-
公开(公告)号：KR1020100073175A
公开(公告)日：2010-07-01
申请号：KR1020080131769
申请日：2008-12-22
Applicant: 한국전자통신연구원
CPC classification number: G06T13/40
Abstract: PURPOSE: A method for creating digital clone of a multi-viewpoint image based dynamic object is provided to generate a 3D human body model which enables a behavior feature reproduction of an actor by restoring a shape of an actor and motion information for each frame based on multi-viewpoint. CONSTITUTION: An actor performs pre-defined motions, and a three-dimensional shape restoration unit(100) restores a multi-viewpoint image based three-dimensional shape information for a T-pose multi-viewpoint image. A standard human body model transition unit(102) creates the initiation model of an actor from restored shape image. An intrinsic human body model generator(104) applies the initial human body model to a multi-viewpoint pose learning image.
Abstract translation: 目的：提供一种用于创建基于多视点图像的动态对象的数字克隆的方法，以生成3D人体模型，其通过基于每个帧恢复运动员的形状和运动信息来实现演员的行为特征再现，基于 多视点。 构成：演员执行预定义的运动，三维形状恢复单元（100）恢复用于T姿势多视点图像的基于多视点图像的三维形状信息。 标准人体模型转移单元（102）从恢复的形状图像创建演员的发起模型。 内在的人体模型发生器（104）将初始人体模型应用于多视角姿势学习图像。
-
公开(公告)号：KR1020100073081A
公开(公告)日：2010-07-01
申请号：KR1020080131666
申请日：2008-12-22
Applicant: 한국전자통신연구원
IPC: G06T3/00
CPC classification number: G06K9/38
Abstract: PURPOSE: An apparatus for separating a foreground from a back ground and a method thereof are provided to enhance the foreground/background separation performance by accurately performing a codeword modeling. CONSTITUTION: A background model generator(300) generates a codebook for foreground/background separation, and includes a codeword generation block(301) and codeword rearrangement block(302). The codebook includes plural codewords, and a foreground/background separation unit(350) separates the foreground from the background by using the generated codebook. A foreground/background decision unit(351) includes a post-processing block(352).
Abstract translation: 目的：提供一种用于从背景分离前景的装置及其方法，以通过精确地执行码字建模来增强前景/背景分离性能。 构成：背景模型生成器（300）生成用于前景/背景分离的码本，并且包括码字生成块（301）和码字重排块（302）。 码本包括多个码字，并且前景/背景分离单元（350）通过使用生成的码本将前景与背景分离。 前景/背景决定单元（351）包括后处理块（352）。
-
公开(公告)号：KR100918095B1
公开(公告)日：2009-09-22
申请号：KR1020070094263
申请日：2007-09-17
Applicant: 한국전자통신연구원
Abstract: 본 발명은 비디오카메라를 통해 입력된 3차원 얼굴 메쉬의 모든 버텍스에 대해 다른 메쉬들과의 대응 관계를 설정하고 평균 3차원 얼굴 모델을 생성하고, 평균 얼굴 모델과 얼굴 모델간의 공분산 행렬의 주성분 분석을 통해 기하 모델 및 텍스쳐 분산 모델을 생성하는 전처리부와, 비디오카메라로부터 입력된 얼굴 연기 동영상 중에서 정면을 응시하는 무표정 상태의 얼굴 영상 프레임에 전처리부에서 생성한 평균 3차원 얼굴 모델을 투영하여 연기자의 3차원 얼굴 모델을 생성하는 얼굴모델생성부와, 애니메이션 제어 모델을 가진 3차원 얼굴 모델 템플릿을 얼굴모델생성부에서 생성한 연기자의 3차원 얼굴 모델에 전이시켜 애니메이션 제어 모델을 갖춘 연기자의 3차원 얼굴모델을 생성하는 전이부와, 전이부에 의해 전이된 애니메이션 제어 모델을 갖춘 연기자의 3차원 얼굴 모델을 표정 연기가 있는 얼굴 애니메이션 비디오 프레임에 투영시키는 투영부와, 투영부에 의해 투영된 오차를 계산하는 오차계산부와, 오차계산부에 의해 계산된 오차가 최소화되는 방향으로 조인트를 이동 및 회전 변환하여 메쉬를 변형하는 메쉬변형부로 구성되므로, 이상에서 설명한 본 발명에 의해 연기자의 얼굴 연기를 한 대의 비디오 카메라로 촬영한 얼굴 연기 동영상으로부터 손쉽게 3차원 애니메이션을 생성할 수 있는 효과가 있다.
