• 한국통신학회논문지
• /
• 제34권6C호
• /
• pp.593-603
• /
• 2009

본 논문은 스테레오 카메라가 이동하는 환경에서 카메라 움직임을 보정하여 새로운 다수의 사람을 검출하는 방법과 검출된 사람을 추적하고, 실루엣을 추출하는 통합된 시스템을 제안한다. 제안하는 시스템은 사람 검출, 추적, 실루엣 추출 3가지 모듈로 구성되어 있으며 3가지 모듈은 카메라가 이동하는 환경을 고려한 것이다. 사람 검출 모듈에서는 카메라 움직임(egomotion) 보정을 이용한 움직이는 영역 추출 결과와 스테레오 정보를 결합하여 움직이는 객체를 검출하였으며, 추적모듈은 변위 정보가 가중된 히스토그램 알고리즘으로 검출된 객체를 추적한다. 실루엣을 추출하는 모듈은 트라이맵(trimap)을 이용하여 사람의 실루엣 부분을 대략적으로 추정하는 단계와 그래프컷(graph cut)을 적용하여 정교하게 실루엣 추출하는 단계로 이루어져 있다. 본 논문에서 제안하는 방법을 실내 환경에서 팬-틸트(pan-tilt) 스테레오 카메라로 획득한 실험데이터를 대상으로 실험한 결과 다수의 사람의 검출 및 추적, 정교한 실루엣 추출이 가능한 것을 확인하였다. 본 논문의 실루엣 추출결과는 제스처 인식이나 걸음걸이 인식 등의 다양한 분야에도 적용가능하다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.136-141
• /
• 2002

This paper presents a design and a control of a biped walking RGO-robot and dynamic walking simulation for this system. The biped walking RGO-robot is distinguished from other one by which has a very light-weight and a new AGO type with servo motors. The gait of a biped walking RGO-robot depends on the constrains of mechanical kinematics and initial posture. The stability of dynamic walking is investigated by ZMP(Zero Moment Point) of the biped walking RGO-robot. It is designed according to a human wear type and is able to accomodate itself to human environments. The joints of each leg are adopted with a good kinematic characteristics. To test of the analysis of joint kinematic properties, we did the strain stress analysis of dynamic PLS and the study of FEM with a dynamic PLS. It will be expect that the spinal cord injury patients are able to train effectively with a biped walking AGO-robot.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.238-243
• /
• 2002

This paper presents a design and a control of a biped walking AGO-robot and dynamic walking simulation for this system. The biped walking RGO-robot is distinguished from other one by which has a very light-weight and a new RGO type with servo motors. The gait of a biped walking AGO-robot depends on the constrains of mechanical kinematics and initial posture. The stability of dynamic walking is investigated by ZMP(Zero Moment Point) of the biped walking AGO-robot. It is designed according to a human wear type and is able to accomodate itself to human environments. The joints of each leg are adopted with a good kinematic characteristics. To test of the analysis of joint kinematic properties, we did the strain stress analysis of dynamic PLS and the study of FEM with a dynamic PLS. It will be expect that the spinal cord injury patients are able to train effectively with a biped walking RGO-robot.

• 한국컴퓨터그래픽스학회논문지
• /
• 제4권2호
• /
• pp.1-13
• /
• 1998

캐릭터 애니메이션의 가장 중요한 목표는 효율적으로 캐릭터의 동작을 제어하는 것이다. 지금까지 인간 보행 애니메이션을 위한 많은 기법들이 제안되었고, 파라미터 보간이나 동작 데이터 매핑 을 사용하여 지친 걸음이나 활기찬 걸음과 같은 보행의 감정을 표현하는 기법도 제안되었다. 본 논문은 하나의 다리를 가진 평면 뜀뛰기 모델에 기반한 인간 주행 모델을 제시한다. 본 논문의 기법은 동작 최적화를 위해 유전자 프로그래밍을 사용하며 다양한 캐릭터 모델에 쉽게 적용될 수 있다. 본 논문은 에너지 최소화 기법을 확장하여 감정 표현을 위한 파라미터 설정에 따라 다양한 동작을 생성할 수 있도록 한다.

• The Journal of Korean Physical Therapy
• /
• 제14권4호
• /
• pp.131-146
• /
• 2002

In the last years, it has become possible to regain some locomotor activity in patients with incomplete spinal cord injury (SCI) through intense training on a treadmill. The ideas behind this approach owe much to insights derived from animal studies. Many studies showed that cats with complete spinal cord transection(spinalized animals) can recover locomotor function. These observations were at the basis of the concept of the central pattern generator located at spinal level. The neural system responsible for the locomotor restoration in both cats and humans is thought to be located at spinal level and is referred to as the central pattern generator(CPG). The evidence for such a spinal CPG in human is emphasis on some recent developments which support the view that there is a human spinal CPG for locomotion. An important element in afferent inputs for both spinal injured cats and humans is the provision of adequate sensory input related locomotor, which can possibly activate and/or regulate the spinal locomotor circuitry This review article deals with the afferent control of the central pattern generator. Furthermore, the application of adequate afferent inputs related locomotor for stroke patients will be able to facilitate locomotion ability, which is automatic, cyclic, rhythmic. These insights can possibly contribute to a better therapeutic approach for the rehabilitation of gait in patients with stroke.

