Infrared light shadow interaction system and method

Abstract

The invention relates to the field of image processing, and discloses an infrared light shadow interaction system and method. The system comprises an image input device, an interaction main platform, an infrared interaction device and a video output device, wherein the image input device is used for acquiring a contour image drawn by a user; the interaction main platform is used for preprocessing the contour image to obtain a mask combination image, and then performing layer synthesis on the mask combination image and a preset static ancient painting material to obtain a multi-layer image; the infrared interaction equipment is used for capturing a laser point track of a user operation point; and the video output equipment is used for displaying the multi-layer image and binding the coordinate information of the laser points with the coordinate position of the mask combination image so as to control the position of the mask combination image in the multi-layer image based on the coordinate information of the laser points. According to the application, an interaction system with user input, intelligent processing and dynamic display feedback is constructed, and a whole-process closed loop from user creation, image processing and immersive interaction is realized.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to an infrared light and shadow interaction system and method. Background Art

[0002] The existing technology has non-contact control capabilities when using infrared laser point recognition to achieve wall projection interaction, but the display content is mostly preset static resources, lacks personalized generation capabilities, and cannot be deeply integrated with the AI ​​image generation mechanism. As a result, the light and shadow interaction technology has significant deficiencies in image generation freedom, infrared interaction accuracy and display level. Specifically, the light and shadow interaction has the problem of static image display. Summary of the Invention

[0003] In order to solve the problem of static image display in light and shadow interaction in the prior art, the present application provides an infrared light and shadow interaction system and method.

[0004] In a first aspect, the present application provides an infrared light and shadow interaction system, comprising: An image input device for acquiring a contour image drawn by a user; The interactive main platform is configured to receive the contour image sent by the image input device, pre-process the contour image to obtain a masked composite image, and perform layer synthesis on the masked composite image and a preset static ancient painting material to obtain a multi-layer image; the masked composite image and the static ancient painting material in the multi-layer image are respectively superimposed and displayed in the form of a single layer, and each layer is independent of each other; Infrared interactive equipment, used to capture the laser point trajectory of the user's operation point and extract the laser point coordinate information in the laser point trajectory; A video output device is used to display the multi-layer image, bind the laser point coordinate information with the coordinate position of the mask combination image in the multi-layer image, and control the position change of the mask combination image in the multi-layer image based on the laser point coordinate information to achieve dynamic visual interaction.

[0005] In an optional embodiment, the infrared interactive device includes an infrared laser lifting rod and an infrared camera; wherein the infrared camera is fixedly arranged at a target position of the video output device so that the infrared signal acquisition range of the infrared camera covers the boundary area of ​​the video output device; The infrared camera is used to capture the laser point trajectory emitted by the infrared laser lifting rod in real time when the user moves the infrared laser lifting rod.

[0006] In an optional embodiment, the preprocessing of the contour image to obtain a masked combined image includes: Call the preset picture-to-picture model to perform style processing on the contour image to obtain a lantern image with a target style. Convert the lantern image with the target style into a transparent background image. Perform image mask processing on the transparent background image to obtain a mask combined image.

[0007] In an optional implementation, the generation process of the picture-to-picture model includes: Obtain and pre-process an image sample set containing target style colored lantern elements. Perform Chinese-English bilingual labeling on each sample image in the image sample set, and embed a custom trigger word in the labeled text, the custom trigger word being bound to a style weight of the picture-to-picture model to be generated, and the custom trigger word being used to quickly trigger the picture-to-picture model to call a target style style feature. Train a Stable Diffusion model structure by using a LoRA algorithm in combination with the image sample set to obtain a picture-to-picture model with target style colored lantern element migration capability.

[0008] In an optional implementation, the obtaining and pre-processing of the image sample set containing target style colored lantern elements includes: Perform cutout and AI synthesis processing on a plurality of ancient painting images containing target style colored lantern elements, and use the obtained cutout sample images and AI sample images as an image sample set for model training. Uniformly enlarge each sample image in the image sample set to a preset pixel size by using a Real-ESRGAN deep learning super-resolution algorithm. Enhance the contours and details of each sample image after enlargement by using a preset edge enhancement algorithm, and perform color repair processing on each sample image by using a color balance algorithm.

[0009] In an optional implementation, the interactive main platform is further configured to: Verify the performance of the trained picture-to-picture model, specifically including: Obtain a lantern structure contour drawn by a user, and use the lantern structure contour as an input picture to trigger the picture-to-picture model to generate a lantern image with target style colored lantern elements based on the custom trigger word and the style weight by using the picture-to-picture model. Compare the lantern image with a lantern image in an ancient painting image corresponding to the picture-to-picture model to obtain a performance verification result of the picture-to-picture model.

[0010] In an optional implementation, the performing of image mask processing on the transparent background image to obtain a mask combined image includes: Overlay the transparent background image on the preset Circle component through the Transform component to obtain a mask image; The mask image is multiplied and synthesized with the preset AI dynamic video material to obtain a mask combined image.

[0011] In an optional embodiment, obtaining a laser point trajectory of a user operation point and extracting laser point coordinate information in the laser point trajectory includes: Acquire a real-time video stream containing the laser point trajectory of the user's operation point, and crop the image in the video stream to obtain a target processing area; the target processing area is an image area containing the screen range of the video output device; performing a blurring process on the target processing area to enhance the brightness characteristics of the laser point within the target processing area, and performing a threshold segmentation process on the blurred target processing area to separate the laser point from the target processing area, thereby obtaining laser point image data containing only the point position information of the laser point; Converting the laser point image data into geometric contour data to obtain geometric edge information of the laser point; The geometric contour data is converted into channel data to obtain the coordinate information of the laser point from the geometric edge information, and the coordinate information is normalized to map the coordinate information from the original pixel coordinate system to the standard coordinate system to obtain the laser point coordinate information.

