• 한국의류학회지
• /
• 제22권1호
• /
• pp.149-158
• /
• 1998

The purpose of this study was to investigate the effect of age on the human thermoregulatory responses and to obtain the basic information of the Korean thermophysiological characteristics under the traditional Korean floor heating system-Ondol. The participants consisted of 10 elderly women, 4 elderly men(over 65 years), 10 young women and 5 young men(in twenties). They were exposed to temperature-controlled Ondol room(20$\pm$1$^{\circ}C$, 50$\pm$5%R.H., floor surface temperature: 30$\pm$1$^{\circ}C$) for 60 minutes and wore the same experimental clothing. The postures were performed sitting and supine on the floor. In each pose, rectal temperature, skin.temperature of 10 areas, mean skin temperature, clothing microclimate, body fat were measured. The results were as follows; 1. The rectal temperature gradually decreased and mean skin temperature gradually increased in young and old groups in both supine and sitting pose on heated Ondol floor for 60 minutes. 2. Rectal temperature was different in each pose. The rectal temperature decreased 0.1$^{\circ}C$ in both groups under the condition of sitting and decreased 0.2'c in elderly group under the condition of supine. In supine pose, elderly group was more declined than young group. Mean skin temperature increased 0.5$^{\circ}C$ in both poses, both groups.

• 한국게임학회 논문지
• /
• 제21권5호
• /
• pp.41-48
• /
• 2021

본 논문은 2개의 포즈(위치 및 회전) 추적 센서를 사용하여 마네킹 모델위에 3차원의 가상 인체를 증강하는 모바일 증강 가시화 기술에 대해서 소개한다. 증강 가시화를 위해 사용된 종래의 카메라 트래킹 기술은 카메라 영상을 사용하기 때문에 카메라의 떨림이나 빠른 이동시 카메라의 포즈 계산에 실패하는 단점이 있으나, 바이브 트래커를 이용하게 되면 이러한 단점을 극복할 수 있다. 또한 증강하고자 하는 객체인 마네킹의 위치가 바뀌거나 회전을 하게 되더라도 마네킹에 부착된 포즈 추적 센서를 사용하여 증강 가시화가 가능한 장점이 있으며 무엇보다 카메라 트래킹을 위한 부하가 없다는 장점을 가진다.

• 정보과학회 논문지
• /
• 제41권11호
• /
• pp.927-934
• /
• 2014

본 논문에서는 Kinect와 같은 RGB-D 센서를 이용하여 사람의 3차원 신체 포즈 스트림 데이터를 생성하고, 이로부터 사람의 일상 행위를 효과적으로 인식하는 방법을 제안한다. Kinect SDK나 OpenNI에서 제공하는 실시간 신체 포즈 데이터는 Kinect 중심의 3차원 데카르트 좌표계로 표현되기 때문에, 시점 변화 문제와 크기 변화 문제를 겪을 가능성이 높다. 이러한 문제를 해결하고 시점 및 크기 불변인 특징을 얻기 위해, 본 논문에서는 신체 포즈 데이터를 실험자의 골반을 원점으로 하는 구면 좌표계로 변환하고 실험자의 팔 길이를 이용한 크기 정규화를 수행한다. 또한, 본 논문에서는 확률 그래프 모델 중 하나인 은닉 조건부 랜덤 필드를 이용하여, 고수준의 일상 행위들이 내포하는 다양한 내부 구조를 효과적으로 표현한다. 두 가지 데이터 집합 KAD-70과 CAD-60을 이용한 실험을 통해, 본 논문에서 제안한 행위 인식 방법과 구현 시스템의 높은 인식 성능을 확인하였다.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.9-17
• /
• 2024

