• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.383-388
• /
• 2005

Depth recovery in robot vision is an essential problem to infer the three dimensional geometry of scenes from a sequence of the two dimensional images. In the past, many studies have been proposed for the depth estimation such as stereopsis, motion parallax and blurring phenomena. Among cues for depth estimation, depth from lens translation is based on shape from motion by using feature points. This approach is derived from the correspondence of feature points detected in images and performs the depth estimation that uses information on the motion of feature points. The approaches using motion vectors suffer from the occlusion or missing part problem, and the image blur is ignored in the feature point detection. This paper presents a novel approach to the defocus technique based depth from lens translation using sequential SVD factorization. Solving such the problems requires modeling of mutual relationship between the light and optics until reaching the image plane. For this mutuality, we first discuss the optical properties of a camera system, because the image blur varies according to camera parameter settings. The camera system accounts for the camera model integrating a thin lens based camera model to explain the light and optical properties and a perspective projection camera model to explain the depth from lens translation. Then, depth from lens translation is proposed to use the feature points detected in edges of the image blur. The feature points contain the depth information derived from an amount of blur of width. The shape and motion can be estimated from the motion of feature points. This method uses the sequential SVD factorization to represent the orthogonal matrices that are singular value decomposition. Some experiments have been performed with a sequence of real and synthetic images comparing the presented method with the depth from lens translation. Experimental results have demonstrated the validity and shown the applicability of the proposed method to the depth estimation.

• 한국정보처리학회논문지
• /
• 제7권5호
• /
• pp.1361-1369
• /
• 2000

For the implementation of 3D Sound Localization system, the binaural filtering by HRTFs is generally employed. But the HRTF filter is of high order and its coefficients for all directions have to be stored, which imposes a rather large memory requirement. To cope with this, research works have centered on obtaining low dimensional HRTF representations without significant loss of information and synthesizing the original HRTF efficiently, by means of feature extraction methods for multivariate dat including PCA. In these researches, conventional linear PCA was applied to the frequency domain HRTF data and using relatively small number of principal components the original HRTFs could be synthesized in approximation. In this paper we applied neural network based nonlinear PCA model (NLPCA) and the nonlinear PLS repression model (NLPLS) for this low dimensional HRTF modeling and analyze the results in comparison with the PCA. The NLPCA that performs projection of data onto the nonlinear surfaces showed the capability of more efficient HRTF feature extraction than linear PCA and the NLPLS regression model that incorporates the direction information in feature extraction yielded more stable results in synthesizing general HRTFs not included in the model training.

• 한국방사선학회논문지
• /
• 제10권8호
• /
• pp.571-576
• /
• 2016

3D 프린팅은 최근 다양한 분야에서 활용 되고 있다. 다양한 활용 분야 중 사람의 얼굴을 3D 프린팅을 위해서는 먼저 3D 얼굴 데이터를 생성해야 한다. 3D 얼굴 데이터 획득을 위해 레이저 스캐너 등이 활용되고 있으나 스캔 중에 사람이 움직이면 안 되는 제약이 있다. 본 논문에서는 단일 영상 기반의 3D 얼굴 모델링 방법과 생성된 3D 얼굴을 가상 성형 등에 쓰일 수 있도록 얼굴 변형 시스템을 제안한다. 3D 얼굴 데이터 생성을 위해 3D 얼굴 데이터베이스로부터 특징점들을 정의하였다. 단일 얼굴 영상으로부터 얼굴을 특징점을 추출 한 후 3D 얼굴 데이터베이스로부터 정의된 3D 얼굴 특징점과 대응하여 입력 얼굴 영상의 3D 얼굴을 생성한다. 3D 얼굴 생성 후에 가상 성형 등의 용도를 위해 얼굴 변형 부분을 적용하였다.

