• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.597-599
• /
• 1997

무인 헬리콥터의 자세 정보를 계측할 수 있는 액체형 균형센서의 특성에 대해 연구하였다. 액체형 균형센서는 시간경과에 따른 누적오차가 없으므로 헬리콥터에 장착하면 장시간동안 균형을 유지시킬 수 있다. 제작된 균형센서의 각 전극에서 측정된 전압으로부터 기울어진 각도를 추정하기 위해 균형센서를 전기적으로 해석하고 측정된 전압과 각도사이의 환산모델을 유도하였다. 구해진 환산모델의 정확성을 실험을 통하여 입증하였다.

• Journal of Internet Computing and Services
• /
• v.7 no.1
• /
• pp.65-74
• /
• 2006

Human tracking is a requirement for the advanced human-computer interface (HCI), This paper proposes a method which uses a component-based human model, detects body parts, estimates human postures, and animates an avatar, Each body part consists of color, connection, and location information and it matches to a corresponding component of the human model. For human tracking, the 2D information of human posture is used for body tracking by computing similarities between frames, The depth information is decided by a relative location between components and is transferred to a moving direction to build a 2-1/2D human model. While each body part is modelled by posture and directions, the corresponding component of a 3D avatar is rotated in 3D using the information transferred from the human model. We achieved 90% tracking rate of a test video containing a variety of postures and the rate increased as the proposed system processed more frames.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.2
• /
• pp.133-140
• /
• 2015

In this paper, a roll angle estimation method of a rolling airframe using a low grade GPS and a roll rate gyro is proposed. The strength of the received signal of the GPS antenna attached on the rolling airframe is maximized when the GPS satellite is placed on the plane determined by the x-axis of the rolling airframe and the GPS antenna axis. Under the assumption that the x-axis of the rolling airframe is coincident with its velocity vector, the roll angle of the rolling airframe is calculated from the relative position vector of the satellite to the GPS when the GPS signal strength becomes maximum. The Kalman filter combined with a roll rate gyro is introduced to increase the determination accuracy of the roll angle. The performance of the proposed method is verified via 6-DOF simulations.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.11
• /
• pp.965-972
• /
• 2016

This paper presents results of flight experiments on a navigation algorithm including multiplicative extended Kalman filter for estimating attitude of the guided munition. The filter describes orientation of aircraft by data fusion with low-cost sensors where measurement update is done by multiplication, rather than addition, which is suitable for quaternion representation. In determining attitude from vector observations, the existing approach utilizes a 3-axis accelerometer as a 2-axis inclinometer by measuring gravity to estimate pitch and roll angles, while GNSS velocity is used to derive heading of the vehicle. However, during accelerated maneuvers such as coordinated flight, the accelerometer provides inadequate inclinometer measurements. In this paper, the measurement update process is newly defined to complement the vulnerability by using different vector observations. The acceleration measurement is considered as a result of a centrifugal force and gravity during turning maneuvers and used to estimate roll angle. The effectiveness of the proposed method is verified through flight experiments.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.5
• /
• pp.38-44
• /
• 2007

This paper presented a location and attitude estimation scheme of a capsule endoscope based on ultrasonic ranging. The scheme comprised eight on-capsule ultrasonic sensors to alleviate measurement errors due to irregularities in human body ultrasonic characteristics. It calculated the coordinate values and angles in a Cartesian coordinate system. The Matlab simulation reflecting random errors yielded the average deviations of 0.8mm in the location and $0.2^{\circ}$ in the attitude angle. These values are far smaller than normal intestine movement ranges inside human body, and will contribute accurate diagnosis of intestine.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.4
• /
• pp.408-415
• /
• 2016

The vehicle attitude and sideslip is critical information to control the vehicle to prevent from unintended motion. Many of estimation strategy use bicycle model or IMU integration, but both of them have limits on application. The main purpose of this paper is development of vehicle orientation estimator which is robust to various vehicle state and road shape. The suggested estimator use 3-axis magnetometer, yaw rate sensor and lateral acceleration sensor to estimate three Euler angles of vehicle. The estimator is composed of two individual observers: First, comparing the known magnetic field and gravity with measured value, the TRIAD algorithm calculates optimal rotational matrix when vehicle is in static or quasi-static condition. Next, merging 3-axis magnetometer with inertial sensors, the extended Kalman filter is used to estimate vehicle orientation under dynamic condition. A validation through simulation tools, Carsim and Simulink, is performed and the results show the feasibility of the suggested estimation method.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.302-314
• /
• 2024

