• 디지털융복합연구
• /
• 제14권1호
• /
• pp.189-194
• /
• 2016

최근 카메라, 캠코더 및 CCTV 등의 사용이 활발해지면서 영상 처리 기술의 수요가 급증하고 있다. 특히 키넥트 센서와 같은 깊이(Depth) 카메라를 사용한 3D 영상 기술에 대한 연구개발이 더욱더 활성화되고 있다. 키넥트 센서는 RGB, 골격(Skeleton) 및 깊이(Depth) 영상을 통해 인체의 3D 골격 구조를 실시간 프레임 단위로 획득할 수 있는 고성능 카메라이다. 본 논문에서는 키넥트 센서를 사용하여 인체의 3D 골격 구조를 모션 캡처하고 범용으로 사용되고 있는 모션 파일 포맷($^*.trc$ 및 $^*.bvh$)으로 선택하여 저장할 수 있는 시스템을 개발한다. 또한 본 시스템은 광학식 모션 캡처 파일 포맷($^*.trc$)을 자기식 모션 캡처 파일 포맷($^*.bvh$)으로 변환할 수 있도록 하는 기능을 가진다. 마지막으로 본 논문에서는 키넥트 센서를 사용하여 캡처한 모션 데이터가 제대로 캡처되어졌는지 모션 캡처 데이터 뷰어를 통하여 확인한다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.491-500
• /
• 2021

본 연구에서는 MS Kinect v2 RGBD 카메라 기반의 Human-Skeleton Keypoints와 2-Stacked Bi-LSTM 모델을 이용하여 낙상 행위를 탐지하는 방법을 제안한다. 기존의 연구는 RGB 영상에서 OpenPose 등의 딥러닝 모델을 이용하여 골격 정보를 추출한 후 LSTM, GRU 등의 순환신경망 모델을 이용해 인식을 수행하였다. 제안한 방법은 카메라로부터 골격정보를 바로 전달 받아 가속도 및 거리의 2개의 시계열 특징을 추출한 후 2-Stacked Bi-LSTM 모델을 이용하여 낙상 행위를 인식하였다. 어깨, 척추, 골반 등 주요 골격을 대상으로 중심관절을 구하고 이 중심관절의 움직임 가속도와 바닥과의 거리를 특징으로 제안하였다. 추출된 특징은 Stacked LSTM, Bi-LSTM 등의 모델과 성능비교를 수행하였고 GRU, LSTM 등의 기존연구에 비해 향상된 검출 성능을 실험을 통해 증명하였다.

• 한국지반공학회논문집
• /
• 제24권11호
• /
• pp.79-89
• /
• 2008

본 연구에서는 낙동강 유역에 분포하는 모래와 실트를 대상으로 실트 함유량에 따른 모래의 비배수 반복전단강도 특성을 파악하기 위하여 이방압밀비($K_c$=1.0, 1.5, 2.0)를 달리하여 일련의 비배수 반복삼축시험을 실시하였다. 시험결과 모든 $K_c$에서 실트 함유량이 증가함에 따라 반복전단응력비(CSR)가 감소하였으며, $K_c$가 증가할수록 실트 함유량 증가에 의한 CSR의 감소가 더 크게 나타났다. 전단시 발생되는 과잉간극수압은 $K_c$에 관계없이 실트 함유량 증가에 따라 초기 과잉간극수압이 크게 발생되어 CSR의 감소에 영향을 미쳤으며, 또한 압밀 후 시료의 skeleton 간극비를 산정하여 분석한 결과 실트 함유량 증가에 비례하여 전반적으로 skeleton 간극비가 크게 증가하여 초기 과잉간극수압의 증가와 더블어 CSR 감소의 주요원인으로 파악되었다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.267-277
• /
• 2024

This paper explores the use of machine learning in game production to create goal-oriented, realistic animations for skeleton monsters. The purpose of this research is to enhance realism by implementing intelligent movements in monsters within game development. To achieve this, we designed and implemented a learning model for skeleton monsters using reinforcement learning algorithms. During the machine learning process, various reward conditions were established, including the monster's speed, direction, leg movements, and goal contact. The use of configurable joints introduced physical constraints. The experimental method validated performance through seven statistical graphs generated using machine learning methods. The results demonstrated that the developed model allows skeleton monsters to move to their target points efficiently and with natural animation. This paper has implemented a method for creating game monster animations using machine learning, which can be applied in various gaming environments in the future. The year 2024 is expected to bring expanded innovation in the gaming industry. Currently, advancements in technology such as virtual reality, AI, and cloud computing are redefining the sector, providing new experiences and various opportunities. Innovative content optimized for this period is needed to offer new gaming experiences. A high level of interaction and realism, along with the immersion and fun it induces, must be established as the foundation for the environment in which these can be implemented. Recent advancements in AI technology are significantly impacting the gaming industry. By applying many elements necessary for game development, AI can efficiently optimize the game production environment. Through this research, We demonstrate that the application of machine learning to Unity and game engines in game development can contribute to creating more dynamic and realistic game environments. To ensure that VR gaming does not end as a mere craze, we propose new methods in this study to enhance realism and immersion, thereby increasing enjoyment for continuous user engagement.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2006년도 추계학술발표대회 논문집
• /
• pp.227-230
• /
• 2006

