• Journal of the Korea Computer Graphics Society
• /
• v.29 no.5
• /
• pp.11-20
• /
• 2023

In this paper, we propose a novel deep learning-based motion reconstruction approach that facilitates the generation of full-body motions, including finger motions, while also enabling the online adjustment of motion generation delays. The proposed method combines the Vive Tracker with a deep learning method to achieve more accurate motion reconstruction while effectively mitigating foot skating issues through the use of an Inverse Kinematics (IK) solver. The proposed method utilizes a trained AutoEncoder to reconstruct character body motions using tracker data in real-time while offering the flexibility to adjust motion generation delays as needed. To generate hand motions suitable for the reconstructed body motion, we employ a Fully Connected Network (FCN). By combining the reconstructed body motion from the AutoEncoder with the hand motions generated by the FCN, we can generate full-body motions of characters that include hand movements. In order to alleviate foot skating issues in motions generated by deep learning-based methods, we use an IK solver. By setting the trackers located near the character's feet as end-effectors for the IK solver, our method precisely controls and corrects the character's foot movements, thereby enhancing the overall accuracy of the generated motions. Through experiments, we validate the accuracy of motion generation in the proposed deep learning-based motion reconstruction scheme, as well as the ability to adjust latency based on user input. Additionally, we assess the correction performance by comparing motions with the IK solver applied to those without it, focusing particularly on how it addresses the foot skating issue in the generated full-body motions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.2347-2352
• /
• 2012

In this paper, a new alternating equalizer and its differential adjustment algorithm are proposed. The proposed alternating equalizer achieves equalization effectively using an algorithm performing symbol decisions based on soft/hard decision. In addition, it is possible to improve the initial blind convergence speed and steady-state error performance simultaneously by adjusting the equalizer differentially according to the relative reliability of the symbol decisions by soft/hard decision devices. The simulation results on 16/64-QAM constellations under multipath propagation channel and additive noise conditions confirmed to support usefulness of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.1
• /
• pp.68-75
• /
• 2007

A single chip NFC transceiver supporting not only NFC active and passive mode but also 13.56MHz RFID reader and tag mode was designed and fabricated. The proposed NFC transceiver can operate as a RFID tag even without external power supply which has dual antenna structure for initiator and target. The area increment due to additional target antenna is negligible because the target antenna is constructed by using a shielding layer of initiator antenna. The analog front end circuit of the proposed NFC transceiver consists of a transmitter and receiver of reader/writer block supporting NFC initiator or RFID reader mode, and a tag circuit for target of passive NFC mode or RFID tag mode. The maximum baud rate of the proposed NFC device is 212kbps by using UART serial interface. The chip has been designed and fabricated using a Magnachip's $0.35{\mu}m$ double poly 4-metal CMOS process, and the effective area of the chip is 2200um by 3600um.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.29-39
• /
• 2019

As mobile robot applications increase in real life, the need of low cost autonomous driving are gradually increasing. We propose a novel vision-based real-time lane detection and tracking system that supports autonomous driving of mobile robots in constrained tracks which are designed considering indoor driving conditions of mobile robots. Considering the processing of lanes with various shapes and the pre-adjustment of operation parameters, the system structure with multi-operation modes are designed. In parameter tuning mode, thresholds of the color filter is dynamically adjusted based on the geometric property of the lane thickness. And in the unstable input mode of curved tracks and the stable input mode of straight tracks, lane feature pixels are adaptively extracted based on the geometric and temporal characteristics of the lanes and the lane model is fitted using the least-squared method. The track centerline is calculated using lane models and the motion model is simplified and tracked by a linear Kalman filter. In the driving experiments, it was confirmed that even in low-performance robot configurations, real-time processing produces the accurate autonomous driving in the constrained track.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.2
• /
• pp.214-219
• /
• 2011

This paper presents a multi-band low noise amplifier(LNA) with switching operation for 2.4, 3.5 and 5.2 GHz bands using CMOS 0.18 um technology. The proposed circuit uses switching transistors to achieve the input and output matching for multi-band. By using the switching transistors, we can adjust the transconductance, gate inductance and gatesource capacitance at input stage and total output capacitance at output stage. The proposed LNA exhibits gain of 14.2, 12 and 11 dB and noise figure(NF) of 3, 2.9 and 2.8 dB for 2.4, 3.5 and 5.2 GHz, respectively.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.7 no.4
• /
• pp.339-345
• /
• 2002

This paper presents a portable power supply equipped with a battery charger. The proposed system can be operated separatedly distinguishing between DC/AC and AC/DC function. The former uses a battery and the latter a line voltage as the power source to operate on an inverter and a battery charger, respectively. To keep the output voltage being sinusoidal and to have the high dynamic performances even In the cases of load variations, a proper control method is adapted. The operational principles and analysis are explained in detail. The validity of the proposed system is proved from the experimental results.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.10
• /
• pp.97-102
• /
• 2004

