• 인터넷정보학회논문지
• /
• 제9권3호
• /
• pp.91-101
• /
• 2008

본 논문에서는 구성요소와 그들 간의 유연한 연결을 가진 인체 모델로 인체를 추적하기 위한 구성요소 기반 확률 전파를 제안한다. 인체는 사람의 동작을 추적하는데 필요한 6개의 인체 부위로 나뉘는데, 머리, 몸통, 왼팔, 오른팔, 왼발, 오른발 등이다. 제안하는 추적 방법은 인체 전체의 실루엣을 추적하지 않는 것이 아니라 구성요소로 이루어진 인체모델을 이용하여 인체의 각 부위를 개별적으로 추적하게 된다. 제안된 인체 추적 시스템은 유아의 동작 교육에 적용되는데, 균형잡기, 앙감질, 뛰기, 걷기, 회전하기, 구부리기, 뻗기와 같은 동작을 추적하는데 이용된다. 제안하는 시스템은 인체 모델의 각 부위를 개별적으로 탐지하고 움직임을 추적하여 평균 97%의 추적율을 획득하였다.

• 한국CDE학회논문집
• /
• 제14권6호
• /
• pp.364-373
• /
• 2009

In this paper, we suggest the method for constructing parameterized human body model which has any required body sizes from 3D scan data. Because of well developed 3D scan technology, we can get more detailed human body model data which allow to generate precise human model. In this field, there are a lot of research is performed with 3D scan data. But previous researches have some limitations to make human body model. They need too much time to perform hole-filling process or calculate parameterization of model. Even more they missed out verification process. To solve these problems, we used several methods. We first choose proper 125 3D scan data from 5th Korean body size survey of Size Korea according to age, height and weight. We also did post process, feature point setting, RBF interpolation and align, to parameterize human model. Then principal component analysis is adapted to the result of post processed data to obtain dominant shape parameters. These steps allow to reduce process time without loss of accuracy. Finally, we compare these results and statistical data of Size Korea to verify our parameterized human model.

• 인터넷정보학회논문지
• /
• 제7권1호
• /
• pp.65-74
• /
• 2006

인체 추적은 차세대 인간과 컴퓨터사이의 상호작용 (HCI)의 필수요소이다. 본 논문에서는 구성요소에 기반을 둔 인체 모델을 이용하여 인체의 각 부위를 검출하여 자세를 추정하고 아바타의 동작을 구현하는 방법을 제안한다. 인체 각 부위의 색상정보와 함께 연결정보, 위치정보 등을 이용하여 인체 각 부위가 검출되고 인체 모델의 각 구성요소에 매칭된다. 이렇게 구한 2D의 인체 자세 정보는 다음 프레임에서 유사도 계산을 통해 사람 추적에 이용될 수 있다. 이 때, 각 구성요소의 상대적인 위치 관계를 이용하여 깊이 정보를 추출하고 이를 움직임 방향으로 변환하여 2-1/2D 인체 모델을 구한다. 인체 각 부위는 자세와 방향성으로 모델링 되고 연결된 3D 아바타의 각 부분은 인체 모델로부터 넘겨받은 정보를 이용하여 3D 회전을 적용함으로써 실시간 아바타 애니메이션을 구현하게 된다. 다양한 자세를 포함하고 있는 실험 동영상에 대해 90%의 인체 추적율을 얻었고, 처리된 프레임 수가 늘어남에 따라 모델이 체계화되어 추적율이 꾸준히 증가하는 결과를 나타냈다.

• 전력전자학회논문지
• /
• 제21권3호
• /
• pp.254-259
• /
• 2016

Recently, DC distribution systems have become a hot issue because of the increase in digital loads and DC generation systems according to the expansion of renewable energy technologies. To obtain the practical usage of DC electricity, safety should be guaranteed. The main concerns for safety are twofold: one side is human protection against electric shocks, and the other is facility protection from short faults. "Effects of current on human beings and livestock" (IEC 60479) defines a human body impedance model in electric shock conditions that consists of resistive components and capacitive components. Although the human body impedance model properly works in AC electricity, it does not well match with the electric shock behavior in DC electricity. In this study, the contradiction of the human body impedance model defined by IEC 60479 in case of DC electricity is shown through experiments for the human body. From the analysis of experimental results, a novel unified human body impedance model in electric shock conditions is proposed. This model consists of resistive components, capacitive components, and an inductance component. The proposed human impedance model matches well for AC and DC electricity environments in simulation and experiment.

