• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.33-36
• /
• 2020

Virtual try on is getting interested from researchers these days because its application in online shopping. But single pose virtual try on is not enough, customer may want to see themselves in different pose. Multiple pose virtual try on is getting input as customer image, an in-shop cloth and a target pose, it will try to generate realistic customer wearing the in-shop cloth with the target pose. We first generate the target segmentation layout using conditional generative network (cGAN), and then the in-shop cloth are warped to fit the customer body in target pose. Finally, all the result will be combine using a Resnet-like network. We experiment and show that our method outperforms stage of the art.

• 방송공학회논문지
• /
• 제27권6호
• /
• pp.944-947
• /
• 2022

최근 코로나바이러스로 인한 마스크 착용이 급증함에 따라 마스크 착용에 대응할 수 있는 기술의 중요성이 증가하고 있다. 얼굴 자세 추정 분야는 운전자 주의, 얼굴 정면화, 시선 감지 등의 다양한 활용성에도 불구하고 마스크 착용에 따른 성능 저하 문제를 해결할 수 있는 연구가 거의 수행되지 않았다. 본 논문은 마스크 착용 유무에 따른 얼굴 자세 추정의 성능 저하에 대한 분석을 토대로, 마스크가 없는 얼굴 이미지의 크기 및 자세를 분석하여 마스크 이미지를 합성할 수 있는 데이터 증강 기법을 제안한다. 제안하는 얼굴에 특화된 증강 기법을 활용한 학습은 마스크 착용 여부와 관계없이 얼굴 자세 추정 벤치마크 데이터 세트인 BIWI에서 강인한 성능을 보이며, 특정 모델에 국한되지 않기 때문에 다양한 얼굴 자세 추정 모델에 적용될 수 있다.

• 한국의류산업학회지
• /
• 제4권6호
• /
• pp.544-549
• /
• 2002

By the movable thermal manikin developed by China Dong Hua university, the laws of clothing thermal insulation influenced by dressing poses are studied. It is found that $I_a$ on nude thermal manikin has no relation to testing pose as a whole (notable level is 5%), while the change of testing pose influences $I_a$ value on parts of body obviously. The testing result $I_{cle}$ on clothed thermal manikin has relation to testing pose. The $I_{cle}$ value of the whole body in seated pose decreases 20 percent compared with that in standing pose (notable level is 1%). In view of heat transmission theory, the reasons are pointed out based on the knowledge of heat transmission.

• 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.

• 치위생과학회지
• /
• 제21권1호
• /
• pp.1-7
• /
• 2021

Background: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is transmitted primarily through droplets, and dental practitioners are at risk of occupational exposure to SARS-CoV-2 infection owing to direct contact with the patient's mouth, aerosols from dental procedures, and saliva. Wearing a mask is believed to be the best method of protection against infection, and a systematic literature review was conducted on whether the dental masks used in dentistry are effective in preventing Coronavirus Infectious Disease-19 (COVID-19). Methods: We used PubMed, Google Scholar, DBpia, NDSL, and KISS databases for this study. Of the 917 documents narrowed down by the search terms "Coronavirus, COVID-19, and dental," 83 documents were collected and studied. Ultimately, 42 of these papers were selected for analysis after considering duplication from the flow chart of the literature selection process. Results: While dental masks are often used when treating patients with unknown COVID-19 status, the Ministry of Food and Drug Safety stated that the use of dental masks is insufficient in preventing cross-transmission of COVID-19; instead, it was recommended that N95 masks, which correspond to KF94 masks, should be worn daily. On the other hand, wearing a dental mask and following precautions such as hand hygiene may not pose a significantly higher risk of infection than wearing an N95 mask when treating COVID-19 patients. Conclusion: There is an ongoing discussion regarding the use of dental masks when treating dental patients, and many argue that different types of masks should be selected according to the degree of infection and the individual's respiratory condition. By considering the safety and efficacy of dental masks in preventing infection, improvements can be made in the management of COVID-19 and dental-related infections.

• 대한가정학회지
• /
• 제24권3호
• /
• pp.51-58
• /
• 1986

This study is to investigate the Function of sleeve for the construction of cuffs. Three measuremental items of sleeve cap high, length of sleeve and puff quantity of upper sleeve cap are compared between when the experimental man raises righthand static pose. The wearing test is done in sewing cuffs of either fixing up cuffs or not-fixing up cuffs, and in no cuffs. Three measuremental items are pulled length from sleeve end, pulled length from side waist line, and pulled dimensions from waist line. 1. The result according to the length and dimensions variation caused by a change of sleeve cap high. 2. The results according to the length and dimensions variation caused by a sort of sleeve length. 3. The results according to the length and dimension variation caused by the puff quantity of sleeve cap.

