• 정보처리학회논문지B
• /
• 제19B권2호
• /
• pp.107-112
• /
• 2012

실시간으로 입력되는 영상으로부터 지역정보 및 색 정보의 단계적 적용에 의한 Pan, Tilt 카메라를 이용한 능동객체추적방법을 제안한다. 환경 잡음을 제거하기 위하여 가우시안 필터링으로 전처리를 행한다. 적응적인 가우시안 혼합 모델링을 이용하여 배경과 객체를 분리한다. 객체가 분할되면 객체의 중심에 가깝게 탐색 윈도우를 설정하고 객체의 색 정보를 추출한다. 추출된 색 정보를 카메라가 이동하는 동안에도 추적이 가능한 CAMShift 추적 알고리즘을 적용하여 객체를 실시간으로 추적한다. 추적에 있어서 객체의 중심점이 화면의 중앙에 놓이도록 Pan, Tilt를 제어함으로써 적합한 추적이 이루어지도록 한다. 실험을 통하여 제안한 방법이 기존의 수동 영역 설정 방법보다 효과적임을 보였다.

• 전기학회논문지
• /
• 제56권1호
• /
• pp.106-111
• /
• 2007

In this study, we designed a digital fuzzy logic controller based on FPGA and microprocessor for MPPT of the sofar power generation system. A fuzzy algorithm to control the power tracking function of a boost converter has been built into the FPGA, and applied to the small scaled solar power generation system. The embodied controller showed a stable operation characteristic with the small output voltage ripple for the intensity change of solar radiation. This result proves that the implementation of the power tracking controller using FPGA is an effective way compared to the existing one using microprocessor.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2104-2107
• /
• 2003

In this paper, we propose the method Model based Non-Rigid Moving Object Tracking. Motion based method becomes difficult to predict precisely when motion gets larger, so that we can solve such difficultly with regarding the moving object as a model. In the model based method, it should be concerned about setting initial model and updating its model in each frame. We used SNAKE in a way to set the initial model, and also proposed a modified SNAKE to handle the previous SNAKE problems. Moreover, with the elliptical setting, we made the initializing process automatically which is highly subject to change in measuring the performance of SNAKE. We used the Hausdorff distance to identify models in each frame. Through our experiments, our Proposed algorithm does effective work in Non-Rigid Moving Object Tracking.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.1757-1758
• /
• 2008

Extended Kalman Filter(EKF) is widely used in tracking position of nonlinear system. but there exists a divergence problem caused by approximation of nonlinear system's linearization. Adaptive fading Kalman filter (AFKF) is one of the effective methods which employs suboptimal fading factors to solve the divergence problem in an EKF In this paper we present an improved TDoA (time difference of arrival) based position tracking by using AFKF.

• 반도체디스플레이기술학회지
• /
• 제17권2호
• /
• pp.67-70
• /
• 2018

Object detection and tracking is an exciting and interesting research area in the field of computer vision, and its technologies have been widely used in various application systems such as surveillance, military, and augmented reality. This paper proposes and implements a novel and more robust object recognition and tracking system to localize and track multiple objects from input images, which estimates target state using the likelihoods obtained from multiple CNNs. As the experimental result, the proposed algorithm is effective to handle multi-modal target appearances and other exceptions.

• Journal of information and communication convergence engineering
• /
• 제6권4호
• /
• pp.444-447
• /
• 2008

In this paper, we proposed the recognition system of car license plates to mitigate traffic problems. The processing sequence of the proposed algorithm is as follows. At first, a license plate segment is extracted from an acquired car image using morphological features and color information, and noises are eliminated from the extracted license plate segment using line scan algorithm and Grassfire algorithm, and then individual codes are extracted from the license plate segment using edge tracking algorithm. Finally the extracted individual codes are recognized by an FCM algorithm. In order to evaluate performance of segment extraction and code recognition of the proposed method, we used 100 car images for experiment. In the results, we could verify the proposed method is more effective and recognition performance is improved in comparison with conventional car license plate recognition methods.

