• 제어로봇시스템학회논문지
• /
• 제21권1호
• /
• pp.40-45
• /
• 2015

In this paper, we present an algorithm for the analysis of poses while playing table-tennis using action recognition. We use Kinect as the 3D sensor and 3D skeleton data provided by Kinect for further processing. We adopt a spherical coordinate system and feature selected using k-means clustering. We automatically detect the starting and ending frame and discriminate the action of table-tennis into two groups of forehand and backhand swing. Each swing is modeled using HMM(Hidden Markov Model) and we used a dataset composed of 200 sequences from two players. We can discriminate two types of table tennis swing in real-time. Also, it can provide analysis according to similarities found in good poses.

• 대한공간정보학회지
• /
• 제11권4호
• /
• pp.21-27
• /
• 2003

IKONOS 2호와 QuickBird 2호의 센서 모델로서 제공되는 RPC(rational polynomial coefficients) 모델은 물리적 센서 모델의 대체 모델로 다양한 센서에 적용 가능하다. 고해상도 위성들이 상용화되면서 각기 센서들의 복잡성과 보안성 문제로 인해 물리적 센서모델을 대체할 수 있는 센서 모델로서 RPC의 활용도가 높아지고 있다. 대표적인 상업용 고해상도 위성인 IKONOS 2호는 물리적 센서 모델을 공개하지 않고 각영상에 대한 RPC만을 제공하며 QuckBird 영상은 센서의 기하 정보와 함께 RPC를 제공한다. 이에 본 연구에서는 물리적 센서모델로부터 RPC를 추출하는 원천 기술을 확보하고 RPC의 물리적 센서모델에 대한대체 적합성을 평가해보고자 하였다. 이를 위해 공간해상도가 높은 항공사진과 국내 위성인 KOMPSAT 1호의 기하 모델로부터 분모식과 차수를 달리하는 RPC모델들을 추출하는 실험을 수행하였다. 최소제곱법을 통해 RPC 초기값을 구하고 Levenberg Marquardt 기법을 이용하여 반복 조정한 RPC를 물리적 센서 모델과 비교 평가하여 최적의 RPC를 결정하였다. 그 결과 항공사진은 분모식이 동일한 1차 RPC가 KOMPSAT 1호는 분모식이 상이한 3차 RPC가 가장 정확도가 높았으며 각 오차(RMSE)는 $2{\times}10^{-5}$ 화소 이하로 나타났다.

• 한국측량학회지
• /
• 제28권6호
• /
• pp.637-643
• /
• 2010

본 연구에서는 비디오카메라와 GPS/MEMS IMU, UMPC를 결합하여 영상과 위치/자세 데이터를 획득하는 휴대용 멀티센서 시스템을 구축하였다. 구축된 시스템을 통해 획득된 데이터를 이용하여 지상기준점을 이용하지 않고 광속조정법 기반의 영상 geo-referencing을 수행하고 정확도 검증을 통해 시스템의 효용성을 평가하였다. 정확도 검증 결과, 지상점의 상대좌표 정확도는 RMSE가수 cm내외로 상당히 정확함을 확인할 수 있었다. 구축된 시스템은 대상 객체의 3차원 모델과 상대좌표를 획득하는데 있어서 충분히 활용 가능하다고 판단된다. 향후에는 시스템 및 카메라의 엄밀한 보정을 통해 절대좌표의 정확도를 개선할 예정이다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.156.5-156
• /
• 2001

Stabilized tracking platform in a missile consisting of a flat planar antenna, pitch/yaw gimbals, gear trains, and current controlled DC drive motors for pitch and yaw gimbal must have a capability to track a target as an inertial sensor in the presence of missile body motion such as maneuvering and vibration. Because of this reason, tracking a target from dynamic platform requires a servo architecture that includes a outer tracking loop(position loop) and inner rate loop that stabilizes the line of sight(LOS). This paper presents a gimbaled platform model including nonlinear phenomena due to viscous and Coulomb friction based on experimental data and torque equilibrium equation, the design concept for the inner tacholoop having P controller structure ...

