• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1101-1104
• /
• 2019

키넥트는 RGBD 카메라로 인체의 뼈대와 관절을 3D 공간에서 스켈레톤 데이터수집을 가능하게 해주었다. 스켈레톤 데이터를 활용한 행동 분류는 RNN, CNN 등 다양한 인공 신경망으로 접근하고 있다. 본 연구는 키넥트를 이용해서 Skeleton Joints를 수집하고, DNN 기반 스켈레톤 모델링 학습으로 행동을 분류한다. Skeleton Joints Processing 과정은 키넥트의 Depth Map 기반의 Skeleton Tracker로 25가지 Skeleton Joints 좌표를 얻고, 학습을 위한 전처리 과정으로 각 좌표를 상대좌표로 변경하고 데이터 수를 제한하며, Joint가 트래킹 되지 않은 부분에 대한 예외 처리를 수행한다. 스켈레톤 모델링 학습 과정에선 3계층의 DNN 신경망을 구축하고, softmax_cross_entropy 함수로 Skeleton Joints를 집는 모션, 내려놓는 모션, 팔짱 낀 모션, 얼굴을 가까이 가져가는 모션 해서 4가지 행동으로 분류한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.764-767
• /
• 2009

Motion capture systems allow to measure the precise position of markers on the human body in real time. These captured motion data, the marker position data, have to be fitted by a human skeleton model to represent the motion of the human. Typical human skeleton models approximate the joints using a ball joint model. However, because this model cannot represent the human skeleton precisely, errors between the motion data and the movements of the simplified human skeleton model happen. We propose in this paper a method for measuring a translation component of wrist, and elbow joints on upper limb using optical motion capture system. Then we study the errors between the ball joint model and acquired motion data. In addition, we discuss the problem to estimate motion of human joint using optical motion capture system.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.

• Earthquakes and Structures
• /
• v.8 no.5
• /
• pp.1017-1038
• /
• 2015

This paper presents a strengthening method that involves the use of ferrocement jackets and chamfers to relocate plastic hinge for non-seismically designed reinforced concrete exterior beam-column joints. An experimental study was conducted to assess the effectiveness of the proposed strengthening method. Four half-scale beam-column joints, including one control specimen and three strengthened specimens, were prepared and tested under quasi-static cyclic loading. Strengthening schemes include ferrocement jackets with or without skeleton reinforcements and one or two chamfers. Experimental results have indicated that the proposed strengthening method is effective to move plastic hinge from the joint to the beam and enhance seismic performance of beam-column joints. Shear stress and distortion within the joint region are also reduced significantly in strengthened specimens. Skeleton reinforcements in ferrocement provide limited improvement, except on crack control. Specimen strengthened by ferrocement jackets with one chamfer exhibits slight decrease in peak strength and energy dissipation but with increase in ductility as compared with that of two chamfers. Finally, a method for estimating moment capacity at beam-column interface for strengthened specimen is developed. The proposed method gives reasonable prediction and can ensure formation of plastic hinge at predetermined location in the beam.

• Structural Engineering and Mechanics
• /
• v.88 no.5
• /
• pp.501-519
• /
• 2023

This paper introduces a new hybrid structural connection joint that combines shear walls with section steel beams, fundamentally resolving the construction complexity issue of requiring pre-embedded connectors in the connection between shear walls and steel beams. Initially, a quasi-static loading scheme with load-deformation dual control was employed to conduct low-cycle repeated loading experiments on five new connection joints. Data was acquired using displacement and strain gauges to compare the energy dissipation coefficients of each specimen. The destruction process of the new connection joints was meticulously observed and recorded, delineating it into three stages. Hysteresis curves and skeleton curves of the joint specimens were plotted based on experimental results, summarizing the energy dissipation performance of the joints. It's noteworthy that the addition of shear walls led to an approximate 17% increase in the energy dissipation coefficient. The energy dissipation coefficients of dog-bone-shaped connection joints with shear walls and cover plates reached 2.043 and 2.059, respectively, exhibiting the most comprehensive hysteresis curves. Additionally, the impact of laminated steel plates covering composite concrete floors on the stiffness of semi-rigid joint ends under excessive stretching should not be disregarded. A comparison with finite element analysis results yielded an error of merely 2.2%, offering substantial evidence for the wide-ranging application prospects of this innovative joint in seismic performance.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.4
• /
• pp.455-462
• /
• 2011

This paper is about the design of a new gravity compensator for the lower body exo-skeleton device. The exo-skeleton devices is for increasing the torque of the human body joint for the purpose of helping the disabled, workers in the industry, and military soldiers. So far, most of studied exo-skeleton devices are actuated by the motors, but motors are limited in energy such that a short durability is always a big problem. In this paper, a new gravity compensator is proposed to reduce the torque load applied to human body joints due to gravity. The gravity compensator is designed using a tortional bar spring, and its structure and characteristics are studied through the test and computer simulation. A design concept on the exo-skeleton device using the gravity compensator is presented. An analysis and computer simulation on the torque reduction of the proposed exo-skeleton device that applies and non-applies the gravity compensator are performed.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.281-290
• /
• 2015

Human action recognition from a video scene has remained a challenging problem in the area of computer vision and pattern recognition. The development of the low-cost RGB depth camera (RGB-D) allows new opportunities to solve the problem of human action recognition. In this paper, we present a comprehensive review of recent approaches to human action recognition based on depth maps, skeleton joints, and other hybrid approaches. In particular, we focus on the advantages and limitations of the existing approaches and on future directions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.5
• /
• pp.1199-1206
• /
• 2015

This paper introduces an algorithm for computing similarity between two poses in the motion capture data with different scale of skeleton, different number of joints and different joint names. The proposed algorithm first performs the topological analysis on the skeleton hierarchy for classifying the joints into more meaningful groups. The global joints positions of each joint group then are aggregated into a point cloud. The number of joints and their positions are automatically adjusted in this process. Once we have two point clouds, the algorithm finds an optimal 2D transform matrix that transforms one point cloud to the other as closely as possible. Then, the similarity can be obtained by summing up all distance values between two points clouds after applying the 2D transform matrix. After some experiment, we found that the proposed algorithm is able to compute the similarity between two poses regardless of their scale, joint name and the number of joints.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1994.04a
• /
• pp.53-58
• /
• 1994

Beam-column joints of the skeleton structure can be classified as geometrical D-region, where the assumption of Bernoulli is not applicable. For the detailing of D-region in concrete structure, "Strut-and-Tie' Model is a very powerful tool, which has been widely used by practical engineers. This paper shows how the methodology of Strut-and-Tie Model can be applied for the various cases of beam-column joints. We can find this mechanical model does not give only an appropriate answer to the given problem but also a better insight to the structral behavior of beam-column joints.