• 한국정보과학회논문지:데이타베이스
• /
• 제30권3호
• /
• pp.237-251
• /
• 2003

이 논문에서는 비디오 데이타의 논리적 구조와 의미적 내용을 효과적으로 검색하기 위한 비디오 검색 시스템을 제안한다. 제안하는 검색 시스템은 비정형화된 비디오 데이타를 원시 데이타 계층, 내용 계층 그리고 키프레임 계층의 세 계층으로 구성하는 계층화된 모델링을 사용한다. 계층화된 모델링에 존재하는 내용 계층은 비디오 데이타에 대한 논리적인 계층 구조와 의미적 내용을 표현한다. 제안하는 검색 시스템은 모델링에 따라 텍스트 기반의 검색은 물론 시각적인 특징 기반의 유사도 검색을 지원한다. 또한 시공간 관계에 기반한 의미적 내용 검색과 유사도 검색을 지원한다.

• 디지털융복합연구
• /
• 제12권6호
• /
• pp.223-229
• /
• 2014

대용량의 지식베이스 시스템에서 유용한 정보를 추출하여 효율적인 의사결정을 수행하기 위해서는 정제된 특징추출이 필수적이고 중요한 부분이다. 러프집합이론에 있어서 최적의 리덕트의 추출과 효율적인 객체의 분류에 대한 문제점을 극복하고 자, 본 연구에서는 조건 및 결정속성의 효율적인 특징추출을 위한 러프엔트로피 기반 퀵리덕트 알고리듬을 제안한다. 제안된 알고리듬에 의해 유용한 특징을 추출하기 위한 조건부 정보엔트로피를 정의하여 중요한 특징들을 분류하는 과정을 기술한다. 또한 본 연구의 적용사례로써 실제로 UCI의 5개의 데이터에 적용하여 특징을 추출하는 시뮬레이션을 통하여 본 연구의 모델링이 기존의 방법과 비교결과, 제안된 방법이 효율성이 있음을 보인다.

• 산업경영시스템학회지
• /
• 제22권52호
• /
• pp.229-239
• /
• 1999

Enterprise integration, which aims to enhance an enterprise's competitive edge, requires a highly structured product information model as a common product database. Previous research works on this issue have been narrowly focused on the transformation of product information between various operation areas, leading to a situation where enterprise integration lacks a formal method of information modeling. In this paper, research works and issues surrounding product information modeling for enterprise integration are reviewed, and the requirements for a product information model are identified. A product information model called L3DPIM (Layered Three Dimentional Product Information Model) is proposed, which is based on a feature-based design process. This model is expected to serve as a modeling paradigm for enterprise integration.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 1999년도 추계학술대회 발표요약문
• /
• pp.47-51
• /
• 1999

Geo-features play a key role in object-oriented or feature-based geo-processing system. So the strategy for how-to-model and how-to-manage the geo-features builds the main architecture of the entire system and also supports the efficiency and functionality of the system. Unlike the conventional 2D geo-processing system, geo-features in 3D GIS have lots to be considered to model regarding the efficient manipulation and analysis and visualization. When the system is running on the Web, it should also be considered that how to leverage the level of detail and the level of automation of modeling in addition to the support for client side data interoperability. We built a set of 3D geo-features, and each geo-feature contains a set of aspatial data and 3D geo-primitives. The 3D geo-primitives contain the fundamental modeling data such as the height of building and the burial depth of gas pipeline. We separated the additional modeling data on the geometry and appearance of the model from the fundamental modeling data to make the table in database more concise and to allow the users more freedom to represent the geo-object. To get the users to build and exchange their own data, we devised a fie format called VGFF 2.0 which stands for Virtual GIS File Format. It is to describe the three dimensional geo-information in XML(extensible Markup Language). The DTD(Document Type Definition) of VGFF 2.0 is parsed using the DOM(Document Object Model). We also developed the authoring tools for users can make their own 3D geo-features and model and save the data to VGFF 2.0 format. We are now expecting the VGFF 2.0 evolve to the 3D version of SVG(Scalable Vector Graphics) especially for 3D GIS on the Web.

