• 한국멀티미디어학회논문지
• /
• 제17권5호
• /
• pp.556-565
• /
• 2014

This paper proposes a method to track object of real-time video transferred through single web-camera and to recognize risk-situation and human actions. The proposed method recognizes human basic actions that human can do in daily life and finds risk-situation such as faint and falling down to classify usual action and risk-situation. The proposed method models the background, obtains the difference image between input image and the modeled background image, extracts human object from input image, tracts object's motion and recognizes human actions. Tracking object uses the moment information of extracting object and the characteristic of object's recognition is moment's change and ratio of object's size between frames. Actions classified are four actions of walking, waling diagonally, sitting down, standing up among the most actions human do in daily life and suddenly falling down is classified into risk-situation. To test the proposed method, we applied it for eight participants from a video of a web-cam, classify human action and recognize risk-situation. The test result showed more than 97 percent recognition rate for each action and 100 percent recognition rate for risk-situation by the proposed method.

• 패션비즈니스
• /
• 제19권4호
• /
• pp.92-108
• /
• 2015

This study aimed at developing a down jacket prototype that utilized sunlight as an alternative energy source with no air pollution. The jacket is filled with flexible solar panels and has a heat-generating function and LED function. In this study, three smart down jacket prototypes were developed, and the jacket's capabilities were demonstrated through the thermal effect on the performance test. The typical output voltage of the flexible solar panels was 6.4V. By connecting the 2 solar cell modules in series, the final output voltage was 12.8V. A battery charge regulator module was used the KA 7809 (TO-220) of 9V. Three heating pads were to be inserted into the belly of the jacket as direct thermal heating elements, and the LED module was configured, separated by a flash and an indicator. The smart down jacket was designed to prevent damage to the down pack without the individual devices' interfering with the human body's motion. Because this study provides insulation from extreme cold with a purpose, the jacket was tested for heat insulation properties of non-heating, heating on the back, heating on the abdomen, and heating on both the back and abdomen in a sitting posture in a static state. Thermal property analysis results from examining the average skin temperature, core temperature, and the temperature and humidity within clothing showed, that placing a heating element in one place was more effective than distributing the heating elements in different locations. Heating on the back was the most effective for maintaining optimal skin temperature, core temperature, and humidity, whereas heating on the abdomen was not effective for maintaining optimal skin temperature, core temperature, or humidity within clothing because of the gap between the jacket and the body.

• 로봇학회논문지
• /
• 제2권4호
• /
• pp.297-303
• /
• 2007

In this paper, we discuss a service to give alarm in the case of emergency for the old and the weak by human behavior recognition in Intelligent Space. Our Intelligent Space consists of mobile robots, sensors and agents. And these components are connected to network framework. Agent analyzes data acquired from networked sensors and determines task of robots and a space to provide a service for humans. In our emergency alarm service, human behavior recognition service module analyzes accelerometer data obtained from body-attached human behavior sensing platform, and classifies into four basic human behavior such as walking, running, sitting and falling-down. For the old and the weak, falling-down behavior may bring about dangerous situations. On such an occasion, agent executes emergency alarm service immediately. And then a selected mobile robot approaches fallen person and sends images of the person to guardians. In this paper, we set up a scenario to verify the emergency alarm service in Intelligent Space, and show feasibility of the service from our simulation experiments.

• 대한인간공학회지
• /
• 제22권2호
• /
• pp.57-69
• /
• 2003

This study was performed to investigate the isometric endurance time as percentages of maximum voluntary contraction. Electromyogram(EMG) and Borg's CR-I0 value were measured by push-pull-up-down tasks for 10 healthy males. The normalized EMG value and the MPF(mean power frequency) were used to estimate the muscle recruitment pattern and the development of muscle fatigue. The subjects exerted and maintained 5 levels of %MVC(maximum voluntary contraction) in $90^{\circ}$ shoulder flexion/ 180oelbow extension at sitting posture. The up-task showed the lower endurance time and higher Borg's CR-I0 value than the other task types. Comparing Rohmert's curve with the endurance time of task types. Rohmert's curve overestimated the endurance time of up-task and underestimated the endurance time of push-pull-down tasks. The normalized EMG value showed that muscles recruitment patterns were different from task types. The 4 muscles(biceps brachii muscle, tricep brachii muscle. middle deltoid muscle. trapezius muscle) recruitment patterns of up-task were higher than those of other tasks. The MPF value decreased with the endurance time, and the shift of MPF at up-task was larger than that of the other task types.

