• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.48-60
• /
• 2011

Nowadays, the 3D community is actively researching on 3D imaging and free-viewpoint video (FVV). The free-viewpoint rendering in multi-view video, virtually move through the scenes in order to create different viewpoints, has become a popular topic in 3D research that can lead to various applications. However, there are restrictions of cost-effectiveness and occupying large bandwidth in video transmission. An alternative to solve this problem is to generate virtual views using a single texture image and a corresponding depth image. A critical issue on generating virtual views is that the regions occluded by the foreground (FG) objects in the original views may become visible in the synthesized views. Filling this disocclusions (holes) in a visually plausible manner determines the quality of synthesis results. In this paper, a new approach for handling disocclusions using depth based inpainting algorithm in synthesized views is presented. Patch based non-parametric texture synthesis which shows excellent performance has two critical elements: determining where to fill first and determining what patch to be copied. In this work, a noise-robust filling priority using the structure tensor of Hessian matrix is proposed. Moreover, a patch matching algorithm excluding foreground region using depth map and considering epipolar line is proposed. Superiority of the proposed method over the existing methods is proved by comparing the experimental results.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.694-699
• /
• 2007

2D에서 3D로 이동하고 있는 현재의 GIS는 자료 크기가 기하급수적으로 커지고 이로 인해 처리속도가 느려지고 있으며 사용자의 실시간 렌더링(Rendering) 욕구는 커지고 있다. 대용량의 공간자료에 대한 처리속도, 3차원 처리기술, 가상현실 처리기술 등의 제약조건과 함께 3차원 GIS를 가시화하기 위해서는 방대한 데이터를 처리하기 위한 시간과 비용이 많이 과다하게 발생하는 문제점을 가지고 있다. 본 논문에서는 이러한 문제를 해결하기 위해 위성 및 항공으로부터 획득된 DEM 데이터를 이용하여 VRML로 가시화하여 3차원의 지형 정보를 생성하였다. 이렇게 생성된 지형 데이터에 LOD(Level of Detail) 기법을 통한 단순화 과정을 거쳐 3차원의 지형정보를 획득하고, 수치지도를 기반으로 한 모델링 및 텍스처 맵핑 과정을 통해 3차원의 도시 정보를 획득하게 된다. 이렇게 획득된 도시 정보에 3차원 공간적인 조건 및 검색을 가능하게 함으로써 언제 어디서든 누구나 쉽게 건물 및 도로에 대한 정보를 검색할 수 있도록 하였고, 네비게이션 및 시뮬레이션 기능을 추가한 웹 기반의 3차원 가상 도시를 구현하였다.

• Journal of Korea Game Society
• /
• v.19 no.6
• /
• pp.49-60
• /
• 2019

Interior Mapping has been used to reduce graphics resources. In this paper, rendering speed(FPS), the number of polygons, shader complexity and each resource size of Interior Mapping were compared to those of actual modeling in order to examine the performance of 3D games when the technology is adapted by utilizing Unreal Engine 4. In addition, for the efficient application, the difference in performance according to the resolution and detail of cube map texture was verified.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.3
• /
• pp.1459-1466
• /
• 2013

Recently, various types of three-dimensional cameras have been used to analyze surrounding environments. In this paper, we suggest a mechanism of adaptively switching active and passive cameras of hybrid cameras, which can extract 3D image information more accurately. The suggested method first obtains brightness and texture features representing the environment from input images. It then adaptively selects active and passive cameras by generating rules that reflect the extracted features. In experimental results, we show that a hybrid 3D camera consisting of passive and active cameras is set up and the proposed method can effectively choose appropriate cameras in the hybrid camera and make it possible to extract three dimensional information more accurately.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.6
• /
• pp.679-691
• /
• 2002

Volume visualization is an important subarea of scientific visualization, and is concerned with techniques that are effectively used in generating meaningful and visual information from abstract and complex volume datasets, defined in three- or higher-dimensional space. It has been increasingly important in various fields including meteorology, medical science, and computational fluid dynamics, and so on. On the other hand, virtual reality is a research field focusing on various techniques that aid gaining experiences in virtual worlds with visual, auditory and tactile senses. In this paper, we have developed a visualization system for CAVE, an immersive 3D virtual environment system, which generates stereoscopic images from huge human volume datasets in real-time using an improved volume visualization technique. In order to complement the 3D texture-mapping based volume rendering methods, that easily slow down as data sizes increase, our system utilizes an image-based rendering technique to guarantee real-time performance. The system has been designed to offer a variety of user interface functionality for effective visualization. In this article, we present detailed description on our real-time stereoscopic visualization system, and show how the Visible Korean Human dataset is effectively visualized on CAVE.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.1
• /
• pp.63-70
• /
• 2009

