公开(公告)号：US20110153431A1

公开(公告)日：2011-06-23

申请号：US12825892

申请日：2010-06-29

申请人： Hye Mi KIM ,  Jae Hean KIM ,  Il Kwon JEONG ,  Jin Ho KIM ,  Myung Gyu KIM ,  Sang Won GHYME ,  Sung June CHANG ,  Man Kyu SUNG ,  Brian AHN ,  Byoung Tae CHOI ,  Young Jik LEE

发明人： Hye Mi KIM ,  Jae Hean KIM ,  Il Kwon JEONG ,  Jin Ho KIM ,  Myung Gyu KIM ,  Sang Won GHYME ,  Sung June CHANG ,  Man Kyu SUNG ,  Brian AHN ,  Byoung Tae CHOI ,  Young Jik LEE

IPC分类号： G06Q30/00 ,  G06K9/46

CPC分类号： G06Q30/00 ,  G06Q30/0269

摘要： Provided is an apparatus for targeted advertising based on images of passersby. A passerby image extraction unit extracts an image of a passerby. A trait information extraction unit extracts trait information regarding the passerby from the extracted image. A targeted advertisement obtainment unit obtains a targeted advertisement to be displayed based on the trait information. A targeted advertisement display unit displays the targeted advertisement.

摘要翻译： 提供了一种基于路人图像的针对性广告的装置。 路人图像提取单元提取路人的图像。 特征信息提取单元从提取的图像中提取关于路人的特征信息。 目标广告获取单元基于特征信息获得要显示的目标广告。 目标广告显示单元显示目标广告。

公开(公告)号：US20110096169A1

公开(公告)日：2011-04-28

申请号：US12909139

申请日：2010-10-21

申请人： Jung Jae YU ,  Jae Hean Kim ,  Hye Mi Kim ,  Jin Ho Kim ,  Il Kwon Jeong

发明人： Jung Jae YU ,  Jae Hean Kim ,  Hye Mi Kim ,  Jin Ho Kim ,  Il Kwon Jeong

IPC分类号： H04N7/18

CPC分类号： H04N7/181

摘要： Provided are a camera tracking system and method and a live video compositing system using the same, which track a main camera with a sub-camera attached to the main camera and thus stably calculate the motion of the main camera even in a dynamic case where most of a static background is occluded by a moving foreground object. The camera tracking system and the live video compositing system can connect feature point tracks that are cut by a foreground object which dynamically moves in an image. Accordingly, the camera tracking system and the live video compositing system can perform the more accurate and quick tracking of a camera even in a case where a foreground object occludes background by dynamically moving.

摘要翻译： 提供了一种相机跟踪系统和方法以及使用该摄像机的实时视频合成系统，该系统跟踪具有附属于主摄像机的子摄像机的主摄像机，因此即使在大多数情况下的动态情况下也能稳定地计算主摄像机的运动 静态背景被移动的前景对象遮挡。 相机跟踪系统和实时视频合成系统可以连接由图像中动态移动的前景对象切割的特征点轨迹。 因此，即使在前景物体通过动态移动遮挡背景的情况下，相机跟踪系统和实时视频合成系统也能够对相机进行更准确和快速的跟踪。

公开(公告)号：US20100158353A1

公开(公告)日：2010-06-24

申请号：US12491010

申请日：2009-06-24

申请人： Jae-Hean KIM ,  Jung Jae Yu ,  Hye-mi Kim ,  Jaehwan Kim ,  Jong Sung Kim ,  Jin Ho Kim ,  Il-Kwon Jeong

发明人： Jae-Hean KIM ,  Jung Jae Yu ,  Hye-mi Kim ,  Jaehwan Kim ,  Jong Sung Kim ,  Jin Ho Kim ,  Il-Kwon Jeong

IPC分类号： G06K9/00

CPC分类号： G06T7/564 ,  G06T7/33 ,  G06T7/97

摘要： A method for restoration of building structure using infinity homographies calculated based on parallelograms includes: calculating, using two or more parallelograms, an infinity homography between those cameras which refer to an arbitrary camera; restoring cameras and the building structure on an affine space using the computed infinity homography and homologous points between images; and transforming the restored result onto the metric space using constraints on orthogonality of vectors joining the restored three-dimensional points, the ratio of lengths of the vectors and intrinsic camera parameters. As a result, intrinsic camera parameters, camera positions on the metric space and the structure of the building are restored. All the restoration is possible even when intrinsic camera parameters corresponding to all the images are not constant.

