• 방송공학회논문지
• /
• 제19권6호
• /
• pp.942-956
• /
• 2014

본 논문은 단안의 RGB 카메라를 이용하는 실시간 손 추적 방법을 제안한다. 손은 높은 degrees of freedom을 가지고 있기 때문에 손 추적은 높은 모호성을 가지고 있다. 따라서 제안하는 방법에서는 손 추적의 모호성을 줄이기 위해서 단계별 손 추적 전략을 채택하였다. 제안하는 방법의 추적 과정은 손바닥 포즈 추적, 손가락 yaw 움직임 추적, 그리고 손가락 pitch 움직임 추적, 세 단계로 구성되어 있으며, 각 단계는 순서대로 수행된다. 제안하는 방법은 손은 평면으로 간주할 수 있다고 가정하고, 평면 손 모델을 이용한다. 평면 손 모델은 손 모델을 현재의 사용자 손 모양에 맞춰서 변경하는 손 모델 재생성을 가능하게 하는데, 이는 제안하는 방법의 강건성과 정확도를 증가시킨다. 그리고 제안하는 방법은 실시간 연산이 가능하고 GPU 기반 연산을 요구하지 않기 때문에, Google Glass와 같은 모바일 장비를 포함한 다양한 환경에 적용가능하다. 본 논문은 다양한 실험을 통해서 제안하는 방법의 성능과 효용성을 입증한다.

• 제어로봇시스템학회논문지
• /
• 제7권4호
• /
• pp.309-318
• /
• 2001

In this paper, we describe methods that analyze a human gesture. A human interface(HI) system for analyzing gesture extracts the head and hand regions after taking image sequence of and operators continuous behavior using CCD cameras. As gestures are accomplished with operators head and hands motion, we extract the head and hand regions to analyze gestures and calculate geometrical information of extracted skin regions. The analysis of head motion is possible by obtaining the face direction. We assume that head is ellipsoid with 3D coordinates to locate the face features likes eyes, nose and mouth on its surface. If was know the center of feature points, the angle of the center in the ellipsoid is the direction of the face. The hand region obtained from preprocessing is able to include hands as well as arms. For extracting only the hand region from preprocessing, we should find the wrist line to divide the hand and arm regions. After distinguishing the hand region by the wrist line, we model the hand region as an ellipse for the analysis of hand data. Also, the finger part is represented as a long and narrow shape. We extract hand information such as size, position, and shape.

• 약학회지
• /
• 제46권5호
• /
• pp.331-336
• /
• 2002

The purpose of this study is to develop a non-invasive blood glucose measurement method by a portable near infrared (NIR) system which was newly integrated by our lab. The portable NIR system includes a tungsten halogen lamp, a specialized reflectance fiber optic probe and a photo diode array type InGaAs detector; which was developed by a microchip technology based on the lithography. Reflectance NIR spectra of different parts of human body (finger tip, earlobe, and inner lip) were recorded by using a fiber optic probe. The spectra were collected over the spectral range 1100 ∼ 1740 nm. Partial least squares regression (PLSR) was applied for the calibration and validation for the determination of blood glucose. The calibration model from earlobe spectra presented better results, showing good correlation with a glucose oxidase method which is a mostly used standard method. This model predicted the glucose concentration for validation set with a SEP of 33 mg/dL. This study indicated the feasibility for non-invasive monitoring of blood glucose by a portable near infrared system.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.49-55
• /
• 2022

Hair styling has a significant influence on human social perception. An increasing number of people are learning hair styling and obtaining hair designer licenses. However, it takes a considerable amount of money and time to learn professional hairstyle and beauty techniques for hair styling. Since COVID-19, there has been a growing need for offline and video lectures due to the decline in onsite training opportunities. This study provides a field practice environment in which real hair beauty is performed in a virtual space. Further, the hairstyle that is most similar to the user's hair taken with a webcam or mobile phone is determined through an image matching system using the speeded up robust features (SURF) method. The matching hairstyle was created into a three-dimensional (3D) hair model. The created 3D hair model uses a head-mounted display (HMD) and a controller that enables finger tracking through mapping to reproduce the haircutting scissors' motion while providing a feeling of real hair beauty.

