• 대한기계학회논문집A
• /
• 제27권5호
• /
• pp.697-704
• /
• 2003

In this paper, the visual tracking system for arbitrary shaped moving object is proposed. The established tracking system can be divided into model based method that needs previous model for target object and image based method that uses image feature. In the model based method, the reliable tracking is possible, but simplification of the shape is necessary and the application is restricted to definite target mod el. On the other hand, in the image based method, the process speed can be increased, but the shape information is lost and the tracking system is sensitive to image noise. The proposed tracking system is composed of the extraction process that recognizes the existence of moving object and tracking process that extracts dynamic characteristics and shape information of the target objects. Specially, active contour model is used to effectively track the object that is undergoing shape change. In initializatio n process of the contour model, the semi-automatic operation can be avoided and the convergence speed of the contour can be increased by the proposed effective initialization method. Also, for the efficient solution of the correspondence problem in multiple objects tracking, the variation function that uses the variation of position structure in image frame and snake energy level is proposed. In order to verify the validity and effectiveness of the proposed tracking system, real time tracking experiment for multiple moving objects is implemented.

• 한국정보과학회논문지:정보통신
• /
• 제29권1호
• /
• pp.97-107
• /
• 2002

본 논문은 대화형 방송환경에서 부가서비스를 제공받기 위해서 탐다운(Top-Down)메뉴 검색을 하는 것이 아니라, 방송영상의 화면 내부에서 부가서비스가 제공되길 원하는 객체를 선택했을 때 선택한 객체에 대한 부가서비스를 제공하는 새로운 방법을 제안한다. 이를 위해서는 실시간으로 방송되고 있는 동영상과 객체정보(위치, 크기, 모양)의 동기를 맞추는 기술과 동영상 내부의 객체 추적 기술이 필수적이다. 동영상과 객체정보의 동기를 맞추는 기술은 마이크로소프트사의 다이렉트쇼(DirectShow)를 이용하였으며, 객체를 추적하기 위한 방법은 객체를 크게 사람과 사물로 나누어, 사람의 얼굴은 모델을 만들어 추적하는 모델 기반 얼굴 추적 방법(Model-based face tracking)을 사용하고 나머지 사물에 대해서는 객체의 영역을 지정하여 영역을 추적하는 움직임 기반 추적 방법(Motion-based Tracking)을 적용하였다. 또한 움직임 기반 추적을 할 수 있도록 하고 모델 기반 추적 방법을 적용하여 움직임이 큰 객체도 검색 영역 확장 없이 정확한 추적을 할 수 있도록 하고 모델 기반 추적 방법에는 타원 모델과 색상 모델을 결합한 얼굴 모델을 적용하여 얼굴이 회전하여도 정확한 추적을 할 수 있도록 개선하였다.

• 전기전자학회논문지
• /
• 제11권4호
• /
• pp.137-144
• /
• 2007

함포의 사격통제장치 성능은 크게 하드웨어(H/W)적인 오차와 소프트웨어(S/W)적인 오차로 구분할 수 있으며, 이중 S/W 오차에 해당하는 표적의 위치, 속도, 가속도 등을 추정하는 추적필터 오차는 탄도계산장치의 성능에 중요한 영향을 미친다. 함포의 정확한 예상탄착점 형성과 사격시 명중률 향상을 위하여 정확한 미래위치의 표적 상태정보가 필요하다. 표적 추적필터 알고리즘은 Single Singer Model, Fixed Gain 필터 알고리즘, IMM, PBIMM등이 있다. 본 논문에서는 최근 국내 함정에 적용예정인 IMM 추적필터를 설계하였다. IMM 추적필터를 위해 CV모델, Song 모델, CTR모델을 사용하여 동역학 모델을 만들었으며, 추적성능을 Monte-Carlo 시뮬레이션을 통해 해석해 보았다.

• 반도체디스플레이기술학회지
• /
• 제10권2호
• /
• pp.25-30
• /
• 2011

This paper presents a tracking vibration estimation system of the track-following system using a tracking loop gain adjustment algorithm and a genetic algorithm. The algorithms are introduced to estimate accurately the tracking vibration quantity in spite of the uncertainties of the tracking actuator. An estimated actuator model can be found by applying a genetic algorithm. Accordingly, the tracking vibration quantity can be estimated from the measured tracking error, the tracking controller and the estimated actuator model. The proposed tracking vibration estimation method is applied to the track-following system of an optical recording device and is evaluated through the experimental result.

