• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.493-498
• /
• 2006

본 논문에서는 3D 파노라믹 가상 환경 생성을 위한 투영기반 메쉬 모델 생성 기법을 제안한다. 제안된 메쉬 모델 생성 기법은 멀티뷰 카메라를 이용해 다수의 시점에서 얻은 실내 환경의 3D 데이터로부터 메쉬 모델을 생성한다. 먼저 미리 보정된 카메라 파라미터를 이용해 입력된 임의의 3D점 데이터를 여러 개의 하위 점군으로 분할한다. 적응적 샘플링을 통해 각 하위 점군으로부터 중복되는 점 데이터를 없애고 새로운 점군을 생성한다. 각각의 하위 점군을 Delaunay삼각화 방법을 통해 메쉬 모델링하고, 인접한 하위 점군의 메쉬들을 통합하여 하나의 메쉬 모델을 생성한다. 제안된 메쉬 모델링 방법은 점군의 분할을 통해 각 부분의 메쉬 모델을 독립적으로 생성하므로 실내 환경과 같은 넓은 영역의 모델링에 알맞다. 또한, 적응적 샘플링을 통해 3D 데이터가 갖는 깊이 정보의 특징을 보존하면서 메쉬 데이터의 크기를 줄인다. 생성된 가상 환경 모델은 가상/증강현실 응용 어플리케이션 등에 적용이 가능하다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.23 no.2
• /
• pp.109-116
• /
• 2005

3D Spatial Data, namely 3D Urban CG model express the building, road, river in virtual world and accumulate, manage the data in the GIS system. It is important infrastructure which expected in many usages. Recently 3D CG urban model needs much manual effort, time and costs to build them. In this paper, we introduce the integration of GIS, CG and automatic production of the $\lceil$3D Spatial Data Infrastructure$\rfloor$. This system make filtering, divide the polygon, generate the outlines of the GIS building map, design the graphic and property information and finally make automatic 3D CG models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.826-829
• /
• 2024

3D 사람 자세 추정 기술은 다양한 응용 분야에서의 높은 활용성으로 인해 대량의 학습 데이터가 수집되어 딥러닝 모델 연구가 진행되어 온 반면, 동물 자세 추정의 경우 3D 동물 데이터의 부족으로 인해 관련 연구는 극히 미진하다. 본 연구는 동물 자세 추정을 위한 예비연구로서, 3D 학습 데이터가 없는 상황에서 단일 이미지로부터 3D 사람 자세를 추정하는 딥러닝 기법을 제안한다. 이를 위하여 사전 훈련된 다중 시점 학습모델을 사용하여 2D 자세 데이터로부터 가상의 다중 시점 데이터를 생성하여 훈련하는 연역적 학습 기반 교사-학생 모델을 구성하였다. 또한, 키포인트 깊이 정보 대신 2D 이미지로부터 레이블링 된 순서 깊이 정보에 기반한 손실함수를 적용하였다. 제안된 모델이 동물데이터에서 적용 가능한지 평가하기 위해 실험은 사람 데이터를 사용하여 이루어졌다. 실험 결과는 제안된 방법이 기존 단안 이미지 기반 모델보다 3D 자세 추정의 성능을 개선함을 보여준다.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.4
• /
• pp.1-11
• /
• 2022

The Skinned Multi-Person Linear Model (SMPL) is the most widely used parametric 3D Human Model optimized and learned from CAESAR, a 3D human scanned database created with measurements from 3,800 people living in United States in the 1990s. We point out the lack of racial diversity of body types in SMPL and propose K-SMPL that better represents Korean 3D body shapes. To this end, we develop a fitting algorithm to estimate 2,773 Korean 3D body shapes from Korean body measurement data. By conducting principle component analysis to the estimated Korean body shapes, we construct K-SMPL model that can generate various Korean body shape in 3D. K-SMPL model allows to improve the fitting accuracy over SMPL with respect to the Korean body measurement data. K-SMPL model can be widely used for avatar generation and human shape fitting for Korean.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.109-114
• /
• 2024

