• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.976-981
• /
• 2006

수화는 청각장애인이 사용하는 시각적인 언어이다. OpenGL 기반의 가상 현실 공간에서 수화 동작을 표현하기 위해서는 수화 동작 데이터를 삽입하고 수정하는 편집 프로그램이 필요하다. 하지만, 기존의 수화 동작 편집기는 수화를 잘 이해하지 못하는 일반 사용자가 손 모양을 정확하게 편집하거나 얼굴 표정을 표현하는데 어려움이 있다. 또한, 수화 사전에 포함되는 각 수화 단어의 데이터 수가 많기 때문에 이를 효율적으로 생성하고 저장하는 프로그램이 절실히 필요하다. 본 논문에서는 사용자의 편의성을 높이기 위해 수화 동작 그래픽 편집기를 개선하는 방법을 제안한다. 이를 위해 각 손 모양에 대해 21 개의 파라마터로 구성된 데이터를 손가락 별로 분류한 후, 손가락 고유 기호로 변환하고, 손 모양 이름과 일련 번호를 부여하여 손 모양 데이터를 얻었으며, 유사한 손 모양을 그룹으로 묶은 손 모양 그룹 데이터를 구성하여 손 모양 데이터 사전을 구축하였다. 구축된 손 모양 사전을 수화 동작 편집기에 적용함으로써 사용자는 손 모양 그룹과 손 모양 이름, 일련번호를 선택하여 손의 각 관절 움직임을 쉽게 편집할 수 있으며, 이를 가상현실 공간에서 움직여 볼 수 있다. 또한, 얼굴 표정과 안색을 편집할 수 있는 기능을 추가함으로써 수화 동작 중에 얼굴 표정을 쉽게 표현할 수 있도록 하였다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.465-472
• /
• 2019

The SPR (Single Photo Resection) is widely used as a method of estimating the EOPs (Exterior Orientation parameters) at the time of taking a photograph, but it requires an initial value and has a disadvantage of being sensitive to the initial value. In this study, we introduce quaternion-based single photo resection and PnP (Perspective-n-Point) algorithm that do not require initial values and compare the results. Photos were taken using a general smartphone, and the ground control point acquisition was based on the hybrid MMS (Mobile Mapping System) point cloud data possessed by the researchers. As a result, when the collinear condition based SPR is true value, quaternion-based SPR has higher attitude angle estimation accuracy than PnP algorithm. In case of camera position estimation, both algorithms showed accuracy within 0.8m when compared with ground control points.

• The Journal of the Korea Contents Association
• /
• v.19 no.10
• /
• pp.146-156
• /
• 2019

New media art moves out of place and time constraints, sublimates the benefits of technology into art, and presents a new way of communication with the audience. This paper analyses the tendency of nonverbal communication methods by analysing examples of facial expressions and sound used in new media art from early times. As a result, it can be seen that the digital paradigm in the new media art has a nonlinear thinking, which makes a perceptual reduction of immersion and dispersion. The facial expression in new media art made it possible not only to overcome the limit of space and time of various expressions through 'visual distortions, enlargement, and virtualisation', but also to enable new ways of communication to display facial parts combined or separated in the digital environment. The sound in new media art does not stay in auditory sense, but pursues multi-sensory and synesthesia by cooperating with visual and tactile, evolves by revealing characteristics of space expansion and sensibility and interaction of audience.

• Archives of design research
• /
• v.17 no.2
• /
• pp.199-208
• /
• 2004

In cyberspace based on internet, users constitute communities and interact one another. Avatar means not only the other self but also the 'another being' that describes oneself in the cyberspace. If user's avatar shows expressive faces and behaves according to his thinking and emotion, he will have a feel of reality much more in the cyberspace. If avatar's countenances can be animated by just typing characters in avatar-based chat communication, the user is able to express his emotions more effectively. In this study, emotion-expressing vocabulary is analyzed and classified. Emotion-expressing vocabulary is essential to develop self-reactive avatar system in which avatar's countenances are automatically converted according to the words typed by users at chat. The results are as follows; First, emotion-expressing vocabulary selected out of Korean adjectives and intransitive verbs is made up of 209 words and is classified into 25 groups. Second, there are only 2 groups out of the 25 groups for positive expressions and others are for negative expressions. Therefore, negative expressions are more abundant than positive expressions in Korean vocabulary. Third, avatar's countenances are modelled according to the 25 groups by using the Quantification Method 3. The result shows that the emotion-expressing vocabulary has dose relations with avatar's countenances and is useful to communicate users' emotions. However, this study has some limits, in that Korean linguistical structure - the whole meaning of context - cannot be interpreted quantitatively.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.443-449
• /
• 2018

Acquiring indoor point cloud, using SLAM (Simultaneous Localization and Mapping) based mobile mapping system, is an element progress for development of as-build BIM (Building Information Model) for the maintenance of the building. In this research we proposed a simulation-based target geometry determination for extrinsic calibration of multiple 2D laser scanning mobile system. Four different types of calibration sites were designed: (1) circle type; (2) rectangle type; (3) double circle type; and (4) double rectangle type. Based on the measurement values obtained from each simulated calibration site geometry, least squares solution based extrinsic calibration was derived. As a result, the rectangle type geometry is most suitable for extrinsic calibration of this system. Also, correlation values between extrinsic calibration parameters were high, and calibration results were distinct according to the calibration sites.

• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.77-89
• /
• 2001

Applying perceptual hierarchy of facial feature points, a neural network model for recognizing facial expressions was designed. Input data were convolution values of 150 facial expression pictures by Gabor-filters of 5 different sizes and 8 different orientations for each of 39 mesh points defined by MPEG-4 SNHC (Synthetic/Natural Hybrid Coding). A set of multiple regression analyses was performed with the rating value of the affective states for each facial expression and the Gabor-filtered values of 39 feature points. The results show that the pleasure-displeasure dimension of affective states is mainly related to the feature points around the mouth and the eyebrows, while a arousal-sleep dimension is closely related to the feature points around eyes. For the filter sizes. the affective states were found to be mostly related to the low spatial frequency. and for the filter orientations. the oblique orientations. An optimized neural network model was designed on the basis of these results by reducing original 1560(39x5x8) input elements to 400(25x2x8) The optimized model could predict human affective rating values. up to the correlation value of 0.886 for the pleasure-displeasure, and 0.631 for the arousal-sleep. Mapping the results of the optimized model to the six basic emotional categories (happy, sad, fear, angry, surprised, disgusted) fit 74% of human responses. Results of this study imply that, using human principles of recognizing facial expressions, a system for recognizing facial expressions can be optimized even with a a relatively little amount of information.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.182-188
• /
• 2004

This paper proposes to synthesize facial images from a few parameters for the pose and the expression of their constituent components. This parameterization makes the representation, storage, and transmission of face images effective. But it is difficult to parameterize facial images because variations of face images show a complicated nonlinear manifold in high-dimensional data space. To tackle this problem, we use an LLE (Locally Linear Embedding) technique for a good representation of face images, where the relationship among face images is preserving well and the projected manifold into the reduced feature space becomes smoother and more continuous. Next, we apply a snake model to estimate face feature values in the reduced feature space that corresponds to a specific pose and/or expression parameter. Finally, a synthetic face image is obtained from an interpolation of several neighboring face images in the vicinity of the estimated feature value. Experimental results show that the proposed method shows a negligible overlapping effect and creates an accurate and consistent synthetic face images with respect to changes of pose and/or expression parameters.

• Journal of Internet Computing and Services
• /
• v.7 no.2
• /
• pp.23-35
• /
• 2006

This work presents o novel method which extract facial region und features from motion picture automatically and controls the 3D facial expression in real time. To txtract facial region and facial feature points from each color frame of motion pictures a new nonparametric skin color model is proposed rather than using parametric skin color model. Conventionally used parametric skin color models, which presents facial distribution as gaussian-type, have lack of robustness for varying lighting conditions. Thus it needs additional work to extract exact facial region from face images. To resolve the limitation of current skin color model, we exploit the Hue-Tint chrominance components and represent the skin chrominance distribution as a linear function, which can reduce error for detecting facial region. Moreover, the minimal facial feature positions detected by the proposed skin model are adjusted by using edge information of the detected facial region along with the proportions of the face. To produce the realistic facial expression, we adopt Water's linear muscle model and apply the extended version of Water's muscles to variation of the facial features of the 3D face. The experiments show that the proposed approach efficiently detects facial feature points and naturally controls the facial expression of the 3D face model.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.2
• /
• pp.185-198
• /
• 2021

Researches using UAVs are being actively conducted in the field of quickly constructing 3D spatial information in small areas. In this study, without using ground control points, a stereo camera was mounted on a UAV to collect images and quickly construct three-dimensional positions through image matching, bundle adjustment, and the determination of a scale factor. Through the experiment, when bundle adjustment was performed using stereo constraints, the root mean square error was 1.475m, and when absolute orientation was performed in consideration of a scale, it was found to be 0.029m. Through this, it was found that when using the data processing method of a UAV equipped with a stereo camera proposed in this study, high-accuracy 3D spatial information can be constructed without using ground control points.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.45-51
• /
• 2013

Today, people who live in sea of information are strongly appearing desire about quicker and more accurate information. For a long time people wanted to know information about place that I am and where I must go out, and there are various methods to have a keen desire for position information. Equipment that is using most among the method is digital camera. In this study, the accuracy of external orientation, GCP and check point depending on array of GCP and regional feature are analyzed after AT(aerial triangulation) with UltraCamX in three selected study area with specific feature. As analysis result, we could get to know that area with a mountainous district rapidly decreased accuracy of external orientation according as number of GCP decreases, and area with high buildings became low in vertical accuracy of checkpoint. This study has performed the analysis of regional factors in aerial triangulation accuracy.