• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1376-1384
• /
• 2019

The cosmetic and behavioral aspects of aging have become increasingly evident over the years. Physical aging in people can easily be observed on their face, posture, voice, and gait. In contrast, bone aging only becomes apparent once significant bone degeneration manifests through degenerative bone diseases. Therefore, a more accurate and timely assessment of bone aging is needed so that the determinants and its mechanisms can be more effectively identified and ultimately optimized. This study proposed a deep learning approach to assess the bone age of an adult using whole-body bone scintigraphy. The proposed approach uses multiple inputs deep neural network architectures using a loss function, called mean-variance loss. The data set was collected from Chonnam National University Hwasun Hospital. The experiment results show the effectiveness of the proposed method with a mean absolute error of 3.40 years.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.5
• /
• pp.398-405
• /
• 2005

The intelligent robots that will be needed in the near future are human-friendly robots that are able to coexist with humans and support humans effectively. To realize this, robots need to recognize their position and posture in known environment as well as unknown environment. Moreover, it is necessary for their localization to occur naturally. It is desirable for a robot to estimate of his position by solving uncertainty for mobile robot navigation, as one of the best important problems. In this paper, we describe a method for the localization of a mobile robot using image information of a moving object. This method combines the observed position from dead-reckoning sensors and the estimated position from the images captured by a fixed camera to localize a mobile robot. Using a priori known path of a moving object in the world coordinates and a perspective camera model, we derive the geometric constraint equations which represent the relation between image frame coordinates for a moving object and the estimated robot's position. Also, the control method is proposed to estimate position and direction between the walking human and the mobile robot, and the Kalman filter scheme is used for the estimation of the mobile robot localization. And its performance is verified by the computer simulation and the experiment.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1331-1334
• /
• 2006

동영상에서의 움직임 추적은 이전 프레임에서 얻어낸 정보를 이용할 수 있다는 점에서 프레임간의 연결 관계에 기반한 움직임 추적이 가능하다. 그러나 사람의 신체는 고정된 형태를 가지고 있지 않기 때문에 프레임 간의 단순한 연결 관계만으로 사람의 자세를 추정하고 움직임을 추적하는 것은 매우 어려운 문제이다. 본 논문에서는 구성요소에 기반한 인체 모델을 이용하여 이전 프레임에서 찾은 블랍들을 연속된 프레임에서 찾은 블랍들로 연결함으로써, 동영상에서 사람의 자세를 추적하는 방법을 제안한다. 주어진 모델에 따라 이전 블랍은 대응되거나, 여러 블랍으로 나뉘거나, 다른 블랍들과 결합되어 사라지거나, 새로 생성되는 등의 4 가지 경우로 나뉘어 질 수 있는데, 각 경우에 대한 처리 방안을 제안하였다. 제안된 방법은 인체들과 블랍들의 리스트 처리를 간단하게 할 뿐만 아니라, 추적의 전처리 과정으로 블랍화를 옳게 수행해야 하는 부담을 덜어주어 과도한 블랍화와 부족한 블랍화 등의 문제를 해결할 수 있다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.3
• /
• pp.306-314
• /
• 2009

The pelvis platform is the mechanical part which accomplishes the activities of diminishing the disturbances from the lower body and maintaining a balanced posture. When a biped robot walks, a lot of disturbances and irregular vibrations are generated and transmitted to the upper body. As there are some important machines and instruments in the upper body or head such as CPU, controller units, vision system, etc., the upper part should be isolated from disturbances or vibrations to functions properly and finally to improve the biped stability. This platform has 3 rotational degrees of freedom and is able to maintain balanced level by feedback control system. Some sensors are fused for more accurate estimation and the control system which integrates synchronization and active filtering is simulated on the virtual environment.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.3
• /
• pp.63-71
• /
• 2014

A single-inverted-pendulum model is presented to simulate and predict the passive response of human balance control. This simplified biomechanical model was comprised of a torsional spring and damper, and a lump mass. An estimation of frequency response function was conducted to parameterize the complexity. The frequency domain identification method is used to identify the parameters of the model. The equivalent viscoelastic parameters of standing body were obtained and there was good conformity between the simulation and experimental result.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.11
• /
• pp.1011-1017
• /
• 2012

