• Journal of Korea Multimedia Society
• /
• v.18 no.12
• /
• pp.1519-1527
• /
• 2015

TFT-LCD automatic defect inspection system for detecting defects in place of the visual tester does pre-processing, candidate defect pixel detection, and recognition and classification through a blob analysis. An over-detection result of defects acts as an undue burden of blob analysis for recognition and classification. In this paper, we propose defect detection method based on the histogram distribution modeling of TFT-LCD image to minimize over-detection of candidate defective pixels. Primary defect candidate pixels are detected estimating the skewness of the luminance distribution histogram of the background pixels. Based on the detected defect pixels, the defective pixels other than noise pixels are detected using the distribution histogram model of the local area. Experimental results confirm that the proposed method shows an excellent defect detection result on the image containing the various types of defects and the reduction of the degree of over-detection as well.

• Korean Institute of Interior Design Journal
• /
• v.14 no.4 s.51
• /
• pp.19-26
• /
• 2005

Digital technology continually makes a space evolves. The real-time behavior design communicates the data with the situation of circumference of the space(visitors moving, interior and exterior situations). The space form was changed because it interfaces in real time. The purpose of this study was finding out the characteristics of real-time behavior space design through the analysis of space formative languages, sensorium, S-R and material. This study will be the one of basic references for the digital space design. The boundary of this study set limits to the works of digital space designer who applies the real-time exchanging data to their design among the digital space design works from 1996 to 2004. But it excepted from the real-time behavior space in virtual realty. Therefore, the objects of this study were the works of onl and NOX(paraSITE, Trans-port 2001, Muscle, MotormeCCa, Handdrawspace, Saltwater Pavilion, Son-O-House, H2O Expo). The method was the contents analysis of space formative languages(Greg Lynn's ten space formative languages; bleb, blob, branch, flower, fold, lattice, teeth, shred, skins and strand), sensorium, S-R and material. The results of the study are as follows: 1) The organizational elements; Space formative languages(bleb, blob, fold, shred, skins, strand), stimulation(Human Participation, Human Moving, Weather Conditions), and response(Spatial Moving, Sound Pattern, Lighting Pattern, color Pattern, Activating Particles, Moving Picture, Virtual Friend) 2) The material Use; Sound, lights, and network have been used in the space. Immaterial matter will be used the main material of space design in 21"'century, 3)The spatial types; formal changing of space, projecting immaterial elements, and changing the sound.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.286-289
• /
• 2012

본 논문은 3차원 깊이 정보를 이용하여 감시카메라에서 움직이는 사람을 검출하고 추적하는 방법을 제안한다. 제안하는 방법은 GMM(Gaussian mixture model)을 이용하여 배경과 움직이는 사람을 분리한 후, 분리된 영역을 CCL(connected-component labeling)을 통하여 각각 블랍(blob) 단위로 나누고 그 블랍을 추적한다. 그 중 블랍 단위로 나누는 데 있어 두 블랍이 합쳐진 경우, 3차원 깊이 정보를 이용하여 두 블랍을 분리하는 방법을 제안한다. 실험을 통하여 제안하는 방법의 결과를 보인다.

• Korean Institute of Interior Design Journal
• /
• v.14 no.5 s.52
• /
• pp.98-105
• /
• 2005

Through advanced computer technology, our physical environment became a flexible and liquid space that is a multi-functional space structure, hetero-alliance, formless, interactivity. We attempt to interpretate Deleuze's Other geometry as a space designer. Hence first, the aim of this study is to define the meaning of the Other and Other geometry. Second, to extract keywords out of the Other geometry to analyze the work. Third, to analyze the work using the space formative languages(blob, blurring, distortion, folding, layering, lightness, nesting, repetition, shear, transparency, twisting, unfolding, warping, waving, and weaving). The 13 works were selected which have been issued after year 2000 with the focus on liquid space studies. The methods of this study are literature research and contents analysis. The results of the analysis were as follows. First, the source is the Other who is a hidden potentials in the surrounding environment, and this source has the capability of making it part of reality anytime. Other geometry means it is a theory that is comprised of various lines that with the kind of experiences that one has in life. Second, the key words that were extracted from the theory of Deleuze's Other geometry were of (1)hetero-alliance(reflected in a sculptured shape or a fluid abstract form), (2)dis-form(by speculating the user's movements, and combining space elements with external forces), (3)interactivity (information was exchanged real time between the user and his environment where the space took on a sensory institution). Finally, after studying the works using the space formative languages, we found that blob, warping, waving were used externally, and repetition, warping and waving for mostly used internally.

