• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.55-61
• /
• 2017

In this paper, we propose a novel tracking method using target separation and detection that are based on discriminative correlation filter (DCF), which is studied a lot recently. 'Retainability' is one of the most important factor of tracking. There are some factors making retainability of tracking worse. Especially, fast movement and occlusion of a target frequently occur in image data, and when it happens, it would make target lost. As a result, the tracking cannot be retained. For maintaining a robust tracking, in this paper, separation of a target is used so that normal tracking is maintained even though some part of a target is occluded. The detection algorithm is executed and find new location of the target when the target gets out of tracking range due to occlusion of whole part of a target or fast movement speed of a target. A variety of experiments with various image data sets are conducted. The algorithm proposed in this paper showed better performance than other conventional algorithms when fast movement and occlusion of a target occur.

• 한국정밀공학회지
• /
• 제14권10호
• /
• pp.50-57
• /
• 1997

A fast tool servo (FTS) for diamond turning improves machining accuracy by quickly compensating relative position errors between the cutter and the workpiece. Therefore, the FTS needs to have large band-width with good tracking performance. Serious hysteresis nonlinearity of PZT actuators used in the FTS, however, deteriorates fast tracking performance. Several types of feedforward hysteresis compensators and feedback controllers are tested to improve tracking performance. Through simulations and experiments, control structure which yields the smallest tracking error is selected. The maximum peak to peak error in tracking a sinusoidal waveform is reduced by one fifth compared to that of a regular PID controller.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.291-294
• /
• 2004

Semantic video object extraction is important for tracking meaningful objects in video and object-based video coding. We propose a fast semiautomatic video object extraction algorithm which combines a watershed segmentation schemes and chamfer distance transform. Initial object boundaries in the first frame are defined by a human before the tracking, and fast video object tracking can be achieved by tracking only motion-detected regions in a video frame. Experimental results shows that the boundaries of tracking video object arc close to real video object boundaries and the proposed algorithm is promising in terms of speed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.99.5-99
• /
• 2002

$\textbullet$ 3-D object tracking framework $\textbullet$ Using fast stereo vision system for range image $\textbullet$ Using CONDENSATION algorithm to tracking object $\textbullet$ For recognizing object, superquardrics model is used $\textbullet$ Our target object is like coils in steel works

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2016년도 전력전자학술대회 논문집
• /
• pp.185-186
• /
• 2016

Maximum power point tracking (MPPT) techniques play a big role in improving the efficiency of photovoltaic (PV) system. Among various schemes, the incremental conductance (INC) method is mostly discussed in literature because of its fast response to the rapid irradiation changes and high tracking accuracy. However, the existing INC algorithm has trade-offs between fast dynamic response and steady state stability. This study proposes a novel INC method to meet high efficiency and fast tracking performance at the same time.

• 제어로봇시스템학회논문지
• /
• 제18권7호
• /
• pp.673-679
• /
• 2012

This paper introduces robust tracking algorithm for fast and erratic moving object. CAMSHIFT algorithm has less computation and efficient performance for object tracking. However, the method fails to track a object if it moves out of search window by fast velocity and/or large movement. The size of the search window in CAMSHIFT algorithm should be selected manually also. To solve these problems, we propose an efficient prediction technique for fast movement of object using Kalman Filter with automatic initial setting and variable configuration technique for search window. The proposed method is compared to the traditional CAMSHIFT algorithm for searching and tracking performance of objects on test image frames.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권6호
• /
• pp.454-461
• /
• 2016

A maximum power point tracking (MPPT) system with fast-tracked time and high power efficiency is presented in this paper. The proposed MPPT system uses an unbounded binary search (UBS) algorithm that continuously tracks the maximum power point (MPP) with a binary system to follow the MPP under rapid-weather-change conditions. The proposed algorithm can decide the correct direction of the MPPT system while comparing the previous power point with the present power point. And then, by fixing the MPP until finding the next MPP, there is no oscillation of voltage MPP, which maximizes the overall power efficiency of the photovoltaic module. With these advantages, this proposed UBS is able to detect the MPP more effectively. This MPPT system is based on a boost converter with a micro-control unit to control analog-to-digital converters and pulse width modulation. Analysis of this work and experimental results show that the proposed UBS MPPT provides fast, accurate tracking with no oscillation in situations where weather rapidly changes and shadow is caused by all sorts of things. The tracking time is reduced by 87.3% and 66.1% under dynamic-state and steady-state operation, respectively, as compared with the conventional 7-bit perturb and observe technique.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2000년도 춘계종합학술대회
• /
• pp.124-127
• /
• 2000

This paper describes the algorithm for more fast tracking by compensation of the staring angle of antenna to receive the satellite signal changed by the mobile vehicle direction. The staring angle is compensated by signal processing from the electronic compass which is called VECTOR2X, and a left-right tracking method. Especially, when mobile vehicle is turning with high speed, it is observed a result which has more fast tracking time by using angle tracking technique compensated by electronic compass than one by only left right tracking method.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권12호
• /
• pp.977-985
• /
• 2009

본 논문은 빠르게 움직이는 인간 신체를 추적할 수 있는 실시간 인간 신체 움직임 추적 알고리듬을 제안한다. 반복 최근접점(Iterative closest point) 알고리듬은 효율적이고 계산량이 적어 실시간 인간 신체 움직임 추적에 적합하지만 잘못된 최근접점(Closest point) 선택으로 인해 국부적 최소점(Local minimum)에 쉽게 빠지게 되어 종종 추적에 실패하게 된다. 이를 극복하기 위해, 반복 최근접점 알고리듬에 움직임 이력(Motion history) 정보를 기반으로 한 파티클 필터 (Particle filter)를 결합한다. 제안하는 인간 신체 움직임 추적은 계층적 트리 구조를 사용함으로써 신체 추적 공간 크기를 줄여주며, 움직임 이력 정보를 이용한 움직임 예측 모델을 사용함으로써 빠른 인간 신체 움직임 추적을 가능하게 한다. 실험 결과는 제안하는 인간 신체 움직임 추적이 정확한 추적 성능과 빠른 수렴 속도를 가진다는 것을 보여 준다.

• 대한전자공학회논문지SP
• /
• 제42권3호
• /
• pp.15-22
• /
• 2005

객체 중심점에서 움직임을 추정하여 빠르게 이동하는 객체의 윤곽선을 추적 할 수 있는 알고리듬을 제안하였다. 방사상 표현(radial representation) 방식을 적용하여 객체 중심점에서만 블록정합 (block matching) 알고리듬으로 움직임을 추정하여 적은 계산량으로 객체 움직임을 추정함으로써 객체 윤곽선을 추적하였다. 객체의 움직임을 추정함으로써 프레임 간 객체의 움직임이 객체 중심에서 윤곽까지 거리 이상 빠르게 이동하는 객체도 추적할 수 있다. 에너지 수렴 과정에서 기울기 영상과 차영상(difference image)을 에너지 함수로 함께 사용함으로 복잡한 배경 등에도 강건하도록 하였다. 실험 결과 움직임이 빠른 객체와 복잡한 배경 속의 객체도 실시간으로 강건하게 추적함을 확인하였다.