• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권6호
• /
• pp.1946-1963
• /
• 2014

Most background subtraction methods focus on dynamic and complex scenes without considering robustness against noise. This paper proposes a background subtraction algorithm based on dictionary learning and sparse coding for handling low light conditions. The proposed method formulates background modeling as the linear and sparse combination of atoms in the dictionary. The background subtraction is considered as the difference between sparse representations of the current frame and the background model. Assuming that the projection of the noise over the dictionary is irregular and random guarantees the adaptability of the approach in large noisy scenes. Experimental results divided in simulated large noise and realistic low light conditions show the promising robustness of the proposed approach compared with other competing methods.

• 한국정보통신학회논문지
• /
• 제17권8호
• /
• pp.1919-1925
• /
• 2013

본 논문은 스쿨존 영역의 교통 환경 분석을 위한 배경영상 추출 알고리즘을 제안하고 있다. 제안된 알고리즘은 교통 환경에서 수시로 발생되는 밝기 변화와 정지 객체에 의한 문제를 해결하고 있다. 전자를 위해 고속 Sigma-Delta 알고리즘을 이용해 배경영상을 현 프레임으로 고속 갱신하고, 후자를 위해 직전 프레임과 오랜 시간의 평균 배경영상을 이용해 동적 영역을 검출하여 정지 객체를 배경영상에서 배제한다. 실험 결과 제안된 알고리즘은 기존 알고리즘들과 비교하여 밝기 변화에 빠르게 잘 적응하고 있고, 배경영역의 SAD (Sum of Absolute Differences)를 약40~80% 정도를 줄여주고 있다.

• 한국산학기술학회논문지
• /
• 제17권1호
• /
• pp.717-724
• /
• 2016

본 논문은 카메라로부터 획득한 컬러 비디오 영상에서 컬러 색상과 에지 그래디언트의 공분산 행렬에 기반한 영상의 변화영역을 검출하는 방법을 제안한다. 컬러 비디오 영상은 RGB 영상 대신에 밝기정보와 색상정보가 분리된 YCbCr 컬러비디오 포맷을 사용한다. CbCr-채널로부터 컬러의 색상분포를 알 수 있는 컬러 공분산 행렬을 계산하며, Y-채널로부터는 영상의 에지 그래디언트 분포를 알 수 있는 공분산 행렬을 계산한다. 컬러 공분산 행렬과 에지 그래디언트 공분산 행렬은 배경영상으로부터 적분영상을 사용하여 사각영역의 합계와 제곱 합계, 곱셈 합계를 효과적으로 계산하여 각 화소에서 빠르게 계산된다. 또한 시간에 따른 변화를 반영하기 위하여 배경영상과 입력영상의 가중평균에 의해 배경영상을 갱신한다. 현재 프레임에서의 배경영상으로부터의 변화영역은 컬러 공분산 행렬과 에지 그래디언트 공분산 행렬을 사용한 통계적 거리측정인 마하라노비스 거리를 이용하여 검출한다. 고속도로의 컬러 비디오 영상의 실험결과에서 컬러색상과 그래디언트의 변화영역을 효과적으로 검출할 수 있었다.

• 한국초전도ㆍ저온공학회논문지
• /
• 제5권3호
• /
• pp.26-29
• /
• 2003

Nowadays, one of the serious problems in KEPCO system is much higher fault current than the SCC(Short Circuit Capacity) of circuit breaker. As the superconductivity technology has developed, the HTS-FCL(High Temperature Superconductor-Fault Current Limiter) can be one of the attractive alternatives to solve the fault current problem. But the parameters of HTS-FCL should be designed optimally to have the best performance. Under this background, this paper presents the optimal design method of parameters for resistive type HTS-FCL using Monte Carlo technique.

• 한국복식학회:학술대회논문집
• /
• 한국복식학회 2003년도 International Costume Conference
• /
• pp.80-80
• /
• 2003

The velocity of change of the world in its speed and scale are very rapid. The new terms like "nano" and "genom map" and etc are continuously generated. The current main themes are focused on the society in change, the information-oriented society. To do it, it is very interesting to consider to view the diverseness of cultures in the western society. Especially this study reconsindered the historical background of the hippy's hairstyles and their influence on the current hairstyles. current hairstyles.