摘要翻译： 使用基于平行四边形计算的无限同态法恢复建筑结构的方法包括：使用两个或更多个平行四边形计算参考任意相机的那些相机之间的无限一体图像; 使用计算的无限一体图像和图像之间的同源点在仿射空间上恢复相机和建筑结构; 以及使用对连接恢复的三维点的向量的正交性的限制，向量的长度比和固有的相机参数将恢复的结果变换到度量空间。 因此，恢复固有摄像机参数，度量空间上的摄像机位置和建筑物的结构。 即使对应于所有图像的内在相机参数不是常数，所有的恢复都是可能的。

公开(公告)号：US20100134494A1

公开(公告)日：2010-06-03

申请号：US12539739

申请日：2009-08-12

申请人： Choong Gyoo LIM ,  Il-Kwon Jeong ,  Byoung Tae Choi

发明人： Choong Gyoo LIM ,  Il-Kwon Jeong ,  Byoung Tae Choi

IPC分类号： G06F13/14 ,  G06T15/60

CPC分类号： G06T9/001 ,  G06T15/005 ,  G06T15/80 ,  G06T2200/16 ,  H04L67/38 ,  H04N21/2343 ,  H04N21/2381 ,  H04N21/41407

摘要： A remote shading-based three-dimensional (3D) streaming apparatus includes a 3D streaming server and a 3D streaming client. The 3D streaming server includes a 3D primitive extraction unit for extracting 3D primitives from 3D scene data provided thereto; a 2D primitive conversion unit for converting the extracted 3D primitives into 2D primitives; a 2D scene and network packet construction unit for constructing 2D scene data and network packets; a network packet transmission unit for transmitting the network packets to a 3D streaming client. The 3D streaming client includes a 2D scene reconstruction unit for reconstructing 2D scene data from the network packets; a 2D primitive extraction unit for extracting 2D primitives from the 2D scene data; a 2D rasterizing unit for determining screen pixel values within a primitive region; and a display unit for providing 3D and/or virtual reality contents using the determined screen pixel value.

摘要翻译： 基于着色的基于三维立体（3D）流式传输设备包括3D流服务器和3D流客户端。 3D流服务器包括用于从提供给它的3D场景数据中提取3D原语的3D原始提取单元; 2D原语转换单元，用于将提取的3D原语转换为2D原语; 用于构建2D场景数据和网络分组的2D场景和网络分组构造单元; 用于将网络分组发送到3D流客户端的网络分组传输单元。 3D流客户端包括用于从网络分组重构2D场景数据的2D场景重建单元; 2D原始提取单元，用于从2D场景数据中提取2D原语; 2D光栅化单元，用于确定原始区域内的屏幕像素值; 以及显示单元，用于使用所确定的屏幕像素值来提供3D和/或虚拟现实内容。

公开(公告)号：US08265337B2

公开(公告)日：2012-09-11

申请号：US12489970

申请日：2009-06-23

申请人： Jung-Jae Yu ,  Jae-Hean Kim ,  Hye-mi Kim ,  Il-Kwon Jeong

发明人： Jung-Jae Yu ,  Jae-Hean Kim ,  Hye-mi Kim ,  Il-Kwon Jeong

IPC分类号： G06K9/00

CPC分类号： H04N5/2224 ,  G06T7/246 ,  G06T7/277 ,  G06T2207/10016

摘要： A camera tracking apparatus for calculating in real time feature information and camera motion information based on an input image includes a global camera tracking unit for computing a global feature map having feature information on entire feature points; a local camera tracking unit for computing in real time a local feature map having feature information on a part of the entire feature points; a global feature map update unit for receiving the computed feature information from the global and local camera tracking units to update the global feature map; and a local feature selection unit for receiving the updated feature information from the global feature map update unit to select in real time the feature points contained in the local feature map. The local camera tracking unit computes the local feature map for each frame, while the global camera tracking unit computes the global feature map over frames.

