• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.225-229
• /
• 2020

Recently, convolutional neural network (CNN) have been showed outstanding performance in the field of image recognition, image processing and computer vision, etc. In this paper, we propose a CNN-based image rotation correction algorithm as a solution to image rotation problem, which is one of the factors that reduce the recognition rate in image recognition system using CNN. In this paper, we trained our deep learning model with Leeds Sports Pose dataset to extract the information of the rotated angle, which is randomly set in specific range. The trained model is evaluated with mean absolute error (MAE) value over 100 test data images, and it is obtained 4.5951.

• Journal of the Korean Geotechnical Society
• /
• v.32 no.1
• /
• pp.5-18
• /
• 2016

In this study, we grasped the resistance state of the back ground which had a notable influence on computing the lateral resistance of the laterally loaded pile group in the homogeneous ground by the model test. Resistance state was grasped as the depth of rotation-point, wedge failure angle, and wedge wing angle. The model experiment is performed by varying the width, spacing and number of piles and the relative density of sand in this study. According to the observation of the rear ground surface deformation of the piles in lateral load, rotation point ratio, wedge failure angle, and wedge wing angle of the front row were similar to those of the middle row; however, those of the back row were relatively smaller. The rotation point ratio, wedge failure angle and wedge wing angle of the piles in parallel were the same as those of a single pile. Based on the model test results, equations for estimation of the rotation-point, wedge failure angle, and wedge wing angle are proposed.

• The Korean Journal of Applied Statistics
• /
• v.21 no.3
• /
• pp.361-375
• /
• 2008

We propose proper methods to impute the item nonresponse in 4-8-4 rotation sample survey. We consider nonignorable nonresponse mechanism that can happen when survey deals with sensitive question (e.g. income, labor force). We utilize modeling imputation method based on Bayesian approach to avoid a boundary solution problem. We also estimate a interview time bias using imputed data and calculate cell expectation and marginal probability on fixed time after removing estimated bias. We compare the mean squared errors and bias between maximum likelihood method and Bayesian methods using simulation studies.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.49-56
• /
• 2011

Recently, animation contents has become extensively available along with the development of cultural industry. In this paper, we propose a method to analyze a face of animation character and extract 3D rotational information of the face. The suggested method first generates a dominant color model of a face by learning the face image of animation character. Our system then detects the face and its components with the model, and establishes two coordinate systems: base coordinate system and target coordinate system. Our system estimates three dimensional rotational information of the animation character face using the geometric relationship of the two coordinate systems. Finally, in order to visually represent the extracted 3D information, a 3D face model in which the rotation information is reflected is displayed. In experiments, we show that our method can extract 3D rotation information of a character face reasonably.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.9 no.2
• /
• pp.100-108
• /
• 2007

The Gwangneung KoFlux supersite, located in a rugged mountain region, is characterized by a low wind speed due to a mountain-valley circulation and rolling terrain. Therefore, it is essential to understand the effect of coordinate rotation on flux measurements by the eddy-covariance method. In this paper, we review the properties of three orthogonal coordinate frames (i.e., double, triple, and planar fit rotations) and apply to flux data observed at the Gwangneung supersite. The mean offset of vertical wind speed of sonic anemometer was inferred from the planar fit (PF) coordinate rotation, yielding the diurnal variation of about $\pm0.05ms^{-1}$. Double rotation $(\bar{v}=\bar{w}=0)$ produced virtually the same turbulent fluxes of heat, water, and $CO_2$ as those from the PF rotation under windy conditions. The former, however, resulted in large biases under calm conditions. The friction velocity, an important scaling parameter in the atmospheric surface layer, was more sensitive to the choice of coordinate rotation method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1352-1355
• /
• 1997

This paper presents the algorithm for estimating the attitude of an underwater vehicle using EFK. The system model is designed by linerizing the nonlinear Euler angle differential equation and the measurements is a speed logger output. The simulation result shows that the estimation lagorithm is adequate for decreasing attitude errors that grow abruptly during the motion with acceleration and rotation. It also shows that we can adapt the algorithm for compensating initial attitude errors generated after initial leveling.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1997.10a
• /
• pp.239-244
• /
• 1997

Recently, the high speed rotation and accuracy is needed in the field of electro-optic devices. But it is difficult for ball bearing to satisfy such conditions. So, we have developed the hemispherical type aerodynamic bearing for LSU(Laser Scanning Unit) motor. The hemispherical type aerodynamic bearing is able to support radial and axial load simultaneously. In this research, We have developed mass production method and tested the perromance of aerodynamic bearing in comparision with ball bearing at the speed of 23,000rpm. In the result, we proved that the properties of aerodynamic bearing is better than ball bearing's.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.1
• /
• pp.70-74
• /
• 2008

In the field of camera motion research, it is widely held that the position (movement) and pose (rotation) of cameras are correlated and cannot be independently separated. A new equation based on inner product is proposed here to independently separate the position and pose. It is proved that the position and pose are not correlated and the equation is applied to estimation of the camera exterior parameters using a real image and 3D data.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2005.05b
• /
• pp.89-93
• /
• 2005

인버터 구동 회전기기의 운전수명을 보장하기 위해서는 기존의 시험 방법에 포함되지 않은 PWM 가변속 구동에 따른 고조파 손실과 과도전압 충격의 문제점을 고려한 새로운 장기 신뢰성 평가 기법이 절실히 필요한 상황이기 때문에 본 연구에서 시험모델을 설정하고자 한다. 결과로는 종래는 비파괴시험에 의한 off-line 진단법이 주로 시행되었지만, 최근에는 상태량을 계측하는 신종 센서의 개발이 진행되어 모니터링법에 의한 on-line 진단법이 점차로 증가하고 있다.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1992.10a
• /
• pp.23-28
• /
• 1992

The ultimate capacity of end-plate connection is investigated through nonlinear finite element analysis. The example models are divided into stiffened case and unstiffened one. The refined finite element models are analyzed by utilizing a general purpose structural analysis computer program ADINA and the moment-rotation relationships of the connection are determined. The results are compared with the regression equation deduced by Krishnamurthy. It is planned to deduce a bilinear regression equation through a parametric study on various dimensions of the connection.