• 한국인터넷방송통신학회논문지
• /
• 제12권2호
• /
• pp.119-126
• /
• 2012

최근 연구에서 모션 인식을 위해 여러 가지 인식 알고리즘을 사용하였다. 예를 들면, HMM, DTW, PCA 등의 기법을 이용하여 권투 모션을 인식하는 방법을 제시했다. 이러한 방법을 이용하기 위해서 연기자로부터 3차원 데이터를 얻기 위해 액티브 마커를 사용하여 손의 위치를 얻는다. 얻은 2차원 위치 정보는 다시 스테레오 기법을 이용하여 3차원 정보로 전환하여 구한다. 본 논문에서는 3차원 모션 데이터를 얻는 방법을 깊이 맵에 대한 알고리즘을 이용하여 구하였다. 그리고 3차원 위치 데이터 정보의 정확성 나타냈으며, 그리고 모션 동작에 대한 인식을 실험을 하였고, 그 실험 결과에 대해서 언급했다.

• 한국유체기계학회 논문집
• /
• 제11권6호
• /
• pp.38-45
• /
• 2008

Development of high efficiency turbine with good performance is one of the main topics in the field of developing wave energy converter. For the development and improvement of the turbine performance, the effect of wave condition on the turbine performance should be considered in detail. Also, water depth is an important factor because incident wave power to the turbine is considerably influenced by the wave particle amplitude of motion and the amplitude is closely related with the water depth. Therefore, in this study, the effect of water depth on the performance of a direct drive turbine(DDT) for wave energy converter is investigated using the DDT which is installed in two types of wave channel. The experimental results show that the DDT captures more wave energy under the condition of relatively shallow water depth. When the water depth is shallow, the horizontal water particle amplitude of motion becomes wider and thus, the water power toward the turbine becomes larger.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 1999년도 봄 학술발표회 논문집
• /
• pp.447-454
• /
• 1999

The compressive capacity and the soil plugging resistance of single open-ended pipe pile were completely decreased in the previous study on the behavior of shorter single pile during simulated seaquake induced by the vertical component of earthquake. But the capacity of single open-ended pipe pile with greater penetration and the capacity of piles group with shorter penetration were expected to be stable after seaquake motion. In this study, first, 2-piles or 4-piles are driven into the calibration chamber included in saturated fine medium sand with several simulated penetrations, and the compressive load test for each piles group was performed. Then, about 95 % compressive load of the ultimate capacity was applied on the pile head during the simulated seaquake motion. Finally, In confirm the reduction of pile capacity during the simulated seaquake motion, the compressive load test for each single pile or piles group after seaquake motion was performed. During the simulated seaquake, the compressive capacity of open-ended pipe piles with greater penetration ( 〉about 27 m) was not degraded even in deep sea deeper than 220 m and soil plug within open-ended pipe pile installed in deep sea was stable after seaquake motion. Also, in the case of 2-piles or 4-pile groups, the compressive capacity after seaquake motion was not degraded at all regardless of pile penetration depth beneath seabed, sea water depth and seaquake frequency.

• 방송공학회논문지
• /
• 제23권1호
• /
• pp.3-10
• /
• 2018

깊이맵은 현재 다양한 분야에서 활용되고 있다. 이러한 깊이맵을 인공 신경망으로 생성하는 연구가 최근 관심을 받고 있다. 본 논문에서는 기존의 기 제작된 깊이맵 생성 알고리즘을 합성곱 신경망으로 구현할 수 있는지에 대한 타당성을 검증한다. 먼저 깊이맵은 관심맵과 운동 히스토리 영상의 가중치 합으로 얻는다. 실험영상과 깊이맵을 합성곱 신경망의 입력과 출력으로 하여, 신경망을 학습시킨다. 정성적, 정량적 실험 결과는 제안한 합성곱 신경망이 깊이맵 생성 방법을 대체할 수 있다는 것을 보여준다.

• 한국산업정보학회논문지
• /
• 제23권4호
• /
• pp.33-40
• /
• 2018

컴퓨터와 영상기술의 발달로 디지털 미디어의 제공방법이 다양해지고 이에 관한 관심이 커짐에 따라 많은 콘텐츠가 제작되고 있다. 이 콘텐츠들은 카메라나 컨트롤러를 통해 인체의 움직임과 사용자 정보를 활용하기 위한 연구가 활발하게 이루어지고 있다. 사용자의 정보를 이용한 콘텐츠는 공공장소에서 다양한 사람들에게 노출되어 광고로 사용 될 수 있다. 본 논문에서 사용자의 키 정보와 움직임 정보를 사용하여 구현되는 캐릭터 플로팅 홀로그램 시스템을 제안한다. 시스템은 깊이 영상에서 사용자의 키와 움직임을 감지하고 이 정보를 토대로 캐릭터를 생성한다. 생성된 캐릭터는 플로팅 홀로그램 디바이스를 이용하여 표현된다. 이 시스템은 사용자 정보를 이용한 마케팅, 광고 및 전시에서 사용될 수 있다.