[0012] In an optional embodiment, controlling the position of the contour image in the multi-layer image based on the laser point coordinate information includes: The horizontal coordinate and the vertical coordinate in the laser point coordinate information are respectively mapped to the displacement parameters of the contour image in the multi-layer image, so as to achieve synchronization of the coordinate position change of the laser point and the coordinate position change of the contour image in the multi-layer image.

[0013] In a second aspect, the present application provides an infrared light and shadow interaction method, which is applied to the aforementioned infrared light and shadow interaction system, and the method includes: Get the outline image drawn by the user; After pre-processing the outline image, a masked composite image is obtained, and the masked composite image is layer-synthesized with a preset static ancient painting material to obtain a multi-layer image; the masked composite image and the static ancient painting material in the multi-layer image are respectively superimposed and displayed in the form of single layers, and each layer is independent of each other; Obtaining a laser point trajectory of a user operation point and extracting laser point coordinate information in the laser point trajectory; The laser point coordinate information is bound to the coordinate position of the mask combination image in the multi-layer image, so as to control the position change of the mask combination image in the multi-layer image based on the laser point coordinate information to achieve dynamic visual interaction.

[0014] The embodiments of the present application have the following beneficial effects: The embodiment of the present application provides an infrared light and shadow interaction system. Through the deep integration of intelligent image processing and infrared laser interaction, an interactive system with user input drive, intelligent image processing, and dynamic display feedback is constructed. Combined with layer synthesis and dynamic control technology, real-time dynamic interaction between images and videos is realized, and an integrated system closed loop of input-image generation-interaction-display is constructed; it breaks through the limitations of traditional technologies in content generation freedom, interaction accuracy and display level, and realizes a full-process closed loop from user creation to image processing output to immersive interaction, while also improving the interaction freedom, visual expression and cultural immersion. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To more clearly illustrate the technical solution of this application, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of this application and should not be considered as limiting the scope of protection of this application. Those skilled in the art can also derive other relevant drawings based on these drawings without inventive effort.

[0016] Figure 1 A schematic structural diagram of an infrared light and shadow interaction system in an embodiment of the present application is shown; Figure 2 A schematic diagram of a flow chart of the infrared light and shadow interaction method in an embodiment of the present application is shown; Figure 3 A schematic diagram of an interactive interface of an image input device in an embodiment of the present application is shown; Figure 4 A schematic diagram showing a process of generating a graph model in an embodiment of the present application is shown; Figure 5 A schematic diagram of a sample image containing a target style colored light element in an embodiment of the present application is shown; Figure 6 A schematic diagram of an image of a static ancient painting material in an embodiment of the present application is shown; Figure 7 A static schematic diagram of an image frame in a multi-layer image in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0018] The components of the embodiments of the present application generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but rather merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort are within the scope of protection of the present application.

[0019] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0020] Furthermore, the terms “first,” “second,” “third,” etc., are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0021] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0022] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0023] The embodiment of the present application provides an infrared light and shadow interaction system, wherein, Figure 1 As shown, the system includes an image input device 110 , an interactive main platform 120 , an infrared interactive device 130 and a video output device 140 .

[0024] The embodiment draws the contour image of an arbitrary object on the image input device 110, and the interactive main platform 120 obtains a multi-layer image with multiple superimposed layers and independent of each other after a series of preset processing on the contour image, and the multi-layer image contains a mask layer; the video output device 140 displays the multi-layer image; in this process, the infrared laser output by the infrared interactive device 130 falls within the image display area of the video output device 140, and the laser point coordinates of the infrared laser in the image display area are bound to the coordinate position of the mask combination image in the multi-layer image, so as to indirectly control the position change of the mask combination image in the multi-layer image through the coordinate position change of the infrared laser, and realize the dynamic interaction of light and shadow.

[0025] The contour image of an arbitrary object in the embodiment is only exemplified by taking a lantern as an example.

[0026] By way of reference, the image input device 110 is used to obtain the contour image of an arbitrary object drawn by a user (the arbitrary object is taken as a lantern, and the contour image here and below refers to the contour image of the lantern).

[0027] That is, the user draws the contour image of the target object by hand on the drawing area of the image input device 110, so that the image input device 110 obtains the electronic contour image from the drawing area and sends the contour image to the interactive main platform 120.

[0028] Optionally, the image input device 110 and the interactive main platform 120 can not directly establish communication, but realize data interaction based on an intermediate device; that is, the image input device 110 can be used as a receiving image intermediate machine, and the contour image recognized in the drawing area is transmitted to an upper machine, and the upper machine transmits the contour image to the interactive main platform 120.

[0029] It should be noted that the communication architecture and the composition of the communication line between the image input device 110 and the interactive main platform 120 can be set according to actual needs, as long as the dynamic interaction of light and shadow can be realized in combination with other parts of the interactive system.

[0030] The interactive main platform 120 is used to receive the contour image, obtain a mask combination image after preprocessing the contour image, perform layer synthesis on the mask combination image and a preset static ancient painting material, and obtain a multi-layer image. The mask combination image contains a mask layer and a bottom layer, and the mask layer is embedded with the contour image after preprocessing.

[0031] Specifically, the interactive main platform 120 pre-processes the outline image to generate a specific masked composite image, and then combines it with the preset static ancient painting material to form a multi-layer image. The masked composite image and the static ancient painting material in the multi-layer image are each displayed as a single layer, and each layer is independent of each other. In other words, editing the content of any layer in the multi-layer image does not affect the content of other layers, and the content visibility of each layer in the multi-layer image is also independent of each other.

[0032] In one example, the interactive main platform 120 includes a LoRA image generation module and a mask synthesis module; wherein, the LoRA image generation module is used to parse the contour image to form dynamically recognizable graphic boundary data, and then call the locally pre-deployed graphic model to perform a series of processes such as stylization to obtain a transparent background image with a target style; the mask synthesis module is used to perform image masking on the transparent background image, and then perform layer synthesis on it with a preset static ancient painting material to obtain a multi-layer image.

