• Journal of the Korean Geographical Society
• /
• 제41권2호
• /
• pp.188-194
• /
• 2006

Three-dimensional topological data is essential for 3D modeling and application such as emergency management and 3D network analysis. This paper reviewed current 3D topological data model and developed a method to construct 3D topological node-relation data structure from 2D computer aided design (CAD) data. The method needed two steps with medial axis-transformation and topological node-relation algorithms. Using a medial-axis transformation algorithm, the first step is to extract skeleton from wall data that was drawn polygon or double line in a CAD data. The second step is to build a topological node-relation structure by converting rooms to nodes and the relations between rooms to links. So, links represent adjacency and connectivity between nodes (rooms). As a result, with the conversion method 3D topological data for micro-level sub-unit of each building can be easily constructed from CAD data that are commonly used to design a building as a blueprint.

• Journal of Broadcast Engineering
• /
• 제28권3호
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.232-235
• /
• 2020

최근 딥러닝을 이용한 자동차 번호판 인식 알고리즘에 있어서 인조 번호판을 생성하여 데이터 수집과 라벨링 작업 시간을 줄이기 위한 연구가 진행되고 있다. 하지만 인조 번호판의 특성상 정면의 이미지로 구성되어 있기 때문에 자동차의 정면에서 촬영된 번호판의 인식률은 높지만 측면에서 촬영된 번호판의 경우 인식률이 낮아진다. 본 논문에서는 다양한 카메라 설치 위치에 따른 다각도로 촬영된 번호판 영상의 인식률을 보완하기 위해 이미지를 3차원으로 회전하여 데이터를 생성하는 인조 번호판 생성기 프로그램을 개발하였다. 3차원 회전을 하였을 때 번호판 인식 성능을 비교하기 위해 기존 방식으로 생성한 번호판과 제안 방식으로 생성한 번호판 각 600,000장씩 생성하여 총 1,200,000장을 생성하였으며, 데이터의 비율에 따라 10가지의 학습 데이터 셋을 구성하였다. 인조 번호판 데이터의 학습 결과를 평가하기 위해 실제 번호판 이미지 1789장으로 테스트 셋을 구성하였고, 기존의 인조 번호판 생성 방식과 인식 정확도를 비교 분석하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제20권3호
• /
• pp.513-518
• /
• 2016

This paper presents a fast 3D mesh generation method using projection for line laser-based 3D scanners. The well-known method for 3D mesh generation utilizes convex hulls for 4D vertices that is converted from the input 3D vertices. This 3D mesh generation for a large set of vertices requires a lot of time. To overcome this problem, the proposed method takes (${\theta}-y$) 2D depth map into account. The 2D depth map is a projection version of 3D data with a form of (${\theta}$, y, z) which are intermediately acquired by line laser-based 3D scanners. Thus, our 2D-based method is a very fast 3D mesh generation method. To evaluate our method, we conduct experiments with intermediate 3D vertex data from line-laser scanners. Experimental results show that the proposed method is superior to the existing method in terms of mesh generation speed.

• Journal of the Korean Association of Geographic Information Studies
• /
• 제10권3호
• /
• pp.113-122
• /
• 2007

The rapid growth of aerial survey and remote sensing technology has enabled the rapid acquisition of very large amounts of geographic data, which should be analyzed using real-time visualization technology. The level of detail(LOD) algorithm is one of the most important elements for realizing real-time visualization. We chose the triangulated irregular network (TIN) method to generate normalized digital elevation model(DEM) data. First, we generated TIN data using contour lines obtained from a two-dimensional(2D) digital map and created a 2D grid array fitting the size of the area. Then, we generated normalized DEM data by calculating the intersection points between the TIN data and the points on the 2D grid array. We used constrained Delaunay triangulation(CDT) and ray-triangle intersection algorithms to calculate the intersection points between the TIN data and the points on the 2D grid array in each step. In addition, we simulated a three-dimensional(3D) terrain model based on normalized DEM data with real-time visualization using a Microsoft Visual C++ 6.0 program in the DirectX API library and a quad-tree LOD algorithm.

