• 제어로봇시스템학회논문지
• /
• 제18권1호
• /
• pp.35-41
• /
• 2012

This paper proposes a moving object detection algorithm for active camera system that can be applied to mobile robot and intelligent surveillance system. Most of moving object detection algorithms based on a stationary camera system. These algorithms used fixed surveillance system that does not consider the motion of the background or robot tracking system that track pre-learned object. Unlike the stationary camera system, the active camera system has a problem that is difficult to extract the moving object due to the error occurred by the movement of camera. In order to overcome this problem, the motion of the camera was compensated by using SURF and Pseudo Perspective model, and then the moving object is extracted efficiently using stochastic Label Cluster transport model. This method is possible to detect moving object because that minimizes effect of the background movement. Our approach proves robust and effective in terms of moving object detection in active camera system.

• 정보처리학회논문지B
• /
• 제13B권4호
• /
• pp.463-470
• /
• 2006

카메라를 통하여 입력되는 객체의 움직임은 잡음이나 조명의 변화에 따라 정확하게 추출하고 추적하는 것이 어렵다. 실시간으로 입력되는 영상에서 객체를 추출하고 움직임을 추적하기 위해서는 고속탐색 알고리즘이 필요하다. 본 논문에서는 정확한 객체의 움직임을 추출하고 고속 추적을 위하여 배경화면의 변화에 강인한 배경영상 갱신 방법과 가변적인 탐색영역을 이용한 정확하고 빠른 알고리즘을 제안한다. 배경영상 갱신 방법은 임계값이 실험적 기준치 보다 작은 경우에는 배경영상을 갱신하고, 큰 경우에는 객체가 유입된 시점으로 판단하여 픽셀검사를 통해 객체의 윤곽점을 추출한다. 추출된 윤곽점은 객체 최소블록의 생성과 일정한 거리를 유지하는 탐색블록을 생성하여 정확하고 빠른 객체의 움직임을 추적한다. 실험결과, 제안한 방법은 95% 이상의 높은 정확도를 보였다.

• 한국영어학회지:영어학
• /
• 제2권4호
• /
• pp.471-494
• /
• 2002

May(1985) argued that the regress problem of antecedent-contained deletion (ACD) construction could be resolved easily by positing QR. But the proposal has some conceptual and empirical problems. To resolve the problems of QR account on ACD, Hornstein(1994) suggested a new approach viz. LF A-movement approach. In the Minimalist framework, an object raises to the [Spec, Agro] to check the accusative case. Through this movement, the regress problem can be resolved naturally without QR. But the LF A-movement account has the same conceptual problem as the QR approach. In addition to the conceptual problem, it has also empirical problems which were pointed out by Kennedy(1997). To solve the problems, I propose that the object raise to [Spec Agro] overtly as Koizumi(1993, 1995) and Lasnik(1995) insisted. In addition to the proposal, I adopt another assumption that only the copy of a quantifier could become a variable by the vehicle change, which was suggested by Brody(1995). With the above proposals, the unnatural QR operation could be dispensed with and the conceptual and empirical problems which were made concerning the LF A-movement approach could be resolved.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.474-474
• /
• 2000

This paper shows that a system with two-link arm can obtain hand reaching movement to a target object projected on a visual sensor by reinforcement learning using a layered neural network. The reinforcement signal, which is an only signal from the environment, is given to the system only when the hand reaches the target object. The neural network computes two joint torques from visual sensory signals, joint angles, and joint angular velocities considering the urn dynamics. It is known that the trajectory of the voluntary movement o( human hand reaching is almost straight, and the hand velocity changes like bell-shape. Although there are some exceptions, the properties of the trajectories obtained by the reinforcement learning are somewhat similar to the experimental result of the human hand reaching movement.