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.768-772
• /
• 2008

Various scanning systems have been studied in many industrial areas to acquire a range data or to reconstruct an explicit 3D model. Currently optical technology has been used widely by virtue of noncontactness and high-accuracy. In this paper, we describe a 3D laser scanning system developped to reconstruct the 3D surface of a large-scale object such as a curved-plate of ship-hull. Our scanning system comprises of 4ch-parallel laser vision modules using a triangulation technique. For multi laser vision, calibration method based on least square technique is applied. In global scanning, an effective method without solving difficulty of matching problem among the scanning results of each camera is presented. Also minimal image processing algorithm and robot-based calibration technique are applied. A prototype had been implemented for testing.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.485-492
• /
• 2020

Information on the energy consumption of buildings that can be obtained through conventional methods is limited. Therefore, this study aims to develop a model that can support decision making about building facility management through digital transformation technologies. Through the IoT sensor, the building's energy data and indoor air quality data are collected, and the monitored data is visualized through the ELK Stack and produced as a dashboard. In addition, the target building is photographed with a 360-degree camera and maps using a tool to create a 360-degree tour. Using such digital transformation technologies, users of buildings can obtain various information in real time without visiting buildings directly. This can lead to changes in actions or actions for building management, supporting facility management decisions, and consequently reducing building energy consumption.

• 대한조선학회논문집
• /
• 제50권3호
• /
• pp.138-144
• /
• 2013

New experimental devices and methods to measure shaft forces of ships are proposed in this paper. The strain gauge type six-component load cell was newly designed and installed to the end of the propeller shaft. The signals generated from the sensor in the propeller rotating are transferred to the new data amplifying and processing board on the shaft and the data is transmitted to the self-made wireless receiver. To find out the characteristics of shaft forces during port and starboard turning motions in sea trial, oblique and combined yaw maneuvering tests at straight, transient, maximum yaw rate, steady conditions were performed with the model ship installed the shaft forces measuring device using circular motion tester of Samsung Ship Model Basin. Characteristics of the measured shaft forces in model tests show quantitatively good agreement with the computed values obtained by the CFD programs using the measured wake data in oblique towing conditions. In the near future, It is hoped that the estimated shaft forces for a ship from this experimental method could be validated through comparison with directly measured values of a ship.

• ETRI Journal
• /
• 제44권2호
• /
• 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.

• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.53-58
• /
• 2023

The storage capacity of 3D-NAND flash memory has been enhanced by the multi-layer dielectrics. The deposition process has become more challenging due to the tight process margin and the demand for accurate process control. To reduce product costs and ensure successful processes, process diagnosis techniques incorporating artificial intelligence (AI) have been adopted in semiconductor manufacturing. Recently there is a growing interest in process diagnosis, and numerous studies have been conducted in this field. For higher model accuracy, various process and sensor data are required, such as optical emission spectroscopy (OES), quadrupole mass spectrometer (QMS), and equipment control state. Among them, OES is usually used for plasma diagnostic. However, OES data can be distorted by viewport contamination, leading to misunderstandings in plasma diagnosis. This issue is particularly emphasized in multi-dielectric deposition processes, such as oxide and nitride (ON) stack. Thus, it is crucial to understand the potential misunderstandings related to OES data distortion due to viewport contamination. This paper explores the potential for misunderstanding OES data due to data distortion in the ON stack process. It suggests the possibility of excessively evaluating process drift through comparisons with a QMS. This understanding can be utilized to develop diagnostic models and identify the effects of viewport contamination in ON stack processes.

• 디지털산업정보학회논문지
• /
• 제10권4호
• /
• pp.79-87
• /
• 2014

In this paper, we implemented the HearCAM platform with Raspberry PI B+ model which is an open source platform. Raspberry PI B+ model consists of dual step-down (buck) power supply with polarity protection circuit and hot-swap protection, Broadcom SoC BCM2835 running at 700MHz, 512MB RAM solered on top of the Broadcom chip, and PI camera serial connector. In this paper, we used the Google speech recognition engine for recognizing the voice characteristics, and implemented the pattern matching with OpenCV software, and extended the functionality of speech ability with SVOX TTS(Text-to-speech) as the matching result talking to the microphone of users. And therefore we implemented the functions of the HearCAM for identifying the voice and pattern characteristics of target image scanning with PI camera with gathering the temperature sensor data under IoT environment. we implemented the speech recognition, pattern matching, and temperature sensor data logging with Wi-Fi wireless communication. And then we directly designed and made the shape of HearCAM with 3D printing technology.