-
公开(公告)号：KR1020090065351A
公开(公告)日：2009-06-22
申请号：KR1020070132851
申请日：2007-12-17
Applicant: 한국전자통신연구원
CPC classification number: G06T13/40 , G06K2009/3291 , G06T7/251 , G06T7/277 , G06T2207/10016 , G06T2207/30201
Abstract: A head motion tracking method for 3D face animation is provided to automatically carry out natural 3D face model animation without a manual work, thereby saving time and a cost. An initial face motion to be adjusted to a 3D model image is obtained from an image inputted from one video camera(S300). A silhouette of the 3D model is produced and projected(S302). The silhouette generated from the 3D model is matched with a silhouette obtained by a statistical characteristic point tracking method(S304). Motion parameters for the 3D model image are obtained through motion compensation using texture to conduct a 3D head motion tracking function(S306). A characteristic point of the 3D model is matched with a characteristic point of a 2D image to calculate initial motion parameters.
Abstract translation: 提供了一种用于3D人脸动画的头部运动跟踪方法，可以自动执行自然3D人脸模型动画，而无需手动工作，从而节省时间和成本。 从从一台摄像机输入的图像获得要调整到3D模型图像的初始面部动作（S300）。 生成并投影3D模型的轮廓（S302）。 从3D模型生成的轮廓与通过统计特征点追踪方法获得的轮廓相匹配（S304）。 通过使用纹理的运动补偿获得3D模型图像的运动参数，以进行3D头运动跟踪功能（S306）。 3D模型的特征点与2D图像的特征点相匹配，以计算初始运动参数。
-
公开(公告)号：KR100443553B1
公开(公告)日：2004-08-09
申请号：KR1020020077324
申请日：2002-12-06
Applicant: 한국전자통신연구원
CPC classification number: G06T13/40
Abstract: In a virtual character control system, a character form mesh linked to articulation information of a character including articulations and at least one item mesh linked to the articulation information are stored in a set format. A temporary mesh generator selects an item mesh attached to the character from among the at least one item mesh according to item removal information, and combines the selected item mesh and the character form mesh to generate a temporary mesh. A character motion controller performs mesh skinning on the temporary mesh according to character motion control information to link the character form mesh and the item mesh to the character motion control information, thereby very effectively controlling motion of the virtual character.
Abstract translation: 在虚拟角色控制系统中，以设定格式存储链接到包括关节的角色的关节信息和链接到关节信息的至少一个项目网格的角色表单网格。 临时网格生成器根据项目移除信息从至少一个项目网格中选择附加到角色的项目网格，并且组合所选项目网格和字符网格以生成临时网格。 字符运动控制器根据字符运动控制信息对临时网格进行网格蒙皮，以将字符网格和物品网格链接到字符运动控制信息，由此非常有效地控制虚拟字符的运动。
-
Patent Agency Ranking
公开(公告)号：KR1020030054108A
公开(公告)日：2003-07-02
申请号：KR1020010084214
申请日：2001-12-24
Applicant: 한국전자통신연구원
IPC: G06T17/10
CPC classification number: G06T15/005
Abstract: PURPOSE: An operation optimizing system in a hardware graphic acceleration board for real-time rendering and an operation optimizing method are provided to improve output speed when a three-dimensional object is output on a computer screen using the hardware graphic acceleration board. CONSTITUTION: An operation optimizing system in a hardware graphic acceleration board for real-time rendering includes a hardware optimization pre-processor(100), a triangle aligner(300), and a triangle selection and outputting unit(400). When geometrical information and surface attribute information of a three-dimensional object are inputted to the hardware optimization pre-processor, the pre-processor analyzes the geometrical information to form a surface attribute list and analyzes triangles constructing the object to generate a group of triangles as many as the number of surface attributes. The triangle aligner aligns the triangles according to camera information. The triangle selection and outputting unit extracts the aligned triangles one by one, selects triangles to be output on a screen among the extracted triangles, and outputs the selected triangles to an output device(500).