• The Journal of the Korea Contents Association
• /
• 제9권10호
• /
• pp.110-121
• /
• 2009

In this paper, we propose the new method that offer detailed-information through relax the system memory limitation about 3D model to user. That method based on making LOD(Level of Detail) model from huge 3D data of structure cultural assets. In our method as transformed AOSP algorithm, first of all it create the hierarchical structure space about 3D data, and create the LOD model by surface simplification. Then it extract the ROI(Region of Interest) of user in simplified LOD model, and then do rendering by original model and same surface detailed-information after process the local detailed in extracted region. To evaluate the proposed method, we have some experiment by using the precise 3D scan data of structure cultural assets. Our method can offer the detailed-information same as exist method, and moreover 45% reduced consumption of memory experimentally by forming mesh structure same as ROI of simplified LOD model. So we can check the huge structure cultural assets particularly in general computer environment.

• Cartoon and Animation Studies
• /
• 통권48호
• /
• pp.199-215
• /
• 2017

Recently, a drone is used for the general purpose application although the drone was builtfor the military purpose. A drone is actively used for the creation of contents, and an image acquisition. In this paper, we develop a 3D library module platform using 3D mesh model data, which is generated by a drone image and its point cloud. First, a lot of 2D image data are taken by a drone, and a point cloud data is generated from 2D drone images. A 3D mesh data is acquired from point cloud data. Then, we develop a service library platform using a transformed 3D data for multi-purpose uses. Our platform with 3D data can minimize the cost and time of contents creation for special effects during the production of a movie, drama, or documentary. Our platform can contribute the creation of experts for the digital contents production in the field of a realistic media, a special image, and exhibitions.

• Proceedings of the Korean Information Science Society Conference
• /
• 한국정보과학회 2005년도 가을 학술발표논문집 Vol.32 No.2 (1)
• /
• pp.709-711
• /
• 2005

이 논문에서는 CATIA, PRO-E 등의 CAD에서 3D 모델을 생성할 때 사용하는 파라메트릭 솔리드 모델링 기법에서 일반적으로 사용하는 방법보다 모델링 데이터의 용량을 크게 줄일 수 있는 방법에 대하여 고찰한다. 3D 파라메트릭 솔리드 모델링 기법은 기본적인 상세 솔리드들을 생성하여 부울(Boolean) 연산으로 이들을 조합하여 복잡한 형상(geometric object)을 만드는데 이 과정에서 많은 부울 연산이 수행된다. 그런데 각각의 상세 솔리드들의 크기가 필요 이상으로 크게 만들어 짐으로써 생성된 모델의 데이터 용량이 방대하게 되고 생성시간에도 영향을 미친다. 여기에서는 실무 경험을 바탕으로 처음에 생성된 상세 솔리드의 불필요한 부분을 제거하여 부울 연산에 알맞은 크기로 변경하여 모델링 데이터의 용량을 줄이는 방법을 제안한다.

• KIPS Transactions on Software and Data Engineering
• /
• 제10권6호
• /
• pp.243-250
• /
• 2021

With the increased development of 3D VR applications augmented by recent VR/AR/MR technologies and by the advance of 3D devices, interchangeability and portability of 3D data have become essential. 3D files should be processed in a standard data format for common usage between applications. Providing standardized libraries and data structures along with the standard file format means that a more efficient system organization is possible and unnecessary processing due to the usage of different file formats and data structures depending on the applications can be omitted. In order to provide the function of using a common data file and data structure, this research is intended to provide a programming binding tool for generating and storing standardized data so that various services can be developed by accessing the common 3D files. To achieve this, this paper defines a common data structure including classes and functions to access X3D files with a standardized scheme using the Python programming language. It describes the implementation of a Python language binding viewer, which is an X3D VR viewer for rendering standard X3D data files based on the language binding interface. The VR viewer includes Python based 3D scene libraries and a data structure for creation, modification, exchange, and transfer of X3D objects. In addition, the viewer displays X3D objects and processes events using the libraries and data structure.

• Journal of IKEEE
• /
• 제23권4호
• /
• pp.1250-1256
• /
• 2019

Although one can easily generate real-world 3D mesh data using a 3D printer or a depth camera, the generated data inevitably includes unnecessary noise. Therefore, mesh denoising is essential to obtain intact 3D mesh data. However, conventional mathematical denoising methods require preprocessing and often eliminate some important features of the 3D mesh. To address this problem, this paper proposes a deep learning based 3D mesh denoising method. Specifically, we propose a convolution-based autoencoder model consisting of an encoder and a decoder. The convolution operation applied to the mesh data performs denoising considering the relationship between each vertex constituting the mesh data and the surrounding vertices. When the convolution is completed, a sampling operation is performed to improve the learning speed. Experimental results show that the proposed autoencoder model produces faster and higher quality denoised data than the conventional methods.