[0033] Optionally, the interactive main platform 120 is a programming development platform with visual interactive creation. The interactive main platform 120 can be independently developed and designed or call an existing development platform, which is not limited in this embodiment; for example, the interactive main platform 120 can be a TouchDesigner platform, etc.

[0034] Furthermore, the infrared interactive device 130 is used to capture the laser point trajectory of the user's operation point and extract the laser point coordinate information in the laser point trajectory.

[0035] In one embodiment, the infrared interactive device 130 includes an infrared laser lifting rod and an infrared camera; wherein the infrared camera is fixedly set at the target position of the video output device 140 so that the infrared signal acquisition range of the infrared camera covers the boundary area of ​​the video output device 140; the infrared camera is used to capture the laser point trajectory emitted by the infrared laser lifting rod in real time when the user moves the infrared laser lifting rod.

[0036] It can be understood that the user interacts with the multi-layer image displayed on the video output device 140 by moving the infrared laser lifting rod. The infrared laser lifting rod emits infrared laser during the movement process, and the infrared laser falls on the display screen (i.e., the image display area) of the video output device 140 to form a laser point trajectory. The laser point trajectory represents the user's laser pointing operation; the infrared camera is used to capture the laser point trajectory of the infrared laser output by the infrared laser lifting rod in real time.

[0037] It is required to note that the infrared laser positioning has a clear and controllable signal source, accurate identification and is not affected by the background and shielding; and the fixedly installed infrared camera can capture the laser point position at a high frequency, realizing millisecond-level response; further, the laser beam trajectory emitted by the infrared laser lifting rod is clear and stable, which can be mapped to fine movement control, and the entity infrared laser lifting rod can strengthen the user's tactile feedback and on-site atmosphere feeling of interaction, and improve the ritual and participation of the exhibition. The form of the infrared laser lifting rod is not limited, and in actual scenes, it can be replaced by devices or apparatuses with infrared laser emission capability, such as a laser pen.

[0038] Further, the video output device 140 is used to display the multi-layer image, bind the laser point coordinate information with the coordinate position of the mask combined image in the multi-layer image, control the position change of the mask combined image in the multi-layer image based on the laser point coordinate information, realize dynamic visual interaction, and further, the user controls the laser displacement emitted by the infrared laser lifting rod, and correspondingly controls the position or rotation angle of the mask combined image in the multi-layer image.

[0039] Optionally, the video output device 140 includes electronic devices such as display screens, projectors and the like, which have the functions of directly receiving video signals and displaying image pictures; for example, the video output device 140 can be a MAXHUB large screen.

[0040] For example, the embodiment adopts TouchDesigner to build the interaction main platform 120, and is assisted by drawing electronic devices, infrared laser lifting rods, infrared cameras, MAXHUB large screens and the like, and hardware and software modules are cooperatively operated to realize a complete closed-loop process from user input to dynamic interaction output.

[0041] As an optional implementation, the system adopts a sensing device to replace the infrared interaction device 130 to identify the user's gestures through the sensing device, and further, in the process of displaying the multi-layer image by the video output device 140, the position of the mask combined image in the multi-layer image is controlled through the gestures to realize dynamic visual interaction. The sensing device can be a camera or other electronic devices with camera or gesture recognition functions.

[0042] The embodiment of the present application processes the contour image drawn by the user through the infrared light and shadow interaction system to obtain the mask combined image, then combines the mask combined image with the static ancient painting material to obtain the multi-layer image, and controls the position of the mask combined image in the combined multi-layer image through the laser point trajectory of the operation point captured by the infrared, and further realizes the real-time interaction control of the user on the dynamic visual effect through the infrared laser.

[0043] Please refer to Figure 2The embodiment of the present application also provides an infrared light and shadow interaction method, which is applied to the infrared light and shadow interaction system as described above, wherein Figure 2 As shown, the method includes the following steps: S210: Acquire a contour image drawn by a user.

[0044] S220 , pre-processing the outline image to obtain a mask combination image, and synthesizing the mask combination image with a preset static ancient painting material to obtain a multi-layer image.

[0045] In this embodiment, a contour image manually drawn by a user is obtained through the image input device 110, and then the interactive main platform 120 preprocesses the contour image, wherein the preprocessing includes stylization processing, background transparency processing, image masking processing and other processes.

[0046] As an optional implementation, the interactive main platform 120 analyzes the outline image using a preset image analysis algorithm before stylizing the outline image. Optionally, during the analysis process, this embodiment may also use a contour detection algorithm to extract contour information from the analyzed outline image data, then select the primary contour that best matches the lantern outline and extract boundary coordinate data from the primary contour. The specific operations and algorithms used in this image analysis process can be configured based on actual needs and are not limited in this embodiment.

[0047] Furthermore, the interactive main platform 120 calls a preset image-generating model, performs stylization processing on the outline image, and then converts it into a transparent background image.

[0048] In one example, the open-source ComfyUI-To-TD plug-in interface is built into the main interactive platform 120 to connect to the ComfyUI graphical generation platform, thereby invoking the functionality of the ComfyUI graphical generation platform's local image generation model (such as Stable Diffusion). Specifically, this embodiment uses the locally pre-deployed image generation model to convert the outline image into a transparent background image (such as a PNG format image) with the target style colored light elements.

[0049] In another example, the program framework of the ComfyUI graphical generation platform can be built inside the interactive main platform 120, so that it can directly have the image processing function of the ComfyUI graphical generation platform, and then directly call the image generation model within the ComfyUI graphical generation platform framework inside the interactive main platform 120 to convert the contour image into a corresponding transparent background image.

[0050] It should be understood that this embodiment does not impose too many restrictions on the relationship or structure between the interactive main platform 120 and the ComfyUI graphical generation platform, as long as the corresponding functions can be combined to achieve the relevant image processing described in this article.

