• 제어로봇시스템학회논문지
• /
• 제16권1호
• /
• pp.69-76
• /
• 2010

The segmentation of moving object in video sequence is a core technique of intelligent image processing system such as video surveillance, traffic monitoring and human tracking. A typical method to segment a moving region from the background is the background subtraction. The steps of background subtraction involve calculating a reference image, subtracting new frame from reference image and then thresholding the subtracted result. One of famous background modeling is Gaussian mixture model (GMM). Even though the method is known efficient and exact, GMM suffers from a problem that includes false pixels in ROI (region of interest), specifically shadow pixels. These false pixels cause fail of the post-processing tasks such as tracking and object recognition. This paper presents a method for removing false pixels included in ROT. First, we subdivide a ROI by using shape characteristics of detected objects. Then, a method is proposed to classify pixels from using histogram characteristic and comparing difference of energy that converts the color value of pixel into grayscale value, in order to estimate whether the pixels belong to moving object area or shadow area. The method is applied to real video sequence and the performance is verified.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.628-631
• /
• 2003

In this paper, we present real-time, accurate face region detection and tracking technique for an intelligent surveillance system. It is very important to obtain the high-resolution images, which enables accurate identification of an object-of-interest. Conventional surveillance or security systems, however, usually provide poor image quality because they use one or more fixed cameras and keep recording scenes without any cine. We implemented a real-time surveillance system that tracks a moving person using four pan-tilt-zoom (PTZ) cameras. While tracking, the region-of-interest (ROI) can be obtained by using a low-pass filter and background subtraction. Color information in the ROI is updated to extract features for optimal tracking and zooming. The experiment with real human faces showed highly acceptable results in the sense of both accuracy and computational efficiency.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.1003-1006
• /
• 1999

Hand segmentation and tracking is essential to the development of a hand gesture recognition system. This research features segementation and tracking of hand regions based the hue component of color. We propose a method that employs HSI color model, and segments and tracks hand regions using the hue component of color alone. In order to track the segmented hand regions, we only apply Kalman filter to a region of interest represented by a rectangle region. Initial experimental results show that the system accurately segments and tracks hand regions although it only uses the hue compoent of color. The system yields near real time throghput of 8 frames per second on a Pentium II 233MHz PC.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2000년도 제1회 학술대회 논문집
• /
• pp.79-80
• /
• 2000

General stereo vision system shows things in 3D, using two visions of left and right side. When the viewpoints of left/right sides are not in accord with each other, it gives fatigue to human eyes and prevents them from having the 3-D feeling. Also, it would be difficult to track mobile objects that are not in the middle of a screen. Therefore, the object tracking function of stereo vision system is to control tracking objects to always be in the middle of a screen while controlling convergence angles of mobile objects in the input image of the left/right cameras. In this paper, object-tracker in stereo vision system is presented which would track mobile objects by using block matching algorithm of preprocessing and JTC.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권1호
• /
• pp.41-47
• /
• 2000

A better tracking performance can be achieved, if visual sensors such as CCD cameras are used in controling a robot manipulator, than when only relative sensors such as encoders are used. However, for precise visual servoing of a robot manipulator, an expensive vision system which has fast sampling rate must be used. Moreover, even if a fast vision system is implemented for visual servoing, one cannot get a reliable performance without use of robust and stable inner joint servo-loop. In this paper, we propose a dynamic control scheme for robot manipulators with eye-in-hand camera configuration, where a dynamic learning controller is designed to improve the tracking performance of robotic system. The proposed control scheme is implemented for tasks of tracking moving objects and shown to be robust to parameter uncertainty, disturbances, low sampling rate, etc.