• Journal of Electrical Engineering and Technology
• /
• 제9권5호
• /
• pp.1774-1779
• /
• 2014

It is known that muscle strength of human body can alter or deteriorate as aging. In this study, we present an inverse dynamics simulation to investigate the effect of muscle strength on performing the daily activities. A 3D musculoskeletal model developed in this study includes several segments of whole body, long and short muscles, ligaments and disc stiffness. Five daily activities such as standing, flexion, finger tip to floor, standing lift close and lifting flexed were simulated with varying the maximum muscle force capacities (MFC) of each muscle fascicles from 30 to $90N/cm^2$ with an increment of $30N/cm^2$. In the result, no solution can be obtained for finger tip to floor and lifting flexed with $30N/cm^2$. Even though the solution was available for standing lift close activity in case of $30N/cm^2$ capacity, many of muscle fascicles hit the upper bound of muscle strength which means that it is not physiologically possible to perform the acvities in reality. For lifing flexed, even the case of $60N/cm^2$ capaciy, represents the moderate healthy people, was not able to find the solutions, showing that 18 muscles among 258 muscle fascicles reached 100% of muscle capacity. The estimated results imply that people who have low muscle strength such as elders or rehabilitation patients were required higher muscle work to perform and maintain the same daily activities than healthy one.

• 한국산학기술학회논문지
• /
• 제20권9호
• /
• pp.525-531
• /
• 2019

인간과 컴퓨터 사이의 보다 자연스러운 상호적인 인터페이스를 효과적으로 구현하기 위해서 사람의 제스처를 활용하려는 노력이 최근 들어 지속적으로 시도되고 있다. 본 논문에서는 연속적으로 입력되는 3차원의 깊이 영상을 받아들여서 손 모델을 정의하고, 정의된 손 모델을 기반으로 사람의 손 영역을 강인하게 추출하는 알고리즘을 제시한다. 본 논문에서 제시된 알고리즘에서는 먼저 21개의 관절을 사용하여 손 모델을 정의한다. 본 논문에서 정의한 손 모델은 6개의 손바닥 관절을 포함하는 손바닥 모델과 15개의 손가락 관절을 포함하는 손가락 모델로 구성된다. 그런 다음, 입력되는 3차원의 깊이 영상을 적응적으로 이진화함으로써, 배경과 같은 비관심 영역들은 제외하고, 관심 영역인 사람의 손 영역만을 정확하게 추출한다. 실험 결과에서는 제시된 알고리즘이 연속적으로 입력되는 깊이 영상으로부터 배경과 같은 영역들은 제외하고 사람의 손 영역만을 기존의 알고리즘에 비해 약 2.4% 보다 강인하게 검출한다는 것을 보여준다. 본 논문에서 제안된 손 영역 추출 알고리즘은 제스처 인식, 가상현실 구현, 3차원 운동 게임, 수화 인식 등과 같은 컴퓨터 비전 및 영상 처리와 관련된 여러 가지의 실제적인 분야에서 유용하게 활용될 것으로 기대된다.

• 한국수소및신에너지학회논문집
• /
• 제21권3호
• /
• pp.167-183
• /
• 2010

This paper analyzes the backgrounds of the standards for protection against electric shock in Global Technical Regulations (GTR) of Fuel Cell Vehicle (FCV). Targets on research were high voltage criteria, safety current, isolation and grounding resistance, time limitation, energy, adequate clearance, and test procedure. Based on human impedance and effect of current in IEC 60479-1, safety of human was examined. Then, isolation and grounding circuit model of FCV were analyzed theoretically. The results give several suggestions: touch voltage less than 25V, AC energy less than 0.0813J, separation considering middle finger length, grounding resistance less than $0.2\Omega$, maximum AC ground voltage of 1V (rms), and isolation resistance between earth and electrical chassis. In MATLAB/Simulink environment, error characteristics of isolation resistance measurement procedure using internal DC sources were analyzed under variations of internal resistance of voltmeter and isolation resistance.

