based on the plurality of sample point color channel values ​​and the plurality of internal relative distances, target color channel values ​​of the plurality of supplementary target points are calculated.

6. The method for automatically generating an animation video according to claim 5, characterized in that: The calculation formula of the target color channel values ​​of the plurality of supplementary target points is: ； in, Representative color channels, To supplement the pixel coordinates of the target point, for The supplementary target point at The target color channel value for each color channel, Representative Colored points, total Colored points, is the pixel coordinate of the color sample point, for The first color sample point at The sample color channel values ​​of the color channels, for The additional target points at The internal relative distance between the colored sample points at is the preset distance decomposition factor.

7. The method for automatically generating an animation video according to claim 2, characterized in that: The animation processing of the original shot video based on the plurality of complete coloring templates to generate a basic animation video specifically comprises the following steps: Based on the plurality of complete coloring templates, performing animation processing on the plurality of frame-by-frame captured images to generate a plurality of frame-by-frame animation images; Recording frame-by-frame order data of a plurality of the images captured frame by frame; According to the frame-by-frame sequence data, a plurality of the frame-by-frame animation images are processed into video form to generate a basic animation video.

8. The method for automatically generating an animation video according to claim 7, characterized in that: The grayscale value distribution analysis of the plurality of frame-by-frame captured images is performed to obtain a plurality of grayscale value distribution data, and the brightness of the animation picture is adjusted according to the plurality of grayscale value distribution data to generate an optimized animation video, which specifically includes the following steps: Selecting a plurality of representative captured images from the plurality of frame-by-frame captured images according to a preset representative selection frequency; Performing grayscale value distribution analysis on a plurality of representative captured images to obtain a plurality of grayscale value distribution data; Generate a plurality of corresponding brightness distribution data according to the plurality of gray value distribution data; According to the plurality of brightness distribution data, brightness adjustment is performed on the plurality of frame-by-frame animation images to generate a plurality of optimized animation images; According to the frame-by-frame order data, multiple optimized animation images are processed into video to generate optimized animation videos.

9. An automatic generation system for animation videos, characterized in that: The system includes an object recognition processing module, a coloring creation receiving module, an RGB color channel analysis module, a supplementary coloring rendering module and an animation video generation module, wherein: An object recognition processing module is used to obtain an original captured video, perform frame-by-frame processing on the original captured video, obtain a plurality of frame-by-frame captured images, perform object recognition on the plurality of frame-by-frame captured images, and construct a plurality of object drawing templates; A coloring creation receiving module is used to create and display a plurality of the object drawing templates, receive partial coloring creations from creators, and generate a plurality of partial coloring templates; An RGB color channel analysis module is used to select a plurality of coloring sample points and a plurality of supplementary target points from the plurality of partial coloring templates, determine the color channel values ​​of the plurality of sample points according to the RGB three color channels, and calculate a plurality of target color channel values; A supplementary coloring rendering module, used to perform supplementary coloring rendering on a plurality of corresponding supplementary target points in a plurality of partial coloring templates according to a plurality of target color channel values, so as to generate a complete coloring template; The animation video generation module is used to perform animation processing on the original shot video based on the multiple complete coloring templates to generate a basic animation video.

10. The automatic generation system of animation video according to claim 9, characterized in that: The system further comprises: The picture brightness adjustment module is used to perform grayscale value distribution analysis on the multiple frame-by-frame images, obtain multiple grayscale value distribution data, adjust the brightness of the animation picture according to the multiple grayscale value distribution data, and generate an optimized animation video.

Images