• Proceedings of the KAIS Fall Conference
• /
• 2011.12a
• /
• pp.241-243
• /
• 2011

인체동작 인식에 대한 연구는 재활치료, 운동선수의 동작 교정 및 모니터링, 3차원 애니메이션 제작등 많은 분야에서 필요로 하고 있다. 동작 인식에 대한 일반적인 방법으로는 반사 마커를 부착하여 여러 대의 적외선 카메라로 관절 운동을 관찰하는 방식이였다. 이러한 방식은 여러 개의 마커를 사용자들이 옷을 벗고 몸에 붙이거나 특수 복장을 착용해야 하는 불편함이 있을 뿐만 아니라 초기 위치 보정에도 많은 시간이 소모된다. 이와 같은 문제점을 해결하기 위하여 본 연구에서는 어떠한 특수 장비를 착용하거나 몸에 부착하지 않고 즉각적으로 인체의 움직임을 트래킹 할 수 있는 마커리스 트래킹시스템을 개발하였다. 이 시스템은 사람의 동작 분석을 하는데 있어 빠르게 측정 및 분석이 가능하고 특수 장비를 착용하지 않아도 됨으로 인해 동작에 방해를 받지 않아서 3차원 영상을 즉각적으로 확인할 수 있는 편리성을 갖추고 있다.

• Journal of the Korean Society of Safety
• /
• v.34 no.5
• /
• pp.132-138
• /
• 2019

Fall accident is the most frequent accident type of occupational accidents. As the age of workers increases, trip and fall accident increases more than other types of occupational accident in the middle-aged group. In this study, the gait characteristics of 25 middle-aged participants (mean ages 47.4, S.D. 5.8) were studied to analyze the trip and fall risks. The Minimum toe clearance(MTC) against the floor surface was measured in the variable conditions of gait speed by a motion capture system. In the 50s age group, the MTC decreased and the MTC tended to reduce the variation with increasing walking speed in the level walking. Therefore, the trip and fall risks for the 50s age group is higher than the 40s age group. Especially, the faster walking speed will increase the trip and fall risks even more.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.162-169
• /
• 2019

Facial rigging technology has been developing more and more since the 21st century. Facial rigging of various methods is still attempted and a technique of capturing the geometry in real time recently also appears. Currently Modern CG is produced image which is hard to distinguish from actual photograph. However, this kind of technology still requires a lot of equipment and cost. The purpose of this study is to perform facial rigging using muscle simulation instead of using such equipment. Original muscle simulations were made primarily for use in the body of a creature. In this study, however, we use muscle simulations for facial rigging to create a more realistic creature-like effect. To do this, we used Ziva Dynamics' Ziva VFX muscle simulation software. We also develop a method to overcome the disadvantages of muscle simulation. Muscle simulation can not be applied in real time and it takes time to simulate. It also takes a long time to work because the complex muscles must be connected. Our study have solved this problem using blendshape and we want to show you how to apply our method to face rig.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.728-735
• /
• 2022

Roofers get exposed to increased risk of knee musculoskeletal disorders (MSDs) at different phases of a sloped shingle installation task. As different phases are associated with different risk levels, this study explored the application of machine learning for automated classification of seven phases in a shingle installation task using knee kinematics and roof slope information. An optical motion capture system was used to collect knee kinematics data from nine subjects who mimicked shingle installation on a slope-adjustable wooden platform. Four features were used in building a phase classification model. They were three knee joint rotation angles (i.e., flexion, abduction-adduction, and internal-external rotation) of the subjects, and the roof slope at which they operated. Three ensemble machine learning algorithms (i.e., random forests, decision trees, and k-nearest neighbors) were used for training and prediction. The simulations indicate that the k-nearest neighbor classifier provided the best performance, with an overall accuracy of 92.62%, demonstrating the considerable potential of machine learning methods in detecting shingle installation phases from workers knee joint rotation and roof slope information. This knowledge, with further investigation, may facilitate knee MSD risk identification among roofers and intervention development.

• The KIPS Transactions:PartA
• /
• v.11A no.4
• /
• pp.277-284
• /
• 2004

This paper presents a facial expression control method of 3D avatar that enables the user to select a sequence of facial frames from the facial expression space, whose level of details the user can select hierarchically. Our system creates the facial expression spare from about 2,400 captured facial frames. But because there are too many facial expressions to select from, the user faces difficulty in navigating the space. So, we visualize the space hierarchically. To partition the space into a hierarchy of subspaces, we use fuzzy clustering. In the beginning, the system creates about 11 clusters from the space of 2,400 facial expressions. The cluster centers are displayed on 2D screen and are used as candidate key frames for key frame animation. When the user zooms in (zoom is discrete), it means that the user wants to see mort details. So, the system creates more clusters for the new level of zoom-in. Every time the level of zoom-in increases, the system doubles the number of clusters. The user selects new key frames along the navigation path of the previous level. At the maximum zoom-in, the user completes facial expression control specification. At the maximum, the user can go back to previous level by zooming out, and update the navigation path. We let users use the system to control facial expression of 3D avatar, and evaluate the system based on the results.

