Search

KR-20260066990-A - Artificial intelligence based indoor and outdoor digital twin spatial data processing system and processing method using the same

KR20260066990AKR 20260066990 AKR20260066990 AKR 20260066990AKR-20260066990-A

Abstract

The present invention relates to an artificial intelligence-based indoor and outdoor digital twin spatial data processing system and a processing method using the same, and more specifically, to an artificial intelligence-based indoor and outdoor digital twin spatial data processing system and a processing method using the same, comprising data collection, image preprocessing, artificial intelligence-based 3D reconstruction, data format conversion, simulation and visualization, and a user interface.

Inventors

  • 백성은

Assignees

  • 주식회사 비트리

Dates

Publication Date
20260512
Application Date
20241105

Claims (5)

  1. A data collection module that collects data from indoor and outdoor environments; An image preprocessing module that refines data collected from the above data collection module; An AI-based 3D reconstruction module that reconstructs data refined in the above image preprocessing module into a 3D model by processing it based on NeRF (Neural Radiance Fields) and 3D Gaussian Splatting; A data format conversion module that converts the data of a 3D model reconstructed by the above AI-based 3D reconstruction module into an international standard 3D data format; A simulation and visualization module that performs simulation and visualization based on data converted by the above data format conversion module; and An AI-based indoor and outdoor digital twin spatial data processing system comprising: a user interface module that provides simulation and visualization data obtained from the simulation and visualization module to a user terminal.
  2. In claim 1, In the above AI-based 3D reconstruction module, the NeRF learns visual data among the refined data using a neural network to calculate the emissivity of individual pixels and generates all viewpoints looking at a specific object based on the location of the corresponding pixels to create a 3D spatial model, and the 3D Gaussian splatting renders the 3D spatial model generated by the NeRF in real time and reconstructs the 3D model for the viewer based on a Gaussian distribution function; an AI-based indoor/outdoor digital twin spatial data processing system.
  3. In claim 2, The above data format conversion module is an AI-based indoor/outdoor digital twin spatial data processing system that reflects data compatibility by converting the data of the 3D model reconstructed by the AI-based 3D reconstruction module into one or more standard formats selected from CityGML, IFC, OBJ, and VRML in accordance with ISO and OGC standards.
  4. In claim 3, The above data collection module includes a visual data collection unit that collects visual data and a physical data collection unit that collects temperature, humidity, and air quality indices. The image preprocessing module includes a normalization unit that equalizes the brightness and color of a data image collected by the visual data collection unit, a noise filtering unit that removes noise from the image equalized by the normalization unit, and a resolution correction unit that controls the resolution of the image generated by the noise filtering unit. The simulation and visualization module comprises a scenario simulation unit that predicts the environment according to conditions preset by the user based on the converted data, configures a scenario, and performs a simulation; a real-time rendering unit that performs 3D rendering in real-time by linking the simulation based on the configuration of the scenario with one or more selected from WebGL, UnrealEngine, and Unity; and a data update unit that provides an updated simulation by reflecting data on the environment where the change occurred whenever a change in the predicted environment occurs. The above user interface module comprises a result visualization unit that provides the simulation and visualization data to a user terminal in a preset format, a simulation control unit that controls the conditions and parameters of the simulation in the preset format according to user customization, and a simulation display unit that displays the results of the simulation on a display in a preset format, comprising an AI-based indoor and outdoor digital twin spatial data processing system.
  5. The data collection module is in the first stage of collecting data from indoor and outdoor environments; The image preprocessing module performs a second step of refining the data collected in the first step; The AI-based 3D reconstruction module processes the data refined in the second step above based on NeRF (Neural Radiance Fields) and 3D Gaussian Splatting in the third step to reconstruct it into a three-dimensional model; The data format conversion module converts the data of the 3D model reconstructed in the third step into an international standard 3D data format in the fourth step; The simulation and visualization module performs simulation and visualization based on the data converted in the fourth step; and a fifth step. An artificial intelligence-based indoor and outdoor digital twin spatial data processing method comprising: a sixth step in which a user interface module provides simulation and visualization data obtained in the fifth step to a user terminal.

Description

Artificial intelligence-based indoor and outdoor digital twin spatial data processing system and processing method using the same The present invention relates to an artificial intelligence-based indoor and outdoor digital twin spatial data processing system and a processing method using the same, and more specifically, to an artificial intelligence-based indoor and outdoor digital twin spatial data processing system and a processing method using the same, comprising data collection, image preprocessing, artificial intelligence-based 3D reconstruction, data format conversion, simulation and visualization, and a user interface. Conventional technologies for constructing 3D spatial information typically involve modeling 3D space using photogrammetry or collecting spatial information using sensors such as LiDAR and generating 3D models based on it. However, these methods have the disadvantage of requiring expensive equipment and taking a long time for data collection and processing. Meanwhile, accurately reconstructing indoor and outdoor spatial data into 3D and reflecting it in a digital twin model currently requires complex calculations and large-scale data processing. In particular, implementing a digital twin model capable of reflecting a real-time changing environment requires highly accurate and rapid 3D reconstruction and data standardization. Therefore, research and development on digital twin models that reflect indoor and outdoor spatial data is necessary. (Related Literature) 1. Korean Registered Patent No. 10-2555580 2. Korean Registered Patent No. 10-2653971 3. Korean Registered Patent No. 10-2657675 4. Korean Registered Patent No. 10-2644982 5. Korean Registered Patent No. 10-2641506 Figure 1 shows a schematic diagram of the artificial intelligence-based indoor and outdoor digital twin spatial data processing system of the present invention. Figure 2 shows a schematic diagram of the data collection module of the present invention. Figure 3 shows a schematic diagram of the image preprocessing module of the present invention. Figure 4 shows a schematic diagram of an artificial intelligence-based 3D reconstruction module using NeRF and 3D Gaussian splatting of the present invention. FIG. 5 shows a schematic diagram of an artificial intelligence-based 3D reconstruction module having a space-dependent resolution control unit, a distance-dependent resolution control unit, and a resolution size control unit of the present invention. FIG. 6(a) shows a schematic diagram of a form having different resolution sizes in the first to third spaces of the present invention, FIG. 6(b) shows a schematic diagram of a form in which the resolution size changes sequentially in adjacent spaces in the first to third spaces of the present invention, and FIG. 6(c) shows a schematic diagram of a form used within the range of maximum and minimum resolution values in the first to third spaces of the present invention. Figure 7 shows a schematic diagram of the simulation and visualization module of the present invention. FIG. 8 shows a schematic diagram of a user interface module of the present invention. Figure 9 shows a flowchart of a processing method using the artificial intelligence-based indoor and outdoor digital twin spatial data processing system of the present invention. Expressions such as “comprising” or “may comprise” that may be used in various embodiments of the present disclosure indicate the presence of the disclosed corresponding function, operation, or component, etc., and do not limit one or more additional functions, operations, or components, etc. Furthermore, in various embodiments of the present disclosure, terms such as “comprising” or “having” are intended to specify the presence of the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. In various embodiments of the present disclosure, expressions such as “or” include any and all combinations of the words listed together. For example, “A or B” may include A, may include B, or may include both A and B. Expressions such as "first," "second," "first," or "second" used in various embodiments of the present disclosure may modify various components of the various embodiments, but do not limit such components. For example, such expressions do not limit the order and/or importance of such components. Such expressions may be used to distinguish one component from another. For example, the first user device and the second user device are both user devices and represent different user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component. When it is stated