• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.423-430
• /
• 2021

Aiming Graph convolutional networks (GCNs) have achieved outstanding performances on skeleton-based action recognition. However, several problems remain in existing GCN-based methods, and the problem of low recognition rate caused by single input data information has not been effectively solved. In this article, we propose a Dual-stream fusion method that combines video data and skeleton data. The two networks respectively identify skeleton data and video data and fuse the probabilities of the two outputs to achieve the effect of information fusion. Experiments on two large dataset, Kinetics and NTU-RGBC+D Human Action Dataset, illustrate that our proposed method achieves state-of-the-art. Compared with the traditional method, the recognition accuracy is improved better.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.47-54
• /
• 2024

With the rapid development of 3D animation, MetaHuman is widely used in film production, game development and VR production as a virtual human creation platform.In the animation production of virtual humans, motion capture is usually used.Since different motion capture solutions use different skeletons for motion recording, when the skeleton level of recorded animation data is different from that of MetaHuman, the animation data recorded by motion capture cannot be directly used on MetaHuman. This requires Reorient the skeletons of both.This study explores an efficient skeleton reorientation method that can maintain the accuracy of animation data by reducing the number of bone chains.In the experiment, three skeleton structures, Rokoko, Mixamo and Xsens were used for efficient redirection experiments, to compare and analyze the adaptability of different skeleton structures to the MetaHuman skeleton, and to explore which skeleton structure has the highest compatibility with the MetaHuman skeleton.This research provides an efficient skeleton reorientation idea for the production team of 3D animated video content, which can significantly reduce time costs and improve work efficiency.

• 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.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.474-475
• /
• 2021

The accuracy of real-time video analysis system based on 3D skeleton data highly depends on the quality of data. This study proposes a methodology to distinguish noise in 3D skeleton frames using Intersection Over Union (IOU) method. IOU is metric that tells how similar two rectangles (i.e., boxes). Simply, the method decides a frame as noise or not by comparing the frame with a set of valid frames. Our proposed method distinguished noise in 3D skeleton frames with the accuracy of 99%. According to the result, our proposed method can be used to track noise in 3D skeleton frames.

• Journal of Korea Multimedia Society
• /
• v.15 no.10
• /
• pp.1257-1263
• /
• 2012

An implementation of animation module using the 3D body data scanned by laser scanner is reported in this paper. Characteristic points of the skeleton in human body were picked up as pivot point for 3D rotation. The body data set wes reconstructed as objects built in hierarchical tree structure, which is based on skeleton model. In order to implement the 3D animation of the laser scanned body data, the vertexes of the objects were connected as skeleton structure and animated to follow dynamic patterns inputted by user.

• Communications for Statistical Applications and Methods
• /
• v.30 no.6
• /
• pp.551-560
• /
• 2023

Recently, there has been significant research into the recognition of human activities using three-dimensional sequential skeleton data captured by the Kinect depth sensor. Many of these studies employ deep learning models. This study introduces a novel feature selection method for this data and analyzes it using machine learning models. Due to the high-dimensional nature of the original Kinect data, effective feature extraction methods are required to address the classification challenge. In this research, we propose using the first four moments as predictors to represent the distribution of joint sequences and evaluate their effectiveness using two datasets: The exergame dataset, consisting of three activities, and the MSR daily activity dataset, composed of ten activities. The results show that the accuracy of our approach outperforms existing methods on average across different classifiers.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.97-108
• /
• 2022

The video-assisted human action recognition [1] field is one of the most active ones in computer vision research. Since the depth data [2] obtained by Kinect cameras has more benefits than traditional RGB data, research on human action detection has recently increased because of the Kinect camera. We conducted a systematic study of strategies for recognizing human activity based on deep data in this article. All methods are grouped into deep map tactics and skeleton tactics. A comparison of some of the more traditional strategies is also covered. We then examined the specifics of different depth behavior databases and provided a straightforward distinction between them. We address the advantages and disadvantages of depth and skeleton-based techniques in this discussion.

• Structural Engineering and Mechanics
• /
• v.77 no.2
• /
• pp.179-196
• /
• 2021

Experimental investigations on the seismic behaviors of the PVC-FRP Confined Reinforced Concrete (PFCRC) columns under low cyclic loading are carried out and two variable parameters including CFRP strips spacing and axial compression ratio are considered. The PFCRC column finally fails by bending and is characterized by the crushing of concrete and yielding of the longitudinal reinforcement, and the column with a high axial compression ratio is also accompanied by the cracking of the PVC tube and the fracture of CFRP strips. The hysteretic curves and skeleton curves of the columns are obtained from the experimental data. With the increase of axial compression ratio, the stiffness degradation rate accelerates and the ductility decreases. With the decrease of CFRP strips spacing, the unloading sections of the skeleton curves become steep and the ductility reduces significantly. On the basis of fiber model method, a numerical analysis approach for predicting the skeleton curves of the PFCRC columns is developed. Additionally, a simplified skeleton curve including the elastic stage, strengthening stage and unloading stage is suggested depending on the geometric drawing method. Moreover, the loading and unloading rules of the PFCRC columns are revealed by analyzing the features of the skeleton curves. The quantitative expressions that are used to predict the unloading stiffness of the specimens in each stage are proposed. Eventually, an analytical model for the PFCRC columns under low cyclic loading is established and it agrees well with test data.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.361-366
• /
• 2018

For each character constituting learning data, different fonts are added in pixel unit to create MASK, and then pixel values belonging to the MASK are divided into three groups. The experimental data are modified into skeletal forms, and then regional boundary operation is used to create a boundary that distinguishes the background region adjacent to the skeleton of the character from the background of the modified experimental data. Discordance values between the modified experimental data and the MASKs are calculated, and then the MASK with the minimum value is found. This MASK is selected as a finally recognized result for the given experiment data. The recognition algorithm using skeleton of the character and the regional boundary operation can easily extend the learning data set by adding new fonts to the given learning data, and also it is simple to implement, and high character recognition rate can be obtained.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.1
• /
• pp.137-144
• /
• 1996

It is important to investigate the growth aspects of craniofacial skeleton in the orthodontics. The purpose of this study is to find the factors, which have a great influence on the growth aspects of craniofacial skeleton, and to evalute the control values of each factor in order to construct orthodontics diagnostic and planning.