Virtual interaction system based on non-abandoned item inheritance protection

Abstract

The invention provides a virtual interaction system based on non-missing item inheritance protection, which relates to a data processing technology and comprises the following steps of: extracting continuous action frames in a non-missing display video based on a display action selected by a user side comprising AR (Augmented Reality) equipment; customizing and generating a display base and an action model matched with the display base according to the moving track of the continuous action frame; and controlling the printing equipment to print the display base and the action model corresponding to the display base, and adaptively customizing the base matched with the display base according to different non-abandoned actions, so that the intuition of non-abandoned action display is improved, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to data processing technology, and more particularly to a virtual interactive system based on the inheritance and protection of intangible cultural heritage projects. Background Technology

[0002] Intangible cultural heritage, or ICH for short, serves as an important carrier of national culture. With the development of digital technology, the digital preservation of ICH has formed a mature technical system. Typical methods include: using AR devices to capture video of ICH display scenes such as traditional dances and handicrafts; and using computer vision to permanently store, digitally retrieve, and virtually display ICH movements. To break the limitation of preservation existing only online, digital preservation of ICH incorporates 3D printing technology. By transforming digital three-dimensional movement models into printed entities, these entities can be used for offline exhibitions, school teaching, and cultural exchanges, allowing for a more intuitive experience of the charm of ICH.

[0003] In existing technologies, 3D printed physical display solutions in the field of intangible cultural heritage mostly adopt standardized designs for the display bases supporting the figures, that is, they are fixed by a flat base of uniform specifications. However, in the performance scene of intangible cultural heritage, the changes in the movements of the people present specific spatial trajectories, while the general base can only provide a single support plane and cannot mark the standing position and movement trajectory corresponding to different movements. As a result, the combination of the printed model and the base lacks correlation, and the audience cannot intuitively feel the movements and details of the people through the physical model, thus reducing the user experience.

[0004] Therefore, how to customize a base that is compatible with different intangible cultural heritage movements in order to improve the intuitiveness of the display of intangible cultural heritage movements and enhance the user experience has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a virtual interactive system based on the inheritance and protection of intangible cultural heritage projects. It can customize and adapt bases to different intangible cultural heritage movements, thereby enhancing the intuitiveness of the intangible cultural heritage movement display and improving the user experience.

[0006] A first aspect of the present invention provides a virtual interactive system based on the inheritance and protection of intangible cultural heritage projects, comprising: The extraction module is used to extract continuous motion frames from intangible cultural heritage display videos based on the display actions selected by the user terminal, including AR devices. The generation module is used to customize and generate a display base and an action model adapted to the display base based on the movement trajectory of the continuous action frames. The printing module is used to control the printing device to print the display base and the corresponding motion model of the display base.

[0007] Optionally, in one possible implementation of the first aspect, extracting continuous motion frames from the intangible cultural heritage display video based on the display actions selected by the user terminal, including the AR device, includes: After displaying data through AR devices, the display action selected by the user is received, and the intangible cultural heritage display video is processed based on the display time period of the display action to obtain the display video segment. Retrieve the preset extraction quantity corresponding to the display action, and perform equal splitting of the display video segment based on the preset extraction quantity to obtain multiple sub-video segments; Image frames from each of the sub-video segments are selected and combined to obtain continuous motion frames.

[0008] Optionally, in one possible implementation of the first aspect, the step of selecting and combining image frames from each of the sub-video segments to obtain continuous action frames includes: The first sub-video segment is used as the starting segment, the last sub-video segment is used as the ending segment, and the remaining sub-video segments are used as the middle segments. The first image frame in the starting segment is selected as the reference frame, the last image frame in the ending segment is selected as the reference frame, and the image frame in the middle position in the middle segment is selected as the reference frame. The filtering number of each image frame is determined based on the image frame's sharpness and the reference frame. Select the image frames with the smallest filter number within each sub-video segment and combine them to obtain continuous action frames.

[0009] Optionally, in one possible implementation of the first aspect, determining the filter number of each image frame based on the image frame's sharpness and the reference frame includes: The preset number is assigned to the reference frame, and the image frames on both sides are numbered sequentially, starting from the reference frame in each sub-video segment, to obtain the first number of each image frame. Based on the clarity of the image frames in the displayed video segment, the image frames of each sub-video segment are sorted in descending order and numbered sequentially to obtain the second number of each image frame; The filtering number for each image frame is obtained by summing the first and second numbers.

