• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.11
• /
• pp.79-88
• /
• 1999

In this paper we address the tracking method which tracks only target object in image sequence including moving object. We use a contour tracking algorithm based on intensity and motion boundaries. The motion of the moving object contour in the image is assumed to be well describable by an affine motion model with a translation, a change in scale and a rotation. The moving object contour is represented by B-spline, the position and motion of which is estimated along the image sequence. we use pattern recognition to identify target object. In order to use linear Kalman Filters we decompose the estimation process into two filters. One is estimating the affine motion parameters and the other the shape of moving object contour. In some experiments with dial plate we show that this method enables us to obtain the robust motion estimates and tracking trajectories even in case of including obstructive object.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.3
• /
• pp.156-163
• /
• 2003

Most watermarking techniques insert watermarks into transform coefficients in the frequency domain because we can consider robust or imperceptible frequency bands against malicious attacks to remove them. However, parameterization of 3-D data is not easy because of irregular attribution of connectivity information, while 1-I) or 2-D data is regular. In this paper we propose a new watermarking scheme for 3-D polygonal mesh models in the DCT domain. After we generate triangle strips by traversing the 3-D model and transform its vertex coordinates into the DCT domain, watermark signals are inserted into mid-frequency bands of AC coefficients for robustness and imperceptibility. We demonstrate that our scheme is robust against additive random noise, the affine transformation, and geometry compression by the MPEG-4 SNHC standard.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.91-94
• /
• 1996

This paper presents an approach to estimation of learning gain in iterative learning control for discrete-time affine nonlinear systems. In iterative learning control, to determine learning gain satisfying the convergence condition, we have to know the system model. In the proposed method, the input-output equation of a system is identified by neural network refered to as Piecewise Linearly Trained Network (PLTN). Then from the input-output equation, the learning gain in iterative learning law is estimated. The validity of our method is demonstrated by simulations.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.2
• /
• pp.146-154
• /
• 2006

In this paper, we propose direct and indirect adaptive fuzzy sliding mode control approaches for a class of nonaffine nonlinear systems. In the direct case, we use the implicit function theory to prove the existence of an ideal implicit feedback linearization controller, and hence approximate it to attain the desired performances. In the indirect case, we exploit the linear structure of a Takagi-Sugeno fuzzy system with constant conclusion to establish an affine-in-control model, and therefore design an indirect adaptive fuzzy controller. In both cases, the adaptation laws of the adjustable parameters are deduced from the stability analysis, in the sense of Lyapunov, to get a more accurate approximation level. In addition to their robustness, the design of the proposed approaches does not require the upper bounds of both external disturbances and approximation errors. To show the efficiency of the proposed controllers, a simulation example is presented.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.188-190
• /
• 2019

Long-term global motion compensation (LT-GMC) was designed to compensate camera motion effectively. The LT-GMC warps a reference picture according to an estimated affine/homography model and stores it in its decoded picture buffer for long-term reference. Most previous works on LT-GMC have focused on improving quality of the warped picture, however, there has been only little consideration on the overhead of its motion coding. In this paper, we address this problem and propose a method, namely Scaling Predictor, to reduce the motion coding overhead for LT-GMC. Our experiment has shown BD-Rate reduction of 1.40% over conventional LT-GMC scheme by applying the proposed method.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.955-958
• /
• 1998

This paper describes the algorithm which extracts moving vehicles from sequential images and tracks those vehicles using Kalman filter. This work is composed of a motion segmentation stage which extracts moving objects from sequential images and gets features of objects, and a motion estimation stage which estimates the position and the motion of moving objects using Kalman filter. In the motion estimation stage, applying to affine motion model we divided the Kalman filter into position filter and velocity filter to employ linear Kalman filter. Multi-target tracking requires a data association component that decides which measurement to use for updating the state of which object. We use pattern recognition method to solve this problem.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.500-504
• /
• 2002

The purpose of this paper is to implement a guidance system for an object on the road. A watch camera equipped on the auto door recognizes the direction for the destination of an object, after that it determines whether opening or closing the door, and then the door is opened automatically, based on the decision. The motion of the moving object is approximated by using the technique of the image processing of tracking images and the affine model. The direction of the moving object is predicted from image information obtained by applying linear Kalman filter to the motion estimation in order to reduce the search region, the moving position, and the direction of the center of the object. Along with the guidance function, the system has the announcing function to the object. The experimental results confirm the veridity and applicability of the proposed system.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.3
• /
• pp.89-96
• /
• 1999

본 논문에서는 빠른 수행 속도를 가지고 여러 대의 차량을 동시에 추적할 수 있는 다중 차량 추적 알고리즘을 제안한다. 이러한 작업은 연속 영상으로부터 움직이는 물체의 동작 정보를 구하는 동작 분할(motion segmentation)단계와 칼만 필터(Kalman filter)를 이용해서 물체의 위치를 예측하는 동작 예측(motion estimation)단계로 나누어진다. 제안된 알고리즘은 아핀 동작 모델(Affine motion model)을 적용하여 동작 정보를 근사화함으로써 두 개의 선형 칼만 필터를 사용하고, 칼만 필터에서 예측된 위치 정보를 동작 분할 과정에 사용하여 빠른 추적이 이루어지도록 하였다. 또한, 다중 물체 추적 시 중요한 데이터 연결 문제(data association problem)를 해결하기 위해서 패턴 인식 방법을 도입하였다. 제안된 알고리즘을 고속 도로 영상에 대해 적용했을 때, 빠르고 정확한 다중 차량 추적이 이루어짐을 실험 결과를 통해 보였다.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.216-218
• /
• 2009

This paper proposes an image processing algorithm to stabilize shaken scenes of UAV(Unmanned Aerial Vehicle) caused by vehicle self-vibration and aerodynamic disturbance. The proposed method stabilizes images by compensating estimated shake motion which is evaluated from global motion. The global motion between two continuous images modeled by 6 parameter warping model is estimated by non-linear square method based on Gauss-Newton algorithm with excluding outlier region. The shake motion is evaluated by subtracting the global motion from aerial vehicle motion obtained by averaging global motion. Experimental results show that the proposed method stabilize shaken scenes effectively.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.621-624
• /
• 1999

This paper describes a distance estimation method of object's motion in soccer image sequence by tracking field features. And we quantitatively evaluate the estimation accuracy We suppose that the input image sequence is taken with a camera on static axis and includes only zooming and panning transformation between frames. Adaptive template matching is adopted for non-rigid object tracking. For background compensation, feature templates selected from reference frame image are matched in following frames and the matched feature point pairs are used in computing Affine motion parameters. A perspective displacement field model is used for estimating the real distance between two position on Input Image. To quantitatively evaluate the accuracy of the estimation, we synthesized a 3 dimensional virtual stadium with graphic tools and experimented on the synthesized 2 dimensional image sequences. The experiment shows that the average of the error between the actual moving distance and the estimated distance is 1.84%.