• 한국정밀공학회지
• /
• 제15권7호
• /
• pp.175-181
• /
• 1998

This paper describes realtime visual tracking system of moving object for three dimensional target using EKF(Extended Kalman Filter). We present a new realtime visual tracking using EKF algorithm and image prediction algorithm. We demonstrate the performance of these tracking algorithm through real experiment. The experimental results show the effectiveness of the EKF algorithm and image prediction algorithm for realtime tracking and estimated state value of filter, predicting the position of moving object to minimize an image processing area, and by reducing the effect by quantization noise of image.

• 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.

• 제어로봇시스템학회논문지
• /
• 제17권4호
• /
• pp.388-396
• /
• 2011

Sun tracking system is the most important subsystem in parabolic dish type solar thermal power plant, since it determines the amount of thermal energy to be collected, thus affects the efficiency of solar thermal power plant most significantly. Various types of sun tracking systems are currently used. Among them, use of photo sensors to located the sun(which is called sensor type) and use of astronomical algorithm to compute the sun position(which is called program type) are two of the mostly used methods. Recently some uses CCD sensor, like CCD camera, which is called image processing type sun tracking system. This work is concerned with the analysis of sun tracking performance of various types of sun tracking systems currently used in the parabolic dish type solar thermal power plant. We first developed a sun tracking error measurement system. Then, we evaluate the performance of five different types of sun tracking systems, sensor type, program type, hybrid type(use of sensor and computed sun position simultaneously), tracking error compensated program type and image processing type. Experimentally obtained data shows that the tracking error compensated program type sun tracking system is very effective and could provide a good sun tracking performance. Also the data obtained shows that the performance of sensor type sun tracking system is being affected by the cloud significantly, while the performance of a program type sun tracking system is being affected by the sun tracking system's mechanical and installation errors very much. Finally image processing type sun tracking system can provide accurate sun tracking performance, but costs more and requires more computational time.

• 한국컴퓨터정보학회논문지
• /
• 제22권5호
• /
• pp.21-28
• /
• 2017

As technology related to digital imaging equipment is developed and generalized, digital imaging system is used for various purposes in fields of society. The object tracking technology from digital image data in real time is one of the core technologies required in various fields such as security system and robot system. Among the existing object tracking technologies, cam shift technology is a technique of tracking an object using color information of an object. Recently, digital image data using infrared camera functions are widely used due to various demands of digital image equipment. However, the existing cam shift method can not track objects in image data without color information. Our proposed tracking algorithm tracks the object by analyzing the color if valid color information exists in the digital image data, otherwise it generates the lightness feature information and tracks the object through it. The brightness feature information is generated from the ratio information of the width and the height of the area divided by the brightness. Experimental results shows that our tracking algorithm can track objects in real time not only in general image data including color information but also in image data captured by an infrared camera.

• 융합신호처리학회논문지
• /
• 제4권4호
• /
• pp.1-6
• /
• 2003

본 논문에서는, 움직이는 영상을 충돌방지 시스템에 의해 검출한다. 이런 영상의 노이즈는 평균 필터로 제거시킨다. 그리고, 이진 차 영상을 이용하여 움직임이 감지되었을 경우에는 라벨링과 투영방법에 의해 움직임 영역만 정확히 추출하였다. 그 후에 시스템의 추적모드에 의해서 이미지가 천천히 움직일 경우 추적창의 중심은 이전 프레임의 추적창으로부터 이동한다. 그리고, 추적 창은 추적모드와 탐지모드로 나누고, 차 영상 데이터의 대차 상관 값에 의해 결정하였다. 탐지모드는 외란에 의한 에러를 감소하기 위해서 탐지-시간 값의 비교로 추적단계를 계속 진행할 것인지 아닌지를 결정하였다. 이와 같은 움직이는 영상의 탐지와 추적을 시뮬레이션으로 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.182-184
• /
• 2005

An embedded system has been applied to many fields including households and industrial sites. The embedded system is implemented fur image tracking in security area. This system supports a fixed IP far the reliable server operation on TCP/IP networks. A real time video image on the is analyzed to detect a certain invader who jumped into the observed area. The digital camera is connected at the USB host port of the target board. The video images from the video camera is continuously analyzed and displayed at the Linux web-server. The moving vector of the invaders on the continuous image frames is calculated and then it sends the calculated pan/tilt movement. That used Block matching algorithm and edge detection algorithm for past speed. And the displacement vector is used at pan/tilt motor control through RS232 serial cable. The experiment result showed tracking performance by the moving part speed of 10 to 150 pixels/sec.