Purpose: This study proposes a fall detection model based on a top-down deep learning pose estimation model to automatically determine falls of multiple workers in an underground utility tunnel, and evaluates the performance of the proposed model. Method: A model is presented that combines fall discrimination rules with the results inferred from YOLOv8-pose, one of the top-down pose estimation models, and metrics of the model are evaluated for images of standing and falling two or fewer workers in the tunnel. The same process is also conducted for a bottom-up type of pose estimation model (OpenPose). In addition, due to dependency of the falling interference of the models on worker detection by YOLOv8-pose and OpenPose, metrics of the models for fall was not only investigated, but also for person. Result: For worker detection, both YOLOv8-pose and OpenPose models have F1-score of 0.88 and 0.71, respectively. However, for fall detection, the metrics were deteriorated to 0.71 and 0.23. The results of the OpenPose based model were due to partially detected worker body, and detected workers but fail to part them correctly. Conclusion: Use of top-down type of pose estimation models would be more effective way to detect fall of workers in the underground utility tunnel, with respect to joint recognition and partition between workers.

• Journal of Astronomy and Space Sciences
• /
• v.22 no.2
• /
• pp.175-186
• /
• 2005

In this paper, the development of the extended kalman filter(EKF) which is based on Koreasat-3 bus system is introduced and the design result is shown through the simulation. Especially to determine the filter gains for accurate estimation, there is assumed that initial estimated parameters are not changed. But although the satellite performs the attitude control by 2Hz, it is verified that the EKF is running rightly using the changed filter gains. Also some cases are considered using the simulation : with each bias for 4-axis gyro and with gyro each axis failure. It is verified that the designed filter can be used as the back-up about gyro failure.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.686-689
• /
• 2018

3D 손 포즈 추정(Hand Pose Estimation, HPE)은 스마트 인간 컴퓨터 인터페이스를 위해서 중요한 기술이다. 이 연구에서는 딥러닝 방법을 기반으로 하여 단일 RGB-Depth 카메라로 촬영한 양손의 3D 손 자세를 실시간으로 인식하는 손 포즈 추정 시스템을 제시한다. 손 포즈 추정 시스템은 4단계로 구성된다. 첫째, Skin Detection 및 Depth cutting 알고리즘을 사용하여 양손을 RGB와 깊이 영상에서 감지하고 추출한다. 둘째, Convolutional Neural Network(CNN) Classifier는 오른손과 왼손을 구별하는데 사용된다. CNN Classifier 는 3개의 convolution layer와 2개의 Fully-Connected Layer로 구성되어 있으며, 추출된 깊이 영상을 입력으로 사용한다. 셋째, 학습된 CNN regressor는 추출된 왼쪽 및 오른쪽 손의 깊이 영상에서 손 관절을 추정하기 위해 다수의 Convolutional Layers, Pooling Layers, Fully Connected Layers로 구성된다. CNN classifier와 regressor는 22,000개 깊이 영상 데이터셋으로 학습된다. 마지막으로, 각 손의 3D 손 자세는 추정된 손 관절 정보로부터 재구성된다. 테스트 결과, CNN classifier는 오른쪽 손과 왼쪽 손을 96.9%의 정확도로 구별할 수 있으며, CNN regressor는 형균 8.48mm의 오차 범위로 3D 손 관절 정보를 추정할 수 있다. 본 연구에서 제안하는 손 포즈 추정 시스템은 가상 현실(virtual reality, VR), 증강 현실(Augmented Reality, AR) 및 융합 현실 (Mixed Reality, MR) 응용 프로그램을 포함한 다양한 응용 분야에서 사용할 수 있다.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.264-272
• /
• 2019

In this paper, we propose a 3D human body reconstruction and refinement method from the frames extracted from a video to obtain natural and smooth motion in temporal domain. Individual frames extracted from the video are fed into convolutional neural network to estimate the location of the joint and the silhouette of the human body. This is done by projecting the parameter-based 3D deformable model to 2D image and by estimating the value of the optimal parameters. If the reconstruction process for each frame is performed independently, temporal consistency of human pose and shape cannot be guaranteed, yielding an inaccurate result. To alleviate this problem, the proposed method analyzes and interpolates the principal component parameters of the 3D morphable model reconstructed from each individual frame. Experimental result shows that the erroneous frames are corrected and refined by utilizing the relation between the previous and the next frames to obtain the improved 3D human reconstruction result.