• The Journal of Korean Physical Therapy
• /
• 제27권2호
• /
• pp.124-127
• /
• 2015

Purpose: The emphasis on gait rehabilitation after stroke depends on training support through the lower limbs, balance of body mass over the changing base of support. However, muscle weakness, lack of control of lower limb, and poor balance can interfere with training after stroke. For this case study report, a wearable robot orthosis was applied to stroke patients in order to verify its actual applicability on balance and gait ability in the clinical field. Methods: Two stroke patients participated in the training using the wearable robot orthosis. Wearable robot orthosis provides patient-initiated active assistance contraction during training. Training includes weight shift training, standing up and sitting down, ground walking, and stair up and down Training was applied a total of 20 times, five times a week for 4 weeks, for 30 minutes a day. Gait ability was determined by Stance phase symmetry profile, Swing phase symmetry profile, and velocity using the GAITRite system. Balance ability was measured using the Biodex balance system. Results: Subjects 1, 2 showed improved gait and balance ability with mean individual improvement of 72.4% for velocity, 19.4% for stance phase symmetry profile, 9.6% for swing phase symmetry profile, and 13.6% for balance ability. Conclusion: Training utilizing a wearable robot orthosis can be useful for improvement of the gait and balance ability of stroke patients.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2009년도 추계학술발표대회 논문집
• /
• pp.168-173
• /
• 2009

The purpose of this study was to analyze behavioral patterns of elderly residents and to identify the characteristics of using furniture and home appliances by elderly-headed households. For this purpose, field studies that included observation and open-ended interview were conducted with 52 households. The data was analyzed with frequency, chi-square test by SPSS 14.0 for windows. The major findings of this study were that: 1) Elderly households had more sitting-down style furniture which was a traditional living mode than western style furniture. 2) They experienced inconvenience to use home appliances that were not designed for the aged. 3) Their behavioral patterns were related with family type and income.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2008년도 제39차 동계학술발표논문집 16권2호
• /
• pp.219-222
• /
• 2009

최근 컴퓨터비젼 분야에서 이벤트 검출 및 인식이 활발히 연구되고 있으며, 도전적인 주제들 중 하나이다. 이벤트 검출 기술들은 많은 감시시스템들에서 유용하고 효율적인 응용 분야이다. 본 논문에서는 사무실 환경에서 발생할 수 있는 이벤트의 검출 및 인식을 위한 방법을 제안한다. 제안된 방법에서의 이벤트는 입장( entering), 퇴장(exiting), 착석(sitting-down), 기립(standing-up)으로 구성된다. 제안된 방법은 하드웨어적인 센서를 사용하지 않고, MHI(Motion History Image) 시퀀스(sequence)를 이용한 인간의 모션 분석을 통해 이벤트를 검출할 수 있는 방법이며, 사람의 체형과 착용한 옷의 종류와 색상, 그라고 카메라로부터의 위치관계에 불변한 특성을 가진다. 에지검출 기술을 HMI 시퀀스정보와 결합하여 사람 모션의 기하학적 특징을 추출한 후, 이 정보를 이벤트 인식의 기본 특징으로 사용한다. 제안된 방법은 단순한 이벤트 검출 프레임웍을 사용하기 때문에 검출하고자 하는 이벤트의 설명만을 첨가하는 것으로 확장이 가능하다. 또한, 제안된 방법은 컴퓨터비견 기술에 기반한 많은 감시시스템에 적용이 가능하다.

• 대한물리치료과학회지
• /
• 제8권2호
• /
• pp.1051-1057
• /
• 2001

This was to study the possible changes of living habit and the resultant changes of human body who indulged in an oriental sitting down culture. our living habits make us take a conveninent direction unconsciously. Also studied the correlation between changes in body related with these living habits. The subjects were 44(22 males and 22 females)normal persons. Frequency and percentage were used in the analysis of data. analysis certain items which require the division of sex seperately in the analysis of result. The limitations of this were the lack of equality and variety in region. age. and sex. This was attempted to get significant results by providing an apportunity to think of activities of daily living habit and studying the relation among living habits with effects of living habit on body.

• 제어로봇시스템학회논문지
• /
• 제8권6호
• /
• pp.484-491
• /
• 2002

We developed a new type of human-sized BWR (biped walking robot) driven by a new actuator based on the ball screw which has high strength and high gear ratio. Each leg of the robot is composed of three pitch joints and one roll joint. In all, a 10 degree-of-freedom robot with two balancing joints was developed. A new type of actuator for the robot is proposed, which is composed of four bar link mechanism driven by the ball screw. The robot overcomes the limit of the driving torque of conventional BWRs. The BWR was designed to walk autonomously by adapting small DC motors for the robot actuators and has a space to board DC battery and controllers. In the performance test, the BWR performed sitting-up and down motion, and walking motion. Through the test, we found the possibility of a high performance biped-walking.

• 한국IT서비스학회지
• /
• 제11권sup호
• /
• pp.113-121
• /
• 2012

In this study, a real-time fall detection system based on a smartphone equipped with three-axis accelerometer and magnetometer was proposed and evaluated. The proposed system provides a service that detects falls in real time, triggers alarm sound, and sends emergency SMS(Short Message Service) if the alarm is not deactivated within a predefined time. When both of the acceleration magnitude and angle displacement of the smartphone attached to waist belt are greater than predefined thresholds, it is detected as a fall. The proposed system was evaluated against activities of daily living(walking, jogging, sitting down, standing up, ascending stairs, and descending stairs) and unintended falls induced by a proprietary pneumatic-powered mattress. With the thresholds of acceleration magnitude 1.7g and angle displacement $80^{\circ}$, it showed 96.5% accuracy to detect the falls while all the activities of daily living were not detected as fall.