• Journal of Welding and Joining
• /
• 제18권1호
• /
• pp.83-90
• /
• 2000

It was attempted to improve seam-tracking performance by applying a new arc-sensing algorithm for FCAW(flux-cored arc welding) process in fillet joints. For this study the authors have introduced three different weight factors: $\circled1$ arc currents at the weaving end are more weighted, $\circled2$ arc currents are evenly weighted along the weaving, and $\circled3$ arc currents at the weaving center are more weighted. To evaluate the 3 factors the values of signal-to-noise(S/N) ratio has been measured. The values were obtained for various welding conditions with different gaps in horizontal and vertical fillet joints. The test results showed that the S/N ratio of the 1st case was highest which resulted in the best of seam tracking performance. In addition, the comparison between the seam tracking performance in horizontal fillet joints and that in vertical ones has been done, and the result showed that tracking performance in vertical joints was relatively better than that in horizontal joints.

• 인터넷정보학회논문지
• /
• 제7권3호
• /
• pp.71-82
• /
• 2006

본 논문은 실내 환경에서 이동객체의 실시간 추적 알고리즘을 제안한다. 제안하는 시스템은 기존에 사용되던 삼각측량 기법과 DCM(Database Correlation Method) 기법을 통해 각각의 위치 데이터를 생성한 후, 그 중 이동객체와 더 근사한 위치 데이터를 실시간으로 선택한다. 또한 Kalman Filter를 사용하여 선택된 위치 데이터를 보정하여 시스템에 적용하므로 이동 객체의 위치 정확도를 향상시켰다. 기존에 연구된 Kalman Filter는 과거의 정보를 이용하여 현재의 위치를 추정해 내는 시스템의 특성상 안정화 되는 시간까지 불확실한 위치 데이터를 가지게 된다. 하지만 제안하는 위치 추적 시스템은 기존의 Kalman Filter를 그대로 적용하지 않고, 더 효율적인 방안을 제시한 후 적용함으로 더 정확한 위치 추적을 가능케 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.329-334
• /
• 1998

This work is concerned with the problem of tracking a maneuvering target. In this paper, an error monitoring and recovery method of perception net is utilized to improve tracking performance for a highly maneuvering tar-get. Many researches have been performed in tracking a maneuvering target. The conventional Interacting Multiple Model (IMM) filter is well known as a suboptimal hybrid filter that has been shown to be one of the most cost-effective hybrid state estimation scheme. The subfilters of IMM can be considered as fusing its initial value with new measurements. This approach is also shown in this paper. Perception net based error monitoring and recovery technique, which is a kind of geometric data fusion, makes it possible to monitor errors and to calibrate possible biases involved in sensed data and extracted features. Both detecting a maneuvering target and compensating the estimated state can be achieved by employing the properly implemented error monitoring and recovery technique. The IMM filter which employing the error monitoring and recovery technique shows good tracking performance for a highly maneuvering target as well as it reduces maximum values of estimation errors when maneuvering starts and finishes. The effectiveness of the pro-posed method is validated through simulation by comparing it with the conventional IMM algorithm.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.133-136
• /
• 2012

본 논문은 무안경 3D 디스플레이 제품의 품질을 향상시키기 위한 여러 가지 효과적인 방법을 구축하는데 목적을 두었다. 무안경 제품은 기존의 안경 방식에 비하여 3D의 depth 화질 품질이 떨어졌고, 특정 거리, 위치에서만 볼 수 있는 단점이 있어, 이를 보완하고자 Head Tracking 기술 및 영상 배치알고리즘 등 여러 가지 기술을 적용하여 기존 system의 단점을 보완하였다. 본 논문은 3D 무안경 구현 방식 중 Parallax Barrier의 3D 품질 향상을 위한 Head Tracking을 통한 사용자의 위치 파악, 영상의 재배치 기술 및 Crosstalk 개선 방법에 대해 보고합니다.