• 복식
• /
• 제56권7호
• /
• pp.42-53
• /
• 2006

The purpose of this research is to study doll's symbolism representing our social culture and the characteristics of clothing design. The ball joint doll was selected, that are pretty much resembled to human body in terms of facial expression, body proportion, joint movement, etc. Results of research are summarized as follows: the ball joint doll is indicated a doll whose joints are free to move with a round shaped joint, which originated by Yochilya simon, who adopted German Hans Bellmer's method.'rho ball joint doll, first, there appeared state of human isolation due to the material civilization and industrial revolution, and trend of adhering to one's own world made human possess dolls. Second, according to the doll play became a representing play culture among Kidult culture, dolls, that are resembled with human being, were recognized as personalized objects. Third, along of expanding digital culture that makes easy to exchange information via Internet, so, ball joint doll market is growing fast, for which various levels of mania are being formed. Take a look at the doll fashion in modern society. In accordance to form of Look, it is largely categorized Young Casual look, Office look, Ethnic look and Military look. When take a look at design specialty, young casual look was presented as a comfortable silhouette and also made of elastic materials and expressed vivid bright tones. Office look image was expressed as a suit of jacket with skirt, and cotton wool polyester materials and acro-matic colors. Ethnic look was represented by Japanese traditional dress and Chinese traditional clothing. The Military look was generally emphasized army uniforms of straight silhouette and shoulder straps.

• 한국의류산업학회지
• /
• 제14권6호
• /
• pp.968-976
• /
• 2012

This study presents a new method called the SPMP (Semi-automatic profile measuring program) to efficiently measure body shape in elderly women. SPMP can automatically measure the angle of axis (19 items), surface (17 items), lengths (14 items), heights (16 items), widths (13 items), and depth (6 items). In total these 85 items are automatically measured very quickly, accurately, and easily after manually marking an initial 36 points. The utility of SPMP was evaluated using several tests. When SPMP measuring results were compared with manual methods (using a ruler and protractor) in thirteen elderly women using a paired t-test, there was no significant difference found between them. Furthermore, when measurements from SPMP were compared with actual measurement results in selected items from seven elderly women's measurements, smaller mean differences were found than those defined by ISO 20685, with the exception of the abdominal area which moves easily with breathing. Seven independent measurements of a single elderly woman were made by seven students using SPMP, and the values of coefficient of variation were less than 5% for all but 8 items. Finally, this study analyzed the correlation of all 85 item measurements, and found that the angle from the upper chest to the neck towards the front in the axis curved forward as much as the axis angle from the thigh to the waist (r=-0.876, $^{**}p$ < 0.01) bent backwards in elderly women. This detailed analysis helps to understand age-related changes in body posture, and will be useful in future studies.

• 복식
• /
• 제54권4호
• /
• pp.63-74
• /
• 2004

This study shows that clothes to be just the same as the real thing can be Produced through the third dimension computer graphics, and then presents that not only the area of fashion design can be expanded in the virtual reality field by doing the simulation of the fashion show, but also the information can be made the real time public ownership and the communication can be fulfilled smoothly. In this study, analyzing the third dimension computer graphic programs to be used much at present, Alias Wavefront Company's Maya software which was the most effective in the clothes simulation and the clothes CAD SGS OptiTex 8.7 which went well substitutive for it were used of them. The conclusions of this study that got through the work manufacture are as follows： The first, if the file manufacturing in the clothes CAD by using the computer was stored, the pattern used 3D simulation was available because it could be summoned in 3D software. The second, if the data of DXF form in Maya program was summoned, they could not be applied by Maya Cloth supported in Nurbs only because they were recognized as the DXF＿layer. So the curve along the outer lines of the pattern was drawn and Maya Cloth was applied to be possible to get the natural silhouette of clothes. The third, when the clothes were manufactured by 3D, if the draping character was applied according to the textile special quality, not only the control of textile's thickness, weight, quality feeling, and silhouette was available, but also the clothes were available to graft the special textile materials. The fourth, the natural motion of model was produced by capturing the actual model's walking action In order to produce the fashion show motion and also the dynamic fashion show was available by the angle of camera, the establishment of lighting, and etc. in the final rendering. The clothes manufactured by 3D are available to change the design by changing the materials, or by adding the details, or by utilizing the special materials on clothes. Therefore, the trial and error following at the clothes manufacture can be reduced. But the elevation of the rendering speed, the price down, the strengthening of personal security, and etc. are required.

• 한국콘텐츠학회논문지
• /
• 제6권1호
• /
• pp.31-40
• /
• 2006

본 논문에서는 걸음걸이 실루엣 영상을 이용한 걸음걸이 인식 방법을 제안한다. 걸음걸이 특징 정보는 걸음걸이의 방향 변화에 많은 영향을 받는다. 따라서 본 논문에서는 평면 호모그래피를 이용하여 실루엣을 고유시점으로 재구성함으로써 방향변화의 영향을 줄이고자 한다. 이때, 평면 호모그래피는 카메라 보정과 같은 복잡한 계산과정 없이 걸음걸이 시퀀스 정보만을 이용하여 추정된다. 동일인의 걸음걸이 실루엣이라 하더라도 배경 제거시의 에러 등으로 인해 공통적인 특성에서 벗어나는 영역이 존재한다. 각 개인의 동일 특성에서 벗어나는 특성을 분석하기 위하여, 본 논문에서는 주성분 분석 기법을 사용한다. 그러나 일반적인 패턴 분류에 적용되는 주성분 분석 기법과는 달리 본 논문에서는 공통적인 특성에서 벗어나는 정도의 판단과 그에 따르는 가중치 부여 기준으로써 사용한다. 실험결과 제안하는 걸음걸이 인식 기법은 걸음걸이 방향 변화에 강인하고, 분별력을 향상시킬 수 있음을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제11권12호
• /
• pp.1658-1667
• /
• 2008