[0010] Optionally, in one possible implementation of the first aspect, the step of customizing and generating a display base based on the movement trajectory of the continuous action frames, and an action model adapted to the display base, includes: Construct a venue model corresponding to the venue in the video segment, and update the motion model in the continuous motion frames to the venue model to obtain the display model; Connect the center points of the motion models in the display model to obtain the movement trajectory; When the length of the movement trajectory is determined to be less than the preset length, a fixed-point trajectory base is generated based on the spatial trajectory of the motion model corresponding to the preset recognition point in the displayed video segment. When the length of the movement trajectory is greater than or equal to the preset length, a movement trajectory base is generated based on the movement trajectory. Based on the fixed-point trajectory base and the moving trajectory base, a display base is obtained, and an action model adapted to the display base is generated.

[0011] Optionally, in one possible implementation of the first aspect, generating a fixed-point trajectory base based on the spatial trajectory of the motion model corresponding to preset recognition points in the displayed video segment includes: Obtain the spatial trajectory of the motion model corresponding to the preset recognition points in the displayed video segment; When it is determined that the spatial trajectory is a circular trajectory, the limb part with the corresponding preset recognition point is taken as the rotation part, and the first length of the longest rotation part is obtained; The construction radius is obtained by multiplying the preset extraction quantity and the first length. A fixed-point circular base is generated based on the construction radius. A uniformly distributed installation groove is determined at any diameter of the fixed-point circular base based on the preset extraction quantity, and a fixed-point trajectory base is generated. When it is determined that none of the spatial trajectories are circular, the limb parts at the corresponding preset recognition points are retrieved as the action parts, and the second length of the longest action part is obtained. The construction side length is obtained by multiplying the preset extraction quantity and the second length. A fixed-point square base is generated based on the construction side length. A uniformly distributed installation groove is determined at any diagonal of the fixed-point square base based on the preset extraction quantity, thereby generating a fixed-point trajectory base.

[0012] Optionally, in one possible implementation of the first aspect, generating the motion trajectory base based on the motion trajectory includes: Obtain the extended length corresponding to the longest limb part, and translate the movement trajectory to both sides based on the extended length to obtain the translated movement trajectory; Connect the two endpoints on the same side of the translated movement trajectory, and determine uniformly distributed mounting grooves at the movement trajectory based on a preset extraction quantity to generate the movement trajectory base.

[0013] Optionally, in one possible implementation of the first aspect, generating a motion model adapted to the display base includes: Configure the corresponding mounting protrusions for the motion model to generate a motion model that is compatible with the display base.

[0014] Optionally, in one possible implementation of the first aspect, the step of selecting and combining image frames from each of the sub-video segments to obtain continuous action frames includes: Receive selection information of image frames in a sub-video segment from the user terminal, and determine the corresponding image frames as combined frames based on the selection information; The combined frames are combined based on the user's selection order to obtain continuous action frames.

[0015] A second aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, is used to implement the first aspect of the present invention and various methods possibly involved in the first aspect.

[0016] The beneficial effects of this invention are as follows: 1. This invention can automatically extract a series of continuous motion frames based on the display actions the user wants to retain, and then customize and dynamically generate a display base and motion model based on the movement trajectory formed by these motion frames. By transforming the performer's spatial movement path into the shape of the base, the final printed physical work can intuitively reproduce the performer's movement trajectory and key postures, making it convenient for users to view intuitively.

[0017] 2. This invention combines automated filtering with personalized user needs in the action frame extraction stage. By extracting a corresponding number of action frames for different types of display actions and equally dividing the video segments, it ensures a uniform temporal distribution of the selected action frames. By dividing the video segments into different stages such as start, middle, and end, and comprehensively considering representativeness and image clarity to obtain filtering numbers, the method automatically selects image frame combinations. Simultaneously, this method also supports manual user intervention to ensure that user needs are met.