• 한국CDE학회논문집
• /
• 제11권2호
• /
• pp.128-137
• /
• 2006

In this paper, a CAD/CAE integrated optimal design system is developed, in which design and analysis process is automated using CAD/CAE softwares for a complex model in which the modeling by parametric feature is not easy to apply. Unigraphics is used for CAD modeling, in which the process is automated by using UG/Knowledge Fusion for modeling itself and UG/Open API function for the other functions respectively. Structural analyses are also carried out automatically by ANSYS using the imported parasolid model. The developed system is applied for the PLS(Plasma Lighting System) consisting of more than 20 components, which is a next generation illumination system that is used to illuminate stadium or outdoor advertizing panel. The analyses include responses by static, wind and impact loads. As a result of analyses, tilt assembly, which is a link between upper and lower body, is found to be the most critical component bearing higher stresses. Experiment is conducted using MTS to validate the analysis result. Optimization is carried out using the software Visual DOC for the tilt assembly to minimize material volume while maintaining allowable stress level. As a result of optimization, the maximum stress is reduced by 57% from the existing design, though the material volume has increased by 21%.

• ETRI Journal
• /
• 제36권4호
• /
• pp.662-672
• /
• 2014

Human action recognition is used in areas such as surveillance, entertainment, and healthcare. This paper proposes a system to recognize both single and continuous human actions from monocular video sequences, based on 3D human modeling and cyclic hidden Markov models (CHMMs). First, for each frame in a monocular video sequence, the 3D coordinates of joints belonging to a human object, through actions of multiple cycles, are extracted using 3D human modeling techniques. The 3D coordinates are then converted into a set of geometrical relational features (GRFs) for dimensionality reduction and discrimination increase. For further dimensionality reduction, k-means clustering is applied to the GRFs to generate clustered feature vectors. These vectors are used to train CHMMs separately for different types of actions, based on the Baum-Welch re-estimation algorithm. For recognition of continuous actions that are concatenated from several distinct types of actions, a designed graphical model is used to systematically concatenate different separately trained CHMMs. The experimental results show the effective performance of our proposed system in both single and continuous action recognition problems.

• 대한전자공학회논문지SP
• /
• 제43권4호
• /
• pp.46-54
• /
• 2006

최근 각종 온라인 상거래 및 개인 신분카드 이용이 늘어나면서 개인 인증의 중요성이 부각되고 있다. RFID(Radio Frequency Identification) tag가 내장된 개인 신분 카드가 점차 증가하고 있지만, 본인의 인증을 할 수 있는 방법이 미비하기 때문에, 자동화 할 수 있는 대책이 시급하다. RFID tag는 현재 메모리 용량이 매우 작기 때문에, 개인의 생체정보를 저장하기 위해서는 효율적인 특징추출 방법이 필요하며, 저장된 특징들을 비교하기 위해서는 새로운 인식방법이 필요하다. 본 논문에서는 인간의 인지학적인 두뇌 원리인 해마 신경망을 공학적으로 모델링하여 얼굴 영상의 특징 벡터들을 고속 학습하고, 각 영상의 최적의 특정을 구성할 수 있는 해마 신경망 모델링 알고리즘을 이용한 개인생체 인증 시스템에 관한 연구를 수행하였다. 시스템은 크게 NMF(Non-negative Matrix Factorization)와 LDA(Linear Discriminants Analysis) 혼합 알고리즘을 이용한 특징 추출 부분과 해마신경망을 모델링하고 인식 성능을 실험하는 것으로 구성 되어 있다. 제안한 시스템의 성능을 평가하기 위하여 실험은 표정변화와 포즈변화가 포함된 이미지를 각각 구분하여 인식률을 확인하였다. 실험 결과, 본 논문에서 제안하는 특정 추출 방법과 학습 방법을 다른 방법들과 비교하였을 때, 학습시간비용과 인식률에서 우수함을 확인하였다.