• 한국디지털건축인테리어학회논문집
• /
• 제7권1호
• /
• pp.15-20
• /
• 2007

This study is aimed to analyze the method of movement expression in the Space-Time of Modern Visual Art. According to the results of analysis. the following is obtained. (1) The still object is perceived by the sense or optical illusion, and its whole image is made through the information processing prodedure. The concept of Space-Time is integrated into the constructivist works by the composition of image through transforming the position of the fundamental geometry and projecting it. (2) The traditional notion that the work of art is still concept of is changed. The movement of observer is caused by inducing the direction and concept of time through the object in three dimensional space.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.291-294
• /
• 2002

A simple computer vision technology to measure the middle-ranged depth with mono camera and plain mirror is proposed The proposed system is structured wiか the rotating mirror in front of the fixed mono camera In contrast to the previous stereo vision system in which the disparity of the closer object is larger than that of the distant object, the pixel movement caused by the rotating mirror is bigger for the pixels of the distant object in the proposed system Being inspired by such feature in the proposed system the principle of the depth measurement based on the relation of the pixel movement and the distance of object have been investigated. Also, the factors to influence the precision of the measurement are analysed The benefits of the proposed system are low price and less chance of occlusion. The robustness for practical usage is an additional benefit of the proposed vision system.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제9권6호
• /
• pp.137-142
• /
• 2020

사물인터넷 기기를 이용한 감시 시스템에 대한 연구가 증가함에 따라 특정 객체의 위치를 추적하는 연구의 필요성이 높아지고 있다. 빠른시간 안에 실시간으로 객체의 이동을 감지하고 이동 경로를 예측하는 것을 목표로 한다. 움직이는 객체를 명확하게 인식하고 검출하는 연구는 많이 이루어졌지만 객체를 인식하는 카메라 간의 정보의 공유를 필요로 하지 않는다. 본 논문에서는 카메라의 기기정보와 카메라에서 촬영하는 영상정보를 이용하여 객체의 이동반경을 예측하고 반경 내의 카메라에 대해 정보를 공유하여 객체의 이동 경로를 제공한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권6호
• /
• pp.1166-1191
• /
• 2011

This paper presents an adaptive active tracking system with sector based scanning for a single PTZ camera. Dividing sectors on an image reduces the search space to shorten selection time so that the system can cover many targets. Upon the selection of a target, the system estimates the target trajectory to predict the zooming location with a finite amount of time for camera movement. Advanced estimation techniques using probabilistic reason suffer from the unknown object dynamics and the inaccurate estimation compromises the zooming level to prevent tracking failure. The proposed system uses the simple piecewise estimation with a few frames to cope with fast moving objects and/or slow camera movements. The target is tracked in multiple steps and the zooming time for each step is determined by maximizing the zooming level within the expected variation of object velocity and detection. The number of zooming steps is adaptively determined according to target speed. In addition, the iterative estimation of a zooming location with camera movement time compensates for the target prediction error due to the difference between speeds of a target and a camera. The effectiveness of the proposed method is validated by simulations and real time experiments.

• 한국산학기술학회논문지
• /
• 제9권4호
• /
• pp.905-910
• /
• 2008

본 논문은 운동 물체에 대한 시뮬레이션 할 수 있는 원판형 모션테이블 제작과 제어 실험 시스템을 제시하였다. 원판형 모션테이블은 3개의 길이가 변하는 축과 중심점을 유지하는 축으로 이루어져 있으며, 원판의 자세 변화에 따른 중심점은 중심축 상에 항상 놓이도록 설계 되어 있다. 제어 시스템은 원판형 모션테이블의 서보모터 3개를 제어함으로써 원판의 자세를 바꿀 수 있도록 설계 되었다. 또한 본 원판형 모션테이블을 이용한 비행제어 시물레이션을 예로 제시하였다. 이러한 소형 모션테이블의 보급과 이를 이용한 실험 교육은 우리나라의 항공우주, 로봇분야의 인력양성에 기여할 것이다.

• 대한인간공학회지
• /
• 제19권2호
• /
• pp.47-61
• /
• 2000

To study the characteristic of the weight center control of humans, the tracking control capability of circular and wave motion by weight center movement was conducted by using the force platform. The control performance(the integrated value of the $|Object\;value(X)-Control\;Value(Y)|^{2}$) and control trace record was used to evaluate the individual performance characteristics. The size of the population for this study was 73, which consisted of engineering students, students majoring in taekwondo, students majoring in dance, all of which were in their twenties, and also people in their sixties. The results of this study indicate that the weight center control characteristics of humans can be represented by the evaluation method and values. People who were capable of tracking the object did not stop nor overshot the objective. In addition, habits or training characteristics and aging seemed to influence the performance of the subjects. In the future, development of different objectives for weight center control could be used to determine the severity of the disease of the subject and the effects of the treatment.