• 한국지능시스템학회논문지
• /
• 제16권3호
• /
• pp.266-270
• /
• 2006

본 논문에서는 은닉 마르코프 모델을 바탕으로 하는 발걸음을 이용한 개인 식별 시스템을 제안한다. 개인의 발걸음은 연속적인 자세나 움직임의 집합으로 나타낼 수 있는데, 구조적으로 연속적인 움직임의 변화는 확률적인 특성을 가지고 있기 때문에 은닉 마르코프 모델을 이용하여 적절하게 모델링 할 수 있다. 개인의 발걸음은 N개의 이산적인 자세 간의 전이로 이루어졌다고 가정하였으며, 이를 계산하기 위해 MMSI라는 발걸음 특징 모델을 제안하였다. MMSI는 발걸음 인식에 중요한 역할을 하는 시공간적인 정보를 가지고 있는 그레이-스케일 영상이다. 실험 결과는 MMSI를 이용하여 은닉 마르코프 모델을 바탕으로 한 발걸음 인식 결과를 보여준다.

• 한국운동역학회지
• /
• 제26권3호
• /
• pp.309-314
• /
• 2016

Objective: There are no guidelines for choosing appropriate gait assistive devices. The aim of this study was to evaluate gait assistive devices in patients with Parkinson's disease. Method: We evaluated 15 individuals with Parkinson's disease who did or did not use one of two different devices including canes and two-wheeled walkers. Data were collected using the GAITRite system. Results: Participants in the group using canes and two-wheeled walkers had significantly increased double support time and decreased gait velocity, normalized gait velocity, and stride length compared with those who did not. Participants who used a two-wheeled walker had significantly decreased gait velocity, normalized gait velocity, and stride length compared with those who used a cane. Furthermore, participants who used a two-wheeled walker had significantly decreased coefficients of variation for step time, stride length, and swing time compared with those who used a cane. Conclusion: Our results indicated that the two-wheeled walker offered the most consistent advantages for decreasing the risk of falling.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.551-554
• /
• 2001

A necessity of remote control robots or various searching robots etc. that accomplish works given instead of human under long distance and extreme environment such as volcano, universe, deep-sea exploration and nuclear power plant etc. is increasing, and so the development and the research regarding these mobile robots are actively progressing. The wheel mobile robot or the track mobile robot have a sufficient energy efficiency under this en, but also have a lot of limits to accomplish works given which are caused from the restriction of mobile ability. Therefore, recently many researches for the walking robot with superior mobility and energy efficiency on the terrain, which is uneven or where obstacles, inclination and stairways exist, have been doing. The research for these walking robots is separated into fields of mechanism and control system, gait research, circumference environment and system condition recognition etc. greatly. It is a research field that the gait research among these is the centralist in actual implementation of walking robot unlike different mobile robots. A research field for gait of walking robot is classified into two parts according to the nature of the stability and the walking speed, static gait or dynamic gait. While the speed of a static gait is lower than that of a dynamic gait, a static gait which moves the robot to maintain a static stability guarantees a superior stability relatively. A dynamic gait, which make the robot walk controlling the instability caused by the gravity during the two leg supporting period and so maintaining the stability of the robot body spontaneously, is suitable for high speed walking but has a relatively low stability and a difficulty in implementation compared with a static gait. The quadruped walking robot has a strong point that can embody these gaits together. In this research, we will develope an autonomous quadruped robot with an asaptibility to the environment by selectry appropriate gait, element such as duty factor, stride, trajectory, etc.

• 한국통신학회논문지
• /
• 제39B권7호
• /
• pp.479-490
• /
• 2014

하지근력증강로봇은 인간의 하체에 착용하여 보행능력을 강화하거나 보조하기 위한 장비다. 보행능력을 향상하기 위해 로봇은 착용자의 걷는 움직임을 감지하고 이에 적합한 로봇의 동작을 구동한다. 본 논문에서는 로봇이 착용자의 움직임을 감지하는 방법을 소개하고, 감지된 데이터를 착용자의 현재 보행단계를 의미하는 보행단계상태 정보로 변환하는 보행단계구분 알고리즘을 제시한다. 로봇은 보행단계상태 정보에 따라 현재 필요한 제어모드를 결정하고 로봇구동기를 작동하기 때문에 잘못된 정보가 전달된다면 로봇은 착용자의 보행능력을 향상할 수 없거나 착용자에게 오히려 불편을 줄 수 있다. 따라서 보행단계구분 알고리즘은 항상 정확한 정보를 제공할 수 있어야 한다. 하지만 본 연구에서 사용하는 센서장치의 경우 작은 움직임에도 민감하게 반응하는 특성이 있어 센서데이터를 임계기준으로 구분하는 방법으로는 항상 정확한 보행단계상태 정보를 구할 수 없다. 이러한 특성을 극복하면서 정확한 정보를 제공하기 위해 확률적 구분 방법을 응용한 나이브-플렉시블 베이지안 보행단계구분 알고리즘을 제안하였고, 실험을 통해 제안 방법의 정확성을 비교 분석하였다.

