• 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.

• 한국통신학회논문지
• /
• 제16권11호
• /
• pp.1201-1209
• /
• 1991

일반적으로 기존의 추적 알고리즘은 표적의 수에 따른 계산량의 기하학적 증가로 실시간 처리 등 실제 응용에 커다란 제한이 되고 있다. 따라서, 본 논문에서는 고밀도 상호 연결 구조와 대규모 병렬 처리로 실시간 처리가 가능한 새로운 신경회로망 이동 표적 추적 시스템에 대한 이론적 분석과 실험을 하였다. 분석 결과, 신경회로망 알고리즘을 이용한 추적 시스템은 표적 정보의 병력 및 집적 연산이 가능하여 표적이 증가한 경우에도 계산량이 크게 증가하지 않고, 학습을 통한 추적의 최적화가 가능하며, 표적의 여러 이동 정보가 상호 연결 강도에 저장되어 다량의 정합 필터 효과를 가질 수 있으므로 신경회로망을 이용한 새로운 표적 추적 시스템의 실시간 응용 가능성을 제시하였다.

• 제어로봇시스템학회논문지
• /
• 제6권2호
• /
• pp.164-172
• /
• 2000

To follow a moving target keeping a certain distance it is essential for a mobile robot to detect the target first and to measure its pose and velocity. This paper proposes a new solution for this problem using the accumulated ultrasonic image which is constructed by accumulating the returned ultrasonic signal along the time axis for a certain number of measurement periods. A moving target is separated by selecting the trajectory whose inclination is different from others in the imag since the inclination of a trajectory represents the relative speed of the target against the mobile robot. The proposed algorithm was implemented on a mobile robot and has shown that the robot follows a moving target successfully.

• 제어로봇시스템학회논문지
• /
• 제11권7호
• /
• pp.587-594
• /
• 2005

In this paper, a robust correlation-based video tracking is proposed to track a moving object in correlated image sequences. A correlation-based video tracking algorithm seeks to align the incoming target image with the reference target block image, but has critical problems, so called a false-peak problem and a drift phenomenon (correlator walk-off. The false-peak problem is generally caused by highly correlated background pixels with similar intensity of a moving target and the drift phenomenon occurs when tracking errors accumulate from frame to frame because of the nature of the correlation process. At first, the false-peaks problem for the ordinary correlation-based video tracking is investigated using a simple mathematical analysis. And, we will suggest a robust selective-attention correlation measure with a gradient preprocessor combined by a drift removal compensator to overcome the walk-off problem. The drift compensator adaptively controls the template block size according to the target size of interest. The robustness of the proposed method for practical application is demonstrated by simulating two real-image sequences.

• 한국의학물리학회지:의학물리
• /
• 제20권4호
• /
• pp.324-330
• /
• 2009

본 연구에서는 정위방사선수술시 움직이는 목표점에 대한 사이버나이프 호흡동기추적장치의 위치 정확성 및 유용성을 평가하고자 한다. 본 연구를 위해 움직이는 목표점을 재현할 수 있는 동적팬톰을 사용하였으며 움직이는 목표점 추적을 위하여 사이버나이프의 호흡동기추적장치인 $Synchrony^{TM}$ 시스템을 사용하였다. 움직이는 목표점의 치료계획을 위하여 4D CT를 이용한 영상획득을 하였고 움직이는 목표점에서의 선량분포와 점선량 측정을 위하여 gafchromic EBT 필름과 0.62 cc 이온 전리함을 사용하였다. 호흡동기추적장치의 정확성을 평가하기 위하여 팬톰의 목표점을 움직였을 때와 정지 상태일 때 목표점에서의 선량분포(처방선량기준 선량분포의 80%)를 비교하였으며 목표점에서의 점선량을 측정하였다. 위치추적장치와 호흡동기추적장치 상호간의 동기화에 의한 정확성은 동기화 되지 않을 경우 평균 $11.5{\pm}3.09\;mm$였으며 동기화 되었을 경우 $0.14{\pm}0.08\;mm$의 차이를 나타내었다. 목표점 정지상태시의 영상과 4D CT를 이용한 움직이는 목표점에 대한 영상을 이용하여 치료계획상의 정확성은 평균 $0.18{\pm}0.06\;mm$의 차이를 나타내었다. 또한 호흡동기추적장치의 정확성은 1 mm 이하로 나타났다. 호흡동기추적장치의 유효성을 확인하기 위하여 움직이는 목표점에 대하여 호흡동기추적장치를 중지하여 측정한 결과 평균 $17.39{\pm}0.14\;mm$였으며 가동하였을 때 $1.37{\pm}0.11\;mm$로 나타났다. 목표점에서의 선량값을 비교한 결과 목표점이 정지상태일 때 $0.68{\pm}0.38%$, 호흡동기추적장치를 이용한 움직이는 목표점에서는 $1.31{\pm}0.81%$의 차이를 나타내었다. 위치추적장치와 호흡동기추적장치 상호간의 동기화에 의한 정확성 확인에서 장치사이에서 동기화가 매우 정확하게 수행됨을 확인하였다. 본 연구의 결과 움직이는 목표점에 대한 정위방사선수술시 호흡동기추적장치를 필수적으로 사용해야하며 본 연구에서 사용된 사이버나이프의 호흡동기추적장치인 Synchrony 시스템의 유용성과 정확성을 평가한 결과 매우 정확함을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.163-163
• /
• 2000