3D GIS(Geographic Information System) processes, analyzes and presents various real-world 3D phenomena by building 3D spatial information of real-world terrain, facilities, etc., and working with visualization technique such as VR(Virtual Reality). It can be applied to such areas as urban management system, traffic information system, environment management system, disaster management system, ocean management system, etc,. In this paper, we propose video visualization technology based on 3D geographic information to provide effectively real-time information in 3D geographic information system and also present methods for establishing 3D building information data. The proposed video visualization system can provide real-time video information based on 3D geographic information by projecting real-time video stream from network video camera onto 3D geographic objects and applying texture-mapping of video frames onto terrain, facilities, etc.. In this paper, we developed sem i-automatic DBM(Digital Building Model) building technique using both aerial im age and LiDAR data for 3D Projective Texture Mapping. 3D geographic information system currently provide static visualization information and the proposed method can replace previous static visualization information with real video information. The proposed method can be used in location-based decision-making system by providing real-time visualization information, and moreover, it can be used to provide intelligent context-aware service based on geographic information.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.41-44
• /
• 2006

본 연구에서 3차원 지형공간정보의 구축 및 처리, 가시화를 위하여 개인용 PC와 임베디드 단말기의 포켓 PC환경에서 자료 호환 및 동시 운영이 가능한 실시간 3차원 GIS의 Prototype의 설계 및 구현과 적용 실험을 하고자 한다 OpenGL(Open Graphic Library)과 OpenGL|ES (Embedded System)를 활용하여 도시경관을 구성하는 주요객체인 지형, 건물, 교통, 식생 등을 통합적으로 저작 및 3D 객체 모델링 및 렌더링이 통합 및 개별 운영 시스템을 설계하고 구현하였다. 구현 단계에서 개인용 PC 운영환경에서는 기능성 향상에 중점을 두어 공간 데이터베이스 설계, 텍스처 영상 매핑처리, 대용량의 3차원 공간정보 처리 및 관리, 가시화, 렌더링, 모델링 기능들을 제공하며, PDA 휴대용 단말운영환경을 지원하는 모바일 시스템에서는 실시간 모바일 저작기능과 렌더링 기능에 주안점을 두어 개발하였다. 한편 연구 결과로 구현된 시스템은 원도우 XP 기반의 개인용 PC와 PDA 단말기 상에서 3D 객체 자료구조가 호환되어 향후 다양한 응용이 가능할 것으로 생각된다.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1349-1365
• /
• 2020

In recent years, in the fields of smart cities and digital twins, research on model generation is increasing due to the advantage of acquiring actual 3D coordinates by using point clouds. In addition, there is an increasing demand for a solid model that can easily modify the shape and texture of the building. In this paper, we propose a method to create a clustered solid building model based on point cloud data. The proposed method consists of five steps. Accordingly, in this paper, we propose a method to create a clustered solid building model based on point cloud data. The proposed method consists of five steps. In the first step, the ground points were removed through the planarity analysis of the point cloud. In the second step, building area was extracted from the ground removed point cloud. In the third step, detailed structural area of the buildings was extracted. In the fourth step, the shape of 3D building models with 3D coordinate information added to the extracted area was created. In the last step, a 3D building solid model was created by giving texture to the building model shape. In order to verify the proposed method, we experimented using point clouds extracted from unmanned aerial vehicle images using commercial software. As a result, 3D building shapes with a position error of about 1m compared to the point cloud was created for all buildings with a certain height or higher. In addition, it was confirmed that 3D models on which texturing was performed having a resolution of less than twice the resolution of the original image was generated.

• Journal of Cadastre & Land InformatiX
• /
• v.48 no.2
• /
• pp.213-225
• /
• 2018

For constructing three-dimensional (3D) spatial information occlusion region problem arises in the process of taking the texture of the building. In order to solve this problem, it is necessary to investigate the automation method to automatically recognize the occlusion region, issue it, and automatically complement the texture. In fact there are occasions when it is possible to generate a very large number of structures and occlusion, so alternatives to overcome are being considered. In this study, we attempt to apply an approach to automatically create an occlusion region based on learning by patterning the blocked region using the recently emerging deep learning algorithm. Experiment to see the performance automatic detection of people, banners, vehicles, and traffic lights that cause occlusion in building walls using two advanced algorithms of Convolutional Neural Network (CNN) technique, Faster Region-based Convolutional Neural Network (R-CNN) and Mask R-CNN. And the results of the automatic detection by learning the banners in the pre-learned model of the Mask R-CNN method were found to be excellent.