[0018] 3. This invention analyzes the overall movement trajectory length of the motion model to automatically distinguish between stationary and moving performances. For stationary performances, it further analyzes the spatial trajectory of the limbs to generate a circular or square base that reflects the dynamic feeling of the performance in place; for moving performances, it directly uses the performer's movement path as a reference to generate a trajectory base with a consistent shape, thus significantly improving the user experience. Attached Figure Description

[0019] Figure 1 A schematic diagram of the structure of a virtual interactive system based on the inheritance and protection of intangible cultural heritage projects provided by the present invention; Figure 2 This is a schematic diagram of an image frame corresponding to a first number provided by the present invention; Figure 3 This is a schematic diagram of a circular base corresponding to a mounting groove provided by the present invention; Figure 4 This is a schematic diagram of a square base corresponding to a mounting groove provided by the present invention; Figure 5 This is a schematic diagram of a mounting groove corresponding to a moving trajectory base provided by the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein.

[0022] It should be understood that in the various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0023] It should be understood that in this invention, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0024] It should be understood that in this invention, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.

[0025] It should be understood that in this invention, "B corresponding to A", "B corresponding to A", "A and B correspond", or "B and A correspond" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.

[0026] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."

[0027] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0028] This invention provides a virtual interactive system based on the inheritance and protection of intangible cultural heritage projects, such as... Figure 1 As shown, it includes: S1, the extraction module, is used to extract continuous motion frames from intangible cultural heritage display videos based on the display actions selected by the user terminal, including AR devices.

[0029] Current technologies rely entirely on users to select images for modeling and printing. When users are interested in performances related to intangible cultural heritage, they need to select images from the video one by one for printing, and the selection of images is subjective and random. Furthermore, intangible cultural heritage performance videos are usually quite long, containing a large amount of movement content, while users are often only interested in a specific, exciting segment. Therefore, a significant amount of time is required for selection, which cannot meet users' personalized customization needs.

[0030] This solution, on the other hand, specifically extracts continuous motion frames corresponding to the actions performed in intangible cultural heritage demonstration videos. In other words, our solution automatically extracts and combines the corresponding video frames from the intangible cultural heritage demonstration videos for different actions to obtain continuous motion frames.

[0031] Among them, the displayed actions refer to specific performance actions in the intangible cultural heritage display videos, such as the carp leaping and spinning. Users will determine the actions they want to save based on AR devices.

[0032] In some embodiments, step S1 (extracting continuous motion frames from the intangible cultural heritage display video based on the display action selected by the user terminal, including the AR device) includes S11-S13: S11, after displaying data through the AR device, receive the display action selected by the user terminal, and extract the intangible cultural heritage display video based on the display time period of the display action to obtain the display video segment.

[0033] It should be noted that currently, the modeling and printing process relies entirely on users selecting corresponding images. However, user selection is subjective and random, and requires a significant amount of time to select, resulting in poor print quality that fails to meet users' personalized customization needs.

[0034] This solution, on the other hand, specifically extracts continuous motion frames corresponding to the performance actions in intangible cultural heritage display videos. In other words, our solution automatically extracts and combines corresponding video frames from the intangible cultural heritage display videos for different actions to obtain continuous motion frames. Compared with the existing technology of manual random extraction, our solution prioritizes the automatic extraction of graphic frames, and secondly, it customizes the extraction of a certain number and position of video frames for the performance actions in the intangible cultural heritage display videos.

[0035] Among them, the "demonstration actions" refer to specific performance actions in intangible cultural heritage demonstration videos, such as the carp leaping over a wall or spinning in circles. It is easy to understand that each demonstration action has a corresponding performance time period, i.e., a demonstration time period.

[0036] Understandably, users can choose intangible cultural heritage performance movements that interest them, such as somersaults. Subsequently, the intangible cultural heritage display video will be segmented and processed according to the time period in which the movement occurs, resulting in a display video segment corresponding to that movement.

[0037] S12, retrieve the preset extraction quantity corresponding to the display action, and perform equal splitting of the display video segment based on the preset extraction quantity to obtain multiple sub-video segments.

[0038] It's important to note that allowing users to manually select the number of images not only increases their workload but also introduces significant arbitrariness in the choice, making it difficult to guarantee that the final physical model can accurately represent the continuity of the action. For example, a complex rolling action might require three models to depict, while a simple waving action only needs two. Therefore, we pre-determine an optimal number of images to extract for different types of actions. That is, we customize the extraction number for different actions and automate the process. The specific number can be determined based on the complexity of the action or manually. On the other hand, by equally dividing the video segment according to this number, we ensure that the subsequently selected image frames are evenly distributed throughout the entire action cycle.

