专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120158377A1 METHOD AND APPARATUS FOR SEARCHING FOR NEIGHBORING PARTICLES BY USING TEMPORAL CONTINUITY 审中-公开
标题翻译：通过使用时间连续性来搜索邻接颗粒的方法和装置
公开(公告)号：US20120158377A1
公开(公告)日：2012-06-21
申请号：US13310067
申请日：2011-12-02
申请人： Soon Hyoung PYO , BONKI KOO
发明人： Soon Hyoung PYO , BONKI KOO
IPC分类号： G06F7/60
CPC分类号： G06F17/5009 , G06F2217/16
摘要： A method for searching for neighboring particles includes: setting neighbor target particles of a current particle to calculate mutual influences between the neighbor target particles and the current particle; selecting neighboring particles depending on a calculation result of the mutual influences to store indexes of the neighboring particles in the current particle; updating locations and information of the current particle based on power of the mutual influences and proceeding to a next time step; determining the neighboring particles selected at a previous time step as the neighbor target particles; and repeating above steps starting from said calculating mutual influences regarding the newly determined neighbor target particles.
摘要翻译：用于搜索相邻粒子的方法包括：设置当前粒子的相邻目标粒子以计算相邻目标粒子与当前粒子之间的相互影响; 根据相互影响的计算结果选择相邻粒子，以存储当前粒子中相邻粒子的指标; 基于相互影响的功率来更新当前粒子的位置和信息，并进行下一个时间步长; 确定在先前时间步长选择的相邻粒子作为相邻目标粒子; 并且从对所确定的新近的目标粒子的所述计算相互影响开始重复上述步骤。

2. 发明申请

US20110052055A1 COLOR CONVERSION SYSTEM AND METHOD 有权
标题翻译：颜色转换系统和方法
公开(公告)号：US20110052055A1
公开(公告)日：2011-03-03
申请号：US12836043
申请日：2010-07-14
申请人： Maeng-Sub CHO , Jin-Seo Kim , Bonki Koo , Soon-Young Kwon , Juyeon You , Ki-Hong Kim
发明人： Maeng-Sub CHO , Jin-Seo Kim , Bonki Koo , Soon-Young Kwon , Juyeon You , Ki-Hong Kim
IPC分类号： G06K9/00
CPC分类号： H04N1/6033 , H04N9/68
摘要： Provided is a color conversion system and method. The color conversion system which converts the color of a filmed image includes: an image separation unit configured to receive a reference image including a color reference table and an action image, and separate the reference and action images from each other; a color data extraction unit configured to output color values of the color reference table included in the reference image; a control unit configured to detect change values obtained by comparing color values included in the reference image with those included in the color reference table, and generate a look-up table for converting the colors of the color reference table included in the reference image into desired colors; and an image conversion unit configured to perform color correction by converting the color values of the action image into coordinates in pixels, using the look-up table outputted from the control unit.
摘要翻译：提供了一种颜色转换系统和方法。转换成像图像的颜色的颜色转换系统包括：图像分离单元，被配置为接收包括颜色参考表和动作图像的参考图像，并且使参考和动作图像彼此分离; 彩色数据提取单元，被配置为输出包括在参考图像中的颜色参考表的颜色值; 控制单元，被配置为检测通过将参考图像中包括的颜色值与包括在颜色参考表中的颜色值进行比较而获得的变化值，并且生成用于将包括在参考图像中的颜色参考表的颜色转换为期望的查找表颜色; 以及图像转换单元，被配置为使用从所述控制单元输出的查找表，将所述动作图像的颜色值转换为像素中的坐标来执行颜色校正。

