• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.269-282
• /
• 2021

As the distribution of 3D content such as augmented reality and virtual reality increases, the importance of real-time computer animation technology is increasing. However, the computer animation process consists mostly of manual or marker-attaching motion capture, which requires a very long time for experienced professionals to obtain realistic images. To solve these problems, animation production systems and algorithms based on deep learning model and sensors have recently emerged. Thus, in this paper, we study four methods of implementing natural human movement in deep learning model and kinect camera-based animation production systems. Each method is chosen considering its environmental characteristics and accuracy. The first method uses a Kinect camera. The second method uses a Kinect camera and a calibration algorithm. The third method uses deep learning model. The fourth method uses deep learning model and kinect. Experiments with the proposed method showed that the fourth method of deep learning model and using the Kinect simultaneously showed the best results compared to other methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Korean Journal of Optics and Photonics
• /
• v.33 no.4
• /
• pp.146-158
• /
• 2022

The detector of a focal-plane-array mid-wave infrared (MWIR) camera has different response characteristics for each detector pixel, resulting in nonuniformity between detector pixels. In addition, image nonuniformity occurs due to heat generation inside the camera during operation. To solve this problem, in the process of camera manufacturing it is common to use a gain-and-offset table generated from a blackbody to correct the difference between detector pixels. One method of correcting nonuniformity due to internal heat generation during the operation of the camera generates a new offset value based on input frame images. This paper proposes a technique for dividing an input image into block image patches and generating offset values using only homogeneous patches, to correct the nonuniformity that occurs during camera operation. The proposed technique may not only generate a nonuniformity-correction offset that can prevent motion marks due to camera-gaze movement of the acquired image, but may also improve nonuniformity-correction performance with a small number of input images. Experimental results show that distortion such as flow marks does not occur, and good correction performance can be confirmed even with half the number of input images or fewer, compared to the traditional method.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.168-178
• /
• 2022

In this study, the resistance test, the vertical static angle of the attack test and VPMM test will be conducted to estimate the maneuverability of underwater vehicles with ahead propeller. The vertical static test will be conducted within the range of -40deg to 40deg, to investigate the cross-flow drag at high incidence angles. The tests will be conducted by dividing the propeller rotation into a case in which the propeller rotates at a specific rpm, and a case in which the propeller rotates naturally, according to the towing speed. Hydrodynamic coefficients of vertical direction will be estimated by the captive model tests. Additionally, the vertical dynamic stability index based on estimated hydrodynamic coefficients will be calculated and the impact of the propeller revolution state on the index will be investigated. The results are expected to be used as reference test data for underwater vehicles with ahead propeller.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.4
• /
• pp.393-400
• /
• 2020

The purpose of this study was to determine whether wrist stabilization exercise combined with taping would improve wrist pain, disability and quality of life in postpartum women with wrist pain. Seventeen wrist pain patients were recruited and were randomly divided into two groups: experimental group (n=8) and control group (n=9). Participants in both groups received taping therapy for 30 minutes before the intervention. Additionally, subject in the experimental group performed wrist stabilization exercise using theraband for 15 minutes (twice a day, five times a week for four weeks) while the control group conducted range of motion exercise for the same amount of time. VAS was used to assess pain level of wrist. Disability was measured using a DASH. Quality of life were measured by SF-36. The wrist pain in the experimental group improved significantly greater than the control group (p<0.05). Significant improvement in the disability was observed in the experimental group compared to the control group (p<0.05). The SF 36 in the experimental group improved significantly greater than the control group (p<0.05). Our findings indicate that wrist stabilization exercise combined with taping is beneficial and effective to improve wrist health and quality of life in postpartum women with wrist pain.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.109-116
• /
• 2023

The purpose of this study was to investigate the influence of gender and load carriage difference on the lower extremity kinetics during stair descent. Ten healthy males and 10 healthy females were recruited (n=20). In the Maximum resultant velocity, it showed more velocity was decreased with difference by the change of gender (males>females) and load carriage (30%, 20%, 10%> 10%). And, resultant velocity showed interaction between gender and a load (load>gender). Main effect by gender during stair descent showed leg length was decreased in females than that of males at initial contact phase. Also, main effect by gender during stair descent showed more hip, knee flexed and plantar flexion of ankle joint in females than that of males. In the kinetics variables, main effect by gender during stair descent showed more higher reaction force of medial-lateral direction, and leg stiffness in males than that of females. We found that females successfully accommodated a load during stair descent by decreasing the range of motion of the hip joint angle and resultant velocity of movement. Males, on the other hand, require greater medial-lateral, vertical reaction force, and leg stiffness to accommodate a load, and control of momentum.