[0039] The preset extraction quantity is the number of image frames to be extracted corresponding to each display action. For example, 3 frames are preset to be extracted for a somersault and 5 frames are preset to be extracted for a spinning action.

[0040] It's easy to understand that equal splitting means dividing the duration of the displayed video segment into equal parts according to this preset number.

[0041] S13, Select and combine the image frames from each of the sub-video segments to obtain continuous action frames.

[0042] In some embodiments, step S13 (selecting and combining image frames from each of the sub-video segments to obtain continuous motion frames) includes A1-A4: A1 uses the first sub-video segment as the starting segment, the last sub-video segment as the ending segment, and the remaining sub-video segments as the middle segments.

[0043] It should be noted that a complete action generally includes three stages: the initial stance, the middle stage, and the final stance. The representative posture characteristics of the action differ at each stage. For example, the key to the initial stance stage lies in the initial form of the action. Existing technologies often treat all sub-video segments equally when selecting image frames, using the same selection criteria and ignoring the differences in the quantity and behavior of the action at different stages. This solution, however, first identifies the role of each sub-video segment. By clearly dividing them into a start segment, a middle segment, and a finish segment, it ensures that the selected image frame combination better reflects the completeness of the action.

[0044] A2. Select the first image frame in the starting segment as the reference frame, the last image frame in the ending segment as the reference frame, and the image frame in the middle position in the middle segment as the reference frame.

[0045] Based on the characteristics of the action phase, we pre-positioned optimal locations within each sub-video segment: the beginning of the starting segment, the end of the ending segment, and the midpoint of the middle segment.

[0046] It should be noted that if there are two image frames in the middle position of the middle segment, both can be used as reference frames.

[0047] A3. Determine the screening number of each image frame based on the image frame's clarity and the reference frame.

[0048] It's important to note that selecting the best image frame requires considering two core factors simultaneously: image sharpness and the representativeness of the pose. This is achieved by determining the distance of each image frame from the baseline frame and its own sharpness, and then combining these two indicators to create a selection number. Sharpness refers to the clarity of the action in the image, facilitating subsequent checks for blurriness, ghosting, or other issues.

[0049] In some embodiments, step A3 (determining the filter number of each image frame based on the image frame's sharpness and the reference frame) includes A31-A33: A31, assign the preset number to the reference frame, and take the reference frame in each sub-video segment as the starting point to sequentially number the image frames on both sides to obtain the first number of each image frame.

[0050] The preset number can be a manually set number, such as 0 or 1. The position of the reference frame is a representative position of the sub-video segment. Therefore, starting from the reference frame, the image frames on both sides are sequentially numbered to obtain the first number of each image frame within the sub-video segment. See also Figure 2 Taking the middle segment as an example, for ease of understanding, only 3 image frames are used here. For example, the baseline value of the middle position is 0, and each side is numbered 1. Subsequently, each image frame will be numbered again according to the clarity. The higher the clarity, the smaller the corresponding number. The smaller the first number, the more representative it is. Therefore, the image frame with the smallest number in each sub-video segment will be selected and combined, which is both clear and representative.

[0051] A32, based on the clarity of the image frames in the displayed video segment, sort the image frames of each sub-video segment in descending order and number them sequentially to obtain the second number of each image frame.

[0052] A33. Based on the sum of the first number and the second number, the filtering number of each image frame is obtained.

[0053] A4: Select the image frame with the smallest filter number within each sub-video segment and combine them to obtain continuous action frames.

[0054] Understandably, the server will select the image frame with the smallest filter number in each sub-video segment as the representative of that sub-video segment, and combine these image frames to obtain continuous motion frames.

[0055] In other embodiments, step S13 (selecting and combining image frames from each of the sub-video segments to obtain continuous motion frames) includes B1-B2: B1 receives selection information of image frames in a sub-video segment from the user terminal, and determines the corresponding image frames as combined frames based on the selection information.

[0056] It should be noted that although automated filtering can be done efficiently, the user's final decision is crucial. When the user is not satisfied with the filtering results, they can actively intervene to make adjustments.