3. 发明授权

US09185401B2 Method and apparatus for camera network calibration with small calibration pattern 有权
标题翻译：具有小校准模式的相机网络校准方法和装置
公开(公告)号：US09185401B2
公开(公告)日：2015-11-10
申请号：US13549323
申请日：2012-07-13
申请人： Jae Hean Kim , Hyun Kang , Ji Hyung Lee , Bonki Koo
发明人： Jae Hean Kim , Hyun Kang , Ji Hyung Lee , Bonki Koo
IPC分类号： H04N7/18 , H04N17/00 , H04N17/02 , G06K9/00 , H04N5/247 , G06T7/00
CPC分类号： H04N17/002 , G06T7/85 , G06T2207/30244 , H04N5/247
摘要： A method for calibrating a camera network includes generating a projection matrix by each of cameras in respect of a calibration pattern that is disposed at a plurality of different positions in a photography zone. A portion of the projection matrix is produced as a sub-projection matrix. Sub-projection matrixes are arranged widthwise and lengthwise to generate one sub-measurement matrix. A singular value decomposition (SVD) is performed on the sub-measurement matrix to change the sub-measurement matrix into a matrix having a rank of 3 and a SVD is performed on the changed sub-measurement matrix. A rotation value of the calibration pattern, and an internal parameter and a rotation value of each camera are extracted to thereby calibrate the camera network.
摘要翻译：一种用于校准摄像机网络的方法包括针对设置在摄影区域中的多个不同位置的校准图案，生成每个照相机的投影矩阵。投影矩阵的一部分作为子投影矩阵产生。子投影矩阵被宽度方向和纵向排列以产生一个子测量矩阵。对子测量矩阵执行奇异值分解（SVD），将子测量矩阵改变为具有等级3的矩阵，并且对改变的子测量矩阵执行SVD。提取校准图案的旋转值，以及每个照相机的内部参数和旋转值，从而校准摄像机网络。

4. 发明授权

US09177414B2 Apparatus and method for rendering point cloud using voxel grid 有权
标题翻译：使用体素网格渲染点云的装置和方法
公开(公告)号：US09177414B2
公开(公告)日：2015-11-03
申请号：US13558230
申请日：2012-07-25
申请人： Il Kyu Park , Chang Woo Chu , Youngmi Cha , Ji Hyung Lee , Bonki Koo
发明人： Il Kyu Park , Chang Woo Chu , Youngmi Cha , Ji Hyung Lee , Bonki Koo
IPC分类号： G06T17/00 , G06T15/04
CPC分类号： G06T15/04 , G06T17/00 , G06T2210/56
摘要： A method for rendering point cloud using a voxel grid, includes generating bounding box including all the point cloud and dividing the generated bounding box into voxels to make the voxel grid; and allocating at least one texture plane to each of the voxels of the voxel grid. Further, the method includes orthogonally projecting points within the voxel to the allocated texture planes to generate texture images; and rendering each voxel of the voxel grid by selecting one of the texture planes within the voxel by using central position of the voxel and the 3D camera position and rendering using the texture images corresponding to the selected texture plane.
摘要翻译：一种使用体素网格渲染点云的方法，包括生成包含所有点云的边界框，并将生成的边界框划分为体素以形成体素网格; 以及将至少一个纹理平面分配给所述体素网格的每个体素。此外，该方法包括将体素内的点正交投影到所分配的纹理平面以产生纹理图像; 以及通过使用体素的中心位置和3D相机位置以及使用与选定的纹理平面相对应的纹理图像进行渲染来选择体素中的纹理平面之一来渲染体素网格的每个体素。

5. 发明申请

US20130057653A1 APPARATUS AND METHOD FOR RENDERING POINT CLOUD USING VOXEL GRID 有权
标题翻译：使用VOXEL GRID渲染点云的装置和方法
公开(公告)号：US20130057653A1
公开(公告)日：2013-03-07
申请号：US13558230
申请日：2012-07-25
申请人： Il Kyu PARK , Chang Woo CHU , Youngmi CHA , Ji Hyung LEE , Bonki KOO
发明人： Il Kyu PARK , Chang Woo CHU , Youngmi CHA , Ji Hyung LEE , Bonki KOO
IPC分类号： H04N13/02
CPC分类号： G06T15/04 , G06T17/00 , G06T2210/56
摘要： A method for rendering point cloud using a voxel grid, includes generating bounding box including all the point cloud and dividing the generated bounding box into voxels to make the voxel grid; and allocating at least one texture plane to each of the voxels of the voxel grid. Further, the method includes orthogonally projecting points within the voxel to the allocated texture planes to generate texture images; and rendering each voxel of the voxel grid by selecting one of the texture planes within the voxel by using central position of the voxel and the 3D camera position and rendering using the texture images corresponding to the selected texture plane.
摘要翻译：一种使用体素网格渲染点云的方法，包括生成包含所有点云的边界框，并将生成的边界框划分为体素以形成体素网格; 以及将至少一个纹理平面分配给所述体素网格的每个体素。此外，该方法包括将体素内的点正交投影到所分配的纹理平面以产生纹理图像; 以及通过使用体素的中心位置和3D相机位置以及使用与选定的纹理平面相对应的纹理图像进行渲染来选择体素中的纹理平面之一来渲染体素网格的每个体素。

