• 제어로봇시스템학회논문지
• /
• 제14권2호
• /
• pp.148-155
• /
• 2008

This paper proposes a method of adaptively generating a gait pattern of biped robot. The gait synthesis is based on human's gait pattern analysis. The proposed method can easily be applied to generate the natural and stable gait pattern of any biped robot. To analyze the human's gait pattern, sequential images of the human's gait on the sagittal plane are acquired from which the gait control values are extracted. The gait pattern of biped robot on the sagittal plane is adaptively generated by a genetic algorithm using the human's gait control values. However, gait trajectories of the biped robot on the sagittal plane are not enough to construct the complete gait pattern because the biped robot moves on 3-dimension space. Therefore, the gait pattern on the frontal plane, generated from Zero Moment Point (ZMP), is added to the gait one acquired on the sagittal plane. Consequently, the natural and stable walking pattern for the biped robot is obtained, as proved by the experiments.

• ETRI Journal
• /
• 제33권2호
• /
• pp.259-266
• /
• 2011

We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

• 한국전자통신학회논문지
• /
• 제8권9호
• /
• pp.1407-1412
• /
• 2013

인간의 건강한 생활을 위해서는 자세 및 골격구조가 중요하며, 이것은 평소의 생활습관과 걸음걸이에 의해서 영향을 받아 변형될 수 있다. 인간의 걸음걸이형태로는 크게 바른걸음, 팔자걸음, 안짱걸음으로 구분할 수 있으며, 이러한 걸음걸이형태를 분석하여 바른자세를 유지하는데 도움이 될 수 있다. 본 논문에서는 스트레인 센서를 이용하여 걸음걸이 패턴을 분석하는 신발을 개발하였으며, 제작된 신발로 걸음걸이 패턴을 구분하여 분석할 수 있었다.

• 한국지능시스템학회논문지
• /
• 제18권1호
• /
• pp.100-108
• /
• 2008

본 논문에서는 이족로봇의 자연스러운 보행 패턴을 생성하기 위해 인간의 보행 회전력(torque)을 주파수 영역에서 분석하고 분석된 데이터를 이용하여 적응적으로 이족로봇의 보행패턴을 생성하는 기법을 제안한다. 인간의 보행 회전력은 시간영역에서 복잡한 형태를 가지므로 DCT(Discrete Cosine Transform)를 이용하여 주파수영역으로 변환시켜 분석한다. 주파수 영역에서 얻어진 보행 회전력의 특징을 이용하여 이족로봇의 sagittal plane에서의 보행패턴을 생성한다. 또한 이족로봇의 안정적이 보행 패턴을 생성하기 위하여 동적 평형 상태임을 판단할 수 있는 Zero Moment Point(ZMP)해석을 통해 frontal plane상의 보행패턴을 생성하여 3차원 공간상의 안정적이고 인간과 같이 자연스러운 보행 패턴을 생성했다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.923-926
• /
• 2000

This paper concerned with the patterns of foot-floor contact and electromyography activities of the lower extremity of the body during the termination of human gait. The termination of human gait is defined as the transition from a steady-state gait to a quiet standing posture. The transition between these two states has not been extensively studied and defined. There appears to be a critical period in the gait cycle that the decision to terminate gait or continue to take an additional step must be made.

• 대한산업공학회지
• /
• 제17권2호
• /
• pp.39-50
• /
• 1991

The movement of human beings - walking, running, jumping and climbing, etc. - have long been of scientific interest. In particular, the science of human walking is called gait analysis. Various instruments have been developed to assist in the study of human gait. Recently gait analysis techniques are used in medical research to investigate the abnormalities of pathological gait. In this study, we constructed a comprehensive gait analysis system consisting of a walkway, a force platform, foot-switches and an ExpertVision motion analysis system. Time-distance gait parameters and vector diagrams can be analyzed by a special application program called Force Analysis System(FOANAS). Using quantitative discrimination of this system, the gait characteristic parameters of normal and pathological gait is facilitated.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권5호
• /
• pp.354-362
• /
• 2010

본 연구는 동적 베이스 망을 이용하여, 사람의 보행 동작을 보행 방향과 보행 자세로 분리하여 계층적으로 분석하는 방법을 제안한다. DBN의 일종인 FHMM을 기본 바탕으로 하여, 걸음걸이 동작 특성을 고려하여 순환 고리형 상태 공간 구조로 '보행 동작 디코더'(Gait Motion Decoder, GMD)를 설계한다. 기존 연구에는 보행자의 식별에만 치중을 하고 보행 방향의 변화, 관찰 각도에 제한적이거나 보행 동작에 대한 분석이 없었다. 반면에 본 연구에서는 동작과 자세를 적극적으로 표현하여 임의 방향의 보행, 방향의 변화, 보행 자세까지 인식할 수 있도록 하였다. 실험 결과 동작과 자세의 관점에서 걸음걸이 방향을 분석한 결과 96.5%의 방향 인식률을 기록하였다. 본 연구는 보행 동작을 방향과 보행 자세로 계층적으로 분석하는 최초의 방법 및 시도이며 향후 상황별 휴먼 동작 분석에 크게 활용할 수 있을 것이다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 한국멀티미디어학회논문지
• /
• 제13권12호
• /
• pp.1778-1785
• /
• 2010

This paper proposes a new video-based method of analyzing human gait which is a highly variable dynamic process. It captures a human gait of varying directions as a trajectory in the phase space. The proposed method includes two options of a stochastic process model and a self-organizing feature map as the tool of feature space representation and analysis. Test results show that the model is highly intuitive and we believe it can contribute to our understanding of human activity as well as gait behavior.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.107.4-107
• /
• 2002

One of the most important functions of a biped robot is to walk naturally like human. For the human being, toe is very important joint in order to walk naturally. Thus, for a biped robot, the existence of toe joint much affects gait pattern generation and contributes to natural walking, which is similar to the human gait or faster walking like running. Since a conventional biped robot has the feet which consist of soles without toes, it seems difficult to walk naturally. For realizing the gait to be similar to human one, toes are necessary to the biped robot. In this paper, the effect of the toe joint for gait pattern generation is studied. In order to find the effect of toe joint, a biped r...