• 대한교통학회지
• /
• 제26권2호
• /
• pp.177-186
• /
• 2008

영상검지기(Video Image Detection System)는 교통운영 및 안전 등 교통류 관리를 위한 다양한 측면에서 이용될 수 있다. 영상검지기법은 크게 Tripwire System과 Tracking System으로 구분할 수 있으며, 가장 대표적으로 이용되는 Autoscope는 Tripwire System에 해당한다. 본 연구에서는 Autoscope의 성능을 구현할 수 있는 Tripwire 기반의 영상검지 기술을 자체적으로 개발함과 동시에, 미시적 교통정보를 취득할 수 있는 개별차량 추적기술을 이용한 Tracking 기반의 영상검지시스템을 개발하였다. 개발된 두 시스템의 통합에 앞서서, 동일한 영상과 분석시간을 가지고 기초적인 교통정보수집 능력에 대한 성능비교 및 분석을 수행하고자 하였으며, 우수성 및 정확성을 판단하기 위한 지표로는 가장 보편적이고 일반적으로 사용되고 있는 Autoscope를 이용하였다. 개발된 두 시스템과 Autoscope를 이용하여 성능비교를 수행한 결과, 교통량의 경우, 실제 교통량 대비 0.35%의 오차를 보였으며 Autoscope와 비교하여 1.78%의 오차를 보였다. 속도에 대한 성능비교는 Autoscope와 비교하여 최대 1.77%의 오차를 보여 개발된 두 시스템의 성능이 우수한 것으로 확인되었다.

• 반도체디스플레이기술학회지
• /
• 제10권1호
• /
• pp.83-89
• /
• 2011

In the case of the tracking system with an active camera, it is very difficult to guarantee real-time processing due to the attribute of vision system which handles large amounts of data at once and has time delay to process. The reliability of the processed result is also badly influenced by the slow sampling time and uncertainty caused by the image processing. In this paper, we figure out dynamic characteristics of pixels reflected on the image plane and derive the mathematical model of the vision tracking system which includes the actuating part and the image processing part. Based on this model, we find a controller that stabilizes the system and enhances the tracking performance to track a target rapidly. The centroid is used as the position index of moving object and the DC motor in the actuating part is controlled to keep the identified centroid at the center point of the image plane.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.642-645
• /
• 1991

This paper presents the results of research on hardware and software of the landmark tracking system to the positions of moving robot in real time. The landmark tracking system is composed of CCD camera, landmark, strobo system and image processing board. The algorithm calculates the position and direction by using the coordinate transformation fomula after calculating the centroid and rotation angle of landmark at fixed position using the image data. The experiment is performed with landmark tracking system is loaded on xyz-table. XYZ-table is used for identifying the true position in our experiment. The results shows that this system has high performance with maxima error of .+-.1 pixels.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2006년 창립20주년기념 정기학술대회 및 국제워크샵
• /
• pp.355-358
• /
• 2006

An underwater mooing target position tracking system using image tracking system of CPMC is developed to use in a test basin. Generally the performance tests of Autonomous Underwater Vehicles(AUVs) are conducted in the sea. Some efforts to perform the test in a test basin are exist, because the real sea tests need much time and manpower. And also the real sea tests are high cost. There is a restriction to acquire the position of AUVs using sonar sensor system in the test tank, because many sound reflecters are exist in a test basin. In this paper a position tracking system for underwater mooing target developed to break though this restriction. A Tank-test is conducted to examine the performance of the position tracking system.