• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3A
• /
• pp.272-280
• /
• 2009

Measurement of the background radio noise is very important process being used in survey of radio noise environment, calculating the threshold level for the frequency occupancy measurement and so forth. First step of background radio noise measurement is to select the sample sub-band which is mostly dominated by the background white Gaussian noise (WGN) within the target band. The second step is to carry out the main measurement of radio noise on this selected sample sub-band for the representative value of the noise power. In this paper, a method for selection of sample sub-band for the effective background radio noise measurement using SVD is proposed under the assumption that background radio noise is WGN. The performance of the proposed method is compared with that of the APD method which is widely used for the same purpose. Simulation results are shown to demonstrate the high performance of the proposed method in comparison with the existing APD method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.2
• /
• pp.359-366
• /
• 2016

The normal tissue in radiation therapy, to minimize radiation, it is most important to maximize local tumor control rates in intensive research the exact dose to the tumor sites. Therefore, the initial, therapist accuracy of detecting movement of the patient fatigue therapist has been a problem that is weighted down directly. Also, by using a web camera, a difference value between the image to be updated to the reference image is calculated, if the result exceeds the reference value, using the system for determining the motion has occurred. However, this system, it is not possible to quantitatively analyze the movement of the patient, the background is changed when moving the treatment bed in the co-therapeutic device was not able to sift the patient. In this paper, using a alpah(${\alpha}$) filter index is an attempt to solve these limitations points, quantifies the movement of the patient, by separating a background image of the patient and treatment environment, and movement of the patient during treatment It senses only, it was possible to reduce the problems due to patient movement.

• Korean Journal of Remote Sensing
• /
• v.30 no.5
• /
• pp.627-639
• /
• 2014

Accurate correction of surface effect from back scattered solar radiance is one of key issue to retrieve aerosol information from satellite measurements. In this study, two different methods are applied to retrieve surface reflectance by using single visible channel measurement from meteorological imager onboard COMS. The first one is minimum reflectance method, which composes the minimum value among previously measured reflectances at each pixel over a certain search window length. This method assumes that the darkest pixel corresponds to the aerosol-free condition, and deduces surface reflectance by correcting atmospheric scattering from the measured visible reflectance. The second method, named as the "atmospheric correction method" in this study, estimates the result by correcting aerosol and atmospheric scattering with ground-based observation of aerosol optical properties. The purpose of this study is to investigate the retrieval accuracy of the widelyused minimum reflectance method. Also, the retrieval error caused by the loading of background aerosol is mainly estimated. The comparison between surface reflectances retrieved from the two methods shows good agreement with the correlation coefficient of 0.87. However, the results from the minimum reflectance method are slightly overestimated than the values from the atmospheric correction method when surface reflectance is lower than 0.2. The average difference between the two results is 0.012 without the background aerosol correction. By considering the background aerosol effect, however, the difference is reduced to 0.010.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.583-586
• /
• 2001

본 연구는 영상에서 이진영상을 얻기위하여 최적의 임계값 결정을 영상에 나타난 물체의 형상정보를 근거로한 비트평면 패턴을 이용한 최적 임계화 방법을 제안한다. 제안된 방법은 원영상의 윤곽정보를 가장 많이 포함하는 최상위 비트평면을 사용하여 영상을 중복되지 않는 두 영역으로 구분한 뒤, 두영역의 화소 밝기값의 평균값을 각 각 구하고 두 평균값 사이에서 임계값을 설정하는 전역 임계화 알고리즘이다. 제안된 방법의 타당성을 검토하기 위하여 표준영상을 가지고 N 개의 비트평면으로 분할 한 후, 비트평면에서 전체영상을 중복되지 않는 물체의 영역과 배경영역으로 나누어 영상의 밝기를 비교한후, 두 영역의 영상 밝기의 중간 값을 추하여 임계값으로 결정한 결과 전체영상의 밝기값 분포만을 분석한 결과 보다 원영상의 윤곽을 더 충실히 얻을 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1995-1996
• /
• 2011

영상 혹은 이미지 내에서 특정 물체를 검출하기 위한 일반적인 방법으로 비올라 존스(Viola-Jones) 알고리즘을 많이 사용하고 있으나 이 방법은 배경의 픽셀이 거의 동일한 값일 때에는 매우 높은 검출률을 보이는 반면 다양한 배경과 물체가 복합적으로 이루어져 있는 이미지의 경우에는 물체 검출 시 오인식 할 가능성이 매우 높다. 이러한 단점들은 얼굴 인식 시스템을 개발함에 있어 매우 불리하게 적용될 수 있는데, 본 연구는 얼굴인식 출입통제 시스템을 개발하는 과정에서 발생하는 이러한 문제점을 보완하기 위하여 비올라 존스 알고리즘에서 이용되는 하 라이크 피춰(Harr-like feature)에 새로운 형태의 사각 특징(Rectangular feature) 및 분산 특징(Varience feature) 추가하여 복잡한 배경에서도 물체 검출 성능을 향상시킬 수 있는 방법을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.331-333
• /
• 2006