It is widely recognized that for 3D human pose estimation (HPE), dataset acquisition is expensive and the effectiveness of augmentation techniques of conventional visual recognition tasks is limited. We address these difficulties by presenting a simple but effective method that augments input images in terms of viewpoints when training a 3D human pose estimation (HPE) model. Our intuition is that meaningful variants of the input images for HPE could be obtained by viewing a human instance in the images from an arbitrary viewpoint different from that in the original images. The core idea is to synthesize new images that have self-occlusion and thus are difficult to predict at different viewpoints even with the same pose of the original example. We incorporate this idea into the training procedure of the 3D HPE model as an augmentation stage of the input samples. We show that a strategy for augmenting the synthesized example should be carefully designed in terms of the frequency of performing the augmentation and the selection of viewpoints for synthesizing the samples. To this end, we propose a new metric to measure the prediction difficulty of input images for 3D HPE in terms of the distance between corresponding keypoints on both sides of a human body. Extensive exploration of the space of augmentation probability choices and example selection according to the proposed distance metric leads to a performance gain of up to 6.2% on Human3.6M, the well-known pose estimation dataset.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.186-203
• /
• 2020

Image-based Virtual Try-On Systems are among the most potential solution for virtual fitting which tries on a target clothes into a model person image and thus have attracted considerable research efforts. In many cases, current solutions for those fails in achieving naturally looking virtual fitted image where a target clothes is transferred into the body area of a model person of any shape and pose while keeping clothes context like texture, text, logo without distortion and artifacts. In this paper, we propose a new improved image-based virtual try-on network system based on keypoints, which we name as KP-VTON. The proposed KP-VTON first detects keypoints in the target clothes and reliably predicts keypoints in the clothes of a model person image by utilizing a dense human pose estimation. Then, through TPS transformation calculated by utilizing the keypoints as control points, the warped target clothes image, which is matched into the body area for wearing the target clothes, is obtained. Finally, a new try-on module adopting Attention U-Net is applied to handle more detailed synthesis of virtual fitted image. Extensive experiments on a well-known dataset show that the proposed KP-VTON performs better the state-of-the-art virtual try-on systems.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.821-824
• /
• 2009

A method to visualize human body is proposed for various human pose. The method affords three 3D-styles of the same body: firstly, one which wares clothes specified from pattern of dresses, second, body shape, lastly bone structure of body. For this objective, standard body data are prepared which is constructed from CT images. Individual body is measured by 3D body scanner. The present status of our research is limited to offer still images, though we are engaged to accommodate various poses.

• 한국정보통신학회논문지
• /
• 제24권10호
• /
• pp.1398-1401
• /
• 2020

We present the concept of a Medical Digital Twin (MDT) that can predict and analyze medical diseases using computer simulations and introduce a dynamic virtual body capture system to create it. The MDT is a technology that creates a 3D digital virtual human body by reflecting individual medical and biometric information. The virtual human body is composed of a static virtual human body that reflects an individual's internal and external information and a dynamic virtual human body that reflects his motion. Especially we describe an early version of the dynamic virtual body capture system that enables continuous simulation of musculoskeletal diseases.

• 한국가정과학회지
• /
• 제7권3호
• /
• pp.35-48
• /
• 2004

In this study, by determining lower limb movements which cause significant changes in body surface lines, body parts with the greatest maximum expansion and contraction rate respectively were illustrated in descending order. Using unmarried female university students aged 18 - 24 as subjects, a total of 32 body surface categories (15 body surface lines and 17 body surface segment lines) were measured in one static and 9 movement poses. In particular, expansion and contraction levels and rates were measured and used in the analysis. The analysis first involved the calculation of the average measurement per body part in body surface line in static pose as well as of the average expansion and contraction levels and rates in 9 lower limb movements. Two-way MANOVA and multiple comparison analysis (Tukey) were conducted on movements and individual somatotypes regarding measurement per body part and expansion and contraction rates. Movements which cause measurements of body surface lines differed significantly in body surface line in static pose versus in movement were then identified. Among average expansion and contraction rates in such movements, maximum average expansion and contraction levels, maximum average expansion and contraction rate, and classes of expansion and contraction rate were determined per body part. The results of this study are as follows. First, 5 lower limb movements; F2, F5, F6, F7, F8, which caused significant changes in body surface lines were determined and illustrated in table 4. Second, the levels, rates, and classes of expansion and contraction rate per body part are illustrated in Tables 5 and 6. Body parts with the greatest maximum expansion rate were, in descending order: upper segment of center back leg line, upper segment of inner leg line, middle segment of center front leg line, posterior crotch length, anterior knee girth, anterior thigh girth, center back leg line, girth at crotch height, anterior midway thigh girth, hip girth, anterior crotch length, knee girth, waist girth, inner leg line, thigh girth, and crotch length. Those with the greatest maximum contraction rate were, in descending order: anterior crotch length, upper segment of center front leg line, lower segment of center back leg line, center front leg line, and posterior thigh girth. The maximum expansion rates and maximum contraction rates, which ranged from 2.05 to $35.95\%$ and from -0.20 to $-30.16\%$ respectively, were classified per body part into 4 ABCD classes. The body part with maximum expansion was the upper segment of the center back leg line at vertical body surface line, expanding by $35.95\%$ or 16.03cm in F5 flexion movement. In contrast, the body part with maximum contraction was the anterior crotch length at vertical body surface line, contracting by $-30.16\%$ or -10.54cm in F5 flexion movement. Both, however, were the body parts to expand or contract the most among all horizontal and vertical body surface lines.

