• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.896-902
• /
• 2013

Crosstalk has been regarded as one of inherent problems in a factor disturbing optimal viewing experiences. For this reason, display developers address the crosstalk issues. However, due to various display characteristics and viewing environments it is hard to estimate the crosstalk generated in real space. This paper proposes an interactive multi-view display simulator based on augmented reality for developing mobile autostereoscopic displays. This display simulator can be used for the developers to estimate the crosstalk and find optimal viewing zone intuitively. Typical parameters for mobile phone use are applied for the estimation. The proposed simulator provides visualized crosstalk in real space for them to determine better viewing zone interactively. The proposed system is expected to help establish ergonomic guidelines for mobile multi-view autostereoscopic display developers, designers, and viewers.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.34-40
• /
• 2018

This paper presents a new method to estimate the pose of a moving object accurately using a monocular camera and a low-end GPS+IMU sensor system. For this goal, we adopted a deep neural network for the semantic segmentation of input images and compared the results with a semantic map of a neighborhood. In this map matching, we use weight tables to deal with label inconsistency effectively. Signals from a low-end GPS+IMU sensor system are used to limit search spaces and minimize the proposed function. For the evaluation, we added noise to the signals from a high-end GPS-IMU system. The results show that the pose can be recovered from the noisy signals. We also show that the proposed method is effective in handling non-open-sky situations.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.9-14
• /
• 2020

With the distribution modernization policy advanced by the government and consumers preference toward it, the so called "modern market" has undergone rapid growth. Conversely, traditional market is losing popularity with consumers as a result of inadequate modern structures, small market size, convoluted relationships, inefficient operation and disordered transactions, among others. Therefore, this study seeks to utilize ubiquitous computing, that is, the upgrade of context aware information to 6W1H and promote the market through the interface with Smartphone and provide advanced information through the augmented reality technology. For the construction of context-aware system using user context, the results may significantly differ according to how reference rules are applied to and implemented on knowledge base. In light of above, through the use of RFID technology and 6W1H context awareness, we seek to promote traditional markets.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.643-648
• /
• 2007

유비쿼터스 컴퓨팅 기술이 문화예술 분야에 접목되면서 수동적이었던 전시 관람 형태가 능동적인 관람 형태로 바뀌고 있다. 특히, 지능형 가이드 시스템의 등장은 기존의 관람 문화를 크게 변화시켰다. 지능형 가이드 시스템이란 사용자에게 전시물에 대한 정보 및 전시장의 위치 정보를 제공해주는 시스템을 말한다. 현재 상용화되고 있는 지능형 가이드 시스템은 크게 휴대폰, PDA, 게임기 등의 휴대형 장치 기반의 가이드 시스템과 HMD와 같은 착용형 장치 기반의 가이드 시스템으로 나뉠 수 있다. 본 논문에서는 이러한 현재 상용화된 시스템들의 한계(예를 들어, 특정 장치를 직접 착용 혹은 소지해야 함)를 서술하고, 이를 보완하는 프로젝터 기반의 가이드 시스템에서 더 나아가 임의의 공간에 원하는 전시물 구성, 설치 등을 신속, 정확하게 수행하는 지능형 가이드 시스템을 제안한다. 프로젝터 기반의 지능형 가이드 시스템은 기반 기술로 지능형 프로젝션 기술을 필요로 하는데, 이는 임의의 환경에서 임의의 위치에 다수의 사용자에게 고화질, 대화면 영상 정보를 제공해 준다. 그러나, 기존의 지능형 프로젝션 기술은 성능 및 안정성을 위해 대부분 가시적인 패턴 및 마커를 사용하는데, 이는 사용자에게 제공되는 정보를 관찰하는 데 방해가 될 수 있다. 본 논문에서는 사용자의 관점에서 유용한 비간섭 지능형 프로젝션 기술을 사용한다. 즉, 본 논문에서는 마커나 패턴을 사용함으로써 정확성이나 안정성은 보장하지만, 마커나 패턴을 은닉하여 사용자의 눈에 띄지 않도록 함으로써, 사용자는 원하는 정보를 아무런 방해 없이 제공받을 수 있다. 제안된 시스템을 미술 작품 감상을 위한 가이드 시스템으로 적용해 본 결과, 사용자는 자유로운 환경에서 자신의 위치나 작품에 대한 설명을 대화면으로 제공받으면서, 편안하게 그림을 감상할 수 있었다.

• Journal of Korea Game Society
• /
• v.13 no.5
• /
• pp.43-54
• /
• 2013

With the consistent development of the 3D application technique, visuals are available at more realistic quality and are utilized in many applications like game. In particular, interacting with 3D objects in virtual environments, 3D graphics have led to a substantial development in the augmented reality. This study proposes a 3D user interface to control objects in 3D space through virtual two-view method using only one camera. To do so, homography matrix including transformation information between arbitrary two positions of camera is calculated and 3D coordinates are reconstructed by employing the 2D hand coordinates derived from the single camera, homography matrix and projection matrix of camera. This method will result in more accurate and quick 3D information. This approach may be advantageous with respect to the reduced amount of calculation needed for using one camera rather than two and may be effective at the same time for real-time processes while it is economically efficient.

