• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.401-403
• /
• 2020

본 논문에서는 박물관에서 사용되는 전시 매체 중 지형 및 건축 문화유산 모형을 활용한 Visual SLAM 기반 증강현실 시스템 활용을 제안한다. 현재 박물관에서 다양한 디지털 전시가 도입되고 관람객과의 상호작용을 중요시하고 있으나 오래전부터 도입된 지형 및 건축 문화유산 모형의 ICT 기술 활용은 미흡한 상황이다. 이에 본 연구에서 제안한 Visual SLAM 기반 증강현실 시스템은 현실 객체의 특징점을 인식하여 3D 객체를 증강하기 때문에 다양한 크기와 형태의 문화유산 모형에 활용될 수 있다. 이러한 시스템 제작을 제안함으로 박물관에 전시되어있는 기존 모형의 활용도 및 전시 효과를 높일 수 있고 다양한 인터랙션 설정으로 추가 정보 또한 제공할 수 있다.

• 한국산업융합학회 논문집
• /
• 제25권5호
• /
• pp.773-782
• /
• 2022

Estimation of cable tension through proper measurements is one of the essential tasks in evaluating the safety of cable structures. In this paper, a study on cable tension estimation using the built-in accelerometer and camera in a smartphone was conducted. For the experimental study, visual displacement measurement using a smartphone camera and acceleration measurement using a built-in accelerometer were performed in the cable-stayed bridge model. The estimated natural frequencies and transformed tensions from these measurements were compared with the theoretical values and results from the normal visual displacement method. Through comparison, it can be seen that the error between the method using the smartphone and the normal visual displacement is sufficiently small to be acceptable. It has also been shown that those errors are much smaller than the difference between the values calculated by the theoretical model. These results show that the deviation according to the type of measurement method is not large and it is rather important to use an appropriate mathematical model. In conclusion, in the case of cable tension estimation, it can be said that the visual displacement measurement and acceleration using a smartphone can be a sufficiently applicable method, just like the normal visual displacement method. It is also noteworthy that the smartphone accelerometer has a larger magnitude error and has more limitations such as high-frequency sampling instability compared to the visual displacement method, but shows almost the same performance as the visual displacement method in this cable tension estimation.

• 대한인간공학회지
• /
• 제36권3호
• /
• pp.255-265
• /
• 2017

Objective: This study aims to survey visual search performance models to assess and predict individual's visual tasks in everyday life and industrial sites. Background: Visual search is one of the most frequently performed and critical activities in everyday life and works. Visual search performance models are needed when designing or assessing the visual tasks. Method: This study was mainly based on survey of literatures related to ergonomics relevant journals and web surfing. In the survey, the keywords of visual search, visual search performance, visual search model, etc. were used. Results: On the basis of the purposes, developing methods and results of the models, this study categorized visual search performance models into six groups: probability-based models, SATO models, visual lobe-based models, computer vision models, neutral network-based models and detection time models. Major models by the categories were presented with their advantages and disadvantages. More models adopted the accuracy among two factors of accuracy and speed characterizing visual tasks as dependent variables. Conclusion: This study reviewed and summarized various visual search performance models. Application: The results would be used as a reference or tool when assessing the visual tasks.

• 대한의용생체공학회:의공학회지
• /
• 제14권1호
• /
• pp.63-72
• /
• 1993

In this paper, the effect of background grey levels on the visual perception of target image displayed on CRT monitor has been investigated. The purpose of this study is to investigate the efficacy of CRT monitor as a display medium of image Information especially in medical imaging field. Tllree sets of experiments have been performed in this study : the first was to measure the luminance response of CRT monitor and to find the best fitting equation, and the second was the psychophysical experiment measuring the threshold grey level differences between the target image and the background required for visual discrimination (or various background grey levels, and the third was to develop a visual model that is predictable of the threshold grey level difference measured in the psychophysical experiment. The result of psycophysical experiment shows that the visual perception performance is significantly degraded in the range of grey levels lower than 50, which is turned out due to she low luminance change of CRT monitor in this range while human eye has been adapted lo relatively bright ambient illumination. And it Is also shown in the simulation study using the developed visual model that the dominant factor degrading the visual performance is the reflected light from the monitor surface by ambient light in general illumination condition.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.610-615
• /
• 2005

Visual servoing is the fusion of results from many elemental areas including high-speed image processing, kinematics, dynamics, control theory, and real-time computing. It has much in common with research into active vision and structure from motion, but is quite different from the often described use of vision in hierarchical task-level robot control systems. We present a new approach to visual feedback control using image-based visual servoing with the stereo vision in this paper. In order to control the position and orientation of a robot with respect to an object, a new technique is proposed using a binocular stereo vision. The stereo vision enables us to calculate an exact image Jacobian not only at around a desired location but also at the other locations. The suggested technique can guide a robot manipulator to the desired location without giving such priori knowledge as the relative distance to the desired location or the model of an object even if the initial positioning error is large. This paper describes a model of stereo vision and how to generate feedback commands. The performance of the proposed visual servoing system is illustrated by the simulation and experimental results and compared with the case of conventional method for dual-arm robot made in Samsung Electronics Co., Ltd.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권3호
• /
• pp.91-100
• /
• 2020