[0057] Therefore, the previously split sub-video segments—start, middle, and end—can be displayed to the user sequentially. Users can reselect, or manually choose a frame they are not satisfied with, and then combine the selected frames into a single frame.

[0058] B2, the combined frames are combined based on the selection order of the user terminal to obtain continuous action frames.

[0059] The user-selected frames are combined in the order of selection to obtain continuous motion frames. If only a single frame is selected, the unsatisfactory frame in the existing continuous motion frames is simply replaced; this will not be elaborated upon here.

[0060] S2, the generation module, is used to customize and generate a display base and an action model adapted to the display base based on the movement trajectory of the continuous action frames.

[0061] In some embodiments, step S2 (customizing and generating a display base and an action model adapted to the display base based on the movement trajectory of the continuous action frames) includes S21-S25: S21, construct a site model corresponding to the display location in the display video segment, and update the motion model in the continuous motion frames to the site model to obtain the display model.

[0062] It's important to note that analyzing a performer's movement trajectory requires a frame of reference, i.e., the spatial environment in which the performance takes place. This approach first constructs a relatively stable venue model as the digital stage for analysis. By sequentially placing motion models representing different postures at different moments, extracted from continuous motion frames, into this unified venue model, subsequent generation of movement trajectories becomes easier.

[0063] It is easy to understand that we will construct a venue model corresponding to the performance location in the video segment. That is, we will construct a virtual venue model corresponding to the actual performance location. The venue model is a three-dimensional environment model constructed based on the performance location in the video segment. The motion model can be based on the performer's character model in the continuous motion frames, which can reflect the performer's posture.

[0064] Understandably, the server first analyzes the background of the video clips to construct a digital model representing the performance venue. Then, it converts each selected consecutive motion frame into a 3D motion model and places them sequentially into this venue model according to their position in the video. Ultimately, this results in a complete display model that includes the venue and multiple consecutive pose motion models.

[0065] S22, connect the center points of the motion models in the display model to obtain the movement trajectory.

[0066] Understandably, the server finds the center position of each motion model, which could be the center point of the human body, and connects these points with lines, the order of the connections depending on the sequence of the actions. The resulting line represents the performer's movement trajectory during the performance.

[0067] S23, when it is determined that the length of the movement trajectory is less than the preset length, a fixed-point trajectory base is generated based on the spatial trajectory of the motion model corresponding to the preset recognition point in the displayed video segment.

[0068] It's important to note that intangible cultural heritage performances can be divided into two main categories: one type involves performances performed in one place or within a very small area, such as spinning in place; the other type requires movement over a large area, such as somersaults and dance steps. Using the same base for both types of performances fails to capture their core dynamic characteristics. Existing technology typically provides physical model bases with uniform, simple shapes. However, by judging the total length of the movement trajectory, we can effectively identify whether the performance is stationary. When the trajectory is short, it indicates the performer is essentially stationary. In this case, we no longer focus on minute displacements but instead analyze the more expressive spatial trajectories drawn by the extremities (such as hands and feet) in space, generating a stationary trajectory base that reflects this sense of dynamic movement. This solves the problem of a single base being unable to adapt to different performance types, making it convenient for users to remember and view intuitively.

[0069] In some embodiments, step S23 (generating a fixed-point trajectory base based on the spatial trajectory of the motion model corresponding to the preset recognition points in the displayed video segment) includes S231-S235: S231, Obtain the spatial trajectory of the motion model corresponding to the preset recognition points in the displayed video segment.

[0070] It should be noted that we utilize several key points on the body that best embody dynamism, such as the wrists and ankles. We obtain their respective spatial trajectories by tracking the three-dimensional positional changes of these points within a continuous motion model.

[0071] Among them, the preset recognition points refer to the key body nodes predefined on the motion model, such as the joints of the limbs. The spatial trajectory is a continuous path formed by these preset recognition points in three-dimensional space as the motion model moves.

[0072] S232, when it is determined that the spatial trajectory is a circular trajectory, the limb part with the corresponding preset recognition point is taken as the rotating part, and the first length of the longest rotating part is obtained.

[0073] Here, a circular trajectory refers to the path traced by the identification point in space that approximates a circle. The rotating part refers to the limb part that makes this circular trajectory, such as an arm or leg.

