• 대한임베디드공학회논문지
• /
• 제11권4호
• /
• pp.219-225
• /
• 2016

Visual object tracking is one of the key tasks in computer vision. Robust trackers should address challenging issues such as fast motion, deformation, occlusion and so on. In this paper, we therefore propose a visual object tracking method that exploits inter-frame correlations of convolutional feature maps in Convolutional Neural Net (ConvNet). The proposed method predicts the location of a target by considering inter-frame spatial correlation between target location proposals in the present frame and its location in the previous frame. The experimental results show that the proposed algorithm outperforms the state-of-the-art work especially in hard-to-track sequences.

• 한국군사과학기술학회지
• /
• 제23권5호
• /
• pp.466-474
• /
• 2020

Semi-active laser missile systems with high accuracy are necessary to asymmetric threats, such as UAV(Unmanned Aerial Vehicle). They are usually used to attack stationary or slow moving targets, therefore we should study on the laser designator which can detect and track fast moving targets in order to deal with UAV. In this study, design specifications are came up through performance analysis of existing laser designators, and laser designation method for fast moving target is developed. The detection and tracking performance of developed laser designator are verified through inside/outside tests on ground/aerial stationary/moving targets. Through this study, we obtain laser designator techniques that could be applied to actual semi-active laser missile systems.

• 제어로봇시스템학회논문지
• /
• 제19권12호
• /
• pp.1119-1124
• /
• 2013

In this paper we propose a novel torque control method for permanent magnet synchronous motors using the SVPWM (Space Vector PWM). The control law is described in the rotating d-q frame and is devised to track a given reference flux with which the reference torque is generated. The key feature of the proposed control is that it provides uniform dynamics with desired closedloop poles independent of the rotating speed and the desired poles can be selected to yield a fast response with only a small amount of torque ripple.

• 한국산학기술학회논문지
• /
• 제17권1호
• /
• pp.315-323
• /
• 2016

본 연구는 동계올림픽의 대표적인 종목인 봅슬레이 경기장 건설을 위한 봅슬레이 트랙 실물크기 모형제작 방법 및 내구성 평가이다. 봅슬레이 경기는 속도감이 엄청나고 그 위험성 또한 대단히 높아 선수의 안전을 위한 안전설계와 고성능 숏크리트를 이용한 정밀 시공이 필수적이다. 또한 봅슬레이 트랙은 다양한 커브와 경사로 이루어져 있어 일반 거푸집 시공이 어렵고, 고강도 고내구성 재료를 통한 시공이 필요하다. 본 연구를 통해 개발 된 봅슬레이 트랙 실물크기 모형제작 방법 및 내구성 평가는 2018 평창 동계 올림픽 슬라이딩 센터 및 봅슬레이 트랙 건설을 국내기술력으로 시공하기 위함 이다.

• 한국컴퓨터정보학회논문지
• /
• 제7권4호
• /
• pp.52-58
• /
• 2002

본 논문은 가변 탐색창을 이용하여 실시간으로 객체를 추적하는 방법에 대해 기술한다. 동영상에서 실시간 객체 추적은 카메라를 이용한 감시 시스템에 필요한데, 감시 대상 환경에 따라 효율성이 크게 좌우된다. 먼저 입력영상과 배경영상의 차를 이용하여 객체의 위치를 탐지하는데, 이를 위해서 객체의 윤곽선과 무게중심을 추출한다. 그리고 객체의 크기와 위치로부터 설정한 가변 탐색창을 이용하여 탐지된 객체의 움직임을 추적한다. 이 때 배경영상과 카메라는 고정된 환경으로 제한한다. 제안 방법의 실험 결과 초당 17-23 프레임으로 기존의 객체 추적 방법들의 평균 10-14 프레임보다 빠른 처리 속도를 나타내었다.

• 대한임베디드공학회논문지
• /
• 제12권6호
• /
• pp.395-403
• /
• 2017

Image processing for object detection and identification has been studied for supply chain management application with various approaches. Among them, feature pointed detection algorithm is used to track an object or to recognize a position in automated supply chain systems and a depth image based feature point detection is recently highlighted in the application. The result of feature point detection is easily influenced by image noise. Also, the depth image has noise itself and it also affects to the accuracy of the detection results. In order to solve these problems, we propose a novel hybrid filtering mechanism for depth image based feature point detection, it shows better performance compared with conventional hybrid filtering mechanism.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.257-259
• /
• 1996

This paper presents the active eye system for tracking a moving object in 3D space. A prototype system able to track a moving object is designed and implemented. The mechanical system ables the control of platform that consists of binocular camera and also the control of the vergence angle of each camera by step motor. Each camera has two degrees of freedom. The image features of the object are extracted from complicated environment by using zero disparity filtering(ZDF). From the cnetroid of the image features the gaze point on object is calculated and the vergence angle of each camera is controlled by step motor. The Proposed method is implemented on the prototype with robust and fast calculation time.

• 제어로봇시스템학회지
• /
• 제1권1호
• /
• pp.16-16
• /
• 1995

Like the usual systems, the industrial robot manipulator has some constraints for motion. Usually we hope that the manipulators move fast to accomplish the given task. The problem can be formulated as the time-optimal control problem under the constraints such as the limits of velocity, acceleration and jerk. But it is very difficult to obtain the exact solution of the time-optimal control problem. This paper solves this problem in two steps. In the first step, we find the minimum time trajectories by optimizing cubic polynomial joint trajectories under the physical constraints using the modified evolution strategy. In the second step, the controller is optimized for robot manipulator to track precisely the optimized trajectory found in the previous step. Experimental results for SCARA type manipulator show that the proposed method is very useful.

• Transactions on Control, Automation and Systems Engineering
• /
• 제1권1호
• /
• pp.16-20
• /
• 1999

Like the usual systems, the industrial robot manipulator has some constraints for motion. Usually we hope that the manipulators move fast to accomplish the given task. The problem can be formulated as the time-optimal control problem under the constraints such as the limits of velocity, acceleration and jerk. But it is very difficult to obtain the exact solution of the time-optimal control problem. This paper solves this problem in two steps. In the first step, we find the minimum time trajectories by optimizing cubic polynomial joint trajectories under the physical constraints using the modified evolution strategy. In the second step, the controller is optimized for robot manipulator to track precisely the optimized trajectory found in the previous step. Experimental results for SCARA type manipulator show that the proposed method is very useful.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.381-386
• /
• 2006

The advantages of precast production are fast construction, reduction of labor and insurance of good quality. In recently, the application of the precast production is increased in the earth retaining wall field. This paper presents the results of the numerical modelling that was carried out to evaluate the stability of precast and prestressed earth retaining wall under dynamic train loading. The two-dimensional explicit dynamic finite element method (ABAQUS) was used to carry out the numerical analyses. The train loading to act track is calculated by using the real measured phase angle data. Mainly, the displacement and acceleration of wall structure in time domain analyzed to evaluate the stability under the dynamic train load.