• 한국자동차공학회논문집
• /
• 제12권1호
• /
• pp.145-152
• /
• 2004

This paper compares seat vibrations of a small passenger car and a SUV. The results also include the comparison of the human body accelerations and the ride values, such as the component ride values, and SEAT values of 12 axis accelerations obtained at the human body and seat track. The ride comfort evaluation is usually carried out by experiments of real cars which are expensive and sometimes may contain errors by passenger's postures. Simulations by computer, on the other hand, enable to solve these problems when the accuracy is proven. This paper, thus, also shows the correlation of human body vibration between experiments and computer simulations. For the computer simulation, korean dummy models are developed from the Hybrid III models by scaling the body data of Hybrid III to those of Korean men and women. From the comparison between the test data and simulation data, a nice correlation in trends was shown.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2839-2852
• /
• 2013

Context-awareness is an essential part of ubiquitous computing, and over the past decade video based activity recognition (VAR) has emerged as an important component to identify user's context for automatic service delivery in context-aware applications. The accuracy of VAR significantly depends on the performance of the employed human body segmentation algorithm. Previous human body segmentation algorithms often engage modeling of the human body that normally requires bulky amount of training data and cannot competently handle changes over time. Recently, active contours have emerged as a successful segmentation technique in still images. In this paper, an active contour model with the integration of Chan Vese (CV) energy and Bhattacharya distance functions are adapted for automatic human body segmentation using depth cameras for VAR. The proposed technique not only outperforms existing segmentation methods in normal scenarios but it is also more robust to noise. Moreover, it is unsupervised, i.e., no prior human body model is needed. The performance of the proposed segmentation technique is compared against conventional CV Active Contour (AC) model using a depth-camera and obtained much better performance over it.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2006년도 가을 학술발표논문집 Vol.33 No.2 (B)
• /
• pp.509-514
• /
• 2006

Human action recognition is an active research area in computer vision. In this paper, we present a robust method for human action recognition by using combined information of human body shape and motion information with multiple views image sequence. The principal component analysis is used to extract the shape feature of human body and multiple block motion of the human body is used to extract the motion features of human. This combined information with multiple view sequences enhances the recognition of human action. We represent each action using a set of hidden Markov model and we model each action by multiple views. This characterizes the human action recognition from arbitrary view information. Several daily actions of elderly persons are modeled and tested by using this approach and they are correctly classified, which indicate the robustness of our method.

• 한국컴퓨터그래픽스학회논문지
• /
• 제28권4호
• /
• pp.1-11
• /
• 2022

선형 스키닝 기반 3D 인체 생성 모델 SMPL (Skinned Multi-Person Linear Model)은 1990년대 미국 거주 미국인들 3천 8백여명을 대상으로 만들어진 3D 신체 데이터베이스인 CEASAR 로부터 최적화 기법을 통해 만들어진 가장 널리 쓰이는 통계적인 3D 모델이다. 본 연구는 한국인 체형의 통계적 특성을 보다 정확히 표현하는 SMPL기반의 한국인 체형 3D 모델을 제안한다. 이를 위해 우리는 한국인 여성 2천7백여명의 신체 각 부위의 실측 데이터에 기존 3D SMPL 모델을 피팅하는 비선형 최적화 알고리즘을 개발한다. 이를 사용하여 한국인 3D 신체 데이터베이스를 구축하고, 주성분 분석 방법으로 한국인 체형 기반 매개화된 3D 모델을 개발한다. 본 연구를 통해 제안하는 한국인의 체형적 특징을 가진 블렌드쉐입과 새로운 체형 파라미터는 기존 모델이 표현하는 체형에 비해 한국인 체형 데이터 특성을 잘 반영함을 확인하였다. 뿐만 아니라, 우리의 모델은 SMPL에 비해 신체 실측 데이터에 대한 피팅 정확도를 개선함을 확인하였다. 제안된 모델은 향후 아바타 생성이나 인체 형상 측정 등 다양한 용도로 사용될 수 있다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.764-767
• /
• 2009

Motion capture systems allow to measure the precise position of markers on the human body in real time. These captured motion data, the marker position data, have to be fitted by a human skeleton model to represent the motion of the human. Typical human skeleton models approximate the joints using a ball joint model. However, because this model cannot represent the human skeleton precisely, errors between the motion data and the movements of the simplified human skeleton model happen. We propose in this paper a method for measuring a translation component of wrist, and elbow joints on upper limb using optical motion capture system. Then we study the errors between the ball joint model and acquired motion data. In addition, we discuss the problem to estimate motion of human joint using optical motion capture system.

• 한국의류학회지
• /
• 제48권1호
• /
• pp.108-119
• /
• 2024

In this study, we aimed to propose enhancements to the dimensions and design of walking aids tailored for elderly women. Specifically, we focused on wheeled walking assistance devices and aligned each structural component with the appropriate human body dimensions to suggest appropriate product dimensions organized by size clusters, aiming to maximize the practicality of the results. We extracted essential factors required for product design, including human body size elements. The dimension extraction method was clustered to establish connections between key human body parameters-such as height, weight, and age groups-and product dimensions. We conducted a comparative analysis of walking aid product dimensions according to the design elements and sizes of models currently available in the market. The outcomes of this study offer objective, data-driven insights into areas where existing models on the market could benefit from improvement and we anticipate that the findings of this study will provide a solid, quantitative foundation for individuals when selecting the most suitable model for their needs.