• 방송공학회논문지
• /
• 제21권6호
• /
• pp.929-943
• /
• 2016

본 논문에서는 인지 화질을 고려하기 위해 S-JND 모델 기반의 율 제어 알고리즘을 제안한다. 제안하는 율 제어 알고리즘은 인간이 가지는 시각 시스템의 특징을 반영하기 위하여 시각적 민감도와 시각적 관심도를 동시에 반영할 수 있도록 제작된 S-JND (Saliency-Just Noticeable Difference) 모델을 사용한다. 율 제어 알고리즘을 통해 비트를 분배하는 과정에서 픽쳐 내에 존재하는 각 CTU (Coding Tree Unit)가 가지는 S-JND threshold를 구한다. 각 CTU의 threshold는 적응적으로 적절한 비트를 분배하는데 사용되고, 따라서 제안하는 비트 분배 모델은 인지 화질을 향상 시킬 수 있다. 제안하는 방법의 성능 검증을 위해서 제안하는 방법을 HM 16.9에 구현하였으며, CTC (Common Test Condition) RA (Random Access), Low-delay B와 Low-delay P의 경우에 Class B와 Class C 영상들에 대해 실험 하였다. 실험 결과, 제안하는 방법은 기존 율 제어 알고리즘 대비 평균 2.3%의 비트율이 감소했고 BD-PSNR은 약 0.07dB 향상이 있었으며 비트 정확도 또한 0.06% 정도 증가하였다. DSCQS (Double Stimulus Continuous Quality Scale) 방법으로 측정한 결과, 제안하는 방법은 기존 방법 대비 0.03 MOS (Mean Opinion Score) 향상을 보였다.

• 지식경영연구
• /
• 제21권3호
• /
• pp.27-44
• /
• 2020

사용자의 정보 과부하 문제의 해결을 목표로 하는 추천 시스템은 개인의 선호를 추론하여 이에 부합하는 아이템을 필터링하여 제공한다. 추천 시스템 관련 기법 중 가장 성공적으로 알려져 있는 협업 필터링은 최근까지 다양한 성능 개선 시도가 이루어지고 있으며 여러 분야에 적용되고 있다. 본 연구에서는 이와 같은 협업 필터링의 성공에 기반하여 소비자의 구매 의사결정에 영향을 미칠 수 있는 시각 정보를 추천 시스템에 반영할 수 있는 VizNCS를 제안한다. 이를 위하여 먼저, 비정형 데이터인 시각 정보에서 특징을 추출하기 위해 합성곱 신경망을 사용하였다. 다음으로, 합성곱 신경망으로 부터 도출된 이미지 특성 정보를 추천 시스템에 반영하기 위하여 기존의 딥러닝 기반의 추천 시스템 중 다른 정보로 확장이 용이한 NCF 기법을 응용하였다. 본 연구에서 제안한 VizNCS의 성능 비교 실험 결과 기본 NCF보다 더 높은 성능을 보였으며 카테고리별 성능 비교 실험을 통해 시각 정보에 영향을 받는 카테고리와 그렇지 않은 카테고리를 발견하였다. 결론적으로 본 연구에서 제안한 VizNCS는 시각정보를 개인화된 추천에 직접 활용함에 따라 시각 정보에 영향을 받는 소비자들의 구매의사결정 행태를 반영할 수 있어 추천 시스템 성능 향상에 기여하였다. 또한, 지금까지 활용이 미미했던 이미지 데이터로 추천 시스템의 원천 데이터 영역을 확장함에 따라 다양한 원천 데이터의 활용 방안을 제시하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1121-1125
• /
• 2003

In this paper we deal with visual servoing that can control a robot arm with a camera using information of images only, without estimating 3D position and rotation of the robot arm. Here it is assumed that the robot arm is calibrated and the camera is uncalibrated. We use a pinhole camera model as the camera one. The essential notion can be show, that is, epipolar geometry, epipole, epipolar equation, and epipolar constrain. These play an important role in designing visual servoing. For easy understanding of the proposed method we first show a design in case of the calibrated camera. The design is constructed by 4 steps and the directional motion of the robot arm is fixed only to a constant direction. This means that an estimated epipole denotes the direction, to which the robot arm translates in 3D space, on the image plane.

• 한국주거학회논문집
• /
• 제10권2호
• /
• pp.247-257
• /
• 1999

This study is aimed to propose the evaluation model of forecasting visual quality of apartment buildings, which would be a useful tool to make the architectural concepts corresponding to user needs. This study was carried out through the four-step experiments as follows. The first step is to take the user's visual evaluation construct. To do this, the 22 adjective phrases were extracted, which were applicable to all apartment buildings. The second step is to analyze the user's visual preference, which is measured by the user's psychological quantity on the apartment buildings by S. D.(Semantic Differential) Method. The third step is to analyzethe five psychological-factors obtained from the Factor Analysis. The perceptual images on the 41 experimental subjects were checked up through evaluating and analyzing the factor scores of each subjects for each psychological-factor. The fourth step is to analyze, the similarity of various characters in a building, which is mirrored on the user's psychological quantity and how buildings are grouped by it.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회 논문집
• /
• pp.340-344
• /
• 2005