摘要翻译： 一种用于基于输入图像计算实时特征信息和相机运动信息的相机跟踪装置，包括用于计算具有关于整个特征点的特征信息的全局特征图的全局相机跟踪单元; 本地相机跟踪单元，用于实时地计算具有关于整个特征点的一部分的特征信息的局部特征图; 全局特征图更新单元，用于从全局和本地相机跟踪单元接收计算出的特征信息以更新全局特征图; 以及本地特征选择单元，用于从全局特征图更新单元接收更新的特征信息，以实时选择包含在本地特征图中的特征点。 本地摄像机跟踪单元计算每个帧的局部特征图，而全局摄像机跟踪单元通过帧计算全局特征图。

公开(公告)号：US20110149039A1

公开(公告)日：2011-06-23

申请号：US12970089

申请日：2010-12-16

申请人： Jae Hwan KIM ,  Jae Hean Kim ,  Jin Ho Kim ,  Il Kwon Jeong

发明人： Jae Hwan KIM ,  Jae Hean Kim ,  Jin Ho Kim ,  Il Kwon Jeong

IPC分类号： H04N13/00

CPC分类号： H04N13/261

摘要： The present invention relates to a device and a method for allowing a user to reproduce new 3-D scene from one or two or more given 2-D video frames that already exist. The present invention provides a device and a method for automating post-image processing requiring a lot of manual work, thereby making it possible to produce and edit new 3-D representation from the existing 2-D video.

摘要翻译： 本发明涉及一种用于允许用户从已经存在的一个或两个或更多给定的2-D视频帧再现新的3-D场景的设备和方法。 本发明提供一种用于自动化需要大量手动工作的后期图像处理的装置和方法，从而使得可以从现有的2-D视频产生和编辑新的3-D表示。

公开(公告)号：US20110148870A1

公开(公告)日：2011-06-23

申请号：US12973533

申请日：2010-12-20

申请人： Myung-Gyu KIM ,  Man-Kyu Sung ,  Sang-Won Ghyme ,  Sung-June Chang ,  Il-Kwon Jeong ,  Byoung-Tae Choi

发明人： Myung-Gyu KIM ,  Man-Kyu Sung ,  Sang-Won Ghyme ,  Sung-June Chang ,  Il-Kwon Jeong ,  Byoung-Tae Choi

IPC分类号： G06T13/00 ,  G06T15/00

CPC分类号： G06T13/40

摘要： Disclosed herein is a method and apparatus for generating graphic tentacle motions. In the method, a 3D tentacle is divided into a 1D center line and a 2D surface based on information about an initial mesh of the 3D tentacle. New locations of sample points of the center line in a new frame are determined from initial locations of sample points of the center line, based on a tentacle root motion. New locations of sample points of the surface in the new frame are determined from initial locations of sample points of the surface, based on both the initial locations of the center line sample points and the tentacle root motion. The surface is coupled to the center line using the locations of the sample points of both the center line and the surface in the new frame.

摘要翻译： 本文公开了一种用于产生图形触觉运动的方法和装置。 在该方法中，基于关于3D触手的初始网格的信息，3D触手被分为1D中心线和2D表面。 基于触角根运动，从中心线的采样点的初始位置确定新帧中心线的采样点的新位置。 基于中心线采样点的初始位置和触手根运动，从新表面的采样点的初始位置确定新帧中的表面采样点的新位置。 使用新框架中的中心线和表面的采样点的位置将表面耦合到中心线。

公开(公告)号：US20110142354A1

公开(公告)日：2011-06-16

申请号：US12787098

申请日：2010-05-25

申请人： Man Kyu SUNG ,  Myunggyu KIM ,  Sang Won GHYME ,  Sung June CHANG ,  Il-Kwon JEONG ,  Byoung Tae CHOI

发明人： Man Kyu SUNG ,  Myunggyu KIM ,  Sang Won GHYME ,  Sung June CHANG ,  Il-Kwon JEONG ,  Byoung Tae CHOI

IPC分类号： G06K9/62

CPC分类号： G06T7/73 ,  G06T2207/10016

摘要： An apparatus for detecting a pose in motion capture data includes: a motion data input unit which receives motion data of characters; a virtual marker attaching unit for forming a point cloud by attaching virtual markers to joints of an end-effector of each character; and a scaling unit for, when a frame has different character size from an a character size of an original frame to be compared is detected, scaling the character size. The apparatus further includes an ICP algorithm execution unit for finding a matching transformation matrix between the original frame and each frame of the motion data, of which character size has been scaled, by applying an ICP algorithm, and determining a frame, in which character's pose has the smallest difference from that in the original frame based on a sum of the distances between the virtual markers chosen by sampling the matched two poses.

