• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1625-1628
• /
• 2003

Recently the VR technique has evolved into a mixed reality (MR) technique, in which a user can observe a real world in front of him/her as well as virtual objects displayed. This has been realized by the employment of a see-through type HMD (S-HMD). We have been developing a mixed reality space employing the MR technique. The objective of our study is to realize a virtual human that acts as a man-machine interface in the real space. It is important in the study to create a virtual human acting naturally in front of a user. In order to give natural motions to the virtual human, we employ a developed motion capture technique. We have already created various 3-D human motion models by the motion capture technique. In this paper, we present a technique for creating a virtual human using a human model provided by a computer graphics software, 3D Studio Max(C). The main difficulty of this issue is that 3D Studio Max(C) claims 28 feature points for describing a human motion, but the used motion capture system assumes less number of feature points. Therefore a technique is proposed in the paper for producing motion data of 28 feature points from the motion data of less number of feature points or from incomplete motion data. Performance of the proposed technique was examined by observing visually the demonstration of some motions of a created virtual human and overall natural motions were realized.

• 한국실내디자인학회논문집
• /
• 제22권5호
• /
• pp.152-161
• /
• 2013

This study is about the visual appreciation by sex with the analysis of time range of observing data which was got through observation experiment with the space of lobby in hospitals. The observation data of the subjects who observed the space include the frequency and time, through which the process of visual appreciation could be evaluated with the definition of the frequency and the time of observation. First, the fact that men had higher frequency of observation than women means the former had more movement than the latter, and another fact of their fewer times can be understood as the time of their staying was shorter. That is, even though the men had more movements of sight, they showed the feature of staying shorter. Second, the rate high and low of observation frequency and times made it possible for observation characteristics to be defined as 'intensive search' 'active search' 'fixed concentration' and 'search wandering.' The definition of understanding this process of visual appreciation can be available for a frame of effective analysis of observation characteristics according to the passage of time. Third, the intense search is the case of 'high frequency' having the feature of high visual appreciation owing to the active visual actions for acquiring information. Men were found to have more intense search which decreased gradually as time passed, while women showed the feature of many times of intense search. Fourth, it was found that with many observation data in a certain range of time the subjects had fixed concentration, where women were found to have repetitive fixed concentration along with the change of observation time while men were seen to have more observation tendency for fixed concentration. Fifth, at the cross tabulation of frequency and times, men had the feature of dispersed visual appreciation while women had more distinction between fixation and movement, which revealed that there is surely the difference between men and women in the process of visual appreciation.

• 전자공학회논문지SC
• /
• 제49권4호
• /
• pp.23-35
• /
• 2012

본 논문은 3차원 공간상에 존재하는 타원형 물체의 위치 및 자세 추정 기법을 다룬다. 영상에 투영된 타원특징을 해석하여 원래의 타원에 대한 3차원 자세정보를 구하는 것은 어려운 문제이다. 본 논문은 타원특징의 3차원 정보를 추출하기 위하여, 두개의 공면점을 도입한 위치 및 자세 추정 알고리즘을 제안한다. 제안된 방법은 모델과 영상좌표계에서 각각 정의되는 타원-공면점에 대한 대응쌍이 주어질 때 두 좌표계에 대한 동차변환행렬의 유일해를 결정한다. 타원-공면점은 폴라리티를 기반으로 원근변환에 불변하는 한 쌍의 삼각특징으로 변환되며, 삼각특징들로부터 평면 호모그래피가 추정된다. 카메라 좌표계에 대한 물체 좌표계의 3차원 위치 및 자세 파라미터들은 호모그래피 분해를 통해 계산된다. 제안된 방법은 3차원 자세 및 위치 추정 오차의 분석과 공면점의 위치에 따른 민감도의 분석을 통해 평가된다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권2호
• /
• pp.182-188
• /
• 2004

