• 한국전자통신학회논문지
• /
• 제19권3호
• /
• pp.633-640
• /
• 2024

이 연구는 헬스케어 분야에서 활용 가능한 AI 기반의 3D 체형 모델링 기술을 개발하고, 이를 통해 사용자의 체형 변화와 건강 상태를 모니터링 할 수 있는 시스템을 제안한다. 사이즈코리아의 데이터를 활용하여 2D 이미지로부터 3D 체형 이미지를 생성하는 모델을 개발하고, 다양한 모델을 비교하여 가장 성능이 우수한 모델을 선정하였다. 최종적으로, 개발된 기술을 통해 개인 맞춤형 건강 관리, 운동 추천, 식단 제안 등의 시스템 프로세스를 제안함으로써 질병 예방 및 건강 증진에 기여하고자 하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2007년도 추계학술대회 논문집
• /
• pp.303-304
• /
• 2007

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.78-79
• /
• 2022

본 논문에서는 RGB-D 카메라를 이용하여 획득한 다수 사용자의 정규화된 스켈레톤의 신체 비율 분석을 통해 각 사용자의 구분 및 위치를 추적하는 기법을 제안한다. 이를 위해 3D 포인트 클라우드로부터 각 사용자의 3D 스켈레톤을 추출한 뒤 신체 비율 정보를 저장한다. 이후 저장된 신체 비율 정보를 전체 프레임에서 출력된 신체 비율 데이터와 유사도를 비교하여 전체 영상에서의 사용자 구분 및 위치추적 알고리즘을 제안한다.

• 복식문화연구
• /
• 제23권2호
• /
• pp.242-253
• /
• 2015

The aim of this study was to use a 3D human body scanner to analyze the cross section of different body parts when a girdle is worn. Two types of girdles were selected as experimental garments: a standard type girdle (Garment A) and a high-waist type girdle (Garment B). Their sizes were 88 (S) and 94 (M). Ten female subjects in their twenties who wear girdles sizes 88 (S) and 94 (M) participated the experiment. Their bodies were scanned three times with the 3D human body scanner, before and after wearing experimental girdles. The data were collected by overlapping the cross sections of the 3D scanned body shape data. The space length was measured from the overlapped cross sections. The results show that human body silhouette are changed after wearing the compression type garments and the amount and place of the body change is different by style of garments. First, the waist girth shape became rounder. Second, there was a definite difference in space amount at abdomen girth between two types of girdle. The abdomen area was pushed toward the front after wearing the standard type girdle (A). The high-waist type girdle (B) pushed abdomen area toward the back. Third, there was clear difference at the hip area after wearing two types of girdle. The hip area pushed toward the front with the standard type girdle (A) and pushed toward the back with the high-waist type girdle (B).

• 복식
• /
• 제67권3호
• /
• pp.81-98
• /
• 2017

The purpose of this study is to provide basic information for the development of pants patterns with a high level of fit and comfort through calculating surface variations of lower body parts by movement, grouping them into factors, and analyzing how their surface variations link to one another. The achieved results will help determine essential elements for constructing pants patterns, such as key measurements of lower body parts, the amount of ease values and selection of fabrics, which should be taken into consideration for allowing better movement in clothing. The study required lower body 3D scanning of women for analysis, and 13 women between the ages of 20-24 participated in the scanning, which was done by using Artec Eva 3D scanner. Their scanned data were digitalized and converted to measure the values of their lower body surface length and girth in pre-determined positions such as walking, stair climbing and sitting on a chair. These measurements have been statistically analyzed through SPSS 21.0 to obtain the average amounts and rates of extension for each of the measurement item. Some of the highlighted study results are as follows: The surface length and girth measurements were grouped into 4 factors based on their average extension rates. The results from correlation analysis between measurement items within each factor demonstrated that common items linked to all the changes in the values of other items in the three movements. But in most cases, items were not always correlated with each other for different movements. The results also showed that there were correlations between girth measurements, length measurements, and girth and length measurements. Therefore, key measurements for daily pants should be determined within reasonable estimations between relevant measurement items, while the measurements for work pants, which often withstand certain postures or repetitive movements, may require measurement items that are appro priate for, and closely related to, certain movements or tasks.

• Fibers and Polymers
• /
• 제7권2호
• /
• pp.195-202
• /
• 2006

Tight-fitting clothing pattern reflecting the accurate information of the 3D body shape has been one of the challenges for garment industry, however, fitting problems still exist. The objectives of the paper is to develop a 2D pattern which fits tightly to the 3D human scan data for sports suits that need comfort and function for maximum performance. In this study, the user graphic interface application software for the semi-automatic garment pattern generation has been implemented using the triangle simplification scheme together with 2D projections of free-falling of 3D surface polygons keeping the original 3D surface area preservation. A typical application of the developed pattern to the functional body suits is presented and verification of the proposed method is also provided.