• Journal of Broadcast Engineering
• /
• v.7 no.1
• /
• pp.2-9
• /
• 2002

Recently. VR( Virtual Reality) applications such as virtual studio and virtual character are wifely used In TV programs. and AR( Augmented Reality) applications are also belong taken an interest increasingly. This paper introduces a virtual screen system. which Is a new AR application for broadcasting. The virtual screen system is a real-time video augmentation system by tracking a chroma-patterned moving panel. We haute recently developed a virtual screen system.'K-vision'. Our system enables the user to hold and morse a simple panel on which live video, pictures of 3D graphics images can appear. All the Images seen on the panel change In the correct perspective, according to movements of the camera and the user holding the panel, in real-time. For the purpose of tracking janet. we use some computer vision techniques such as blob analysis and feature tracking. K-vision can work well with any type of camera. requiring no special add-ons. And no need for sensor attachments to the panel. no calibration procedures required. We are using K-vision in some TV programs such as election. documentary and entertainment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.7
• /
• pp.641-647
• /
• 2015

This paper proposes a new strategy for a quad-rotor to track a moving object efficiently by using image processing and an extended Kalman filter. The goal of path planning for the quad-rotor is to design an optimal path from the start point to the destination point. To lengthen the freight time of the quad-rotor, an optimal path is required to reduce the energy consumption. To track a moving object, the mark signed on the moving object has been detected by a camera mounted first on the quad-rotor. The center coordinates of the mark and its area are calculated through the blob analysis which is one type of image processing. The mark coordinates are utilized to obtain information on the motion direction and the area of the mark is utilized to recognize whether the object moves backward or forward from the camera on the quad-rotor. In addition, an extended Kalman filter has been applied to predict the direction and speed of the dynamically moving object. Through these schemes, it is aimed that the quad-rotor can track the dynamic object efficiently in terms of flight distance and time. Through the two different route freights of the quad-rotor, the performance of the proposed system has been demonstrated.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.6
• /
• pp.1-9
• /
• 2014

Recently, a study is conducting to image collection and auto detection of attribute information using mobile mapping system. The road sign attribute information detection is difficult because of various size and placement, interference of other facilities like trees. In this study, a text detection method that does not rely on a Korean character template is required to successfully detect the target text when a variety of differently sized texts are present near the target texts. To overcome this, the method of incremental right-to-left blob projection (IRBP) was suggested as a solution; the potential and improvement of the method was also assessed. To assess the performance improvement of the IRBP that was developed, the IRBP method was compared to the existing method that uses Korean templates through the 60 videos of street signs that were used. It was verified that text detection can be improved with the IRBP method.

• Journal of Satellite, Information and Communications
• /
• v.9 no.1
• /
• pp.57-64
• /
• 2014

Recently, many human-friendly communication methods have been studied for human-machine interface(HMI) without using any physical devices. One of them is the vision-based gesture recognition that this paper deals with. In this paper, we define some gestures for interaction with objects in a predefined virtual world, and propose an efficient method to recognize them. For preprocessing, we detect and track the both hands, and extract their silhouettes from the low-resolution hand images captured by a webcam. We modeled skin color by two Gaussian distributions in RGB color space and use blob-matching method to detect and track the hands. Applying the foodfill algorithm we extracted hand silhouettes and recognize the hand shapes of Thumb-Up, Palm and Cross by detecting and analyzing their modes. Then, with analyzing the context of hand movement, we recognized five predefined one-hand or both-hand gestures. Assuming that one main user shows up for accurate hand detection, the proposed gesture recognition method has been proved its efficiency and accuracy in many real-time demos.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2001.11b
• /
• pp.51-56
• /
• 2001

최근에 TV 방송에서 가상스튜디오나 가상캐릭터와 같은 가상현실(VR:Vinual Reality) 기술이 자주 사용되고 있으며, 증강현실(Ah: Augmented Reality) 기술에 대한 관심도 높아지고 있다. 본 논문에서는 증강현실 기술을 방송에 응용한 가상스크린 시스템에 대해 소개한다. 가상스크린 시스템은 움직이는 색상패턴 패널을 추적하여 실시간으로 그 위에 동영상을 합성하는 증강 영상 시스템이다. KBS 기술연구소에서는 가상스크린 시스템을 개발하고 'K-비전'이라 이름지었다. 이 시스템은 사용자가 들고 움직이는 패널에 동영상이나 그래픽 영상 등을 보여줄 수 있는데, 보여지는 모든 영상은 카메라의 움직임과 패널의 움직임에 따라 정확하게 입혀진다. 패널 추적을 위하여 블럽분석(blob analysis)이나 특징추적(feature tracking)과 같은 영상처리 기술을 이용한다. K-비전은 모든 타입의 카메라와 사용 가능하며, 특별한 부가장치가 필요하지 않다. 센서를 부착하지 않아도 되고, 캘리브레이션(calibration) 과정 또한 필요하지 않다. K-비전은 선거개표방송, 다큐멘터리, 오락 프로그램 등 생방송 프로그램에서 활용한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.6
• /
• pp.514-521
• /
• 2000

In this study, a surface generating system with a bundle of wires, which can reproduce a certain range of surface roughness of the objects without direct machining process, is implemented. The system consists of a bundle of wires, a PZT actuator, a vertical table system actuated linearly along two perpendicular axes, and an image processing system. Through the development of the operational software for all of those subsystems by a common language(Visual C＋＋) of the implemented system, the complete process except arrangement of a bundle of wires are automated. Lastly, through the experiments of generating the flat surface of some virtual object and then of measuring the reproduced surface roughness, it is confirmed that the implemented system has excellent performance.