[0051] Alternatively, in a practical scenario, Figure 3 As shown, the user draws a hand-drawn outline image on the image input device 110, and the interactive main platform 120 calls the image generation model to perform a series of processing (such as stylization and background transparency) on the outline image to obtain a transparent background image with the target style. The transparent background image is then synchronously displayed to the user through the image input device 110. During this process, the interactive main platform 120 also performs image masking and layer synthesis on the transparent background image with the target style.

[0052] In actual scenarios, the user can redraw the contour image multiple times through the image input device 110. For example, the image input device 110 identifies the contour image in the target drawing box on the display interface, and only saves the contour image in the current target drawing box after receiving the response information generated when the user triggers the "Done" button or component on the display interface, and uses it as the target contour image for subsequent processing and transmits it to the interactive main platform 120.

[0053] If the image input device 110 receives a response message generated when the user triggers a "redraw" button or component on the display interface during the user's drawing process, the outline image in the current target drawing frame is cleared.

[0054] After the interactive main platform 120 processes the outline image transmitted by the image input device 110 accordingly, it outputs a transparent background image with a target style to the image input device 110, and then the image input device 110 transmits the transparent background image to the target display frame on the display interface for display.

[0055] In one embodiment, the interactive main platform 120 may convert the outline image into a masked composite image and then transmit the masked composite image to the image input device 110, causing the image input device 110 to display the masked composite image within a target display frame on the display interface. In other words, the object displayed within the target display frame on the display interface of the image input device 110 may be a transparent background image with a target style or a masked composite image, which is not limited in this embodiment.

[0056] As an optional implementation, the image-generated model can also be installed in the image input device 110. When the image input device 110 recognizes the image in the painting area, it can call the local image-generated model for processing, and then transmit the processed transparent background image with the target style to the interactive main platform 120 for the next processing (i.e., image mask processing and layer synthesis processing).

[0057] The graph-based graph model can be pre-trained; in one embodiment, Figure 4 As shown in Figure 2, the generation process of the graph model includes the following steps: S410: Acquire and pre-process an image sample set containing target style colored light elements.

[0058] Perform cutout and AI synthesis processing on multiple painting images containing target style lantern elements, and use the obtained cutout sample images and AI sample images as the image sample set for model training. The image sample set contains multiple cutout sample images and multiple AI sample images. The number of images contained in the image sample set is not limited here. Among them, the target style lantern elements are specifically set according to actual needs and are not limited to this. This embodiment takes the target style as the Bianjing lantern elements as an example. Figure 5 As shown, the painting image is an ancient painting image containing elements of ancient Bianjing lanterns.

[0059] Furthermore, we collected ancient paintings containing elements of ancient Bianjing lanterns from an image repository, such as works on ancient palace themes. The required image data was obtained from these ancient paintings in a high-resolution (no less than 2K) digital format to ensure image quality and processability. Subsequently, through an image annotation and segmentation process, we used image editing tools (such as Photoshop) to accurately extract the lantern areas within the image data, removing the background and generating images with a uniform white background (e.g., PNG format). Next, we employed a uniform cropping ratio and composition method to ensure that each white background image maintained a centered subject and clear composition. This resulted in a collection of images of ancient Bianjing lanterns that exhibited both stylistic purity and data consistency, serving as the image sample set.

[0060] In one example, because original ancient paintings of Bianjing lanterns often suffer from low resolution, blurred lines, and degraded colors, the image sample set can be preprocessed before being used as training samples for model training to systematically optimize image quality, thereby improving the accuracy of subsequent model training. This preprocessing process can be implemented by the AI ​​image processing module within the interactive main platform 120; this preprocessing includes, but is not limited to, image magnification, image enhancement, and image equalization.

[0061] For example, the Real-ESRGAN deep learning super-resolution algorithm is used to uniformly enlarge each sample image in the image sample set to a preset pixel size to meet the size requirements of subsequent model training. The preset pixel size is set according to actual needs and is not limited to this. For example, the preset pixel size is 1024×1024 pixels. Next, a preset edge enhancement algorithm is used to enhance the contours and details of each enlarged sample image to strengthen the pattern contours and structural details and improve the image's process restoration degree; then, a color balancing algorithm is used to perform color restoration on each sample image to automatically repair the image hue, saturation, and light and dark contrast. In addition, this embodiment can also perform a series of image enhancement processes (such as rotation, mirroring, scaling, etc.) on the images after the above preprocessing to effectively improve the diversity of training samples and the style generalization ability of the model.

[0062] All sample images obtained after the above processing are unified into images with centralized composition, transparent background, and resolution of 1024×1024 to ensure style consistency and training stability.

[0063] S420: Annotate each sample image in the image sample set in both Chinese and English, and embed a custom trigger word in the annotated text. The custom trigger word is bound to the style weight of the image-generated model to be generated. The custom trigger word is used to quickly trigger the image-generated model to call the style features of the target style.

[0064] Each sample image in the image sample set is annotated with the Prompt keyword, using both Chinese and English to enhance the model's cross-semantic generation capabilities. For example, the English annotation text might be: "deng, a lantern, Song Dynasty, imperial lantern, silk texture, ancient Chinese craft style, white background"; the Chinese annotation text might be: "lantern, a lantern, ancient, palace lantern, silk texture, ancient Chinese craft style, white background." All images form a one-to-one correspondence with the Prompt keyword annotated text as training samples.

[0065] Next, to further improve the consistency of style activation and the stability of model reasoning, a custom trigger word (such as "deng") is uniformly embedded in all Prompt keyword annotated texts. This custom keyword will be bound to the style weight of the graph-based model during the subsequent model training process, and serve as a semantic anchor point for calling the graph-based model in the reasoning stage. It can then be used to quickly activate the specific style features of the "ancient Bianjing lantern style" when the graph-based model converts the user's hand-drawn outline image into a transparent background image with the style of ancient Bianjing lanterns, thereby improving the style recognition and calling efficiency of the graph-based model.

[0066] S430, uses the LoRA algorithm combined with the image sample set to train the Stable Diffusion model structure, and obtains an image-based model with the ability to migrate target style lantern elements.