摘要翻译： 一种用于检测运动捕获数据中姿势的装置，包括：运动数据输入单元，其接收人物的运动数据; 虚拟标记附着单元，用于通过将虚拟标记附接到每个角色的末端执行器的关节来形成点云; 以及缩放单元，用于当检测到具有与要比较的原始帧的字符大小不同的字符尺寸时，缩放字符尺寸。 该装置还包括ICP算法执行单元，用于通过应用ICP算法来找出原始帧与运动数据的每个帧之间的匹配变换矩阵，其中字符大小已被缩放，并且确定一个帧，其中字符的姿态 基于通过对匹配的两个姿态进行采样而选择的虚拟标记之间的距离的总和，与原始帧中的差异具有最小差异。

公开(公告)号：US20100119109A1

公开(公告)日：2010-05-13

申请号：US12498189

申请日：2009-07-06

申请人： Hye-mi KIM ,  Jae Hean Kim ,  Jung Jae Yu ,  Jin Ho Kim ,  Il-Kwon Jeong

发明人： Hye-mi KIM ,  Jae Hean Kim ,  Jung Jae Yu ,  Jin Ho Kim ,  Il-Kwon Jeong

IPC分类号： G06K9/00

CPC分类号： G06T7/246 ,  G06T2200/28 ,  G06T2207/20021

摘要： A multi-core multi-thread based Kanade-Lucas-Tomasi (KLT) feature tracking method includes subdividing an input image into regions and allocating a core to each region; extracting KLT features for each region in parallel and in real time; and tracking the extracted features in the input image. Said extracting the features is carried out based on single-region/multi-thread/single-core architecture, while said tracking the features is carried out based on multi-feature/multi-thread/single-core architecture.

摘要翻译： 基于多核多线程的Kanade-Lucas-Tomasi（KLT）特征跟踪方法包括将输入图像细分为区域并将核分配给每个区域; 并行和实时提取每个区域的KLT特征; 并跟踪输入图像中提取的特征。 所述提取特征是基于单区域/多线程/单核架构进行的，而所述跟踪特征是基于多特征/多线程/单核架构进行的。

公开(公告)号：US07091977B2

公开(公告)日：2006-08-15

申请号：US10821869

申请日：2004-04-12

申请人： Il Kwon Jeong ,  In Ho Lee

发明人： Il Kwon Jeong ,  In Ho Lee

IPC分类号： G06T13/00 ,  G06T15/70

CPC分类号： G06T13/20 ,  G06T2210/21

摘要： Disclosed is an animation method of deformable objects using an oriented material point and generalized spring model. The animation method comprises the following steps of: modeling a structure of a deformable object into oriented material points and generalized springs; initializing forces and torques acting on the material points, calculating the forces acting on the material points owing to collision of the material points and gravity, calculating the spring forces and torques acting on the material points, obtaining new positions and postures of the material points; updating positions, velocities, postures and angular velocities of the material points based upon physics, and displaying and storing updated results. The oriented material point and generalized spring model of the invention contains the principle of the conventional mass-spring model, but can animate deformable objects or express their structures in more intuitive manner over the conventional mass-spring model. Also, the material point and generalized spring model of the invention can express elongate deformable objects such as hair and wrinkled cloth, which cannot be expressed in the prior art, so as to animate features of various objects.

摘要翻译： 公开了使用定向材料点和广义弹簧模型的可变形物体的动画方法。 动画方法包括以下步骤：将可变形物体的结构建模成定向材料点和广义弹簧; 初始化作用在材料点上的力和扭矩，计算由于材料点和重力的碰撞而作用在材料点上的力，计算作用在材料点上的弹簧力和扭矩，获得材料点的新位置和姿态; 基于物理学更新材料点的位置，速度，姿态和角速度，以及显示和存储更新的结果。 本发明的定向材料点和广义弹簧模型包含常规质量弹簧模型的原理，但可以以更直观的方式对可变形物体进行动画化或表达其结构，超过常规质量弹簧模型。 此外，本发明的材料点和广义弹簧模型可以表现在现有技术中不能表达的诸如毛发和起皱布的细长可变形物体，以便对各种物体的特征进行动画化。