• 한국멀티미디어학회논문지
• /
• 제15권4호
• /
• pp.501-507
• /
• 2012

Human body motion is a non-verbal part for interaction or movement that can be used to involves real world and virtual world. In this paper, we explain a study on natural user interface (NUI) in human hand motion recognition using RGB color information and depth information by Kinect camera from Microsoft Corporation. To achieve the goal, hand tracking and gesture recognition have no major dependencies of the work environment, lighting or users' skin color, libraries of particular use for natural interaction and Kinect device, which serves to provide RGB images of the environment and the depth map of the scene were used. An improved Camshift tracking algorithm is used to tracking hand motion, the experimental results show out it has better performance than Camshift algorithm, and it has higher stability and accuracy as well.

• 제어로봇시스템학회논문지
• /
• 제19권9호
• /
• pp.760-767
• /
• 2013

In this paper, we developed a Manta-type AUV (Autonomous Underwater Vehicle) and analyzed its control performance as well as its dynamic characteristics underwater. The nonlinear motion of equations, which are expressed in terms of hydrodynamic coefficients obtained by various experiments, are used to simulate the motion of a Manta AUV underwater. We applied the sliding-mode theory to control the heading angle and depth of the vehicle, and confirmed the effectiveness of the control algorithm through simulations and sea-trials.

• Journal of applied mathematics & informatics
• /
• 제23권1_2호
• /
• pp.127-140
• /
• 2007

We present the boundary value problem (BVP) for the heave motion due to a vertical circular cylinder in water of finite depth. The BVP is presented in terms of velocity potential function. The velocity potential is obtained by considering two regions, namely, interior region and exterior region. The solutions for these two regions are obtained by the method of separation of variables. The analytical expressions for the hydrodynamic coefficients are derived. Computational results are presented for various depth to radius and draft to radius ratios.

• 디지털융복합연구
• /
• 제11권1호
• /
• pp.243-248
• /
• 2013

본 논문에서는 2D/3D 동영상 변환을 위해 깊이가 할당될 전경을 초점 정보와 색상분석 기반의 그룹화를 이용하여 추출하고, 전경의 깊이를 초점 정보와 움직임 정보를 이용하여 생성하는 방법을 제안하였다. 2D영상에서 전경을 추출하기 위해 영상의 초점 정보의 움직임을 추정하여 전경 후보 영상을 생성하고, 전경 후보 영상에 존재하는 객체 내부의 홀 영역을 색상 분석을 이용한 채움 과정을 수행하여 전경 영역을 추출하였다. 생성된 전경 영역에 깊이를 할당하기 위해 해당 프레임에 존재하는 초점 값을 분석하여 초기 깊이 정보를 생성하고 움직임 정보를 가중하여 깊이 정보를 할당하였다. 생성된 깊이 정보의 품질을 평가하기 위해 기존에 제안된 알고리즘의 결과 영상과 비교하였다.

• 한국항해학회지
• /
• 제23권2호
• /
• pp.29-42
• /
• 1999

An accurate method of estimating ship maneuverability needs to be developed to evaluate precisely and improve the maneuverability of ships according to the water depth. In order to estimate maneuverability by a mathematical model. The hydrodynamic forces acting on a ship hull and the flow field around the ship in maneuvering motion need to be estimated. The ship speed new the berth is very low and the fluid flow around a ship hull is unsteady. So, the transient fluid motion should be considered to estimate the drag force acting on the ship hull. In the low speed and short time lateral motion, the vorticity is created by the body and grow up in the acceleration stage and the velocity induced by the vorticity affect to the body in deceleration stage. For this kind of problem, CFD is considered as a goof tool to understand the phenomena. In this paper, the 2D CFD code is used for basic consideration of the phenomena to solve the flow in the cross section of the ship considering the ship is slender and the water depth is large enough. The flow fields Added and hydrodynamic forces for the some prescribed motions are computed and compared with the preliminary experiment results. The comparison of the force with measurement is shown a fairly good agreement in tendency. The 3D Potential Calculation based on the Hess & Smith Theory is employed to predict the surge, sway added mass and yaw added moment of inertia of hydrodynamic coefficients for M/V ESSO OSAKA according to the water depth. The results are also compared with experimental data. Finally, the sway added mass of hydrodynamic coefficients for T/S HANNARA is suggested in each water depth.