본 연구에서는 도로 빗물받이의 차집효율을 분석하기 위하여 측구 부분을 대상으로 수리모형을 제작하여 실험을 실시하고, 실측된 결과를 FHWA의 범용프로그램인 Visual Urban 모형의 해석결과와 비교하여 이 모형의 국내 적용성을 분석하였다. 실험에는 국내 표준규격인 40x50cm의 쇠살대 유입구(grater inlet)를 사용하였으며, 측구의 유량은 도로의 차선 및 빗물받이의 간격을 고려하여 $4\~13{\ell}/sec$를 선택하였다. 도로의 종경사는 $2,\;4,\;6\%$를 선택하고, 측구의 횡경사는 $4,\;6,\;8\%$를 선택하여, 총 36회의 실험을 실시하였다. Visual Urban 모형을 적용하여 모의한 결과와 실측값을 비교한 결과 종$\cdot$횡경사가 작은 경우에는 오차의 범위가 $6\%$정도였으며 종경사 $4\%$, 횡경사 $8\%$이상이면 비교적 일치하였다.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.59-66
• /
• 2003

To be the design method supporting aesthetic ability of human, CAAD system should essentially recognize architectural form in the same way of human. In this study, visual perception process of human was analyzed to search proper computational method performing similar step of perception of it. Through the analysis of visual perception, vision was separated to low-level vision and high-level vision. Edge detection and neural network were selected to model after low-level vision and high-level vision. The 24 images of building, tree and landscape were processed by edge detection and trained by neural network. And 24 new images were used to test trained network. The test shows that trained network gives right perception result toward each images with low error rate. This study is on the meaning of artificial intelligence in design process rather than on the design automation strategy through artificial intelligence.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권3호
• /
• pp.112-121
• /
• 2002

This paper describes a new bike system for the postural balance rehabilitation training. Virtual environment and three dimensional graphic model is designed with CAD tools such as 3D Studio Max and World Up. For the real time bike simulation, the optimized WorldToolKit graphic library is embedded with the dynamic geometry generation method, multi-thread method, and portal generation method. In this experiment, 20 normal adults were tested to investigate the influencing factors of balancing posture. We evaluated the system by measuring the parameters such as path deviation, driving velocity, COP(center for pressure), and average weight shift. Also, we investigated the usefulness of visual feedback information by weight shift. The results showed that continuous visual feedback by weight shift was more effective than no visual feedback in the postural balance control It is concluded this system might be applied to clinical use as a new postural balance training system.

• 조형예술학연구
• /
• 제5권
• /
• pp.5-34
• /
• 2003

This study aims at the observation of some analytical levels-especially those of syntactico-semantical- of the visual expressions in general. As far as the syntactical parts are concerned, there were two steps to be approached. One is to select the paradigms according to the Saussure-Hambidgean suggestions, the other to derive syntagmas from what is called the 'chaos-system', one of nonlinear dynamics. In result, paradigms could be acquired 5 sorts with its so many varieties, as visual templates(VT), supplemented by their reciprocals(R) and complements(CLE), and syntagmas five orbits from each constant c=0 to c=10. In additional, in connection with semantic parts, the study introduced a Gremasian model of discourses and narratives for the interpretation of signifiers. By this, we could cover the conjunctive relationships(+) and the disjunctive(-) of the whole structure of visual expression. Finally, we certified that the above could be fully approved in terms of recent worldly cognitive scientic psychological discoveries.

• 한국주거학회논문집
• /
• 제12권2호
• /
• pp.77-85
• /
• 2001

Along with the development of creative design ideas, how to effectively present design concepts is also an important consideration on housing plan process. This could consequently make it possible to automate presentations. In spite of such needs of presentations any significant efforts for the systematic design presentation have not been made yet. The research goals established in order to solve these problems are to develop structures of presentation and analyze the cases of it. This paper explains structures of housing plan presentations in two ways: the compositional elements of panel presentations and the relationships among the elements. The elements include a project title, a synopsis, design concepts, building layouts, floor plan1 and 2, longitudinal and latitudinal elevations, sections, projection and perspective views, and model photographs. Among various relationships among panel compositional elements this study uses relationships based on the Gestalt theory, the balance theory by Rudolf Arnheim and the optical array theory by Gibson. The relationships investigated on the basis of the visual perception theories include the relationships between compositional elements and background space, visual weight balance, horizontal and vertical balances, grouping, and visual layout patterns.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.629-632
• /
• 1999

In this paper, color coordinate system transformation based visual servo controller has been considered. Mobile robot always has a position error and an orientation error resulted from wheel slipping etc.. Even more, the errors have accumulative properties. So feedback from environments is important. In this paper, by using color model faster land mark extraction can be achieved. And the global position and the orientation of mobile robot can be known by only two land marks positions in image coordinate system. Finally, the adoption of visual information in path tracking problem makes visual servo control.