In this paper, a new predistorter controlling modified individual order jntermodulation distortion signals is proposed. The proposed predistorter generates and controls predistorted third and high order IM signals independently. Using predistorted signals, jntermodulation distortion signals of power amplifier are suppressed effectively. The predistortion linearizer has been implemented to operate in Korean PCS basestation transmitting band (1840～1870MHz). The test results show that IMD3 and IMD5 (C/I) of power amplifier are improved more than 40dB and 23dB for CW two tone signals, respectively. The predistorter improves the adjacent channel power ratio (ACPR) more than 10dB at 885KHz offset point for CDMA (IS-95) signals.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.27 no.12
• /
• pp.1390-1396
• /
• 2003

본 연구는 타이트 스커트의 트임의 개수가 왼쪽 옆선에 1개 있을 때와 왼쪽 옆선, 오른쪽 옆선에 각각 1개씩 모두 2개 있을 때 평지 보행, 계단 승강, 버스 승강 등과 같은 일상동작에 잘 적응할 수 있는 타이트 스커트의 적정 트임 길이를 설정하는 것을 목표로 하였다. 아울러 각 동작시의 트임 길이에 따른 생리적인 반응을 의복압, 산소 섭취량을 통해 알아보고자 하였다. 평균보폭은 4m 구간을 평상시대로 걸을 때의 발자국간 평균거리를 이용하였으며 국민표준체위조사보고서(1997)에 의한 평균체형을 가진 9명의 피험자를 정하였다. 스커트의 형태는 무릎길이인 타이트 스커트로 정하였다. 스커트의 트임은 왼쪽 옆선에 1개 있는 경우와 왼쪽 옆선, 오른쪽 옆선에 각각 1개씩 있는 경우의 2종류이다. 트임이 1개인 스커트는 2cm 간격으로, 트임이 2개인 스커트는 1cm 간격으로 트임 위치를 표시하여 길이를 조정하였다. 적정 트임 길이는 Likert 척도에 의한 만족도 평가로 측정하였으며 의복압은 air-bag system으로, 산소 섭취량은 Quark $B^2$ 으로 측정하였다. 본 연구의 결과는 다음과 같다. 1. 스커트의 최소 적정 트임 길이는 트임 1개일 때 평지 보행시 4cm, 계단 승강시 12cm ,버스 승강시 18cm이며, 트임 2개일 때 평지 보행시 2cm, 계단 승강시 8cm, 버스 승강시 15cm로 나타났다. 2. 의복압의 경우, 동일 트임 길이에서 트임 1개의 의복압이 트임 2개의 의복압보다 높았지만 트임 개수에 따른 전체 트임 길이로 보면 트임 1개의 의복압이 트임 2개의 의복압 보다 낮게 나타났다. 동작별로는 버스 승강의 의복압이 가장 높고 계단 승강, 평지 보행 순으로 낮아졌다. 3. 산소 섭취량의 경우, 동일 트임 길이에서 트임 1개와 트임 2개의 산소 섭취량은 거의 비슷하였다. 트임 개수에 따른 전체 트임 길이로 보면 트임 1개의 산소 섭취량이 트임 2개의 산소 섭취량보다 낮게 나타났다. 동작별로는 버스 승강의 산소 섭취량이 가장 높고 계단 승강, 평지 보행 순으로 낮아졌다.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.827-836
• /
• 2012

After successful advent of Microsoft's Kinect, many interactive contents that control user's 3D avatar motions in realtime have been created. However, due to the Kinect's intrinsic IR projection problem, users are restricted to face the sensor directly forward and to perform all motions in a standing-still position. These constraints are main reasons that make it almost impossible for the 3D character to navigate the virtual environment, which is one of the most required functionalities in games. This paper proposes a new method that makes 3D character navigate the virtual environment with highly realistic motions. First, in order to find out the user's intention of navigating the virtual environment, the method recognizes walking-in-place motion. Second, the algorithm applies the motion splicing technique which segments the upper and the lower motions of character automatically and then switches the lower motion with pre-processed motion capture data naturally. Since the proposed algorithm can synthesize realistic lower-body walking motion while using motion capture data as well as capturing upper body motion on-line puppetry manner, it allows the 3D character to navigate the virtual environment realistically.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.491-498
• /
• 2019

Digital twin is a technology that virtualizes physical objects of the real world on a computer. It is used by collecting sensor data through IoT, and using the collected data to connect physical objects and virtual objects in both directions. It has an advantage of minimizing risk by tuning an operation of virtual model through simulation and responding to varying environment by exploiting experiments in advance. Recently, artificial intelligence and machine learning technologies have been attracting attention, so that tendency to virtualize a behavior of physical objects, observe virtual models, and apply various scenarios is increasing. In particular, recognition of each robot's motion is needed to build digital twin for co-robot which is a heart of industry 4.0 factory automation. Compared with modeling based research for recognizing motion of co-robot, there are few attempts to predict motion based on sensor data. Therefore, in this paper, an experimental environment for collecting current and inertia data in co-robot to detect the motion of the robot is built, and a motion prediction model based on the collected sensor data is proposed. The proposed method classifies the co-robot's motion commands into 9 types based on joint position and uses current and inertial sensor values to predict them by accumulated learning. The data used for accumulating learning is the sensor values that are collected when the co-robot operates with margin in input parameters of the motion commands. Through this, the model is constructed to predict not only the nine movements along the same path but also the movements along the similar path. As a result of learning using SVM, the accuracy, precision, and recall factors of the model were evaluated as 97% on average.