Augmented Reality is being widely used not only for Smartphone users but also in industries such as maintenance, construction area. With smartphone, due to the low localization accuracy and the requirement of special infrastructure, current LBS (Localization Based Service) is limited to show P.O.I. (Point of Interest) nearby. Improvement of IMU (Inertial Measurement Unit) based deadreckoning is presented in this paper. Additional sensors such as the magnetic compass and magnetic flux sensors are used as well as the accelerometer and the gyro for getting more movement information. Based on the pedestrian movement, appropriate sensor information is selected and the complementary filter is used in order to enhance the accuracy of the localization. Additional sensors are used to measure the movements of the upper body and the head and to provide the user's line of sight.

• The Journal of Korea Robotics Society
• /
• v.15 no.3
• /
• pp.205-211
• /
• 2020

In this paper, we propose a modified ORB-SLAM (Oriented FAST and Rotated BRIEF Simultaneous Localization And Mapping) for precise indoor navigation of a mobile robot. The exact posture and position estimation by the ORB-SLAM is not possible all the times for the indoor navigation of a mobile robot when there are not enough features in the environment. To overcome this shortcoming, additional IMU (Inertial Measurement Unit) and encoder sensors were installed and utilized to calibrate the ORB-SLAM. By fusing the global information acquired by the SLAM and the dynamic local location information of the IMU and the encoder sensors, the mobile robot can be obtained the precise navigation information in the indoor environment with few feature points. The superiority of the modified ORB-SLAM was verified to compared with the conventional algorithm by the real experiments of a mobile robot navigation in a corridor environment.

• IE interfaces
• /
• v.10 no.3
• /
• pp.197-208
• /
• 1997

In workplace design, an ergonomic solution should ensure low postural stress in the operator during his/her work. Stress caused by awkward working postures of the trunk, shoulders and legs can result in fatigue, discomfort, musculo-skeletal disorders and nerve entrapment syndromes. Since discomfort and musculo-skeletal disorders are both related to exposure to biomechanical load on the musculo-skeletal system, minimization of discomfort will contribute to reduction of the risk for musculo-skeletal disorders as well. Therefore, in this study, perceived discomfort on the human body joints was measured in the standing postures using the magnitude estimation in order to have a standardized numerical scale for joint discomfort. Nine healthy graduate students participated voluntarily in the laboratory study. The results revealed that perceived discomfort of all the joints increased as the joints deviated from neutral position. Especially, it showed drastic increment on perceived discomfort when deviation from neutral position in each human body joint increased from 75% to 100%. in terms of relative range of motion(R0M). On the basis of these experimental results, a preliminary ranking for assessment of stressfulness of non-neutral postures around the human body joints was suggested.

• Journal of Computational Design and Engineering
• /
• v.1 no.1
• /
• pp.1-12
• /
• 2014

In this paper, we propose a new method of reconstructing the hand models for individuals, which include the link structure models, the homologous skin surface models and the homologous tetrahedral mesh models in a reference posture. As for the link structure model, the local coordinate system related to each link consists of the joint rotation center and the axes of joint rotation, which can be estimated based on the trajectories of optimal markers on the relative skin surface region of the subject obtained from the motion capture system. The skin surface model is defined as a three-dimensional triangular mesh, obtained by deforming a template mesh so as to fit the landmark vertices to the relative marker positions obtained motion capture system. In this process, anatomical dimensions for the subject, manually measured by a caliper, are also used as the deformation constraints.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.811-813
• /
• 2005

주어진 영상에서 인체를 찾고 그 자세를 인식하기 위해 자세나 조영 조건의 변화에 됨 민감한 방법으로 구성요소에 기반한 접근이 있다. 본 논문에서는 10개의 구성요소와 그들간의 유연한 연결로 구성된 인체모델을 사용한다. 각 구성요소는 기하학적, 명시적, 다른 구성요소와의 연결요소에 대한 정보로 구성되어 있다. 인체구성요소 사이의 계층적 연결은 일반-상세 탐색으로 시간효율적인 인체 매칭을 가능케 한다. 본 논문에서는 새로운 인체를 찾을 때마다 인체 구성요소를 갱신함으로써 자세 및 조명 변화에 보다 적응적으로 자세를 추정하는 방법을 제안한다.