• 복식문화연구
• /
• 제8권4호
• /
• pp.587-601
• /
• 2000

The purpose of this study : 1. The total 56 range measurements of active dynamic motion of 40 subjects (20's and 30's) were measured using 3-D dynamic motion analysis system. 2. Various comparisons were performed for the right and left side, male, age groups (20's, 30's, and 40's ∼ 60's) using previous studies. The results were compared with the other studies in the aspects of age. In this study, the 3-D motion analysis system based on photogrammetry was established and used to analyze the human's motion and posture. The system consists of VICON 140, data acquisition system, and data analysis program (KRISSMAS). The result of this study were as follows : 1. Comparing 20's with 30's the result shows that 30's have larger ROM at some joints, which is inconsistent with the previous result. The reason is that female subjects in 20's were improperly sampled according to the representatives of anthropometry characteristics. 2. There are significant differences in some joints related with age. 20's male subjects have more flexible joints in the neck while 30's male subjects have more flexibility in their shoulder joint and elbow joint. But most of the significances were not high (p〈0.05). The prediction that the right side of Korean bodies would be more flexible was not a good hypothesis. And the joints flexibilities are not correlated with Rohrer's Index.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1856-1869
• /
• 2015

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.

• 한국멀티미디어학회논문지
• /
• 제17권6호
• /
• pp.741-750
• /
• 2014

This paper presents a real-time motion restoration system for people who need remedial exercise of musculoskeletal based on Inverse Kinematics. A new approach is suggested to recognize a gesture based on restored human motion which is calculated the 3D positions of intermediate joints using 3D positions of body features estimated from images. For generating the 3D candidate positions of intermediate joints which cannot be extracted from images, we apply an Inverse Kinematics theory to compute the target position of intermediate joints. And we can reduce the number of candidate positions by applying the various physical constraints of body. Finally, we can generate the more accurate final position using the Kalman filter for a motion tracking and the relationship between the previous frame information and the candidate positions. The system provide motion information which are rotation angle and height in real-time, therefore the rehabilitation exercises can be performed based on the information and figured out proper exercise for individual status.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.404-407
• /
• 2003

In this paper, we have designed the humanoid robot's leg parts with 12 D.O.F. This robot uses ankle's joints to confirm stability of walking performance. It is less movable to use ankle's joints than to do upper body's balancing joints like IWR-III, which needs three parts of via points, support leg, swing leg and balancing joints. Instead, the proposed humanoid robot needs support leg and swing leg via points. ZMP(Zero Moment Point) is utilized to guarantee the stability of robot's walking. The humanoid robot uses the ankle's joints to compensate for IWR-III's balancing joints movement. Actually we concern about a motor performance when making a real humanoid robot. So a simulator is employed to know each joint torque of humanoid robot. This simulator needs D-H(Denavit-Hartenberg) parameters, robot's mass property and two parts of via points. The simulation results are robot's walking trajectories and each motor torque. Using the walking trajectories, we can see the robot's walking scene with 3D simulator. Before we develop the humanoid robot, simulation of the humanoid robot's walking performance is very helpful. And the torque data will be used to make humanoid's joint module.

• 디지털융복합연구
• /
• 제14권6호
• /
• pp.513-518
• /
• 2016

다양한 연구결과에도 불구하고 전신진동운동이 인체에 미치는 기전은 명확히 제시되고 있지 않으며, 진동이 하지관절의 운동역학적 변화에 대해 분석한 연구는 미비한 실정이다. 그러므로 이 연구는 어떠한 하지관절의 운동역학적 변인이 수직점프 능력에 영향을 미치는지 분석하고자 한다. 최근 6개월간 하지에 정형외과적 병력이 없는 건강한 성인 남성 5명과 여성 5명은 5분간 30Hz의 전신진동운동을 실시한 전 후로 스쿼트 점프를 각각 3회씩 실시하였고, 수직점프 시 하지관절의 운동역학적 변화를 분석하기 위하여 3D 영상분석 시스템을 활용하였다. 대상자들의 스쿼트 점프 높이는 전신진동운동 처치 이후 향상되는 것으로 나타났으며, 발목과 무릎관절에서 하지관절 모멘트와 파워가 증가하는 것으로 나타났다. 그러나 지면반력 값과 엉덩관절의 모멘트와 파워는 전신진동운동의 처치 전 후에 통계적으로 유의한 차이가 나지 않는 것으로 나타났다. 30Hz의 전신진동운동을 실시한 결과 발목과 무릎관절은 진동이 인체내 긍정적인 영향을 미치는 것으로 나타났으나 엉덩관절의 경우 부정적인 영향을 미치는 것으로 나타났다.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2005년도 춘계학술발표대회 개요집
• /
• pp.103-105
• /
• 2005