• Journal of Navigation and Port Research
• /
• v.46 no.6
• /
• pp.554-561
• /
• 2022

Technology development related to maritime autonomous surface ships (MASS) is actively progressing around the world. However, since there are still many technically unresolved problems such as communication, cybersecurity, and emergency response capabilities, it is expected that it will take a lot of time for MASS to be commercialized. In this study, we proposed a ship group navigation system in which one leader ship and several follower ship are grouped into one group. In this system, when the leader ship begins to navigate, the follower ship autonomously follows the path of the leader ship. For path following, PD (proportional-derivative) control is applied. In addition, each ship navigates in a straight line shape while maintaining a safe distance to prevent collisions. Speed control was implemented to maintain a safe distance between ships. Simulations were performed to verify the ship group navigation system. The ship used in the simulation is the L-7 model of KVLCC2, which has related data disclosed. And the MMG (Maneuvering Modeling Group) standard method proposed by the Japan Society of Naval Architects and Ocean Engineering (JASNAOE) was used as a model of ship maneuvering motion. As a result of the simulation, the leader ship navigated along a predetermined route, and the follower ship navigated along the leader ship's path. During the simulation, it was found that the three ships maintained a straight line shape and a safe distance between them. The ship group navigation system is expected to be used as a navigation system to solve the problems of MASS.

• Journal of the Korean Society of Radiology
• /
• v.16 no.7
• /
• pp.879-887
• /
• 2022

In this study, we tried to confirm whether the mechanical sequential elevation method of the body pressure measuring bed actually induces segmental motion for each part of the spine. To this end, a lateral X-ray examination was performed, and it was confirmed that the sequential pressure device induces a step-wise segmentation of the spine by mechanically lifting each part of the spine vertically. Then, pain, walking ability, and depression scale were measured and analyzed in subjects who were aware of back pain. VAS(p<0.05) and ODI(p<0.05) for 10 days tended to decrease in average after bed use. In the gait ability test(p<0.05), as the number of times of bed use increased, the moving time in the test decreased and the moving distance increased. In addition, GSDDF(p<0.05) decreased after bed use. As a result, it was confirmed that the spinal segmentation caused by the heat and acupressure provided by the bed affected gait and depression as well as pain relief.

• The Korea Journal of Herbology
• /
• v.34 no.4
• /
• pp.27-35
• /
• 2019

Objectives : Osteoarthritis is characterized by degeneration of articular cartilage, which is characterized by chronic pain, stiffness and decrease range of motion. The present study was designed to compare the therapeutic effect of Dioscoreae Rhizoma water extract (DRW) and Dioscoreae Rhizoma 30% ethanol extract (DRE) on the monosodium iodoacetate (MIA)-induced osteoarthritis rats. Methods : Osteoarthritis was induced by injection of MIA ($50{\mu}{\ell}$ with $80mg/m{\ell}$) into the knee joint cavity of rats. After adaptation period for seven days, rats were divided by 5 groups (n=10/group): normal group, control group, positive control (indomethacin 5 mg/kg), DRW 200 mg/kg treated group, DRE 200 mg/kg treated group (n=10/group). The hind paw weight distribution was measured with the changes of reactive oxygen species (ROS), peroxynitrite ($ONOO^-$) in articulation tissue. Also, the cyclooxygenase-2 (COX-2), inducible nitric oxide synthase (iNOS), tumor necrosis factoralpha ($TNF{\alpha}$), interleukin-6 (IL-6), matrix metalloproteinase-1 (MMP-1), and tissue inhibitor of metalloproteinases-1 (TIMP-1) were investigated by western blot analysis. Results : The administration of DRW and DRE significantly decreased the hind paw weight distribution. The ROS and $ONOO^-$ levels of cartilaginous tissue were significantly decreased in DRW and DRE compared to control group. The results showed that DRE decreased inflammatory cytokines such as iNOS and $TNF{\alpha}$. Also DRE decreased MMP-1 and increased TIMP-1. Conclusions : Based on the above results, Dioscoreae Rhizoma extract seems to have the therapeutic effect on osteoarthritis via suppression of inflammation.