[0074] It is easy to understand that when a preset recognition point of the human body is detected to have a circular trajectory around the center position of the human body, for example, around the center point of the action model, and then an arm or leg is detected to have a circular trajectory around it, it means that the person is turning around. Then the limb part of the corresponding preset recognition point is taken as the turning part, and the first length of the longest turning part is obtained, such as the leg length. Since the person is turning, a circular base will be generated, thus reflecting the rotation.

[0075] S233, the construction radius is obtained by multiplying the preset extraction quantity and the first length, a fixed-point circular base is generated based on the construction radius, and a uniformly distributed installation groove is determined at any diameter of the fixed-point circular base based on the preset extraction quantity, thereby generating a fixed-point trajectory base.

[0076] It should be noted that we multiply the length of the rotating part (representing the rotation radius) by the preset extraction quantity to estimate the base size required to accommodate all models, and use it as the construction radius.

[0077] Understandably, we will multiply the first length by the total number of models to obtain a value as the radius of the base, and generate a circular platform accordingly. Then, the system will evenly cut several mounting grooves along any diameter of this circular base, the number of grooves being the same as the number of models, for subsequent installation of the models. See [link to documentation]. Figure 3 When the preset extraction quantity is 2, grooves are uniformly made on the diameter.

[0078] S234, when it is determined that none of the spatial trajectories are circular trajectories, the limb parts of the corresponding preset recognition points are retrieved as the action parts, and the second length of the longest action part is obtained.

[0079] It should be noted that, in addition to rotation, stationary performances also include a large number of non-rotational, reciprocating, or stretching movements, such as kicking and punching. For these types of movements, a circular base is obviously unsuitable, so a flat base is used to demonstrate the movements.

[0080] It is not difficult to understand that when the spatial trajectory is not a circular trajectory, all the limbs involved in the movement (arms, legs, etc.) are treated as the action parts, and the longest one is found, usually the leg, and its length is measured to obtain the second length.

[0081] S235, the construction side length is obtained by multiplying the preset extraction quantity and the second length, a fixed-point square base is generated based on the construction side length, and a uniformly distributed installation groove is determined at any diagonal of the fixed-point square base based on the preset extraction quantity, thereby generating a fixed-point trajectory base.

[0082] It should be noted that for non-rotational stationary movements, a square base is a more suitable choice, as it can better reflect the stability of the movement and the range of planar extension.

[0083] We multiply the length of the longest moving part by the number of models to obtain the construction side length. This method also ensures that the base size matches the range of motion and the number of models. We chose to arrange the mounting grooves on the diagonal, which maximizes the use of the square space and accommodates a large range of motion.

[0084] Understandably, the server will use the longest limb, typically the leg, multiply its length by the total number of models, and use the resulting value as the side length of the square, generating a square platform accordingly. Then, the system will evenly cut mounting grooves, matching the number of models, along any diagonal of this square base. (See...) Figure 4 When the preset extraction quantity is 2, the slots are evenly made on the diagonal.

[0085] It is easy to understand that the mounting grooves are evenly distributed along the corresponding diagonals and diameters.

[0086] S24, if the length of the moving trajectory is greater than or equal to the preset length, generate the moving trajectory base according to the moving trajectory.

[0087] It's important to note that for performances with significant positional changes, the core dynamic aesthetic lies in the movement path on the stage. A simple base wouldn't capture this. However, when the movement trajectory is determined to be long, constituting a large-scale moving performance, we directly use this trajectory itself as the core to generate the base. The shape of the base will directly map to or follow the performer's movement path, ensuring that the entire physical artwork not only showcases the performer's posture but also reproduces their movement route.

[0088] In some embodiments, step S24 (generating a movement trajectory base based on the movement trajectory) includes S241-S242: S241, obtain the extended length corresponding to the longest limb part, and translate the movement trajectory to both sides based on the extended length to obtain the translated movement trajectory.

[0089] It's important to note that when the performance is a moving performance, the movement trajectory itself is simply a line without width. If the base were directly generated based on this line, it would be too thin to provide stable support for the moving model. Therefore, this line needs to be expanded into a wide, strip-shaped area. We use the longest limb of the performer, such as the length of an outstretched arm or leg, as the basis for this expansion. This length represents the space occupied by the performer. Then, using this length as a reference, the movement trajectory line is translated and expanded to both sides. This ensures that the generated base has sufficient width to support the model while also being visually proportionate to the performer.