Laser welding technology for automobile body is studied. laser system, robot and seam tracking system are used for 3D laser welding system The laser system is used 4kW Nd:YAG laser(HL4006D) of Trumpf and the robot system is used IRB6400R of ABB. The seam tracking system is SMRT-20LS of ServoRobot. The welding joints of steel plate are butt and lap joint. The 3-D welding for non-linear tailored blank is performed after experiments of bead on plate. Finally, the welding process for non-linear tailored blank is developed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.

• 대한인간공학회지
• /
• 제30권6호
• /
• pp.715-725
• /
• 2011

Objective: This study is aimed at developing Articulated Human Models(AHM) using superquadrics to improve the geometric accuracy of the body shape. Background: The previous work presents the AHM with geometrical simplification such as ellipsoids to improve analysis efficiency. However, because of the simplicity, their physical properties such as a center of mass and moment of inertia are computed with errors compared to their actual values. Method: This paper introduces a three steps method to present the AHM with superquadrics. First, a 3D whole body scan data are divided into 17 body segments according to body joints. Second, superquadric fitting is employed to minimize the Euclidean distance between body segments and superquadrics. Finally, Fee-Form Deformation is used to improve accuracy over superquadric fitting. Results: Our computational experiment shows that the superquadric models give better accuracy of dynamic analysis than that of ellipsoid ones. Conclusion: We generate the AHM composed of 17 superquadrics and 16 joints using superquadric fitting. Application: The AHM using superquadrics can be used as the base model for dynamics and ergonomics applications with better accuracy because it presents the human motion effectively.

• 한국게임학회 논문지
• /
• 제13권1호
• /
• pp.19-30
• /
• 2013

본 논문에서는 노인 및 재활 환자를 대상으로 재활 훈련을 위한 기능성 게임을 제안한다. 제안한 재활 훈련용 기능성 게임은 3D depth 카메라를 이용한 전신 동작 인식 기반의 인터페이스를 제공한다. 사용자가 카메라 앞에서면 배경과 사용자를 구분한 다음 사용자의 전신을 15개의 관절로 인식하고 각 관절이 위치와 방향의 변화를 분석하여 게임에 필요한 제스쳐를 인식한다. 게임 콘텐츠는 상지훈련, 하지훈련, 전신훈련, 밸런스 훈련을 위한 게임으로 구성하였으며 2D 게임과 3D 게임으로 나누어 구현하였다. 본 논문에서 제안된 시스템은 3D depth 카메라를 이용하여 주변 환경 변화에도 안정적으로 작동하며, 별도의 기기를 사용하지 않고도 전신 움직임 기반의 제스쳐 인식을 이용하여 게임을 진행하게 함으로써 재활의 효과를 높일 수 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.199-202
• /
• 2002

We described a real-time 3D computer vision system called MIMIC(Motion interface f Motion information Capture system) that can capture and save motion of an actor. This system analyzes input images from vision sensors and searches feature information like a head, hands, and feet. Moreover, this estimates intermediated joints as an elbow and hee using feature information and makes 3D human model having 20 joints. This virtual human model mimics the motion of an actor in real-time. Therefore this system can realize the movement of an actor unaffectedly because of making intermediated joint for complete human body contrary to other marker-free motion capture system.