• 한국산업정보학회논문지
• /
• 제5권2호
• /
• pp.9-15
• /
• 2000

본 논문에서는 영상 데이터 베이스의 색인화를 위해 영상의 색상과 객체가 갖는 복잡도를 이용한 내용기반 영상 검색 방법을 제시하였다. 일반적으로 색상 특징을 이용한 검색방법은 영상내 객체의 모양에 대한 공간 정보 특성을 고려하지 않으므로 검색 효율이 저하되었다. 본 논문에서는 기존의 방법인 색상특징과 제안한 체인코드에 의한 객체의 복잡도를 특징으로 하는 공간정보를 결합한 방법을 제안하였다. 실험결과 영상의 모양 특징도 고려한 제안한 방법이 내용기반 검색에서 색상 특징만을 고려한 기존의 방법보다 우수하였다.

• 한국인쇄학회:학술대회논문집
• /
• 한국인쇄학회 2000년도 춘계 학술발표회 논문집
• /
• pp.35-44
• /
• 2000

Because Image on the CRT change under different illuminants, human is difficult to see original color of object. If what is information of used illuminant on capturing object know, image can be transformed according to viewing condition using the linear matrix method. To know information of used illuminant at an image, the spectral radiance of illuminant can be estimated using the linear model of Maloney and Wandell form an image. And then image can be properly transformed it using color appearance model. In this paper, we predict the spectral radiance of illuminant using spectral power distribution of specular light and using surface spectral reflectance at maximum gray area. and then we perform visual experiments for the corresponding color reproduction according to viewing condition. In results, we ensure that the spectral radiance of illuminant at an image can be well estimated using above algorithms and that human visual system is 70% adapted to the monitor's white point and 30% to ambient light when viewing softcopy images.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.1017-1028
• /
• 2019

Pedestrian tracking is a particular object tracking problem and an important component in various vision-based applications, such as autonomous cars and surveillance systems. Following several years of development, pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surrounding environments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, which incorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames are localized using a CNN-based algorithm, and then detected pedestrians are assigned to their corresponding tracklets based on similarities between color distributions. The experimental results show that our system is able to overcome various difficulties to produce highly accurate tracking results.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.868-871
• /
• 2009

21세기를 본 논문에서는 칼라분포에 기반한 적응 외형 모델을 파티클 필터에 적용한 이동물체 추적방법을 제시하였다. 칼라 기반의 추적은 서로 다른 외형의 변화에 따라 빠르게 움직이는 이동물체를 다중 관측 모델을 결합하여 추적할 수 방법을 제시하고 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.42.1-42
• /
• 2001

This paper presents a fuzzy-based method for classification skin color object in a complex background under varying illumination. Parameters of fuzzy rule base are generated using a genetic algorithm(GA). The color model is used in the YCbCr color space. We propose a unique fuzzy system in order to accommodate varying background color and illumination condition. This fuzzy system approach to skin color classification is discussed along with an overview of YCbCr color space.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.1021-1022
• /
• 2008

This paper proposes an object segmentation method using centre of mass model and $CIELa^*b^*$ color feature. The proposed method detects moving objects using geometric and colorimetic information. The method is robust to illumination changes and it reduces noise by block-wise computation.

• 대한의용생체공학회:의공학회지
• /
• 제5권2호
• /
• pp.127-132
• /
• 1984

This paper proposes the method that evoked potentials stimulated by object colors are analyzed and examined on the phenomemon of color sensory. The method which is used to estimate the signal is time-varying. filtering (TVF).At the results of experiment which used object colors, it is shown that color sensory times of red are within the range of 0.0~0.25[sec], those of yellow are within the range of 0.25~0.55[sec], and those of blue are within the range of 0.55~O.75[sec]; they are inclined to sequence in accending order as red, yellow, and blue.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1158-1159
• /
• 2009

Tri-stimulus values of CIE-XYZ and RGB values obtained by photographic film, CCD camera or scanner depend on the spectral sensitivity of imaging devices and the spectral radiant distribution of the illumination. It is important to record and reproduce the reflectance spectra of the object for true device independent color reproduction and high accurate recording of the scene. In this paper, a method to record the reflection spectra of the object is introduced and its application to spectral endoscopes is presented.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.165-171
• /
• 2004

Robots will be able to coexist with humans and support humans effectively in near future. One of the most important aspects in the development of human-friendly robots is to cooperation between humans and robots. In this paper, we proposed a method for multi-object identification in order to achieve such human-centered system and robot localization in intelligent space. The intelligent space is the space where many intelligent devices, such as computers and sensors, are distributed. The Intelligent Space achieves the human centered services by accelerating the physical and psychological interaction between humans and intelligent devices. As an intelligent device of the Intelligent Space, a color CCD camera module, which includes processing and networking part, has been chosen. The Intelligent Space requires functions of identifying and tracking the multiple objects to realize appropriate services to users under the multi-camera environments. In order to achieve seamless tracking and location estimation many camera modules are distributed. They causes some errors about object identification among different camera modules. This paper describes appearance based object representation for the distributed vision system in Intelligent Space to achieve consistent labeling of all objects. Then, we discuss how to learn the object color appearance model and how to achieve the multi-object tracking under occlusions.

• 한국정보통신학회논문지
• /
• 제24권2호
• /
• pp.231-237
• /
• 2020

본 논문에서는 포아송 방정식을 기반으로 하는 영상 합성에 있어서 합성된 영상의 자연성을 향상시키기 위한 효율적인 동영상 혼합 블랜딩 기법을 제안한다. 영상 블랜딩 과정에서는 영상 합성의 목적에 따라 포아송 블랜딩과 알파 브랜딩 등 다양한 방법이 사용되고 있다. 본 논문에서 제안하는 혼합 블랜딩 방식은 포아송 블랜딩과 알파 블랜딩의 장점들을 조합함으로써 합성 영상에서 이음매가 없고 또한 객체의 색상 왜곡이 감소되는 특징을 갖는다. 먼저 소스 영상의 객체를 포아송 블랜딩 방법으로 합성한 후, 블랜딩 된 객체와 원래의 객체의 색차를 비교한다. 그리고 색차값이 임계값 이상인 경우, 소스 영상의 객체에 대해 알파 블랜딩을 수행하고 이를 포아송 블랜딩 된 객체와 가중치를 부여하여 합산한다. 모의실험과 분석을 통해 제안된 방법이 포아송 블랜딩과 알파 블랜딩에 비해 합성 영역의 자연성이 우수할 뿐 아니라 요구되는 계산량도 비교적 적다는 것을 볼 수 있다.