[0067] This embodiment aims to build an efficient, low-resource, and highly adaptable image-to-image model with style transfer capabilities. Specifically, it uses the Stable Diffusion model structure (such as Stable Diffusion XL (SDXL) 1.0) as the model backbone architecture and adopts the LoRA (Low-Rank Adaptation) algorithm for fine-tuning modeling to achieve high-fidelity transfer and image generation of the style of ancient Bianjing lanterns.

[0068] For further example, the model was trained using the Kohya-SS open-source trainer. The core parameters were set as follows: Alpha 8, learning rate 1e-4, 10 training epochs, batch size 2, AdamW optimizer, and fp16 half-precision hybrid training to conserve graphics memory and improve computational efficiency. Furthermore, the model training employed a caption + image pairing input mechanism, and within the model architecture, a weight decoupling tuning strategy was implemented for the Text Encoder and UNet modules. This ensured that LoRA parameters were applied only to key submodules, enabling precise adaptation to the target style while retaining the general capabilities of the large model, ensuring high fidelity in image detail, composition, and texture. The final model was exported in the .safetensors format, containing only weight differential parameters, keeping the file size under 160MB. This allows for flexible deployment and multi-style fusion, making it suitable for the ComfyUI graphical generation platform, enabling efficient dynamic generation tasks with multiple styles coexisting.

[0069] In one embodiment, this embodiment also involves performance verification of the trained image-generated image model; specifically, after the interactive main platform 120 obtains the lantern structure outline drawn by the user through the image input device 110, it adopts the image-generated image mode and uses the lantern structure outline as the input image to trigger the image-generated image model to generate a lantern image with target style lantern elements based on custom trigger words and style weights; the lantern image is compared with the lantern image in the ancient painting image corresponding to the image-generated image mode to obtain the performance verification result of the image-generated image model.

[0070] For example, after the image-generated model is trained, it is loaded into the ComfyUI graphical generation platform and its stylistic expressiveness is verified through an image generation workflow. During the verification process, the image-generated model uses an image-generated mode, allowing users to manually draw the outline of a lantern structure using the outline sketching panel (or image input device 110) as an input to guide the generation process. The image-generated model, combined with the prompt trigger word "deng" and style weight information, generates a complete image of ancient Bianjing lanterns. This process verifies the image-generated model's adaptability and ability to reproduce the target style under structural control, providing a foundation for stable style output for the infrared light and shadow interaction system. Furthermore, the transparent background image output by the image-generated model is compared with the lantern image in the original ancient painting. Visual metrics such as color reproduction, detail preservation, structural symmetry, and stylistic consistency are evaluated to ensure that the model output image has a high degree of cultural reproducibility. Furthermore, the model output is further integrated with the main interactive platform 120, enabling real-time transmission and access of the model output image.

[0071] Furthermore, the interactive main platform 120 uses the trained image-to-image model to convert the user's hand-drawn outline image into a transparent background image with the target style. The transparent background image is then masked and layered with the preset static ancient painting material to produce a multi-layer image. The multi-layer image is a dynamic video.

[0072] Specifically, a transparent background image with the target style is superimposed on a Circle component within the ComfyUI graphical generation platform or the ComfyUI graphical generation platform embedded in the interactive main platform 120 using a Transform component to obtain a mask image; the mask image is multiplied and synthesized with a preset AI dynamic video material to obtain a masked composite image; and the masked composite image is synthesized with a preset static ancient painting material to obtain a multi-layered image. The Circle component is used to draw a circle and supports setting properties such as circle size, fill color, and border color.

[0073] Exemplarily, the preset static ancient picture material can be pre-processed by AI technology for picture restoration; the preset AI dynamic video material is a dynamic scroll video constructed based on the static ancient painting material (i.e. the static ancient picture material) containing the lantern festival scene by using AI technology, and the video content includes typical scenes such as streets, bridges and lantern festivals generated based on AI image restoration and material enhancement. As shown in Figure 6 , the “River at Qingming Festival” is taken as the static ancient picture material for example. The related processing process of the AI technology involved in the static ancient picture material and the AI dynamic video material can be set and processed according to actual needs, and the embodiment is not limited thereto.

[0074] Further, the static ancient painting material (i.e. the static ancient picture material) and the AI dynamic video material pre-produced are respectively imported through two Movie File In TOP nodes in the interactive main platform 120. The two materials are preliminarily combined by using the Composite TOP node to provide a basis for subsequent image mask processing.

[0075] Then, a corresponding Circle component is added in the interactive main platform 120, and the transparent background image with the target style output by the image generation model is superimposed on the Circle component by using the Transform component in the “over” mode. The edge feathering value and brightness of the Circle component are adjusted, and the transparent background image is vertically and horizontally centered and aligned with the Circle component. The Transform component combines the two, and outputs a mask image.

[0076] To define the mask area, the mask image produced by the Transform component in the above step is connected to the AI dynamic video material, and the output parameter “Combine with Input” is set to “Set Resolution Only” to ensure that the output image only contains the resolution information of the mask area, without introducing other image content.

[0077] In the process of connecting the mask image to the AI dynamic video material, the mask image and the AI dynamic video material are connected together by using the Multiply TOP component for multiplication synthesis to obtain a mask combined image. Since the RGB values of the transparent background area in the mask image are all 0, and the RGB values of the circular area and the color lamp outline in the transparent background image are all 1; after multiplying the mask image and the AI dynamic video material, the RGB values of the transparent area remain 0, and the circular area and the color lamp outline area can be preserved in the video content, achieving the effect of displaying the video only in the circular area.

[0078] Next, use the Composite TOP node to combine the processed Circle video mask effect (i.e., the masked composite image) with the static ancient painting material to form the final output image (i.e., the multi-layered image). In other words, in the Composite component, the static ancient painting material is overlaid on the AI ​​dynamic video material to achieve the infrared flashlight mask effect.