In this paper, we design and implement a worker motion 3D visualization module based on human sensors. The three key modules that make up this system are Human Sensor Implementation, Data Set Creation, and Visualization. Human Sensor Implementation provides the functions of setting and installing the human sensor locations and collecting worker motion data through the human sensors. Data Set Creation offers functions for converting and storing motion data, creating near real-time worker motion data sets, and processing and managing sensor and motion data sets. Visualization provides functions for visualizing the worker's 3D model, evaluating motions, calculating loads, and managing large-scale data. In worker 3D model visualization, motion data sets (Skeleton & Position) are synchronized and mapped to the worker's 3D model, and the worker's 3D model motion animation is visualized by combining the worker's 3D model with analysis results. The human sensor-based worker motion 3D visualization module designed and implemented in this paper can be widely utilized as a foundational technology in the smart factory field in the future.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.3
• /
• pp.50-54
• /
• 2009

Recently, many researches have been conducted to develop 3D Indoor/Outdoor Spatial Data Models. The 3D data created based on these data models have complex data structures. In order to manage these data efficiently, it is better to use a DBMS. There have been many researches to maintain the 3D data in Geo-DBMS, such that Oosterom (2002) and Arens (2005) developed a method to store 3D Building model, geometric and topological data of coverage in DBMSa. In this study, we propose a method to store the CityGML data into the RDBMS, Oracle Spatial 11g.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• 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.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.4
• /
• pp.41-48
• /
• 2008

Currently used 3D models, which are mostly focused on visualization of 3D objects and lack topological structure, have limitation in being used for 3D spatial analyses and applications. However, implementing a full topology for the indoor spatial objects is less practical due to the increase of complexity and computation time. This study suggests an alternative method to build a 3D indoor model with less complexity using a spatial DBMS. Storing spatial and nonspatial information of indoor spaces in DB tables enables faster queries, computation and analyses. Also it is possible to display them in 2D or 3D using the queried information. This study suggests a 2D-3D hybrid data model, which combines the 2D topology constructed from CAD floor plans and stored in a spatial DBMS and the 3D visualization functionality. This study showed the process to build the proposed model in a spatial DBMS and use spatial functions and queries to visualize in 2D and 3D. And, then, as an example application, it illustrated the process to build an indoor evacuation simulator.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.1
• /
• pp.57-62
• /
• 2006

This treatise proposes a develop system that manufactures 3D clothes model who is used in 3D clothes getting dressed simulation. Need 3D human body model and 3D clothes model to do getting dressed simulation. Create priority work Matrix javelin to design clothes model and design 2D piece from designer Connect designed piece plain using backstitch line and create numerical value data because using designed piece and backstitch data finally and make 3D clothes model. Consist of piece design module, to read clothes data and save module, getting dressed simulation module in system that propose in this treatise.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.352-354
• /
• 2021

본 논문에서는 2D 이미지를 입력으로 받는 3D 모델러 결과를 이용한 피부 반사 및 투과 요소를 조절한 데이터 셋 생성 방법을 제안한다. 고화질 얼굴 이미지로 된 Flickr-Faces-HQ 데이터셋을 이용해 3D 모델러의 결과인 3 차원 얼굴 모델과 텍스처를 추출해 이를 이용해 피부 반사 및 투과 요소를 조절한 2D 영상 생성 방법을 제시한다. 따라서 피부 반사 요소를 조절하기 위해 여러 조명과 카메라로 이루어진 라이트 스테이지 (light stage)와 같은 환경 없이 비용을 절약할 수 있다. 동시에 피부 투과 요소 측정 장비에 대한 한계를 극복하고 원하는 조건을 설정해 이미지를 생성할 수 있는 방법과 데이터셋을 제안한다.