• 전자통신동향분석
• /
• 제36권4호
• /
• pp.92-102
• /
• 2021

Outdoor sports activities have been restricted by serious air pollution, such as fine dust and yellow dust, and abnormal meteorological change, such as heatwave and heavy snow. These environmental problems have rapidly increased the demand for indoor sports activities. Virtual sports, such as virtual golf, virtual baseball, virtual soccer, etc., allow playing various sports games without going outdoors. Indoor sports industries and markets have seen rapid growth since the advent of virtual sports. Most virtual sports platforms use screen-based virtual reality techniques, which are why they are called screen sports. However, these platforms cannot support various sports games, especially virtual match games, such as squash, boxing, and so on, because existing screen-based virtual reality sports techniques use real balls and players. This article presents screen-based haptic-augmented reality technologies for a new virtual sports platform. The new platform does not use real balls and players to solve the limitations of previous platforms. Here, various technologies, including human motion tracking, human action recognition, haptic feedback, screen-based augmented-reality systems, and augmented-reality sports content, are unified for the new virtual sports platform. From these haptic-augmented reality technologies, the proposed platform supports sports games, including indoor virtual matches, that existing virtual sports platforms cannot support.

• Journal of Mechanical Science and Technology
• /
• 제16권3호
• /
• pp.283-291
• /
• 2002

The paper demonstrates the tracking performance of a sliding horizon feedback/feedforward preview optimal control when applied to a hydraulic motion simulator which has been built to provide a means of replicating the actual ride dynamics of an automobile seat/human system. The design was developed by solving an ordinary differential equation problem instead of a Ricatti equation. Simulation results indicate that the proposed technique has good performance improvement in phase tracking when compared to the classical design methods. It is also found that the controller can be adjusted more easily for robustness due to more tuning parameters.

• 전자공학회논문지SC
• /
• 제49권1호
• /
• pp.20-28
• /
• 2012

보행을 관찰하고 객관적인 정보를 추출하여 그 기능을 평가하는 것을 보행 분석이라고 한다. 최근 사용되는 보행 측정 장비들은 다수의 카메라, 지면 반력 측정 장치로 구성되어 고가이며, 이를 설치할 넓은 장소를 필요로 한다는 단점이 있다. 본 연구에서는 이러한 문제점을 해결하기 위해 단일 카메라를 통해 얻은 영상에서 마커 없이 인체의 3차원 보행 동작을 측정하는 기법을 제안한다. 파티클 필터를 사용하여 훈련 데이터와 보행에 관한 사전 정보 없이 사람의 동작을 추적한다. 인체와 지면에 관한 동역학을 통해 물리적으로 합당한 인체의 동작들을 생성하였다. 보행 영상에서 계산한 모든 관절의 평균 에러는 제안한 방법에서 $12.4^{\circ}$로, 기존 파티클 필터의 에러 $34.6^{\circ}$보다 작았다. 이러한 결과를 바탕으로 단일 카메라만으로 보행을 정량적으로 측정하여 기존 복잡한 장비를 대체할 수 있는 가능성을 제시하였다.

• 한국지능시스템학회논문지
• /
• 제17권7호
• /
• pp.913-918
• /
• 2007

본 논문에서는 인간과 로봇의 인터액션을 위해 연속된 이미지 정보로부터 얻을 수 있는 색상(color)과 기울기(gradient) 정보를 이용하여 인간 몸의 실루엣 추출 기법을 제안한다. 연속된 이미지 정보로부터 얻어진 RGB 영상 정보에서 색상 배경 제거 기법은 각각의 신체 비율 정보로부터 추출된 모션 영역 정보에서 색상 공판별 평균 이미지 정보를 얻고 옷 색상 정보를 볼록 합하여 계산된다. 기울기 배경 제거 기법은 공간상 정보와 시간상 정보의 볼록 합으로 계산된다. 최종적으로 색상 정보와 기울기 정보의 볼록 합을 하여 인간 몸의 실루엣을 추출한다. 마지막으로, 실험을 통하여 제안된 기법의 성능을 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.291-294
• /
• 2004

Semantic video object extraction is important for tracking meaningful objects in video and object-based video coding. We propose a fast semiautomatic video object extraction algorithm which combines a watershed segmentation schemes and chamfer distance transform. Initial object boundaries in the first frame are defined by a human before the tracking, and fast video object tracking can be achieved by tracking only motion-detected regions in a video frame. Experimental results shows that the boundaries of tracking video object arc close to real video object boundaries and the proposed algorithm is promising in terms of speed.