[0079] In short, the interactive main platform 120 can realize the synthesis of multiple layers. The multi-layer image includes multiple layers, specifically a static ancient painting layer, an AI dynamic video layer, and a mask layer that can be controlled by the user. Among them, the lantern image in the mask layer is the mask combination image with the target style bound to the Circle component. Figure 7 As shown, you can get an image with multiple layers superimposed (i.e., a multi-layer image).

[0080] Clearly, the final image displayed by video output device 140 utilizes a dual-layer overlay mechanism, with the upper layer being the static ancient painting layer and the lower layer being the AI ​​dynamic video material. The user-controlled Circle component area (i.e., the mask layer) acts as a mask window, displaying the underlying dynamic content in its location while the unmasked area remains static. In other words, in the image displayed by video output device 140, the masked composite image and the static ancient painting material are each displayed as a single layer, and each layer is independent of the other. As a result, in the image, only the masked composite image portion appears as dynamic video, while the rest of the image is static.

[0081] It can be understood that based on this infrared light and shadow interactive system, users can first draw the structural outline of the lantern, and then generate a corresponding transparent background image with the style elements of ancient Bianjing lanterns through the image-generated model. After masking and combining it with the AI ​​dynamic video, it is layered with static ancient painting materials to obtain a multi-layer image. This multi-layer image is synchronized and displayed on the video output device 140, realizing the complete process from structural input to style generation to multimedia presentation. The system forms an end-to-end cultural content generation chain from lantern structural outline construction to image style generation and real-time interactive display, which can be widely used in multiple application scenarios such as lantern art creation assistance and digital interpretation of intangible cultural heritage elements.

[0082] S230: Obtain a laser point trajectory of the user operation point, and extract laser point coordinate information in the laser point trajectory.

[0083] In this embodiment, the interactive main platform 120 captures the laser point trajectory of the user's operation point, and then binds the coordinate information of the laser point trajectory with the coordinate information of the lantern image in the multi-layer image displayed in the video output device 140 to achieve interactive control of the lantern image.

[0084] As a further example, a real-time video stream including the laser point trajectory of the user operation point is first obtained, and the image in the video stream is cropped to obtain a target processing area; wherein, the target processing area is an image area including the screen range image of the video output device 140.

[0085] Next, the target processing area is blurred to enhance the brightness characteristics of the laser point in the target processing area, and the blurred target processing area is threshold segmented to separate the laser point from the target processing area to obtain laser point image data containing only the point position information of the laser point.

[0086] Then, the laser point image data is converted into geometric contour data to obtain the geometric edge information of the laser point; the geometric contour data is converted into channel data to obtain the coordinate information of the laser point from the geometric edge information, and the coordinate information is normalized to map the coordinate information from the original pixel coordinate system to the standard coordinate system to obtain the laser point coordinate information.

[0087] It can be understood that based on the composition structure of the above-mentioned infrared light and shadow interaction system, in an actual scenario, the user holds an infrared laser lifting rod with an infrared laser function and performs laser pointing operations on the video output device 140. The infrared camera arranged at a fixed position of the video output device 140 captures in real time the infrared laser point trajectory emitted by the infrared laser lifting rod that only appears within the screen range of the video output device 140.

[0088] In the interactive main platform 120, the infrared camera is connected via the Video Device In component to obtain a real-time video stream. To ensure processing efficiency and accuracy, the Crop component is used to crop the image in the real-time video stream, limiting the processing area to capture only the screen area of ​​the video output device 140. Subsequently, the Blur TOP component is used to blur the image within the limited processing area to enhance the brightness characteristics of the laser point. Threshold TOP is used to perform threshold processing to separate the laser point from the background, resulting in an image containing only the laser point position information (i.e., laser point image data).

[0089] Convert images containing only laser point information into geometric outline data using the Trace SOP to extract the edge information of the laser point. Use the SOP to CHOP to convert the geometric outline data into channel data to obtain the horizontal and vertical coordinates of the laser point (i.e., X (tx) and Y (ty) coordinates). Select the X and Y channels using the Select CHOP, and use the Math CHOP to normalize the horizontal and vertical coordinate data, mapping it from the original pixel coordinate system to a standardized range of 0 to 1 to match the coordinate system of subsequent graphics. Furthermore, the normalized coordinate data can be cached using the Null CHOP to ensure data stability and accessibility.

[0090] S240, binding the laser point coordinate information with the coordinate position of the mask combination image in the multi-layer image, so as to control the position change of the mask combination image in the multi-layer image based on the laser point coordinate information, thereby realizing dynamic visual interaction.

[0091] In this embodiment, the video output device 140 maps the horizontal coordinate and vertical coordinate in the laser point coordinate information to the displacement parameters of the mask combination image in the multi-layer image, so as to bind the laser point coordinate information with the coordinate position of the mask combination image in the multi-layer image, thereby realizing the synchronization of the laser point coordinate position change and the mask combination image coordinate position change in the multi-layer image.

[0092] As a further example, the X and Y coordinates of the laser point after normalization in the previous step are mapped to the displacement parameters of the mask window respectively, so as to achieve real-time synchronization between the laser point position and the mask image position, allowing the user to directly control the movement direction and movement position of the mask image in the multi-layer image through physical laser movements.

[0093] That is, by identifying the coordinates of the laser point and binding the coordinates of the laser point with the coordinates of the mask image in the mask combination image, when the position of the laser point is identified to change, the mask image is controlled to move to the pointing position of the laser point in the multi-layer image accordingly, so as to achieve synchronous movement of the positions of the laser point and the mask image. When the user holds and moves the infrared laser lifting rod, the mask image in the multi-layer image can move with the movement of the lifting rod, thereby completing the interaction between light and shadow.

