• Journal of Korea Game Society
• /
• v.13 no.6
• /
• pp.75-84
• /
• 2013

The recording and matching method of pose and gesture based on PC-window platform is introduced in this paper. The method uses the gesture detection camera, Xtion which is for the Windows PC. To develop the method, the API is first developed which processes and compares the depth data, RGB image data, and skeleton data obtained using the camera. The pose matching method which selectively compares only valid joints is developed. For the gesture matching, the recognition method which can differentiate the wrong pose between poses is developed. The tool which records and tests the sample data to extract the specified pose and gesture is developed. 6 different pose and gesture were captured and tested. Pose was recognized 100% and gesture was recognized 99%, so the proposed method was validated.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.286-299
• /
• 2022

Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• Steel and Composite Structures
• /
• v.52 no.2
• /
• pp.135-143
• /
• 2024

Once the foundation displacement of the transmission tower occurs, additional stress will be generated on the tower members, which will affect the seismic response of transmission tower-line systems (TTLSs). Furthermore, existing research has shown that the reciprocating slippage of joints needs to be considered in the seismic analysis. The hysteretic behavior of joints is obtained by model tests or numerical simulations, which leads to the low modeling efficiency of TTLSs. Therefore, this paper first utilized numerical simulation and model tests to construct a BP neural network for predicting the skeleton curve of joints, and then a numerical model for a TTLS considering the bolt slippage was established. Then, the seismic response of the TTLS under foundation displacement was studied, and the member stress changes and the failed member distribution of the tower were analyzed. The influence of foundation displacement on the seismic performance were discussed. The results showed that the trained BP neural network could accurately predict the hysteresis performance of joints. The slippage could offset part of the additional stress caused by foundation settlement and reduce the stress of some members when the TTLS with foundation settlement was under earthquakes. The failure members were mainly distributed at the diagonal members of the tower leg adjacent to the foundation settlement and that of the tower body. To accurately analyze the seismic performance of TTLSs, the influence of foundation displacement and the joint effect should be considered, and the BP neural network can be used to improve modeling efficiency.

• Steel and Composite Structures
• /
• v.26 no.1
• /
• pp.67-78
• /
• 2018

The application of rib stiffeners is common on steel connections, with regard to the stiffened angle connection, experimental results about the influence of stiffeners under monotonic and cyclic loading are very limited. Consequently, this paper presents the experimental investigation on four types angle connections with or without stiffener under static loading and another four type stiffened angle connections subjected to cyclic loading. The static experimental result showed that the rib stiffener weld in tension zone of the connection greatly enhanced its initial rotational stiffness and flexural strength. While a stiffener was applied to the compression zone of the connection, it had not obvious influences on the initial rotational stiffness, but increased its flexural strength. The moment-rotation curves, skeleton curves, ductility, energy dissipation and rigidity were evaluated under cyclic loading. Stiffened top-and-seat angle connections behaved as semi-rigid and partial strength, and rotation of all stiffened angle connections exceeded 0.04rad. The failure modes between monotonic and cyclic loading test were completely different and indicated certain robustness.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.43-50
• /
• 2021

In this paper, we design and implement KITNESS, a windows application that feeds back the accuracy of fitness motions based on Kinect sensors. The feature of this application is to use Kinect's camera and joint recognition sensor to give feedback to the user to exercise in the correct fitness position. At this time, the distance between the user and the Kinect is measured using Kinect's IR Emitter and IR Depth Sensor, and the joint, which is the user's joint position, and the Skeleton data of each joint are measured. Using this data, a certain distance is calculated for each joint position and posture of the user, and the accuracy of the posture is determined. And it is implemented so that users can check their posture through Kinect's RGB camera. That is, if the user's posture is correct, the skeleton information is displayed as a green line, and if it is not correct, the inaccurate part is displayed as a red line to inform intuitively. Through this application, the user receives feedback on the accuracy of the exercise position, so he can exercise himself in the correct position. This application classifies the exercise area into three areas: neck, waist, and leg, and increases the recognition rate of Kinect by excluding positions that Kinect does not recognize due to overlapping joints in the position of each exercise area. And at the end of the application, the last exercise is shown as an image for 5 seconds to inspire a sense of accomplishment and to continuously exercise.

• Imaging Science in Dentistry
• /
• v.32 no.1
• /
• pp.41-47
• /
• 2002

Osteochondroma is a benign lesion of osseous and cartilagenous origin. It is a relatively common benign tumor of the skeleton, occurring most often in the metaphyseal region of long bone. However, it is rare in the facial bones. Reported foci in the mandible were the condyle, coronoid process, and symphysis region. Synovial chondromatosis is an uncommon benign condition of unknown etiology which affects the articular joints. Foci of cartilage develop through metaplasia in the underlying connective tissue of the synovial membrane. These cartilagenous foci and fragments may undergo calcification and ossification. We experienced 4 patients with abnormal appearance of mandibular condyle. This report describes 3 cases of osteocondroma and 1 case of synovial chondromatosis of the mandibular condyle with review of the literature.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.182-191
• /
• 2004

This study is focused on the development of a child human model, which is composed of skin, skeleton, joints and muscle, etc. The dimension of child outer skin is referred to anthropometric data from KRISS (Korea Research Institute of Standards and Science). The positions of joint and mass properties of body segments are calculated from ATB(Articulated Total Body) program, GEBOD. The properties of bones and muscles are obtained by the way of scaling from adult human model. To verify the developed human model, ROM simulation and sled test is conducted. Developed human model can be effectively applied to the evaluation of human injury in crash situation and development of child restraint system. The explicit finite element program $PAM-CRASH^TM$ was used to simulate six-year old child human model.

• Imaging Science in Dentistry
• /
• v.40 no.1
• /
• pp.45-52
• /
• 2010

Synovial chondromatosis is an uncommon disorder characterized by metaplastic formation of multiple cartilaginous and osteocartilaginous nodules within connective tissue of the synovial membrane of joints. Osteochondroma is a benign lesion of osseous and cartilagenous origin. It is frequently found in the general skeleton, but is rare in the mandibular condyle. We experienced 2 patients with abnormal appearance of temporomandibular joint. Histologic diagnoses were not obtained, because surgery was unwarranted in view of the lack of symptoms and the benign differential diagnosis. We describes 2 cases that show the characteristics of both disease simultaneously.

• Journal of Industrial Technology
• /
• v.22 no.B
• /
• pp.45-50
• /
• 2002

Airbag systems have improved the occupant safety in reducing the injuries of driver and passenger during collisions. They have occasionally caused fatalities; especially to small occupant and children. Recent airbag related fatalities of children have raised serious concerns on how to evaluate the safety of children in various crash environments. This paper present the development of the 3-year-old human model. Child human model is composed of skin, skeleton and joints. The positions of joint and mass properties of body segments are calculated from ARB(Ariticulated Rigid Body) program GEBOD. To verify the developed human model, ROM simulation and OOP simulations are conducted.