• 한국컴퓨터정보학회논문지
• /
• 제22권1호
• /
• pp.1-7
• /
• 2017

In this paper, we propose an efficient method that is tracking an object in real time using particle filter and adaptive observation model. When tracking object, it happens object shape variation by camera or object movement in variety environments. The traditional method has an error of tracking from these variation, because it has fixed observation model about the selected object by the user in the initial frame. In order to overcome these problems, we propose a method that updates the observation model by calculating the similarity between the used observation model and the eight-way of edge model from the current position. If the similarity is higher than the threshold value, tracking the object using updated observation model to reset observation model. On the contrary to this, the algorithm which consists of a process is to maintain the used observation model. Finally, this paper demonstrates the performance of the stable tracking through comparison with the traditional method by using a number of experimental data.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권6호
• /
• pp.407-412
• /
• 2015

In model-based tracking, an accurate 3D model of a target object or scene is mostly assumed to be known or given in advance, but the accuracy of the model should be guaranteed for accurate pose estimation. In many application domains, on the other hand, end users are not highly distracted by tracking errors from certain levels of modeling errors. In this paper, we examine perceptual tracking errors, which are predominantly caused by modeling errors, on subjective evaluation and compare them to computational tracking errors. We also discuss the tolerance of modeling errors by analyzing their permissible ranges.

• 제어로봇시스템학회논문지
• /
• 제18권5호
• /
• pp.502-508
• /
• 2012

Heliostat, as a concentrator to reflect the incident solar energy to the receiver, is the most important system in the tower-type solar thermal power plant since it determines the efficiency and ultimately the overall performance of solar thermal power plant. Thus, a good sun tracking ability as well as a good optical property of it are required. Heliostat sun tracking system uses usually an open loop control system. Thus the sun tracking error caused by heliostat's geometrical error, optical error and computational error cannot be compensated. Recently use of sun tracking error model to compensate the sun tracking error has been proposed, where the error model is obtained from the measured ones. This work is a development of heliostat sun tracking error measurement and compensation method using BCS (Beam Characterization System). We first developed an image processing system to measure the sun tracking error optically. Then the measured error is modeled in linear polynomial form and neural network form trained by the extended Kalman filter respectively. Finally error models are used to compensate the sun tracking error. We also developed the necessary image processing algorithms so that the heliostat optical properties such as maximum heat flux intensity, heat flux distribution and total reflected heat energy could be analyzed. Experimentally obtained data shows that the heliostat sun tracking accuracy could be dramatically improved using either linear polynomial type error model or neural network type error model. Neural network type error model is somewhat better in improving the sun tracking performance. Nevertheless, since the difference between two error models in compensation of sun tracking error is small, a linear error model is preferred in actual implementation due to its simplicity.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.295-298
• /
• 1995

We performed a research to improve the performance of active bar model which is used in tracking algorithm. Active bar model is a simplified model of snake model. If we used the sctive bar model, the numerical procedure for real time tracking problem can be carried out faster than snake model. However the demerit of active bar algorithms is that we can't used the provious image data because each time it has to reconstruct the active bar. In this paper we proposed advanced algorithm for active bar model. The proposed model can improve tracking abilities by preserving the active bar during the process and changing the energy functional.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2340-2344
• /
• 2003

This paper considers a tracking filter algorithm which can track a maneuvering target. Multiresolutional Interacting Multiple Model (MRIMM) algorithm is proposed to reduce computational burden. In this paper multiresolutional state space model equation and multiresolutional measurement equation are derived by using wavelet transform. This paper shows the outline of MRIMM algorithm. Simulation results show that MRIMM algorithm maintains a good tracking performance and reduces computational burden.

• 한국군사과학기술학회지
• /
• 제8권3호
• /
• pp.24-32
• /
• 2005

This paper describes the tracking filter performance for Naval Gun Ballistic Computation Unit(BCU). BCU needs tracing filter for gun firing. Using data of tracking sensor, BCU calculates the future position of Target and Gun order in the time of flight. In this paper, tracing filter is designed with interacting multiple model(IMM). The tracking algorithm based on the IMM requirers a considerable number of sub-model for the various maneuvering target in order to have a good performance. But, in the case of ship target, the maneuvering is restricted compared with the air target. Considering the maneuvering properties and adjusting the mode transition probabilities and the process noise of sub-model, We designed the IMM3 algorithm for Naval tracking filter with three sub-model.