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.4
• /
• pp.356-367
• /
• 2014

A robotic sapatial augmented reality (RSAR) system, which combines robotic components with projector-based AR technique, is unique in its ability to expand the user interaction area by dynamically changing the position and orientation of a projector-camera unit (PCU). For a moving PCU mounted on a conventional robotic device, we can compute its extrinsic parameters using a robot kinematics method assuming a link and joint geometry is available. In a RSAR system based on user-created robot (UCR), however, it is difficult to calibrate or measure the geometric configuration, which limits to apply a conventional kinematics method. In this paper, we propose a data-driven kinematics control method for a UCR-based RSAR system. The proposed method utilized a pre-sampled data set of camera calibration acquired at sufficient instances of kinematics configurations in fixed joint domains. Then, the sampled set is compactly represented as a set of B-spline surfaces. The proposed method have merits in two folds. First, it does not require any kinematics model such as a link length or joint orientation. Secondly, the computation is simple since it just evaluates a several polynomials rather than relying on Jacobian computation. We describe the proposed method and demonstrates the results for an experimental RSAR system with a PCU on a simple pan-tilt arm.

• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.585-594
• /
• 2011

On live performance such as play and musical, various stage effects are utilized to attract a diverse audience. These stage effects include traditional direction techniques, striking display effects and all kinds of ways of being immersed in the scene. In this paper, we propose a novel digital visual effects(digilog) for controlling the surface texture of objects based on spatial augmented reality. For this purpose, we present a method of neutralizing the appearance of an arbitrary object using a projector-camera system. To make the object appear as if it is a transparent object by projecting a carefully determined compensation image onto the surface of objects, we use the homography method for a simple and effective off-line projector-camera calibration. The successful uses of the basic algorithm of Smart Projector for measuring radiometric parameters led us believe that this method may be used for temporal variation of plays and musicals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.637-644
• /
• 2021

In general, in the fields of computer vision, robotics, and augmented reality, the importance of 3D space and 3D object detection and recognition technology has emerged. In particular, since it is possible to acquire RGB images and depth images in real time through an image sensor using Microsoft Kinect method, many changes have been made to object detection, tracking and recognition studies. In this paper, we propose a method to improve the quality of 3D reconstructed images by processing images acquired through a depth-based (RGB-Depth) camera on a multi-view camera system. In this paper, a method of removing noise outside an object by applying a mask acquired from a color image and a method of applying a combined filtering operation to obtain the difference in depth information between pixels inside the object is proposed. Through each experiment result, it was confirmed that the proposed method can effectively remove noise and improve the quality of 3D reconstructed image.

• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.1-10
• /
• 2021

The purpose of the study is to investigate the impact and analyze the effect of smart learning based class to on the students with low academic achievement level. The study performed in G University in 2018 among students taking calculus II class. It includes 16 students with low academic achievement level, whose grades were under C in the previous calculus I class. They belonged to special class consisted of very low academic achievement level and had to pass calculus II. 3D and AR were actively used in the class. The result shows that they got visual understanding of space, which revealed through analyzing SNS, mid-term and final examination, lecture evaluation. Also, smart learning based mathematics class utilizing smartphone's application elevated academic achievement level and influenced positively on the interest and attitude toward mathematics regardless of previous academic achievement level.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.187-190
• /
• 2022

본 논문은 메타버스 등 인공지능 연계 증강/가상현실 부동 중계 플랫폼에서 부동산 영상 기반 매물 소개 시스템 구축에서 사생활 및 개인정보가 영상에 담기게 될 수 있는 위험이 존재하기에 부동산 영상 내의 개인정보 및 민감 정보를 인공지능 기술을 기반으로 검출하여 삭제해주고 복원해주는 인공지능 기술 연구개발을 목표로 하였다. 한국형 부동산 내 민감 object 를 정의하고, 최신 인공지능 딥러닝 기술 기반 민감 object detection 알고리즘을 연구 개발하며, 영상에서 삭제된 부분은 인공지능 기술을 기반으로 물체가 없는 실제 공간영상으로 복원해주는 영상복원 기술도 연구 개발하였다. 한국형 부동산 환경 (영상 촬영 조도, 디스플레이 스타일, 주변 가구 배치 등)에 맞는 인공지능 모델 구축을 위하여, 자체적으로 한국 영상 database 구축 및 Transfer learning for target domain adaptation 을 진행하였다. 제안된 알고리즘은 일반적인 환경에서 98%의 정확도와 challenge 환경에서 (occlusion 빛 반사, 저조도 등) 81%의 정확도를 보였다. 본 기술은 Proptech 분야에서 주목받고 있는 메타버스 기반 온라인 중계 서비스 기술을 활성화하기 위하여 기획되었으며, 특히 메타버스 부동산 중계 플랫폼의 활성화를 위하여 사생활 보호 측면에서 필요한 중요 기술을 인공지능 기술을 활용하여 연구 개발하였다.