• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.49-58
• /
• 2011

Typically, vision-based AR systems operate on the basis of prior knowledge of the environment such as a square marker. The traditional marker-based AR system has a limitation that the marker has to be located in the sensing range. Therefore, there have been considerable research efforts for the techniques known as real-time camera tracking, in which the system attempts to add unknown 3D features to its feature map, and these then provide registration even when the reference map is out of the sensing range. In this paper, we describe a real-time camera tracking framework specifically designed to track a monocular camera in a desktop workspace. Basic idea of the proposed scheme is that a real-time camera tracking is achieved on the basis of a plane tracking algorithm. Also we suggest a method for re-detecting features to maintain registration of virtual objects. The proposed method can cope with the problem that the features cannot be tracked, when they go out of the sensing range. The main advantage of the proposed system are not only low computational cost but also convenient. It can be applicable to an augmented reality system for mobile computing environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.4C
• /
• pp.341-350
• /
• 2006

The sand table training is one of the most effective training method in military operations which can accomplish missions such as simulation and rehearsal without limitations related to time, space, money and so on. Previous sand table training has many problems like that the sand table cannot represent real field condition because of its physical properties. So, it is hard to be preserved and impossible to include much of information into them. In this paper, we make an approach based on Augmented Reality(AR) to solve these problems and propose an efficient military training briefing tool with virtual sand table environment described as actual battle field Virtual Tactical Map(VTM) can realize a virtual military training with simple action like moving marker or tangible interface by hand. Real-time state information of VTM gives us more organic intelligence for entire situation. Tangible AR interface provides users with a contents authoring tool that is natural, intuitive and easy to deal with as interaction between user in real world and system that augmented real world with virtual object. VTM is a newly designed military training briefing tools. A military training content can be reproduced and it is possible that user uses this content later. Thus, it shows us potential possibilities of AR applications on military leaning field.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.20-30
• /
• 2012

The biggest advantage of AR is that it allows unique experience in the real world through a virtual object. However, there is a limit in the marker techniques to do registration for the virtual object. Therefore, it is possible for a complication that only allows restrictive interaction to come up. This paper provides marker technique of the next generation which can supplement limitations of existing marker technique. Such marker is a combination of IR LED's, and is a convergence of LED VCL concepts of M2M. Environment where the user belongs to and their unique choice will be expressed into one context. Also, the context will be delivered to the system through OOK IR LED marker algorithm. Marker can be operated on the spot to change virtual objects according to the user's taste, registration can be done at the same time for several virtual objects, and control become possible.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• Journal of Broadcast Engineering
• /
• v.16 no.4
• /
• pp.614-623
• /
• 2011

We propose a real-time tracking algorithm for an augmented reality (AR) system for TV broadcasting. The tracking is initialized by detecting the object with the SURF algorithm. A multi-scale approach is used for the stable real-time camera tracking. Normalized cross correlation (NCC) is used to find the patch correspondences, to cope with the unknown and changing lighting condition. Since a zooming camera is used, the focal length should be estimated online. Experimental results show that the focal length of the camera is properly estimated with the proposed online calibration procedure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2705-2711
• /
• 2011

The recent development in multimedia technology such as audio technology needs high quality audio system. Especially, Real Audio Technology is to be developed to play realistic sound. To meet this demands, researches on 3-Dimensional Audio which provides realistic audio effect in virtual reality and augmented reality are conducted. In this paper, how to provide realistic audio effect by using better audio technologies in augmented reality was investigated. In the study, the movements of the 3-Dimensional model on the markers were used to provide the sense of reality in virtual and real world. Namely, the sound was modified according to the movement of the model. The change in distance and angle of the model affected the sound volume and the pitch.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.1
• /
• pp.63-76
• /
• 1996

In this paper, we propose a new dynamic spatial index structure, called PR -file, for handling spatial objects and the modified hierarchical variance which measures the degree of spatial locality at each level. Under the assumption that a multidimensional search space has a circular domain, PR-file uses the modified hierarchical variance for clustering spatially adjacent objects. The insertion and splitting algorithms of PR_file preserve and index which has a low hierarchical variance regardless of object distributions. The simulation result shows that PR- file has a high hit ratio during a retrieval of objects by using an index with low hierarchical variance. And it shows a characteristic that the larger the bucket capacity, the higher the bucket utilization.

• Korean Institute of Interior Design Journal
• /
• v.26 no.4
• /
• pp.93-102
• /
• 2017

The study of space through image evaluation has reached the stage of measuring the emotion with the development of IT technology and the advent of VR AR era. Many researches have been trying to evaluate the space and measure the emotion in objective form by providing various forms of spatial images such as photographs, sketches, and CG. In order for these studies to be used as objective data with logical relevance, it is necessary to describe in detail the method of collecting the data used in the experiment, the characteristics of the test procedure, and the method of analysis. This study is a basic study for constructing a database by systematically organizing the attributes, experimental methods and experimental procedures of subjects. From the viewpoint of securing the objectivity and reproducibility of the paper, we analyzed the spatial image evaluation process focusing on 1) evaluation subject, 2) experimental method, and 3) analysis standard. It is necessary to examine whether the object of evaluation and the form of image and the method of providing it meet the purpose of the study. In addition, the size and order of the image, the viewing time and the interval (break time) should be different according to the gender and group experiment and the individual test method.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2011.02a
• /
• pp.208-208
• /
• 2011

최근 유연기판 기술을 기반으로 대면적 roll to roll 공정기술 개발이 활발히 연구됨에 따라 이에 적용 가능한 대면적 플라즈마 소스의 중요성이 대두되고 있다. 대면적 플라즈마 처리 공정에 적용 가능한 소스 중 closed drift 타입의 선형 이온 소스는 제작 및 대면적화가 용이함에 따라 다양한 산업 분야에서 사용되고 있다. 선형 이온 소스를 다양한 표면처리 공정에 효과적으로 적용하기 위해서는 방전 특성에 대한 이해를 바탕으로 각 공정에 맞는 이온빔 전류 밀도, 방전 전압 등의 방전 인자 조절이 필수적이다. 본 연구에서는 표면 개질, 식각 및 박막 증착 등의 다양한 분야에 활용 가능한 선형 이온 소스를 개발하였으며, 선형 이온 소스를 통한 표면 식각 공정을 집중적으로 연구하였다. 전극 및 자기장 구조에 따른 선형 이온 소스 내 플라즈마 방전거동 분석을 위해 object oriented particle in cell(OOPIC) 전산모사를 수행하였으며, 이를 통해 식각 또는 증착 공정에 적합한 이온 소스의 구조 및 공정 조건을 예측하였다. 또한 OOPIC 전산모사를 통해 예측된 이온빔 인출 경향을 Faraday cup을 이용한 이온빔 전류 밀도 측정을 통해 확인하였다. 실리콘 기판 식각 공정의 경우, 이온 전류밀도 및 에너지에 따른 식각 거동 분석, 이온빔 입사각 변화에 따른 식각 특성 분석을 통해 최적 식각 공정 조건을 도출하였다. 특히, 이온빔 입사각 변화에 따른 식각률 변화는 일반적으로 알려진 입사각에 따른 스퍼터링율과 유사한 경향을 보였다. 이온빔 에너지 3 kV, Ar 압력 1.3 mTorr 조건에서 기판 정지 상태시 약 8.5 nm/s의 식각 속도를 얻었다.