• 한국건축시공학회지
• /
• 제15권1호
• /
• pp.133-141
• /
• 2015

바닥의 미끄럼 저항은 보행자 안전을 위해 반드시 필요한 성능이다. 본 연구는 실제 인간의 미끄럼과 잘 대응하는 미끄럼 시험장치를 개발하기 위한 기초적 연구로서, 지면 마찰력(RCOF)과 표면 거칠기(Rz) 및 3가지 미끄럼 저항계수(C.S.R, BPN, SCOF) 간의 상관성을 분석하였다. 보행 속도가 증가할수록 보간 거리, 보폭, 분당 보행 수 모두 증가하며, 보행 속도와 RCOF 간에는 유의한 상관성이 있었다. 그러나 RCOF와 각 미끄럼 저항계수 간에는 상관성이 거의 없기 때문에 RCOF만으로는 바닥의 미끄럼 저항 특성을 파악하기 힘들다.

• 대한인간공학회지
• /
• 제34권5호
• /
• pp.363-375
• /
• 2015

Objective: This study aims to recognize the risk of current traffic systems and to investigate a method to decrease risk by doing exercise using an elastic-band and cognitive rehabilitation. Background: The existing traffic system usually focuses on the ordinary citizens, which may not be appropriate to the elderly. It may affect the cognition and walking speed of the elderly. This study tries to examine whether cognition and muscle training is appropriate to improve their vulnerability. Therefore this study will provide human ergonomics - based basic data in relation to the elderly to identify the risk of current signal system and to mitigate the risk. Method: A total of 30 elderly participants were divided into two groups: experimental and control groups. Experimental group (n=15) was trained to strengthen their muscles and to promote cognition, whereas control group (n=15) was not. The training was conducted twice a week for three weeks. To strengthen muscles, a yellow colored elastic-band was used, and a computer program for cognitive rehabilitation was used to develop cognition. In the experimental group, there were significant differences between pre and post exercises However, the control group didn't show any significant difference. The increase in cognition and walking speed was found in the experimental group, whereas there were no differences in the control group. Statistically there was no significant difference between the two groups. Results: The results of this study show that the exercise program using the elastic-band gave a positive effect on gait training thanks to the development of muscle power and balance. Conclusion: This study did not show any statistical difference or significant differences between the two groups, since time was restricted, we believe. Application: The results of the walking speed will help to prevent traffic collision.

• 제어로봇시스템학회논문지
• /
• 제16권10호
• /
• pp.939-947
• /
• 2010

With the rising numbers of elderly and disabled people, the demand for welfare services using a robotic system and not involving human effort is likewise increasing. This study deals with a mobile-robot system combined with a BWS (Body Weight Support) system for gait rehabilitation. The BWS system is designed via the kinematic analysis of the robot's body-lifting characteristics and of the walking guide system that controls the total rehabilitation system integrated in the mobile robot. This mobile platform is operated by utilizing the AGV (Autonomous Guided Vehicle) driving algorithm. Especially, the method that integrates geometric path tracking and obstacle avoidance for a nonholonomic mobile robot is applied so that the system can be operated in an area where the elderly users are expected to be situated, such as in a public hospital or a rehabilitation center. The mobile robot follows the path by moving through the turning radius supplied by the pure-pursuit method which is one of the existing geometric path-tracking methods. The effectiveness of the proposed method is verified through the real experiments those are conducted for path tracking with static- and dynamic-obstacle avoidance. Finally, through the EMG (Electromyography) signal measurement of the subject, the performance of the proposed system in a real operation condition is evaluated.

• 한국운동역학회지
• /
• 제26권1호
• /
• pp.135-142
• /
• 2016

Objective: The purpose of this study was to investigate the acute effect of walking on high heels on the behavior of fascicle length and activation of the lower limb muscles. Methods: Twelve healthy inexperienced high heel wearers (age: $23.1{\pm}2.0yr$, height: $162.4{\pm}4.9cm$, weight: $54.4{\pm}8.5kg$) participated in this study. They walked in high heels (7 cm) and barefoot on a treadmill at their preferred speed. During the gait analysis, the lower limb joint kinematics were obtained using a motion analysis system. In addition, the changes in fascicle length and the level of activation of the medial gastrocnemius (MG) were simultaneously monitored using a real-time ultrasound imaging technique and surface electromyography, respectively. Results: The results of this study show that the MG fascicle operates at a significantly shorter length in high heel walking ($37.64{\pm}8.59mm$ to $43.99{\pm}8.66mm$) in comparison with barefoot walking ($48.26{\pm}9.02mm$ to $53.99{\pm}8.54mm$) (p < .05). In addition, the MG fascicle underwent lengthening during high heel walking with relatively low muscle activation while it remained isometric during barefoot walking with relatively high muscle activation. Conclusion: Wearing high heels alters the operating range of the MG fascicle length and the pattern of muscle activation, suggesting that prolonged wearing of high heels might induce structural alterations of the MG that, in turn, hinder normal functioning of the MG muscle during walking.

• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.35-42
• /
• 2021

본 연구에서는 3차원 RGB-D Xtion2 카메라를 이용하여 보행자의 골격좌표를 추출한 결과를 바탕으로 동적인 특성(속도, 가속도)을 함께 고려하여 딥러닝 모델을 통해 사람을 인식하는 방법을 제안한다. 본 논문의 핵심목표는 RGB-D 카메라로 손쉽게 좌표를 추출하고 새롭게 생성한 동적인 특성을 기반으로 자체 고안한 1차원 합성곱 신경망 분류기 모델(1D-ConvNet)을 통해 자동으로 보행 패턴을 파악하는 것이다. 1D-ConvNet의 인식 정확도와 동적인 특성이 정확도에 미치는 영향을 알아보기 위한 실험을 수행하였다. 정확도는 F1 Score를 기준으로 측정하였고, 동적인 특성을 고려한 분류기 모델(JCSpeed)과 고려하지 않은 분류기 모델(JC)의 정확도 비교를 통해 영향력을 측정하였다. 그 결과 동적인 특성을 고려한 경우의 분류기 모델이 그렇지 않은 경우보다 F1 Score가 약 8% 높게 나타났다.