• 한국초전도ㆍ저온공학회논문지
• /
• 제5권2호
• /
• pp.1-7
• /
• 2003

Nowadays, one of the serious problems in KEPCO(Korea Electric Power Co-Operation) system is the more higher fault current than the SCC(Short Circuit Capacity) of circuit breaker. There are many alternatives to reduce the increased fault current such as isolations of bus ties, enhancement of SCC of circuit breaker, applications of HVDC-BTB(High Voltage Direct Current-Back to Back) and FCL(fault current limiter). But, these alternatives have some drawbacks in viewpoints of system stability and cost. As the superconductivity technology has been developed, the HTS-FCL(High Temperature Superconductor -Fault Current Limiter) can be one of the attractive alternatives to solve the fault current problem. Under this background, this paper presents the EMTDC(Electro-Magnetic Transient Direct Current) model for resistance type HTS-FCL considering the nonlinear characteristic of final resistance value when quenching phenomena occur.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.245-248
• /
• 2002

This paper has been studied a new method to update the background image of a visual surveillance system which is not stationary. In order to do this, we use another background model designed with the whole monitored images in a regular time period. By comparing each changed area computed from the two background model images and current monitored image, the areas which will be updated are decided.

• 건축역사연구
• /
• 제11권3호
• /
• pp.87-103
• /
• 2002

In contemporary architecture, there are developing aspects of variety design in material, image and form. These various architectural trends even change classical media and this concept is based on the background of current idea - digital, information-media, imagination with paradigm. So this study aims to show the present status of the expressions in the contemporary architecture of Korea under its media situation. Namely usual thoughts for design have to be changed because our life is surrounded by many kinds of powerful media signs and various mixed cultural circumstances. And like this, we know for study about the relation between media and current architecture, still more Korean present condition. In chapter one, the background, purpose and method of study are explained. In chapter two, the general concept of media is inquired in this study. In the process of searching for the formingbasic background, the characteristic of this study is understood. In chapter three, this study inquires the aspect of media expression in modern architecture. In chapter four, according to chapter three, this study shows the present status of media expressions in the contemporary architecture of Korea. In chapter five, a synthetic conclusion is presented.

• 건축역사연구
• /
• 제11권1호
• /
• pp.7-19
• /
• 2002

Contemporary architecture is developing aspects of variety design in form and material. The various architectural trends even change classical materiality. This concept has the background of current idea - digital, information, imagination with paradigm. So this study aims to show the present status of the expressions in the contemporary architecture in Korea under its dematerialized situation. And like this, we know for study about the relation between dematerialization and current architecture, still more Korean present condition. In chapter one, the background, purpose and method of study are explained. In chapter two, this study inquires the general concept of dematerial. In the process of searching for the forming basic background this study understands the characteristic. In chapter three, this study inquires the aspect of dematerialized expression in modern architect. In chapter four, with characteristics drawn in chapter three, this study show the present status of the expressions in the contemporary architecture in Korea under its dematerialized situation. In chapter five, a synthetic conclusion is presented.

• 한국멀티미디어학회논문지
• /
• 제17권4호
• /
• pp.420-432
• /
• 2014

In detection of moving objects from video sequences, an essential process for intelligent visual surveillance, the cast shadows accompanying moving objects are different from background so that they may be easily extracted as foreground object blobs, which causes errors in localization, segmentation, tracking and classification of objects. Most of the previous research results about moving cast shadow detection and removal usually utilize color information about objects and scenes. In this paper, we proposes a novel cast shadow removal method of moving objects in gray level video data for visual surveillance application. The proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the corresponding regions in the background scene. Then, the product of the outcomes of application determines moving object blob pixels from the blob pixels in the foreground mask. The minimal rectangle regions containing all blob pixles classified as moving object pixels are extracted. The proposed method is simple but turns out practically very effective for Adative Gaussian Mixture Model-based object detection of intelligent visual surveillance applications, which is verified through experiments.