The tracking system on the moving vehicle is made up of two parts. One is a stabilizer which is flatting the system against the moving vehicle, the other is a tracker which is tracking the target. This makes use of the geometric information of the tracking target and that utilizes the dynamic information of the moving vehicle equipping the tracking system. Especially the stabilizer is very important for an ocean vehicle affected by wave, wind, and current. In this paper, the stabilizer of sun tracking system for a ship is developed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.1211-1212
• /
• 2008

In this paper, we propose image process modeling as a part of location based surveillance system for unauthorized target recognition and tracking in harbor, airport, military zone. For this, we compress and store background image in lower resolution and perform object extraction and motion tracking by using sobel edge detection and difference picture method between real images and a background image. In addition to, we use Independent Component Analysis Neural Network for moving target recognition. Experiments are performed for object extraction and tracking of moving targets on road by using static camera in 20m height building and it shows the robust results.

• 제어로봇시스템학회논문지
• /
• 제16권11호
• /
• pp.1044-1052
• /
• 2010

In this paper, a new realtime algorithm called the RTPBTD-HPDAF (Recursive Temporal Profile Base Target Detection with Highest Probability Data Association Filter) is presented for tracking fast moving small targets with IIR (Imaging Infrared) sensor systems. Spatial filter algorithms are mainly used for target in IIR sensor system detection and tracking however they often generate high density clutter due to various shapes of cloud. The TPBTD (Temporal Profile Base Target Detection) algorithm based on the analysis of temporal behavior of individual pixels is known to have good performance for detection and tracking of fast moving target with suppressing clutter. However it is not suitable to detect stationary and abruptly maneuvering targets. Moreover its computational load may not be negligible. The PTPBTD-HPDAF algorithm proposed in this paper for real-time target detection and tracking is shown to be computationally cheap while it has benefit of tracking targets with abrupt maneuvers. The performance of the proposed RTPBTD-HPDAF algorithm is tested and compared with the spatial filter with HPDAF algorithm for run-time and track initiation at real IIR video.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.125-130
• /
• 1991

This paper presents a tracking filter using pseudomeasurements in an estimated line-of-sight Cartesian coordinate system(ELCCS) whose x-axis is on the line-of-sight to an estimated target position. A target dynamics model and a measurement equation in the ELCCS are derived first and then a tracking filter in the ELCCS named moving coordinate tracking filter(MCTF) is proposed. It is shown that this MCTF is equivalent to a Kalman filter in the inertial Cartesian coordinate system which is widely used in the target tracking system. By approximating the MCTF for a pseudomeasurement noise and an error covariance matrix in the ELCCS, decoupling of three axes can be achieved. In this case, named decoupled moving coordinate tracking filter(DMCTF), computation time can be drastically reduced by utilizing its parallel structure. Finally, the stochastic properties of the MCTF and DMCTF are presented. Especially, a sufficient condition of nondestabilizing deviation for the DMCTF is proposed. The performance of the MCTF and DMCTF are compared with a conventional Kalman tracking filter.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.673-676
• /
• 2003

This paper deals with the problem of moving object detection and location in computer vision. We describe a new object-dependent motion analysis method for tracking target in an image sequence taken from a moving platform. We tackle these tasks with three steps. First, we make an active contour model of a target in order to build some of low-energy points, which are called kernels. Then we detect interest points in two windows called tracking windows around a kernel respectively. At the third step, we decide the correspondence of those detected interest points between tracking windows by the probabilistic relaxation method In this algorithm, the detecting process is iterative and begins with the detection of all potential correspondence pair in consecutive image. Each pair of corresponding points is then iteratively recomputed to get a globally optimum set of pairwise correspondences.