• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.420-425
• /
• 2009

In this paper, image detection and recognition algorithms are studied with respect to embedded carrier system. There are many suggested techniques to detect and recognize objects. But they have the propensity to need much calculation for high hit rate. Advanced and modified method needs to study for embedded systems that low power consumption and real time response are requested. The proposed methods were implemented using Intel(R) Open Source Computer Vision Library provided by Intel Corporation. And they run and tested on embedded system using a ARM920T processor by cross-compiling. They showed 1.6sec response time and 95% hit rate and supported the automated moving carrier system smoothly.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.805-812
• /
• 1989

An efficient diagnostic approach for real-time operation aiding expert system in chemical process plants is discussed. The approach is based on the hybrid of the simplified symptom tree(SST) and the fault consequence digraph(FCD), representation of propagation patterns of fault states. The SST generates fault hypothesis efficiently and the FCD resolve the real fault accurately. Frame based knowledge representation and object-oriented programming make diagnostic system general and efficient. Truth maintenance system enables robust pattern matching and provides enhanced explain facilities. A prototype expert system for supports operation of naphtha furnaces process, called OASYS, has been built and tested to demonstrate this methodology. Utilization of diversified process symbolic data, produced using dynamic normal standards, overcomes the problem of qualitative Boolean reasoning and enhance the applicability.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.12
• /
• pp.1223-1231
• /
• 2009

We derive a systematic and iterative calibration algorithm, and position and pose estimation algorithm for the mobile robots in formation system based on the vision system. In addition, we develop a coordinate matching algorithm which calculates matched sequence of order in both extracted image coordinates and object coordinates for non interactive calibration and pose estimation. Based on the results of calibration, we also develop a camera simulator to confirm the results of calibration and compare the results of simulations with those of experiments in position and pose estimation.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.5
• /
• pp.666-672
• /
• 2011

In this paper, we describes the development of automatic inspection system for detecting the defects on photovoltaic wafer by using machine vision. Until now, The defect inspection process was manually performed by operators. So these processes caused the produce of poorly-made articles and inaccuracy results. To improve the inspection accuracy, the inspection system is not only configured, but the image processing algorithm is also developed. The inspection system includes dimensional verification and pattern matching which compares a 2-D image of an object to a pattern image the method proves to be computationally efficient and accurate for real time application and we confirmed the applicability of the proposed method though the experience in a complex environment.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.763-768
• /
• 1999

The space variant imaging system which mimics the human beings visual system has some merits such as wide field-of-view, the low computational cost and the high accuracy in matching of correspondence points of stereo images. In this presentation, a visual servoing system based on the space variant imaging technique is proposed for the control of the rehabilitation robot arm. The position information of an object obtained by space variant imaging techniques is used for the visual servoing. According to the empirical data, the degree of correlation extracted by the space variant imaging technique is more accurate than that of the space invariant imaging technique.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1911-1914
• /
• 2003

This paper proposes efficient system for multiview images using backward quadtree disparity estimation. Previous quadtree method usually divides current image. In this work, backward quadtree divides reference image. So, it does not need to code quadtree data. For backward quadtree, quadtree information map is generated. By using this map, adaptive dividing is possible. And, conventional bi-directional matching method is used with backward quadtree. These methods increase subject and object quality of decoded test images. For multiview images, panorama synthesizing method was used. Panorama image and right-most image are used for reference image for intermediate view images coding.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1980-1983
• /
• 2003

자동으로 분할된 영상에서 각각의 영역들은 동질의 특징을 가지는 성분들로 구성되어 있다. 그러나 대부분의 경우 하나의 영역만으로는 특정한 혹은 의미 있는 오브젝트를 정확히 표현 할 수 없다. 이 중에서 하나 이상의 영역 즉 비슷한 특징을 갖는 몇몇 영역들의 집합이 사용자에게 있어서 의미 있는 오브젝트를 구성한다고 볼 수 있다 이를 전제로 본 논문에서는 분할된 영상 내에 존재하는 기저 영역들의 모멘트 추출을 기반으로 하는 객체 매칭 기법을 제안한다. 제안된 매칭 방법에서는 자동 영상 분할된 각 영역들로부터 모멘트를 추출하고 이 정보를 이용하여 조합된 영역에 대한 모멘트를 계산하게 되고, 다시 이들 조합된 영역의 모멘트를 이용하여 그 영역의 쉐입(shape) 특징 벡터를 추출한다. 이를 통하여 사용자가 찾고자 하는 영역과 분할영상내의 모든 영역의 조합에 대해서 초기에 추출된 정보만을 이용하여 매칭할 수 있도록 하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.542-543
• /
• 2015

본 논문에서는 차량에 설치된 스테레오 카메라를 이용하여 객체 후보를 검출하는 기법을 제안한다. 단일 카메라를 이용하면 색상 정보만을 획득할 수 있지만 스테레오 카메라를 이용하면 추가적으로 깊이 영상(depth image)을 획득할 수 있다. 깊이 정보를 이용하면 카메라의 주변 환경을 재구성 할 수 있으며, 객체 후보 검출의 성능을 향상 시킬 수 있다. 스테레오 매칭(Stereo matching)을 통해 획득한 깊이 영상을 열 단위 분석을 통해 객체로 판단되는 영역을 검출한다. 검출한 영역 경계 부근의 오류를 줄이기 위해 밝기 차를 분석한다. 실험을 통해 제안하는 시스템이 효과적으로 객체 후보를 검출하는 것을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.968-976
• /
• 2003

In this paper, we propose a novel method for lip recognition. Lip model is built based on the concatenated gray level distribution model, and the recognition problem is simplified as the minimization problem of matching object function. The Down Hill Simplex Algorithm is used for the minimization with the proposed novel method for setting initial condition, which can refrain Iteration from converging to local minima. The proposed algorithm shows extracting lip shape from the test image where Active Shape Model fails.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.999-1004
• /
• 2002

This paper presents the color displays using more than three primary colors, for the reproduction of wider color gamut, and high-fidelity color reproduction. First, Natural Vision system, which is currently under development for the natural color reproduction in visual telecommunication applications, is introduced, The natural vision is based on spectrum instead of trichromatic color space, and enables high-fidelity color reproduction using multispectral and multiprimary technologies. Then, sixprimary color projection displays using LCD and DLP, and a four-primary color flat panel display are shown. It is experimentally demonstrated that the color gamut becomes much larger than conventional RGB-based display. In addition, it is proved that the spectral color reproduction using multiprimary display suppresses the influence of observer metamerism, and as a result, the color matching between the display and the real object is well improved.