[0094] In another embodiment, the video output device 140 may only implement image display and infrared signal capture functions, while the interactive main platform 120 binds the coordinates of the laser point with the coordinates of the mask image in the mask combination image, and then, when it is recognized that the position of the laser point has changed, the mask image is controlled to move to the pointing position of the laser point in the multi-layer image accordingly, so as to achieve synchronous movement of the positions of the laser point and the mask image, and the control effect of this process is displayed through the video output device 140; for example, the video output device 140 captures the laser point trajectory or laser point position of the user operation point through infrared, and then sends the laser point trajectory or laser point position to the interactive main platform 120 in real time. The interactive main platform 120 identifies the coordinates of the laser point in the display area of ​​the video output device 140 based on the received laser point trajectory or laser point position, and then binds the coordinates of the laser point with the coordinates of the mask image in the mask combination image. Then, when it is determined that the position of the laser point has changed based on the received laser point position, the mask image is controlled to move to the pointing position of the laser point in the multi-layer image through the video output device 140.

[0095] That is, both the video output device 140 and the interactive main platform 120 can implement the binding process of the laser point position coordinates and the mask image position coordinates, and the specific execution device of the process is not limited here.

[0096] In actual scenarios, the user can control the movement of the lantern image in the multi-image image in the video output device 140 by moving the infrared laser lifting rod, thereby achieving the effect of long-distance light and shadow interaction between the infrared laser and the lantern image.

[0097] As can be understood, the user inputs an image by hand-drawing the outline of a lantern, and the interactive system invokes the image generation model to perform stylized processing to generate a transparent background image in the style of ancient Bianjing lanterns. This image is then masked and layered to output a multi-layered image. An infrared laser device is used to achieve real-time control of the movement position and direction of the masked image within the multi-layered image. Ultimately, multi-layer synthesis and dynamic visual interaction are achieved within the interactive main platform 120, thus completing a closed loop from user input to image generation to dynamic display, enhancing interactive freedom, visual expressiveness, and cultural immersion. Users experience an immersive cultural experience, from "hand-drawn lantern generation" to "laser-controlled lantern movement" to "lighting up dynamic night tour scenes," creating an innovative fusion of traditional aesthetics and digital image generation.

[0098] Among them, by integrating infrared laser interaction technology and the stable diffusion image generation model fine-tuned by low-rank adaptation (LoRA), an end-to-end system process is realized from user hand-drawn input to personalized image generation, and then to multi-layer dynamic synthesis display. It breaks through the limitations of existing technologies in interaction depth, image content generation freedom, dynamic visual feedback, etc., and overall achieves higher freedom of content creation, more immersive visual experience and more accurate physical interaction response.

[0099] Furthermore, compared to traditional infrared interactive systems that can only trigger modes with preset image content, users can only perform simple response operations (such as zooming in, replacing, etc.) within limited projected content, lacking the ability to create content based on the user's subjective intentions. The embodiment of the present application introduces a user-defined drawing input and real-time generation mechanism for image-generated models at the interactive front end, allowing users to input lantern outline structure information through free hand-drawing, and combined with the Prompt keyword trigger mechanism, to achieve active definition and precise guidance of image content. User input is not limited to geometric outlines, but can also attach semantic tags, participating in the content control process before generating images, greatly enhancing the creative expression space and controllability of the interaction, and possessing a high degree of personalization, unpredictability, and creative freedom. Through this "creation-generation-fusion" mechanism, a closed content loop from user input to image output is achieved, significantly improving the system's generation dynamics and interactive openness.

[0100] Secondly, in terms of image control methods, compared with the existing technology that only uses prompt words as input parameters and lacks image control paths in the user behavior dimension, this application combines the structural guidance mechanism of ControlNet to generate artistic images with both ancient aesthetics and modern graphic quality based on the lantern outline drawn by the user, taking into account the flexibility of hand-drawing and the quality stability of AI generation.

[0101] Moreover, the application of traditional image generation systems mostly stays at the level of single-image display or offline output, lacking deep binding with real-time interactive devices, especially in terms of dynamic multi-layer synthesis. There is an obvious gap. The present application realizes the real-time binding and layer synthesis of generated images and dynamic video materials through the interactive main platform 120, and constructs a three-layer structure of static ancient paintings-interactive mask windows-underlying dynamic videos, thereby forming a composite visual effect of interactive triggering-local dynamic visualization-overall static control, and enhancing the correlation between visual rhythm and user feedback. The synthesis logic realizes the dynamic introduction of generated content in fixed scenes. This control method not only improves the spatial accuracy of interaction, but also enhances the user's subjective sense of control through the binding between physical behavior and image movement, making the display effect immersive, responsive, and multi-dimensional. It has obvious applicability advantages in scenes such as cultural exhibitions, public art, and interactive entertainment.

[0102] In addition, in terms of the construction of visual content, this application digitally reconstructs static ancient painting scenes through AI modeling and physical rendering methods to obtain AI dynamic video materials. This AI dynamic video material not only restores spatial structures such as Bianjing street scenes, water systems, pavilions, etc., but also realistically reconstructs lantern styles, lighting logic, and environmental dynamic effects based on material properties. Details such as the swaying of lanterns, the flickering of candlelight, and the refraction of water waves enhance the realism and artistry of cultural expression, enabling the entire system to achieve a high degree of integration between cultural reproduction and technological realization, solving the problems in existing technologies of lack of dynamic expression in static pictures and lack of cultural precipitation in interactive content.

[0103] Based on this, this application has made systematic improvements in multiple dimensions, which not only enhances the interactive capabilities and content customization of AI image generation, but also enhances the real-time linkage between user participation behavior and image visual output. Ultimately, it has achieved significant technical improvements in cultural expression effects, interactive experience methods and visual presentation quality.

[0104] An embodiment of the present application further provides a computer device. Exemplarily, the computer device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program, thereby causing the computer device to execute the above-mentioned infrared light and shadow interaction method.

[0105] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0106] The memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), and electrically erasable programmable read-only memory (EEPROM). The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving an execution instruction.