[0090] Among them, the longest limb usually refers to the arm or leg that the performer extends the most during the movement.

[0091] Understandably, the server first measures the length of the performer's longest outstretched limb (such as an arm) and uses this as a basis to calculate an expansion width. Then, the system shifts the movement trajectory line to the left and right by this width, resulting in two new parallel lines that become a strip-shaped path.

[0092] S242, connect the two endpoints on the same side of the translated movement trajectory, and determine uniformly distributed mounting grooves on the movement trajectory based on a preset extraction quantity to generate the movement trajectory base.

[0093] It should be noted that after translation, we obtained an open strip-shaped area with open ends. To form a closed and complete base entity, this area needs to be sealed. Furthermore, the positions for mounting the models need to be planned on the base. We will connect the endpoints on the same side of the strip-shaped area to form a closed outline, which is the final shape of the moving trajectory base. Simultaneously, along the original moving trajectory centerline, we will evenly calculate the mounting points for each model based on the number of models and set mounting grooves at these points.

[0094] Understandably, the server will seal both ends of the ribbon-like path, transforming it into a complete, closed planar shape. Then, the system will evenly plan several mounting points along the center line of this shape—the original movement trajectory—based on the total number of models to be installed, and create mounting grooves at these points. This results in a base with a shape consistent with the movement path and equipped with mounting holes. (See...) Figure 5 The number of mounting grooves is 3, evenly distributed at the base of the moving track.

[0095] S25, based on the fixed-point trajectory base and the moving trajectory base, a display base is obtained, and an action model adapted to the display base is generated.

[0096] Understandably, by statistically analyzing the fixed-point trajectory base and the moving trajectory base, a display base is obtained, and a motion model adapted to the display base is generated.

[0097] In some embodiments, step S25 (generating an action model adapted to the display base) includes S251: S251, Configure the corresponding mounting protrusions for the motion model to generate a motion model that is compatible with the display base.

[0098] The mounting protrusion is a raised structure added to the bottom for inserting into the base groove, and is generally located at the bottom of the action model, such as the foot area.

[0099] It is easy to understand that we will configure corresponding mounting protrusions on the bottom of the fixed character model. Here, the motion model will be configured with corresponding mounting protrusions to generate a motion model that is compatible with the display base. This is the existing technology. The protrusions are set on the bottom of the model through the motion shape, which makes it convenient to combine with the corresponding mounting grooves later.

[0100] In other embodiments, step S25 (generating a motion model adapted to the display base) includes: The limb part corresponding to the displayed action is obtained as the active part, and the preset recognition point of movement in the active part is determined as the movement point. The motion model is made movable by connecting the moving points and configuring the corresponding mounting protrusions to generate a motion model that is compatible with the display base.

[0101] It's easy to understand that we can also identify the joint points corresponding to the moving limbs as movement points, and then connect the moving points in the motion model. For example, when swinging an arm, we can print the corresponding joints of each character model and configure protrusions to generate a motion model that fits the display base. One method uses fixed printing, while the other allows for movable printing of the joints of multiple character models on the base, making the display more intuitive.

[0102] S3, printing module, used to control the printing device to print the display base and the corresponding motion model of the display base.

[0103] Understandably, the system will send all the pre-designed models, including the custom display base and several motion models with mounting protrusions, to the 3D printer for printing.

[0104] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods provided in the various embodiments described above.

[0105] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A virtual interactive system based on the inheritance and protection of intangible cultural heritage projects, characterized in that: include: The extraction module is used to extract continuous motion frames from intangible cultural heritage display videos based on the display actions selected by the user terminal, including AR devices. The generation module is used to customize and generate a display base and an action model adapted to the display base based on the movement trajectory of the continuous action frames. The printing module is used to control the printing device to print the display base and the corresponding motion model of the display base.

2. The system according to claim 1, characterized in that, The extraction of continuous motion frames from intangible cultural heritage display videos based on display actions selected by the user terminal, including AR devices, includes: After displaying data through AR devices, the display action selected by the user is received, and the intangible cultural heritage display video is processed based on the display time period of the display action to obtain the display video segment. Retrieve the preset extraction quantity corresponding to the display action, and perform equal splitting of the display video segment based on the preset extraction quantity to obtain multiple sub-video segments; Image frames from each of the sub-video segments are selected and combined to obtain continuous motion frames.