Abstract translation: 目的：提供用于实时渲染的硬件图形加速板中的操作优化系统和操作优化方法，以在使用硬件图形加速板在计算机屏幕上输出三维对象时提高输出速度。 构成：用于实时渲染的硬件图形加速板中的操作优化系统包括硬件优化预处理器（100），三角形对准器（300）和三角形选择和输出单元（400）。 当将三维物体的几何信息和表面属性信息输入到硬件优化预处理器时，预处理器分析几何信息以形成表面属性列表，并分析构造对象的三角形以生成一组三角形 许多作为表面属性的数量。 三角形对齐器根据摄像机信息对齐三角形。 三角形选择和输出单元逐个提取对齐的三角形，选择在提取的三角形之间在屏幕上输出的三角形，并将所选择的三角形输出到输出设备（500）。
-
-
-
公开(公告)号：KR1020170082077A
公开(公告)日：2017-07-13
申请号：KR1020160001248
申请日：2016-01-05
Applicant: 한국전자통신연구원
Abstract: 아이템스캐닝장치및 방법이개시된다. 본발명의일실시예에따른아이템스캐닝장치는표준거치대모델에부착된특징점들과기 스캐닝된아이템에대한 3차원부분모델을이용하여, 상기아이템에서스캔이필요한부분을추출하고, 상기스캔이필요한부분에상응하는위치정보를계산하는위치정보계산부; 카메라를이용하여상기아이템을촬영한영상을이용하여, 상기위치정보에상응하는깊이정보및 텍스쳐정보를획득하는촬영부; 및상기깊이정보및 상기텍스쳐정보에기반하여상기아이템에대한 3차원모델을복원하는복원부를포함한다.
Abstract translation: 一种物品扫描装置和方法被公开。 根据本发明实施例的物品扫描装置通过使用附接到标准安装台模型的特征点和扫描物品的三维部分模型提取物品中需要扫描的部分， 位置信息计算单元，用于计算对应于位置信息的位置信息; 图像拍摄单元，其使用相机使用物品的图像来获取与位置信息相对应的深度信息和纹理信息; 以及重建单元，用于基于深度信息和纹理信息来重建项目的3D模型。
-
公开(公告)号：KR101740259B1
公开(公告)日：2017-05-29
申请号：KR1020110102601
申请日：2011-10-07
Applicant: 한국전자통신연구원
CPC classification number: G06T7/0081 , G06K9/00664 , G06K9/00697 , G06T7/11 , G06T7/136 , G06T7/194 , G06T2200/04 , G06T2207/10028 , G06T2207/20021
Abstract: 본발명은 3차원포인트클라우드의공간을다수개의그리드셀로균등분할하는단계, 3차원포인트클라우드의공간상에서바닥에해당하는베이스면을설정하는단계, 베이스면의수직에있는모든그리드셀의포인트를누적하는단계및 포인트가누적된그리드셀을상기누적된포인트의개수에따라물체와바닥으로분할하는단계를포함하는것을특징으로한다.
Abstract translation: 本发明涉及一种用于将三维点云的空间均匀划分为多个网格单元，在三维点云的空间上设置与底部对应的底面的方法和设备， 根据累计点的数量将累计的网格单元划分为物体和楼层。
-
-
-
-
-
-
-
-
-
Search Results
94
records
(took 0.023 seconds)