• 한국멀티미디어학회논문지
• /
• 제11권11호
• /
• pp.1575-1591
• /
• 2008

본 논문에서는 스테레오 카메라로부터 신체 중 발의 3차원 가상 모델을 실시간으로 합성할 수 있도록 동작을 검출하는 새로운 방법을 제안한다. 발에 가상 모델을 같은 위치에 합성하려면 관절의 움직임을 일정하게 추적하는 움직임 검출 과정이 필수적이다. 복잡한 움직임 속에서의 정확한 정합 이 기술이 해결해야 할 가장 중요한 문제이다. 본 논문에서는 두 가지 형태의 마커 그룹을 사용한 동적 정합을 제안한다. 바닥의 평면 정보는 발과 3차원 가상 발 모델의 관계를 조정하고 발의 자세와 위치를 측정한다. 발의 회전은 발등의 중심 골격에 따라 부착한 두 개의 마커(Marker) 그룹을 사용하여 추정했다. 이 논문에서는 제안한 시스템을 직접 구현하고, 다양한 실험을 통해 시스템에 적용된 각 알고리즘의 정확도를 측정했다.

• 한국의류산업학회지
• /
• 제15권6호
• /
• pp.1000-1009
• /
• 2013

Well-fitting riding breeches provide a comfortable ride. Horse-riding breeches should fit the lower body with patches located on the inside of hip and knees to prevent tears and slips. This study provides information about the fit of women's breeches using 3D human body scan data wearing commercially available two breeches according to posture. To get information about breeches fit, we measured the angle of waist line, the length, and the area of the breeches fit on four 20's women. This research showed the problem which was down for waist back line in the case of the horseback riding pose. The back waistline of the riding breeches should be raised compared to the front waistline; subsequently, an increased waistline angle results in less back waistline decrease. The breeches have plenty of length from back waist to crotch so the breech fit can be improved. The thigh circumference increased when riding in the front; therefore, good elasticity of the weft direction of the fabric is recommended. The length increase and the peripheral increase of the front knee significantly increased the surface area of the knee; consequently, knee patch material should be a two-way elastic fabric in all directions to enhance comfort according to riding motion.

• 한국컴퓨터그래픽스학회논문지
• /
• 제25권3호
• /
• pp.85-92
• /
• 2019

디지털 스토리텔링에 등장하는 3차원 가상 캐릭터에는 외형뿐만 아니라 자세나 동작에서도 캐릭터의 개성이 반영된 고유의 스타일이 부여된다. 그러나 사용자가 웨어러블 동작센서를 사용하여 직접 캐릭터의 신체 동작을 제어하는 경우 캐릭터 고유의 스타일이 무시될 수 있다. 본 연구에서는 가상 캐릭터를 위해 제작된 소량의 애니메이션 데이터만을 이용하는 검색 기반 캐릭터 동작 제어 기술을 사용하여 캐릭터 고유의 스타일을 유지하는 기술을 제시한다. 대량의 학습 데이터를 필요로하는 기계학습법을 피하는 대신 소량의 애니메이션 데이터로부터 사용자의 자세와 유사한 캐릭터 자세를 직접 검색하여 사용하는 기술을 제안한다. 제시된 방법을 검증하기 위해 전문가에 의해 제작된 가상현실 게임용 캐릭터 모델과 애니메이션 데이터를 사용하여 실험하였다. 평범한 사람의 모션캡쳐 데이터를 사용했을 때와의 결과를 비교하여 캐릭터 스타일이 보존됨을 증명하였다. 또한 동작센서의 개수를 달리한 실험을 통해 제시된 방법의 확장성을 증명하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1202-1205
• /
• 2005

This paper describes a method for vision-based person identification that can detect, track, and recognize person from video using multiple cues: height and dressing colors. The method does not require constrained target's pose or fully frontal face image to identify the person. First, the system, which is connected to a pan-tilt-zoom camera, detects target using motion detection and human cardboard model. The system keeps tracking the moving target while it is trying to identify whether it is a human and identify who it is among the registered persons in the database. To segment the moving target from the background scene, we employ a version of background subtraction technique and some spatial filtering. Once the target is segmented, we then align the target with the generic human cardboard model to verify whether the detected target is a human. If the target is identified as a human, the card board model is also used to segment the body parts to obtain some salient features such as head, torso, and legs. The whole body silhouette is also analyzed to obtain the target's shape information such as height and slimness. We then use these multiple cues (at present, we uses shirt color, trousers color, and body height) to recognize the target using a supervised self-organization process. We preliminary tested the system on a set of 5 subjects with multiple clothes. The recognition rate is 100% if the person is wearing the clothes that were learned before. In case a person wears new dresses the system fail to identify. This means height is not enough to classify persons. We plan to extend the work by adding more cues such as skin color, and face recognition by utilizing the zoom capability of the camera to obtain high resolution view of face; then, evaluate the system with more subjects.