얼굴 구성 요소 각각에 대한 파라미터로부터 특정한 포즈나 표정을 갖는 얼굴 이미지를 합성하는 방법을 제안한다 이러한 파라미터화는 얼굴 이미지의 표현과 저장, 전송을 효과적으로 수행할 수 있도록 한다. 그러나 얼굴 이미지의 변화는 고차원의 이미지 공간에서 복잡한 비선형 매니폴드를 구성하기 때문에 파라미터화 하는 것이 쉽지 않다. 이러한 문제점을 해결하기 위해, 얼굴 이미지에 대한 표현방법으로 LLE (Locally Linear Embedding) 알고리즘을 사용한다. LLE 알고리즘은 얼굴 이미지들 사이의 관계를 유지하면서 저차원의 특징 공간으로 투사된 매니폴드를 더욱 부드럽고 연속적으로 만들어준다. 그 다음, 특징공간에서 특정한 포즈나 표정 파라미터에 해당하는 포인트를 추정하기 위해 snake 모델을 적용한다. 마지막으로, 추정된 특징 값의 주변에 있는 여러 장의 얼굴 이미지들의 가중치 평균을 구해 합성된 결과이미지를 만든다 실험결과를 통해 제안된 방법을 이용하면 겹침 현상이 적고 포즈나 표정에 대한 파라미터의 변화와 일치하는 이미지를 합성한다는 것을 보인다.

• 대한전자공학회논문지SP
• /
• 제41권2호
• /
• pp.41-50
• /
• 2004

MPEG-4 표준에서는 객체 단위의 부호화를 수행하기 위해 자연영상으로부터 비디오 객체를 분리하는 영상분할(segmentation) 기술이 필요하다. 영상분할 방법은 크게 자동 영상분할(automatic segmentation)과 반자동 영상분할(semi-automatic segmentation)의 두 부류로 나눌 수 있다. 지금까지 개발된 대부분의 자동 영상분할 방법은 비디오 객체의 명확한 수학적인 모델을 제시하기 곤란하며 한 화면에서 개별 객체를 추출하기 어렵기 때문에 그 성능에 한계가 있다. 본 논문에서는 이러한 문제점을 극복하기 위해 active contour 알고리즘을 이용한 반자동 영상분할 알고리즘을 제안한다. 초기 곡선으로부터 변화 가능한 모든 곡선의 집합을 모양공간으로 정의하고 그 공간을 선형공간이라고 가정하면, 모양공간(shape space)은 모양 행렬에 의해 행(column) 공간과 남은 빈(left null) 공간으로 나뉘어진다. 본 논문에서 제안하는 알고리즘은 행공간의 모양공간 벡터를 이용하여 초기 곡선으로부터 영상의 특징점까지의 변화를 기술하고 동적 그래프 검색 알고리즘을 이용하여 객체의 세밀한 부분을 묘사한다. 모양 행렬과 객체의 윤곽을 추정하기 위한 SUSAN 연산자의 사용으로 제안한 알고리즘은 저수준 영상처리로부터 생성되는 불필요한 특징점을 무시할 수 있다. 또한, 모양 행렬의 사용으로 생긴 제약은 동적 그래프 검색 알고리즘으로 보상한다.

• 교육시설
• /
• 제6권4호
• /
• pp.5-15
• /
• 1999

This study aims to suggest guidelines of open classroom in open elementary school. It consists of following three parts. The first part takes a theoretical review of open education and open classroom. And the second makes analysis of architectural characteristics of open classroom as case studies which are analyzed in terms of modul, function and ratio of open space, etc. The last part is user need analysis of the open space.