• 한국콘텐츠학회논문지
• /
• 제4권3호
• /
• pp.91-97
• /
• 2004

이동 객체 추적 시스템을 위한 한 연구 분야로 차영상을 이용하여 움직임을 추정하는 기법이 있다. 움직임 추정을 위해 차영상을 이용하는 경우 임계값을 적용하여 배경 영역과 이동 객체 영역을 구분할 수 있도록 이진화를 수행하는 과정이 필수적이다. 본 논문에서는 차영상에서 배경과 객체의 특성 변화에 적응적인 임계값 결정 기법을 제안하였다. 제안 기법은 차영상의 히스토그램 모양을 분석하여 적절한 임계값을 결정하도록 하였다. 그레이 스케일 영상의 이진화에 사용되는 일반적인 임계값 기법들과 성능을 비교 평가하였다. 60개의 실험 영상에 대해 평가한 결과 제안 기법이 수작업으로 확인한 최적의 임계값과 평균 오차 2.8로 성능의 우수성을 확인하였다.

• 한국정보통신학회논문지
• /
• 제18권10호
• /
• pp.2417-2426
• /
• 2014

간접 시선 추적 시스템은 적외선 조명을 각막에 반사시켜 그 모습을 카메라로 촬영하여 얻은 이미지에서 시선을 계산한다. 적외선 조명이 각막에 반사되어 이미지에 나타난 점을 글린트라고 한다. 최근 간접 추적 시스템은 머리의 움직임에 민감하지 않고 캘리브레이션 과정을 거치지 않도록 하기 위해 여러 개의 적외선 조명, 즉 여러개의 글린트를 사용하는 경우가 많다. 하지만 실험 도중 글린트의 일부가 보이지 않을 수 있는데, 이러한 경우 해당 프레임에서는 시선 계산을 할 수 없게 된다. 본 논문에서는 여러 개의 적외선 조명을 사용하는 시선 추적 시스템에서 여러 가지 이유로 유실되거나 인식이 어려운 글린트의 모습을 살펴본 후, 인식이 가능한 나머지 글린트 위치를 이용하여 이러한 글린트의 위치를 복원하는 알고리즘을 제안한다. 이 알고리즘을 통해 시선 추적 시 유효한 이미지 프레임의 개수를 증가 시키고, 복원 단계에서 글린트의 위치 변형 모델을 이용하여 글린트의 왜곡 또한 보정하여 시선 추적 결과의 오차도 줄일 수 있다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.3037-3040
• /
• 2000

Real-Time object tracking has emerged as an important component in several application areas including machine vision. surveillance. Human-Computer Interaction. image-based control. and so on. And there has been developed various algorithms for a long time. But in many cases. they have showed limited results under uncontrolled situation such as illumination changes or cluttered background. In this paper. we present a novel. computationally efficient algorithm for tracking human face robustly under illumination changes and cluttered backgrounds. Previous algorithms usually defines color model as a 2D membership function in a color space without consideration for illumination changes. Our new algorithm developed here. however. constructs a 3D color model by analysing plenty of images acquired under various illumination conditions. The algorithm described is applied to a mobile head-eye robot and experimented under various uncontrolled environments. It can track an human face more than 100 frames per second excluding image acquisition time.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.89-92
• /
• 2001

In this paper, we propose a new approach for tracking a moving object in moving image sequences using active contour models and optical flow. In our approach object segmentation is achieved by active contours, and object tracking is done by motion estimation based on optical flow. To get more dynamic characteristics, Lagrangian dynamics combined to the active contour models. For the optical flow computation, a method, which is based on Spatiotempo-ral Energy Models, is employed to perform robust tracking under poor environments. A prototype real tracking system has been developed and applied to a contents-based video retrieval systems.

• ETRI Journal
• /
• 제30권6호
• /
• pp.774-782
• /
• 2008

An operational orbit determination (OD) and prediction system for the geostationary Communication, Ocean, and Meteorological Satellite (COMS) mission requires accurate satellite positioning knowledge to accomplish image navigation registration on the ground. Ranging and tracking data from a single ground station is used for COMS OD in normal operation. However, the orbital longitude of the COMS is so close to that of satellite tracking sites that geometric singularity affects observability. A method to solve the azimuth bias of a single station in singularity is to periodically apply an estimated azimuth bias using the ranging and tracking data of two stations. Velocity increments of a wheel off-loading maneuver which is performed twice a day are fixed by planned values without considering maneuver efficiency during OD. Using only single-station data with the correction of the azimuth bias, OD can achieve three-sigma position accuracy on the order of 1.5 km root-sum-square.