Recently, housing market & circumstances considering society change have changed dramatically. Such changes have affected system exchange of apartment housing greatly and promoted new housing system breaking with bearing wall structure. From this point of view, this study examined ultimate systematic items for promoting better housing system after extracting existing building regulation and housing regulation. This study only analyzed system change considering skeleton(support) with housing regulation, building regulation and fire service law. Consequently, apartment housing will intend residential open building breaking with existing bearing wall structure by promoting change of skeleton & infill system afterward.

• 한국세라믹학회지
• /
• 제53권1호
• /
• pp.50-55
• /
• 2016

In order to make a highly ordered three-dimensionally macro-porous structure of zirconia ceramics, porogen precursors PMMA beads were prepared by emulsion polymerization using acrylic monomer. The monodisperse PMMA latex beads were closely packed by centrifugation as a porogen template for the infiltration of zirconium acetate solution. The mixed compound of PMMA and zirconium acetate was dried. According to the firing schedule, dry compacts of PMMA and zirconium acetate were calcined at $475^{\circ}C$ to obtain micro-, macro-, and meso- structures of polycrystalline zirconia with monodispersed porosity. Inorganic frameworks composed of $ZrO_2$ were formed and showed a three Dimensionally Ordered Microstructure [3DOM] of $ZrO_2$ ceramics. The obtained $ZrO_2$ skeleton was calcined at $710^{\circ}C$. The 3DOM $ZrO_2$ skeleton showed color tuning in solutions such as deionized [DI] $H_2O$ and/or methanol. The monodispersed crystalline micro-structure with micro/meso porosity was observed by FE-SEM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3924-3940
• /
• 2020

Dynamic hand gesture recognition(d-HGR) plays an important role in human-computer interaction(HCI) system. With the growth of hand-pose estimation as well as 3D depth sensors, depth, and the hand-skeleton dataset is proposed to bring much research in depth and 3D hand skeleton approaches. However, it is still a challenging problem due to the low resolution, higher complexity, and self-occlusion. In this paper, we propose a hand-shape feature extraction(HSFE) network to produce robust hand-shapes. We build a hand-shape model, and hand-skeleton based on LSTM to exploit the temporal information from hand-shape and motion changes. Fusion between two models brings the best accuracy in dynamic hand gesture (DHG) dataset.

• 대한수의학회지
• /
• 제41권3호
• /
• pp.293-298
• /
• 2001

This study was conducted to observe the bone and cartilage formation of mouse fetuses. Mouse litters were sacrificed at pregnant 14th and 18th day and examined for gross skeletal formation using cartilage and bone staining. We identified well developed cartilage formation at the 14th pregnant day in mouse fetus. However mouse fetus at the 14th pregnant day did not show any part of bone formation. At 18th pregnant day, mouse fetus showed well developed body shape and bone and cartilage formation. This results will provide basic information for the evaluation of mouse malfromation and impairment of skeleton formation. Further study will be needed for exact explanation of bone formation from cartilage portion.

• Journal of Computing Science and Engineering
• /
• 제8권3호
• /
• pp.149-156
• /
• 2014

Skeletonization is a morphological operation that transforms an original object into a subset, which is called a 'skeleton'. Skeletonization has been intensively studied for decades and is a challenging issue especially for special target objects. This paper proposes a novel approach to the skeletonization of text images based on stroke width detection. First, the preliminary skeleton is detected by using a Canny edge detector with a Tensor Voting framework. Second, the preliminary skeleton is smoothed, and junction points are connected by interpolation compensation. Experimental results show the validity of the proposed approach.

• 한국멀티미디어학회논문지
• /
• 제15권10호
• /
• pp.1257-1263
• /
• 2012

본 연구는 3D레이저 스캔 방식으로 계측된 인체 데이터를 대상으로 하여 인체의 여러 동작들에 대한 애니메이션 모듈 구현을 목표로 하였다. 이를 위하여 애니메이션 회전을 위한 기준점인 인체의 골격 기준점을 추출하고 추출된 기준점을 이용하여 골격을 잡고 각 골격에 따른 계층트리를 구성하였다. 구성된 계층트리의 골격에 해당되는 오브젝트 정점들을 골격과 연결하고 주어진 애니메이션 3차원 정점들에 행동 패턴을 적용하여 스캔데이터에 애니메이션을 구현하였다.