• 한국기계가공학회지
• /
• 제9권1호
• /
• pp.67-73
• /
• 2010

Finding sufficient supplies of clean energy for future is one of the society's most important challenges according to technologies. Alternative renewable energy source such as sun energy can be substituted for exceeding human energy need. The main factor affect to solar performance is a collective intensity. To enhance intensity, suitable equipment is a solar tracker. This paper presents design and evaluation of 1 layer polar motion control system for solar tracker suitable for building integrated system. To evaluation of tracking accuracy and adaptability, solar tracker with 64 links is implemented. In experimental results, the accuracy of tracking has under ${\pm}0.0287^{\circ}$ and the thickness has under 140mm.

• 대한전자공학회논문지SP
• /
• 제38권6호
• /
• pp.684-691
• /
• 2001

본 논문에서는 비디오 카메라를 통하여 획득한 연속적인 영상에서 사람의 머리를 인식하고 추적하는 시스템을 구현한다. 사람의 머리를 인식하기 위한 특징 벡터로서 얼굴 표면상의 특성인 사람의 피부색과 형태상의 특성인 타원 모델링을 이용한다. 또한 복잡한 배경으로부터 움직인 영역을 획득하기 위하여 시변 에지 검출 방법을 사용하고 획득된 영상에서 물체의 움직임을 판별하기 위하여 수직 투영 방법을 이용한다. 설정된 움직임 영역부분에 대하여 피부색을 갖고 있는 여러 개의 얼굴 후보영역을 설정하고 사람의 얼굴을 대표할 수 있는 타원 매핑을 적용하여 가장 최적으로 매핑되는 영역을 사람의 얼굴 부분으로 인식한다. 본 논문에서 제안한 방법은 사람 얼굴이 360도 회전하는 경우와 부분적으로 가려진 경우 그리고 좌우로 기울어진 경우에서도 우수한 성능을 보여주고 있다. 본 논문에서는 움직임 기반 추적 방법과 인식 기반 추적 방법을 이용하여 사람의 얼굴 부분이 빠르게 움직이는 경우에도 정확한 사람 얼굴 추적이 가능하도록 한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1960-1963
• /
• 2003

For applications such as video surveillance and human computer interface, we propose an efficiently integrated method to detect and track faces. Various visual cues are combined to the algorithm: motion, skin color, global appearance and facial pattern detection. The ICA (Independent Component Analysis)-SVM (Support Vector Machine based pattern detection is performed on the candidate region extracted by motion, color and global appearance information. Simultaneous execution of detection and short-term tracking also increases the rate and accuracy of detection. Experimental results show that our detection rate is 91％ with very few false alarms running at about 4 frames per second for 640 by 480 pixel images on a Pentium IV 1㎓.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권1호
• /
• pp.60-65
• /
• 2012

This paper presents a method for occluded object based motion estimation and tracking system in dynamic image sequences using particle filter with 3D reconstruction. A unique characteristic of this study is its ability to cope with partial occlusion based continuous motion estimation using particle filter inspired from the mirror neuron system in human brain. To update a prior knowledge about the shape or motion of objects, firstly, fundamental 3D reconstruction based occlusion tracing method is applied and object landmarks are determined. And optical flow based motion vector is estimated from the movement of the landmarks. When arbitrary partial occlusions are occurred, the continuous motion of the hidden parts of object can be estimated by particle filter with optical flow. The resistance of the resulting estimation to partial occlusions enables the more accurate detection and handling of more severe occlusions.

• International Journal of Contents
• /
• 제16권3호
• /
• pp.1-17
• /
• 2020

Human motion recognition is essential for user-centric services such as surveillance-based security, elderly condition monitoring, exercise tracking, daily calories expend analysis, etc. It is typically based on the movement data analysis such as the acceleration and angular velocity of a target user. The existing motion recognition studies are only intended to measure the basic information (e.g., user's stride, number of steps, speed) or to recognize single motion (e.g., sitting, running, walking). Thus, a new mechanism is required to identify the transition of single motions for assessing a user's consecutive motion more accurately as well as recognizing the user's body and surrounding situations arising from the motion. Thus, in this paper, we collect the human movement data through Android smartphones in real time for five targeting single motions and propose a mechanism to recognize a consecutive motion including transitions among various motions and an occurred situation, with the state transition model to check if a vulnerable (life-threatening) condition, especially for the elderly, has occurred or not. Through implementation and experiments, we demonstrate that the proposed mechanism recognizes a consecutive motion and a user's situation accurately and quickly. As a result of the recognition experiment about mix sequence likened to daily motion, the proposed adoptive weighting method showed 4% (Holding time=15 sec), 88% (30 sec), 6.5% (60 sec) improvements compared to static method.