Reconstruction of 3D objects from a single view image is generally an ill-posed problem because of the projection distortion. A monocular vision based 3D object localization method is proposed in this paper, which approximates an object on the ground to a simple bounding solid and works automatically without any prior information about the object. A spherical or cylindrical object determined based on a circularity measure is approximated to a bounding cylinder, while the other general free-shaped objects to a bounding box or a bounding cylinder appropriately. For a general object, its silhouette on the ground is first computed by back-projecting its projected image in image plane onto the ground plane and then a base rectangle on the ground is determined by using the intuition that touched parts of the object on the ground should appear at lower part of the silhouette. The base rectangle is adjusted and extended until a derived bounding box from it can enclose the general object sufficiently. Height of the bounding box is also determined enough to enclose the general object. When the general object looks like a round-shaped object, a bounding cylinder that encloses the bounding box minimally is selected instead of the bounding box. A bounding solid can be utilized to localize a 3D object on the ground and to roughly estimate its volume. Usefulness of our approach is presented with experimental results on real image objects and limitations of our approach are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1856-1869
• /
• 2015

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2767-2780
• /
• 2016

Video-based human-activity recognition has become increasingly popular due to the prominent corresponding applications in a variety of fields such as computer vision, image processing, smart-home healthcare, and human-computer interactions. The essential goals of a video-based activity-recognition system include the provision of behavior-based information to enable functionality that proactively assists a person with his/her tasks. The target of this work is the development of a novel approach for human-activity recognition, whereby human-body-joint features that are extracted from depth videos are used. From silhouette images taken at every depth, the direction and magnitude features are first obtained from each connected body-joint pair so that they can be augmented later with motion direction, as well as with the magnitude features of each joint in the next frame. A generalized discriminant analysis (GDA) is applied to make the spatiotemporal features more robust, followed by the feeding of the time-sequence features into a Hidden Markov Model (HMM) for the training of each activity. Lastly, all of the trained-activity HMMs are used for depth-video activity recognition.

• 한국의류학회지
• /
• 제30권6호
• /
• pp.992-1000
• /
• 2006

The main purpose of this research is to develop the methodology of objective evaluation of clothing appearance by eye movement analysis. The visual clothing items used in this study were skirt, one-piece, pants and shirt with the style variation of silhouette and details. By observing eye movement during visual evaluation of clothing, we can achieve the basic fixation data of eye movement. Moreover, we developed the Matlab program to extract the fixation coordinate and number of eye fixation on each part of the clothing item. As results, there were differences in the duration of fixation time for each item and the fixation time was not different by styles within a clothing item. However, we could find differences in the fixation time within a style, in other words, we could select the important parts of the clothing by observing the fixation time in a certain clothing item. It is also noted that time required in visual information processing differs depending on the item, and there was a region which contain more information independent with styles in the same item. By developing the objective method of visual evaluation that correspond to human's visual information processing, the results are expected to be applied in the retrieval program in internet shopping mall or in the development of contents for advertisement of clothing.

• 한국정보통신학회논문지
• /
• 제14권2호
• /
• pp.469-478
• /
• 2010

본 논문은 3차원 발 자세를 추정하기 위한 효과적 형상 기술자를 제안하였다. 처리 시간을 단축시키기 위하여 특수 제작된 3차원 발 모형을 2차원 투영하여 발 형상 데이터베이스를 구축하고, 3차원 자세 요약정보를 메타 정보로 추가한 2.5차원 영상 데이터베이스를 구성하였다. 그리고 특징 공간 크기가 작고 다른 형상 기술자에 비하여 자세 추정 성능이 뛰어난 수정된 Centroid Contour Distance를 제안하였다. 제안된 기술자의 성능을 분석하기 위하여, 검색 정확도와 시공간 복잡도를 계산하고 기존의 방식들과 비교하였다. 실험 결과를 통하여 제안된 기술자는 특징 추출 시간과 자세 추정 정확도면에서 기존의 방식들보다 효과적인 것으로 나타났다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.403-406
• /
• 2005

The purpose of this paper is to propose ways to remove false color noise (FCN) generated during de-mosaicing on RGB Bayer pattern images. In case of images sensors adapting Bayer pattern color filters array (CFA), de-mosaicing is conducted to recover the RGB color data in single pixels. Here, FCN phenomena would occur where there is clearer silhouette or contrast of colors. The FCN phenomena found during de-mosaicking process appears locally in the edges inside the image and the proposed method of eliminating this is to convert RGB color space to YCbCr space to conduct smoothing process. Moreover, for edges where different colors come together, censoring based smoothing technique is proposed as a way to minimize color blurring effect.