• 한국산학기술학회논문지
• /
• 제11권7호
• /
• pp.2579-2585
• /
• 2010

본 논문은 단안 카메라로부터 입력된 영상에서 모션 기반의 검색을 사용한 동적인 사람 자세 추적 방법을 제안한다. 제안된 방법은 3차원 공간에서 하나의 사람 자세 후보를 생성하고, 생성된 자세 후보를 2차원 이미지 공간으로 투영하여, 투영된 사람 자세 후보와 입력 이미지와의 특징 값 유사성을 비교한다. 이 과정을 정해진 조건을 만족 할 때까지 반복하여 이미지와의 유사성과, 신체 부분간 연결성이 가장 좋은 3차원 자세를 추정한다. 제안된 방법에서는 입력 이미지에 적합한 3차원 자세를 검색할 때, 2차원 영상에서 추정된 신체 각 부분들의 모션 정보를 사용해 검색 공간을 정하고 정해진 검색 공간에서 탐색하여 사람의 자세를 추정한다. 2차원 이미지 모션은 비교적 높은 제약이 있어서 검색 공간을 의미있게 줄일 수 있다. 이 방법은 모션 추정이 검색 공간을 효율적으로 할당 해주고, 자세 추적이 여러 가지 다양한 모션에 적응할 수 있다는 장점을 가진다

• 전자공학회논문지SC
• /
• 제42권4호
• /
• pp.11-18
• /
• 2005

인간은 의사 표현을 위해 음성언어 뿐 아니라 몸짓 언어(body languages)를 많이 사용한다 이 몸짓 언어 중 대표적인 것은, 물론 손과 팔의 사용이다. 따라서 인간 팔의 운동 해석은 인간과 기계의 상호 작용(human-computer interaction)에 있어 매우 중요하다고 할 수 있다. 이러한 견지에서 본 논문에서는 다음과 같은 방법으로 컴퓨터비전을 이용한 인간팔의 3차원 자세 추정 방법을 제안하다. 먼저 팔의 운동이 대부분 회전 관절(revolute-joint)에 의해 이루어진다는 점에 착안하여, 컴퓨터 비전 시스템을 활용한 회전 관절의 3차원 운동 해석 기법을 제안한다. 이를 위해 회전 관절의 기구학적 모델링 기법(kinematic modeling techniques)과 컴퓨터 비전의 경사 투영 모델(perspective projection model)을 결합한다. 다음으로, 회전 관절의 3차원 운동해석 기법을 컴퓨터 비전을 이용한 인간 팔의 3차원 자세 추정 문제에 웅용한다. 그 기본 발상은 회전 관절의 3차원 운동 복원 알고리즘을 인간 팔의 각 관절에 순서 데로 적용하는 것이다. 본 알고리즘은 특히 유비쿼터스 컴퓨팅(ubiquitous computing)과 가상현실(virtual reality)를 위한 인간-컴퓨터 상호작용(human-computer interaction)이라는 응용을 목표로, 고수준의 정확도를 갖는 폐쇄구조 형태(closed-form)의 해를 구하는데 주력한다.