[0107] The present application also provides a computer storage medium for storing the computer program used in the above-mentioned computer device. The computer storage medium may be a readable storage medium, a non-volatile storage medium, or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or flowchart, and the combination of boxes in the structure diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0109] In addition, the functional modules or units in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0110] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a smart phone, personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0111] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. An infrared light and shadow interactive system, characterized in that: include: An image input device for acquiring a contour image drawn by a user; The interactive main platform is configured to receive the contour image sent by the image input device, pre-process the contour image to obtain a masked composite image, and perform layer synthesis on the masked composite image and a preset static ancient painting material to obtain a multi-layer image; the masked composite image and the static ancient painting material in the multi-layer image are respectively superimposed and displayed in the form of a single layer, and each layer is independent of each other; Infrared interactive equipment, used to capture the laser point trajectory of the user's operation point and extract the laser point coordinate information in the laser point trajectory; A video output device is used to display the multi-layer image, bind the laser point coordinate information with the coordinate position of the mask combination image in the multi-layer image, and control the position change of the mask combination image in the multi-layer image based on the laser point coordinate information to achieve dynamic visual interaction.

2. The infrared light and shadow interactive system according to claim 1, characterized in that: The infrared interactive device includes an infrared laser lifting rod and an infrared camera; wherein the infrared camera is fixedly arranged at the target position of the video output device so that the infrared signal acquisition range of the infrared camera covers the boundary area of ​​the video output device; The infrared camera is used to capture the laser point trajectory emitted by the infrared laser lifting rod in real time when the user moves the infrared laser lifting rod.

3. The infrared light and shadow interactive system according to claim 1, characterized in that: The preprocessing of the contour image to obtain a masked combined image comprises: Calling a preset image-generated image model to perform stylization processing on the outline image to obtain a lantern image with a target style; Converting the lantern image with the target style into a transparent background image; Perform image masking processing on the transparent background image to obtain a masked combined image.

4. The infrared light and shadow interactive system according to claim 3, characterized in that: The generation process of the graph-based graph model includes: Obtain and preprocess an image sample set containing target style lighting elements; Annotate each sample image in the image sample set in both Chinese and English, and embed a custom trigger word in the annotated text. The custom trigger word is bound to the style weight of the image-generated graph model to be generated. The custom trigger word is used to quickly trigger the image-generated graph model to call the style features of the target style. The LoRA algorithm is used in combination with the image sample set to train the Stable Diffusion model structure, and an image-based model with the ability to migrate target style lantern elements is obtained.

5. The infrared light and shadow interactive system according to claim 4, characterized in that: The step of obtaining and preprocessing an image sample set containing target style colored light elements includes: Perform cutout and AI synthesis processing on multiple ancient painting images containing target style lantern elements, and use the resulting cutout sample images and AI sample images as the image sample set for model training; Using the Real-ESRGAN deep learning super-resolution algorithm to uniformly enlarge each sample image in the image sample set to a preset pixel size; A preset edge enhancement algorithm is used to enhance the contours and details of each of the amplified sample images, and a color balancing algorithm is used to perform color restoration on each of the sample images.

6. The infrared light and shadow interactive system according to claim 4 or 5, characterized in that: The interactive main platform is also used for: The performance of the trained graph-based graph model is verified, specifically including: Obtaining a lantern structure outline drawn by a user, using an image-generated image mode, and using the lantern structure outline as an input image to trigger the image-generated image model to generate a lantern image with target style lantern elements based on the custom trigger words and the style weights; The lantern image is compared with the lantern image in the ancient painting image corresponding to the image-generated image model to obtain the performance verification result of the image-generated image model.

7. The infrared light and shadow interactive system according to claim 3, characterized in that: The performing image masking processing on the transparent background image to obtain a masked combined image includes: Overlay the transparent background image on the preset Circle component through the Transform component to obtain a mask image; The mask image is multiplied and synthesized with the preset AI dynamic video material to obtain a mask combined image.

8. The infrared light and shadow interactive system according to claim 3, characterized in that: The step of obtaining a laser point trajectory of a user operation point and extracting laser point coordinate information from the laser point trajectory includes: Acquire a real-time video stream containing the laser point trajectory of the user's operation point, and crop the image in the video stream to obtain a target processing area; the target processing area is an image area containing the screen range of the video output device; performing a blurring process on the target processing area to enhance the brightness characteristics of the laser point within the target processing area, and performing a threshold segmentation process on the blurred target processing area to separate the laser point from the target processing area, thereby obtaining laser point image data containing only the point position information of the laser point; Converting the laser point image data into geometric contour data to obtain geometric edge information of the laser point; The geometric contour data is converted into channel data to obtain the coordinate information of the laser point from the geometric edge information, and the coordinate information is normalized to map the coordinate information from the original pixel coordinate system to the standard coordinate system to obtain the laser point coordinate information.

9. The infrared light and shadow interactive system according to claim 3, characterized in that: The controlling the position of the contour image in the multi-layer image based on the laser point coordinate information includes: The horizontal coordinate and the vertical coordinate in the laser point coordinate information are respectively mapped to the displacement parameters of the contour image in the multi-layer image, so as to achieve synchronization of the coordinate position change of the laser point and the coordinate position change of the contour image in the multi-layer image.

10. An infrared light and shadow interaction method, characterized in that: Applied to the infrared light and shadow interaction system according to any one of claims 1 to 9, the method comprising: Get the outline image drawn by the user; After pre-processing the outline image, a masked composite image is obtained, and the masked composite image is layer-synthesized with a preset static ancient painting material to obtain a multi-layer image; the masked composite image and the static ancient painting material in the multi-layer image are respectively superimposed and displayed in the form of single layers, and each layer is independent of each other; Obtaining a laser point trajectory of a user operation point and extracting laser point coordinate information in the laser point trajectory; The laser point coordinate information is bound to the coordinate position of the mask combination image in the multi-layer image, so as to control the position change of the mask combination image in the multi-layer image based on the laser point coordinate information to achieve dynamic visual interaction.

Images