• 한국문헌정보학회지
• /
• 제39권2호
• /
• pp.123-146
• /
• 2005

이 연구에서는 문서 자동분류에서 분류자질 선정과 가중치 할당을 위해서 일관된 전략을 채택하여 kNN 분류기의 성능을 향상시킬 수 있는 방안을 모색하였다. 문서 자동 분류에서 분류자질 선정 방식과 자질 가중치 할당 방식은 자동분류 알고리즘과 함께 분류성능을 좌우하는 중요한 요소이다. 기존 연구에서는 이 두 방식을 결정할 때 상반된 전략을 사용해왔다. 이 연구에서는 색인파일 저장공간과 실행시간에 따른 분류성능을 기준으로 분류자질 선정 결과를 평가해서 기존 연구와 다른 결과를 얻었다. 상호정보량과 같은 저빈도 자질 선호 기준이나 심지어는 역문헌빈도를 이용해서 분류 자질을 선정하는 것이 kNN 분류기의 분류 효과와 효율 면에서 바람직한 것으로 나타났다. 자질 선정기준으로 저빈도 자질 선호 척도를 자질 선정 및 자질 가중치 할당에 일관되게 이용한 결과 분류성능의 저하 없이 kNN 분류기의 처리 속도를 약 3배에서 5배정도 향상시킬 수 있었다.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.31-40
• /
• 2013

In this paper, a novel method is proposed to build an ensemble of classifiers by using a feature selection schema. The feature selection schema identifies the best feature sets that affect the arrhythmia classification. Firstly, a number of feature subsets are extracted by applying the feature selection schema to the original dataset. Then classification models are built by using the each feature subset. Finally, we combine the classification models by adopting a voting approach to form a classification ensemble. The voting approach in our method involves both classification error rate and feature selection rate to calculate the score of the each classifier in the ensemble. In our method, the feature selection rate depends on the extracting order of the feature subsets. In the experiment, we applied our method to arrhythmia dataset and generated three top disjointed feature sets. We then built three classifiers based on the top-three feature subsets and formed the classifier ensemble by using the voting approach. Our method can improve the classification accuracy in high dimensional dataset. The performance of each classifier and the performance of their ensemble were higher than the performance of the classifier that was based on whole feature space of the dataset. The classification performance was improved and a more stable classification model could be constructed with the proposed approach.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2003년도 Proceeding
• /
• pp.223-230
• /
• 2003

Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e 'g', documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors, and are usually high-dimensional data. The performance of conventional multidimensional data structures(e'g', R- Tree family, K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R＊-tree is the most successful variant of the R-tree. In this paper, we propose a SOM-based R＊-tree as a new indexing method for high-dimensional feature vectors.The SOM-based R＊-tree combines SOM and R＊-tree to achieve search performance more scalable to high dimensionalities. Self-Organizing Maps (SOMs) provide mapping from high-dimensional feature vectors onto a two dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological of the feature map, and preserves the mutual relationship (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. Each node of the topological feature map holds a codebook vector. A best-matching-image-list. (BMIL) holds similar images that are closest to each codebook vector. In a topological feature map, there are empty nodes in which no image is classified. When we build an R＊-tree, we use codebook vectors of topological feature map which eliminates the empty nodes that cause unnecessary disk access and degrade retrieval performance. We experimentally compare the retrieval time cost of a SOM-based R＊-tree with that of an SOM and an R＊-tree using color feature vectors extracted from 40, 000 images. The result show that the SOM-based R＊-tree outperforms both the SOM and R＊-tree due to the reduction of the number of nodes required to build R＊-tree and retrieval time cost.

• 한국CDE학회논문집
• /
• 제11권1호
• /
• pp.27-40
• /
• 2006

The exchange of parameterized feature-based CAD models is important for product data sharing among different organizations and automation systems. The role of feature-based modeling is to gonerate the shape of product and capture design intends In a CAD system. A feature is generated by referring to topological entities in a solid. Identifying referenced topological entities of a feature is essential for exchanging feature-based CAD models through a neutral format. If the CAD data contains the modification history in addition to the construction history, a matching mechanism is also required to find the same entity in the new model (post-edit model) corresponding to the entity in the old model (preedit model). This problem is known as the persistent naming problem. There are additional problems arising from the exchange of parameterized feature-based CAD models. Authors have analyzed previous studies with regard to persistent naming and characteristics for the exchange of parameterized feature-based CAD models, and propose a solution to the persistent naming problem. This solution is comprised of two parts: (a) naming of topological entities based on the object spore information (OSI) and secondary name (SN); and (b) name matching under the proposed naming.