• International Journal of Control, Automation, and Systems
• /
• 제3권2호
• /
• pp.152-158
• /
• 2005

Commercial lower limb prostheses or orthotics help patients achieve a normal life. However, patients who use such aids need prolonged training to achieve a normal gait, and their fatigability increases. To improve patient comfort, this study proposed a method of predicting gait angle using neural networks and EMG signals. Experimental results using our method show that the absolute average error of the estimated gait angles is $0.25^{\circ}$. This performance data used reference input from a controller for the lower limb orthotic or prosthesis controllers while the patients were walking.

• 전기학회논문지P
• /
• 제65권2호
• /
• pp.130-135
• /
• 2016

Gait recognition has advantage of non-contact type recognition. But It has disadvantage of low recognition rate when the pedestrian silhouette is changed due to bag or coat. In this paper, we proposed new method using combination of gait energy image feature and thermal face image feature. First, we extracted a face image which has optimal focusing value using human body rate and Tenengrad algorithm. Second step, we extracted features from gait energy image and thermal face image using linear discriminant analysis. Third, calculate euclidean distance between train data and test data, and optimize weights using genetic algorithm. Finally, we compute classification using nearest neighbor classification algorithm. So the proposed method shows a better result than the conventional method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.549-551
• /
• 1998

This paper deals with the new gait implementation of biped walking robot(IWR-III). In the case of using old gait. The trunk should be stopped during the phase changing time. But using new gait, the trunk moves continuously for all walking time. As a result, IWR-III has a walking gait similar to human being, and the motion of balancing joints can be reduced by the trunk ahead effect in the double support phase, moreover, ZMP tracking is improved, therefore the stability of IWR-III is improved. The trajectory is planned with a 5th order spline interpolation and stability of IWR-III is certified with a biped simulator.

• Structural Engineering and Mechanics
• /
• 제54권5호
• /
• pp.937-953
• /
• 2015

This paper investigates the load model for single footfall trace of human walking. A large amount of single person walking load tests were conducted using the three-dimensional gait analysis system. Based on the experimental data, Fourier series functions were adopted to model single footfall trace in three directions, i.e. along walking direction, direction perpendicular to the walking path and vertical direction. Function parameters such as trace duration time, number of Fourier series orders, dynamic load factors (DLFs) and phase angles were determined from the experimental records. Stochastic models were then suggested by treating walking rates, duration time and DLFs as independent random variables, whose probability density functions were obtained from experimental data. Simulation procedures using the stochastic models are presented with examples. The simulated single footfall traces are similar to the experimental records.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1994년도 춘계학술대회논문집
• /
• pp.136-144
• /
• 1994

In this study, the human gait trajectories during normal walking were synthesized using the inverse kinematics and optimization techniques. The synthesis based on a lower extremity model consisting of a torso and two legs. Each leg has three segments: thigh, shank, foot, and is assumed to move with six degrees-of-freedom. In order to synthesize trajectiories of this redundant system, the sum of angular displacements of articulating joints was selected as an objective function to be minimized. The proposed algorithm in this study is very useful for the analysis of human gait. For the gait analysis, the trajectories of four points in each leg should be measured. However, by using the algorithm, measuring the trajectories of two points is sufficient, and thus the experimental set-up can be simplified. The predicted joint trajectories showed a good agreement with those obtained from the experiment. The statistical analysis and graphic simula- tions are also presented.

• 한국산업정보학회논문지
• /
• 제12권5호
• /
• pp.39-46
• /
• 2007

최근 유비쿼터스 환경에서 개인 인증을 위한 연구가 활발하게 진행되고 있다. 그 중에서 걸음걸이 인식은 원거리에서 사람의 물리적인 특성을 이용하여 개인을 인증하는데 효과적인 방법이다. 본 논문에서는 걸음걸이 인식을 위해 평균 이동 알고리즘(mean shift algorithm)과 geodesic 활성 윤곽선 모델(active contour models) 기반의 사람 외형 추출 및 추적 시스템을 제안한다. 활성 윤곽선 모델은 움직이고, 변화하기 쉬운 물체를 다루는데 효과적이다. 그러나 활성 윤곽선 모델의 성능은 초기 커브에 의존적인 한계를 가지고 있다. 이 문제를 극복하기 위해 전형적인 geodesic 활성 윤곽선 모델에 평균 이동 알고리즘을 결합한다. 기본 개념은 진화시키기 전에 level set 방법을 사용하여 초기 커브를 사람 영역에 위치시키고, 그 영역을 충분히 둘러싸도록 크기를 조정한 후에 커브를 진화시킨다. 이러한 방법은 움직임이 큰 물체를 다루거나 진화 횟수를 줄이기 위해 효과적이다. 제안된 시스템은 사람 영역 검출 모듈과 사람 외형 추적모듈로 구성된다. 사람 영역 검출 모듈에서는 배경영상 제거(background subtraction)와 모폴로지 연산(morphologic operation)으로 사람의 실루엣을 검출한다. 이때, 사람의 외형은 평균 이동 알고리즘과 geodesic 활성 윤곽선 모델에 의해 정확하게 검출된다. 실험 결과에서 제안된 방법이 걸음걸이 인식(gait recognition)을 위해 사람의 외형을 효과적으로 정확하게 추출하고 추적됨을 보여준다.