기존의 영상 기반 질문-응답(VQA) 문제들과는 달리, 새로운 영상 기반 상식 추론(VCR) 문제들은 영상에 포함된 사물들 간의 관계 파악과 답변 근거 제시 등과 같이 추가적인 심층 상식 추론을 요구한다. 본 논문에서는 영상 기반 상식 추론 문제들을 위한 새로운 심층 신경망 모델인 KG_VCR을 제안한다. KG_VCR 모델은 입력 데이터(영상, 자연어 질문, 응답 리스트 등)에서 추출하는 사물들 간의 관계와 맥락 정보들을 이용할 뿐만 아니라, 외부 지식 베이스인 ConceptNet으로부터 구해내는 상식 임베딩을 함께 활용한다. 특히 제안 모델은 ConceptNet으로부터 검색해낸 연관 지식 그래프를 효과적으로 임베딩하기 위해 그래프 합성곱 신경망(GCN) 모듈을 채용한다. VCR 벤치마크 데이터 집합을 이용한 다양한 실험들을 통해, 본 논문에서는 제안 모델인 KG_VCR이 기존의 VQA 최고 모델과 R2C VCR 모델보다 더 높은 성능을 보인다는 것을 입증한다.

• 한국산학기술학회논문지
• /
• 제8권4호
• /
• pp.803-809
• /
• 2007

본 논문은 인간의 언어정보처리 과정 중 시각단어재인(visual word recognition) 과정에서 음운정보(phonological information)와 철자정보(orthography information)의 역할 및 심성어휘집의 표상(representation) 형태를 알아보기 위해 신경망(neural network)을 이용한 계산주의적 모델(computational model)을 제안한다. 제안하는 모델은 한국어 2음절을 입력 값으로 사용하는 입력층(input layer), 은닉층(hidden layer) 그리고 의미를 표현하는 출력층(output layer)으로 구성된 전방향 신경회로망(feed forward network) 구조로 설계하였다. 실험결과 계산주의적 모델은 한국어에 대한 시각 단어재인 시 보이는 언어현상 중 음운, 철자 이웃 크기효과(phonological and orthographic neighborhood effect)를 나타냈으며, 이를 통해 한국어 시각단어재인 과정에서 심성어휘집이 음운정보로 표상되어 있음을 시사하는 증거를 보였다.

• 한국실내디자인학회논문집
• /
• 제19호
• /
• pp.53-58
• /
• 1999

The goal of this paper is to understand the visual information process and the characteristics of behaviour of the architectural design process using visual protocol analysis through the actual experiment by the architect. The visual protocol analysis is developed on the basis of the theories of the visual information processing model and visual mental image, which can explain visual representation in architectural design process. A protocol study is reported in which the experimental data by architect is analyzed through the protocol analysis method. The whole design process is divided into the stage of 9 tasks which are classified into 18 visual representatiov. The results about visual cognition in cognitive science are reviewed and summarized, and these findings will help understand the architectural design nature.

• 디지털산업정보학회논문지
• /
• 제8권4호
• /
• pp.289-297
• /
• 2012

It is a recent trend to utilize a variety of visual tools(process map, mindmap, ERD) to create, when we create the design of information system or business models. Theses visual tool is standardized tools as process map or BPMN, on the other hand, there is also a non-standardized tools as mindmap. The utilization of the non-standardized tools as mindmap in startups is a increasing trend, because of the order the release of creative thinking to design new business model. Mindmaps can be divided into pen-based mindmap(of hand-written) and computer-based mindmap. This study was conducted under the premise of a different thinking pattern, when you take advantage of pen-based mindmap and computer-based mindmap. In other words, the pen-based mindmap is a tool for deductive reasoning and the computer-based mindmap is a tool would be more appropriate for inductive thinking. The purpose of this study is to investigate these relationships through experiments. In this study propose guidelines how visual tools, when designing a social media business models.

• 한국의류학회지
• /
• 제44권5호
• /
• pp.789-809
• /
• 2020

Growth in online channels has created fierce competition; consequently, retailers have to invest an increasing amount of effort into attracting consumers. In this study, eye-tracking technology examined consumers' visual behavior to gain an understanding of information searching behavior in exploring product information for fashion products. Product attribute information was classified into two image-based elements (model image information and detail image information) and two text-based elements (basic text information, detail text information), after which consumers' visual behavior for each information element was analyzed. Furthermore, whether involvement affects consumers' information search behavior was investigated. The results demonstrated that model image information attracted visual attention the quickest, while detail text information and model image information received the most visual attention. Additionally, high-involvement consumers tended to pay more attention to detailed information while low-involvement consumers tended to pay more attention to image-based and basic information. This study is expected to help broaden the understanding of consumer behavior and provide implications for establishing strategies on how to efficiently organize product information for online fashion stores.