• 한국의류학회지
• /
• 제29권7호
• /
• pp.1008-1017
• /
• 2005

When we develop 2D pattern from replica of human body with small pieces, it is inevitable to have some replica pieces overlapped or departed. In this study, the optimized method of 2D pattern development from the 3D replica pieces was investigated using dress-form. Among six arrangement methods, anchoring two vertexes of a replica to neighboring vertexes of a next replica induces the optimized 2D pattern by evenly distributing stress across the 3D replica pieces. Anchoring neighboring vertexes resulted in automatic widening k overlapping (W & O) the interspaces among replicas of dress-form, thereby stress was distributed more evenly than any other method. W&O arrangement method was verified to be the best by examining the 3D space distribution images between body surface and twelve experimental garments.

• 한국의류학회지
• /
• 제32권5호
• /
• pp.846-858
• /
• 2008

This study was designed to propose a method to draft bodice block pattern from 3D body scan data. Subjects were ten elderly women in their 60's, who wear basic size(B: 94cm, W: 82cm) garment. Scanning was done using 3D whole body scanner(WB4, Cyberware). Measurements for 3D data and cross section were attained using Auto CAD, by which a upper bodice pattern for elderly women was drawn on the basis of short measured method. The results are as following: As for most items, no significant differences were shown between measurements from Martin's anthropometry and those from 3D scan data, suggesting measurement from 3D scan data could be used to draft a pattern. The drafting equations acquired were as follows; width of pattern=B/2+5.5, width of waist=W/2+3.5cm, dart amount=8cm. Dart distributions were 23%(B.P.) : 20%(front armpit) : 17%(side seam) : 18%(back armpit) : 15%(back protruded point) : 7% (center back line). Through wearing test using 5-point Likert scale, resultant pattern was evaluated as appropriate for elderly women's pattern to get over 4 point. As a result, it might be said that 3D scanning application is effective for elderly women in that it doesn't take time so much as Martin's anthropometry and that their body shape vary compared with those of young women.

• 문화기술의 융합
• /
• 제6권4호
• /
• pp.803-806
• /
• 2020

3차원 영상을 활용한 체형 측정 방식은 최근 3차원 측정 카메라와 알고리즘의 발전으로 인하여 보편적으로 활용되고 있다. 기존의 3차원 영상 장비들은 고가의 장비들로 보편화에 한계가 있었다. 최근 저렴한 3D 카메라와의 보급과 다양한 측정 방식의 발달로 인하여 여러 가능성을 보이고 있다. 이는 정확한 데이터 수집을 필요로 하는 의료기기 시장에 많은 영향을 미칠 수 있을 것으로 보인다. 인공지능을 활용한 다양한 의료기기 제품들이 등장하고 있는데 정확한 인공지능 알고리즘을 개발하기 위해서는 정확한 데이터 수집이 가장 중요하다. 3차원 영상을 활용한 인공지능 알고리즘 개발에 3D 카메라를 활용한 수집 장비들은 주요한 요소로 작용할 것으로 보여진다.

• 한국의류학회지
• /
• 제33권7호
• /
• pp.1109-1120
• /
• 2009

This study develops a fitted torso type basic pattern for men by utilizing 3D body scan data. Recent fashion trends are reflected in the development of the pattern. The subjects were 15 men in their 20's, who wear size 95 (M size). Body scan data was obtained through a 3D whole body scanner (WB4, Cyberware, USA), and a body surface development figure for developing male fitted torso type basic pattern was attained through the use of Rapid Form 2006 as well as Auto CAD 2006 programs. The results are as follows: A body surface development figure through body surface segment method showed high exactitude in an error range of 100$\pm$1%. In addition, it occurred in an error range of 100:1:3% because of the hard scanning conditions in the incline of the shoulder and armpit areas. However, the body surface development figure as well as the direct measurement results can be used as basic data for the given patternmaking since the error range falls into 100$\pm$3%. Dart amounts obtained from the average cross section were center back 2.2cm (24.3%), back armpit point 3.8cm (41.8%), front armpit point 3.0cm (33.9%). As shown the jacket pattern, the biggest dart amount was portioned out at the back armpit point. The drafting equations for the development pattern acquired are as follows; Full width=C/2+5cm, back length=height/4-1cm, armhole depth=(C/10+12cm)+3cm, back width=2C/10+2cm, front width=2C/10. The development pattern was a fitted torso basic pattern that was composed of 3 pieces, so it would be very useful in developing shirt or jacket patterns. According to the results of the evaluation of the developed pattern appearance, it obtained higher scores of over 3.5 points in almost items, meaning that the developed pattern is appropriate for a male fitted torso type basic pattern. It suggests a possibility of patternmaking from a body surface development figure in 2-D to prototype.