3. The system according to claim 2, characterized in that, The step of selecting and combining image frames from each of the sub-video segments to obtain continuous action frames includes: The first sub-video segment is used as the starting segment, the last sub-video segment is used as the ending segment, and the remaining sub-video segments are used as the middle segments. The first image frame in the starting segment is selected as the reference frame, the last image frame in the ending segment is selected as the reference frame, and the image frame in the middle position in the middle segment is selected as the reference frame. The filtering number of each image frame is determined based on the image frame's sharpness and the reference frame. Select the image frames with the smallest filter number within each sub-video segment and combine them to obtain continuous action frames.

4. The system according to claim 3, characterized in that, The step of determining the screening number of each image frame based on the image frame's sharpness and the reference frame includes: The preset number is assigned to the reference frame, and the image frames on both sides are numbered sequentially, starting from the reference frame in each sub-video segment, to obtain the first number of each image frame. Based on the clarity of the image frames in the displayed video segment, the image frames of each sub-video segment are sorted in descending order and numbered sequentially to obtain the second number of each image frame; The filtering number for each image frame is obtained by summing the first and second numbers.

5. The system according to claim 2, characterized in that, The process of customizing and generating a display base based on the movement trajectory of the continuous action frames, and an action model adapted to the display base, includes: Construct a venue model corresponding to the venue in the video segment, and update the motion model in the continuous motion frames to the venue model to obtain the display model; Connect the center points of the motion models in the display model to obtain the movement trajectory; When the length of the movement trajectory is determined to be less than the preset length, a fixed-point trajectory base is generated based on the spatial trajectory of the motion model corresponding to the preset recognition point in the displayed video segment. When the length of the movement trajectory is greater than or equal to the preset length, a movement trajectory base is generated based on the movement trajectory. Based on the fixed-point trajectory base and the moving trajectory base, a display base is obtained, and an action model adapted to the display base is generated.

6. The system according to claim 5, characterized in that, The method of generating a fixed-point trajectory base based on the spatial trajectory of the motion model corresponding to the preset recognition points in the displayed video segment includes: Obtain the spatial trajectory of the motion model corresponding to the preset recognition points in the displayed video segment; When it is determined that the spatial trajectory is a circular trajectory, the limb part with the corresponding preset recognition point is taken as the rotation part, and the first length of the longest rotation part is obtained; The construction radius is obtained by multiplying the preset extraction quantity and the first length. A fixed-point circular base is generated based on the construction radius. A uniformly distributed installation groove is determined at any diameter of the fixed-point circular base based on the preset extraction quantity, and a fixed-point trajectory base is generated. When it is determined that none of the spatial trajectories are circular, the limb parts at the corresponding preset recognition points are retrieved as the action parts, and the second length of the longest action part is obtained. The construction side length is obtained by multiplying the preset extraction quantity and the second length. A fixed-point square base is generated based on the construction side length. A uniformly distributed installation groove is determined at any diagonal of the fixed-point square base based on the preset extraction quantity, thereby generating a fixed-point trajectory base.

7. The system according to claim 5, characterized in that, The step of generating a motion trajectory base based on the motion trajectory includes: Obtain the extended length corresponding to the longest limb part, and translate the movement trajectory to both sides based on the extended length to obtain the translated movement trajectory; Connect the two endpoints on the same side of the translated movement trajectory, and determine uniformly distributed mounting grooves at the movement trajectory based on a preset extraction quantity to generate the movement trajectory base.

8. The system according to claim 5, characterized in that, The generation of the motion model adapted to the display base includes: Configure the corresponding mounting protrusions for the motion model to generate a motion model that is compatible with the display base.

9. The system according to claim 2, characterized in that, The step of selecting and combining image frames from each of the sub-video segments to obtain continuous action frames includes: Receive selection information of image frames in a sub-video segment from the user terminal, and determine the corresponding image frames as combined frames based on the selection information; The combined frames are combined based on the user's selection order to obtain continuous action frames.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, is used to implement the system according to any one of claims 1 to 9.

Images