• Journal of Korean Neurosurgical Society
• /
• 제59권6호
• /
• pp.544-550
• /
• 2016

Objective : Cerebral endothelial cells have unique biological features and are fascinating candidate cells for stroke therapy. Methods : In order to understand the molecular mechanisms of human cerebral endothelial cell (hCMEC/D3) transplantation in a rat stroke model, we performed proteomic analysis using 2-dimensional electrophoresis and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. Protein expression was confirmed by quantitative real-time PCR and Western blot. Results : Several protein spots were identified by gel electrophoresis in the sham, cerebral ischemia (CI), and CI with hCMEC/D3 treatment cerebral ischemia with cell transplantation (CT) groups, and we identified 14 differentially expressed proteins in the CT group. Proteins involved in mitochondrial dysfunction (paraplegin matrix AAA peptidase subunit, SPG7), neuroinflammation (peroxiredoxin 6, PRDX6), and neuronal death (zinc finger protein 90, ZFP90) were markedly reduced in the CT group compared with the CI group. The expression of chloride intracellular channel 4 proteins involved in post-ischemic vasculogenesis was significantly decreased in the CI group but comparable to sham in the CT group. Conclusion : These results contribute to our understanding of the early phase processes that follow cerebral endothelial cell treatment in CI. Moreover, some of the identified proteins may present promising new targets for stroke therapy.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권11호
• /
• pp.851-859
• /
• 2002

본 연구는 마우스의 입력을 사람의 손동작으로 대체하는 휴먼마우스 시스템을 위한 새로운 손끝 좌표 추적기법과 마우스 포인터 움직임 결정법을 제안한다. 손끝좌표 추적에는 얼굴영역 추적을 위해 제안되었던 CAMSHIFT 알고리즘을 개선하여 적용하였다. 정확한 손 영역 검출을 위하여 각 사용자의 환경에 최적화된 피부영역 컬러 정보를 얻을 수 있는 실시간 피부영역 학습과 손의 자유로운 움직임으로 인하여 발생하는 손 영역의 크기 및 방향변화를 고려한 영역제한 기법을 적용하였다. 또한 손의 주축을 이용한 손끝좌표 계산법을 통해 빠르고 정확하게 손끝의 위치를 찾을 수 있다. 실시간 손끝좌표 검출에는 처리속도의 한계가 있어 얻어지는 좌표의 연속성이 결여되어 마우스 포인터의 움직임이 연결되지 않는 문제점이 있다. 연속적인 마우스 포인터의 움직임 표현을 위해 손끝좌표의 이동거리를 통해 마우스 포인터의 속도와 가속도를 계산하여 마우스 포인터의 운동방정식을 정의하고 이를 이용하여 마우스 포인터의 위치를 결정한다. 제안한 알고리즘을 적용하여 실험한 결과 빠르고 정확한 손끝좌표 추적과 마우스 포인터의 자연스러운 움직임이 가능함을 보였다.

• 센서학회지
• /
• 제15권5호
• /
• pp.334-340
• /
• 2006

A compact biosignal monitoring device was developed. Electrodes for electrocardiogram (ECG) and a LED and silicon detector for photoplethysmogram (PPG) were used. A lead II type was arranged for ECG measurement and reflected light was measured at the finger tip for PPG. A single chip microprocessor (model ADuC812, Analog Device) controlled a measurement protocol and processed measured signals. PPG and ECG had a sampling rate of 300 Hz with 8-bit resolution. The maximum power consumption was 100 mW. The microprocessor computed pulse transit time (PTT) between the R-wave of ECG and the peak of PPG. To increase the resolution of PTT, analog peak detectors obtained the peaks of ECG and PPG whose interval was calculated using an internal clock cycle of 921.6 kHz. The device was designed to be operated by 3-volt battery. Biosignals can be measured for $2{\sim}3$ days continuously without the external interruptions and data is stored to an on-board memory. Our system was successfully tested with human subjects.