• Smart Structures and Systems
• /
• v.13 no.2
• /
• pp.177-201
• /
• 2014

With the increased size and flexibility of the tower and blades, structural vibrations are becoming a limiting factor towards the design of even larger and more powerful wind turbines. Research into the use of vibration mitigation devices in the turbine tower has been carried out but the use of dampers in the blades has yet to be investigated in detail. Mitigating vibrations will increase the design life and hence economic viability of the turbine blades and allow for continual operation with decreased downtime. The aim of this paper is to investigate the effectiveness of Semi-Active Tuned Mass Dampers (STMDs) in reducing the edgewise vibrations in the turbine blades. A frequency tracking algorithm based on the Short Time Fourier Transform (STFT) technique is used to tune the damper. A theoretical model has been developed to capture the dynamic behaviour of the blades including the coupling with the tower to accurately model the dynamics of the entire turbine structure. The resulting model consists of time dependent equations of motion and negative damping terms due to the coupling present in the system. The performances of the STMDs based vibration controller have been tested under different loading and operating conditions. Numerical analysis has shown that variation in certain parameters of the system, along with the time varying nature of the system matrices has led to the need for STMDs to allow for real-time tuning to the resonant frequencies of the system.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.254-268
• /
• 2013

This paper presents an augmented reality (AR) based rehabilitation exercise system to enhance the motor function of the hands for the paretic/hemi-paretic patient. The existing rehabilitation systems rely on mechanical apparatus for palsy rehabilitation, but we aim to use the rehabilitation system at home with easy configuration and minimized equipment by the computer vision based approach. The proposed method evaluates the interaction status of the fingertip action by using the position and the contact of the fingertip markers. We obtain the 2D positions of the fingertip markers from a single camera, and then transform the 3D positions from the calibrated camera space by using an ARToolKit marker. We adopt simple geometric calculation by the conversion of the 2D interest points into the 3D interaction points for the simple interactive task in AR environment. Some experimental results show that the proposed method is practical and simply applicable to the applications with personal AR interaction.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.678-683
• /
• 2006

A novel and intuitive way of accessing applications of mobile devices is presented. The key idea is to use grip-pattern, which is naturally produced when a user tries to use the mobile device, as a clue to determine an application to be launched. To this end, a capacitive touch sensor system is carefully designed and installed underneath the housing of the mobile terminal to capture the image of the user's grip-pattern. The captured data is then recognized by a recognizer with dedicated preprocessing and postprocessing algorithms. The recognition test is performed to validate the feasibility of the proposed user interface system.

• Computational Structural Engineering
• /
• v.5 no.1
• /
• pp.109-118
• /
• 1992

Lateral bracing has long been used in design practice to enhance the carrying capacity of the lateral buckling of the beam. Many factors, critically important to lateral bracing performance, do not appear in design formulas. Some of these factors are discussed in this study for the application to short I - beams under repeated loadings through parametric studies with an analytical model : the brace location along the length of the beam, the height of the bracing above the shear center of the beam, and the strength and stiffness of the brace. The parametric studies are carried out using a propped cantilever arrangement, and also using a geometrically (fully) nonlinear beam model for the brace as well as the beam to capture the system buckling. An idealized bracing system is configured to restrain lateral motion, but not rotation. A multiaxial cyclic plasticity model is also implemented to better represent cyclic metal plasticity in conjunction with a consistent return mapping algorithm.

• IE interfaces
• /
• v.23 no.2
• /
• pp.100-107
• /
• 2010

For proper ergonomic evaluation using a digital human model simulation (DHMS) system such as $RAMSIS^{(R)}$, the postures of humanoids for designated tasks need to be predicted accurately. The present study (1) evaluated the accuracy of driving postures of humanoids predicted by RAMSIS, (2) proposed a method to improve its accuracy, and (3) examined the effectiveness of the proposed method. The driving postures of 12 participants in a seating buck were measured by a motion capture system and compared with their corresponding postures predicted by RAMSIS. Significant discrepancies ($8.7^{\circ}$ to $74.9^{\circ}$) between predicted and measured postures were observed for different body parts and driving tasks. Two methods (constraints addition and user-defined posture) were proposed and their effects on posture estimation accuracy were examined. Of the two proposed methods, the user-defined posture method was found preferred, reducing posture estimation errors by 11.5% to 84.9%. Both the posture prediction accuracy assessment protocol and user-defined posture method would be of use for practitioners to improve the accuracy of predicted postures of humanoids in virtual environments.