다양한 환경을 포항하고 있는 동영상에서 움직이는 객체를 추출, 인식하기 위해서는 배경 모델링이 중요하다. 기존의 대표적인 배경 모델링 방법으로 통계적 방법을 이용한 $W^4$ 방법이 있지만 칼라 영상의 다양한 환경에서 한계를 보인다. 본 논문은 큐 기반 배경 모델링을 이용한다. 이때 주요한 환경 변수가 되는 슬라이딩 윈도우의 큐 크기와 RGB 값의 그룹핑 크기, 프레임의 갱신검사 주기를 적응적으로 결정하기 위한 방법을 제안한다. 환경 변수를 결정하기 위친 객체 검출율, 객체 오검출율, 갱신율을 평가 기준으로 삼는다. 제안된 방법으로 실시간 처리에 부적합한 기존의 영상 처리 기법들을 개선하여 보다 효과적으로 객체를 인식할 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.131-133
• /
• 2016

본 논문은 연속적인 비디오 시퀀스에서 움직이는 객체의 영역을 효율적으로 분할하기 위하여 커널 기반 객체 추적과 Grab-Cut 알고리즘을 결합한 비디오 영역 분할 방법을 제안한다. 제안 방법에서는 추적 목표 객체의 초기 위치를 사각영역으로 선택하면, 사각의 외부 영역을 배경색상으로 인지하고, 배경 색상을 고려한 목표 객체의 주요 색상을 분석한다. 이를 기반으로 커널기반 객체 추적 기법을 적용하여 빠르게 객체의 영역을 추출한다. 추적한 각 객체의 영역에서 중앙 객체 영역과 배경 영역의 색 정보를 초기값으로 하여 Grab-Cut 알고리즘을 수행하고 사각형 형태가 아닌 객체의 실루엣 최적화된 영역으로 분할한다. 제안 방법을 스포츠 방송, 광고, 영화 등의 특수 효과로 활용되고 있는 stromotion 영상 생성에 적용하기 위하여 프레임별 추출된 객체의 영상을 새로운 프레임 영상에 합성하는 작업을 수행하여, 초당 10 프레임의 처리 속도에서 원하는 스트로모션 효과 영상을 생성하였다.

• Korean Journal of Cognitive Science
• /
• v.15 no.4
• /
• pp.21-30
• /
• 2004

Additive color mixture of two different background colors appeared in the afterimage of a gray circle centered on an isoluminant bichromatic background (red/green, blue/green, or blue/yellow background). The chromatic mixture still appeared in the afterimage of a gray circle on a bichromatic background at different luminance levels, and also appeared in a large test field. The saturation of the induced color was observed to increase as the overall luminance of adaptation background stimulus increase of the size of test field decreases. It was found that the chromatic mixture does not appear with a chromatic or achromatic boundary inserted on the center of the test field. The boundary seems to prevent the induced color on each side of test field from spreading to the other side so that the induced color does not appear mixed but divided into two different colors. Without a boundary on the test stimulus, the color information induced in the afterimage seems to be too weak to create a subjective boundary between the two colors and consequently propagate inward appearing mixed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.9
• /
• pp.1972-1978
• /
• 2010

AAM(Active Appearance Model) is one of the most effective ways to detect deformable 2D objects and is a kind of mathematical optimization methods. The cost function is a convex function because it is a least-square function, but the search space is not convex space so it is not guaranteed that a local minimum is the optimal solution. That is, if the initial value does not depart from around the global minimum, it converges to a local minimum, so it is difficult to detect face contour correctly. In this study, an AAM-based face tracking algorithm is proposed, which is robust to various lighting conditions and backgrounds. Eye detection is performed using SIFT and Genetic algorithm, the information of eye are used for AAM's initial matching information. Through experiments, it is verified that the proposed AAM-based face tracking method is more robust with respect to pose and background of face than the conventional basic AAM-based face tracking method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.6
• /
• pp.1269-1274
• /
• 2014

In computer vision research, binarization procedure is one of the most frequently used tools to discriminate target objects from background in grey level binary image. Fuzzy binarization is a reliable technique in environment with high uncertainty such as medical image analysis by setting the threshold as the average of minimum and maximum brightness with triangle type fuzzy membership function. However, this technique is also known as contrast sensitive method thus its discrimination power is not so great when the image has low contrast difference between objects and backgrounds and suffer from information loss as a result. Thus, in this paper, we propose a fuzzy binarization using ART2 algorithm to handle such low contrast image analysis. Proposed ART2 algorithm is applied to determine the medium point of membership function in the fuzzy binarization paradigm. The proposed methods shows low information loss rate in our experiment.