6. 发明授权

US08902305B2 System and method for managing face data 有权
标题翻译：用于管理脸部数据的系统和方法
公开(公告)号：US08902305B2
公开(公告)日：2014-12-02
申请号：US13566938
申请日：2012-08-03
申请人： Bon Woo Hwang , Kap Kee Kim , Seung-Uk Yoon , Bonki Koo , Ji Hyung Lee
发明人： Bon Woo Hwang , Kap Kee Kim , Seung-Uk Yoon , Bonki Koo , Ji Hyung Lee
IPC分类号： H04N13/00 , H04N13/02 , G06K9/00 , G06T17/00
CPC分类号： G06K9/00275 , G06K9/00993 , G06T17/00
摘要： A system for managing face data includes a global face capturing unit configured to capture a global face image; and a global face data generation unit configured to obtain shape information and texture information of global face data, and generate the global face data. Further, the system includes a local face capturing unit configured to capture a plurality of local face images; and a global face posture extraction unit configured to estimate a position and a direction of the face of a captured user. Furthermore, the system includes a local capturing device posture extraction unit configured to extract posture information of the local face capturing unit; and a local face data generation unit configured to generate texture information and shape information, and generate local face data.
摘要翻译：一种用于管理面部数据的系统包括被配置为捕获全局人脸图像的全局人脸捕获单元; 以及全局人脸数据生成部，被配置为获得全局面部数据的形状信息和纹理信息，并生成全局面部数据。此外，该系统包括被配置为捕获多个局部脸部图像的局部脸部捕获单元; 以及全局面部姿势提取单元，被配置为估计所捕获的用户的脸部的位置和方向。此外，该系统包括：本地捕获装置姿势提取单元，被配置为提取局部面部拍摄单元的姿势信息; 以及局部面部数据生成部，其生成纹理信息和形状信息，生成局部面部数据。

7. 发明申请

US20110234763A1 APPARATUS AND METHOD FOR TRANSMITTING/RECEIVING MULTI-VIEW STEREOSCOPIC VIDEO 审中-公开
标题翻译：用于发送/接收多视点立体视频的装置和方法
公开(公告)号：US20110234763A1
公开(公告)日：2011-09-29
申请号：US12909518
申请日：2010-10-21
申请人： Bon-Woo HWANG , Kap-Kee KIM , Bonki KOO
发明人： Bon-Woo HWANG , Kap-Kee KIM , Bonki KOO
IPC分类号： H04N13/02
CPC分类号： H04N21/2365 , H04N13/194 , H04N13/398 , H04N21/21805
摘要： An apparatus for transmitting a multi-view stereoscopic video includes: a control unit configured to receive a group of stereoscopic images taken by a plurality of stereoscopic imaging devices; a generation unit configured to select at least one stereoscopic frame from stereoscopic frames of the received group of stereoscopic images, arrange the selected stereoscopic frames successively, and generate a multi-view stereoscopic video; an encoding unit configured to encode the generated multi-view stereoscopic video; and a transmission unit configured to transmit the encoded multi-view stereoscopic video through a transmission network.
摘要翻译：一种用于发送多视点立体视频的设备包括：控制单元，被配置为接收由多个立体成像设备拍摄的一组立体图像; 生成单元，被配置为从所接收的立体图像组的立体帧中选择至少一个立体帧，连续排列所选立体帧，并生成多视点立体视频; 编码单元，被配置为对所生成的多视角立体视频进行编码; 以及发送单元，被配置为通过传输网络发送经编码的多视点立体视频。

8. 发明申请

US20110128286A1 IMAGE RESTORATION APPARATUS AND METHOD THEREOF 审中-公开
标题翻译：图像恢复装置及其方法
公开(公告)号：US20110128286A1
公开(公告)日：2011-06-02
申请号：US12695319
申请日：2010-01-28
申请人： Ji Young PARK , Bonki Koo
发明人： Ji Young PARK , Bonki Koo
IPC分类号： G06T17/00
CPC分类号： G06T17/00 , G06T7/564 , G06T2200/28 , G06T2207/30196 , G06T2210/52
摘要： An image restoration apparatus includes: a control processor unit for separating foreground and background from a loaded input image to transmit each of the separated foreground and background images as a three-dimensional (3D) texture; and a graphic processor unit for generating a visual hull of voxel units corresponding to the transmitted 3D texture, transforming the generated visual hull into mesh units, performing data alignment and pixel transform, determining a screen display value to perform rendering using the determined screen display value.
摘要翻译：图像恢复装置包括：控制处理器单元，用于从加载的输入图像分离前景和背景，以将分离的前景和背景图像中的每一个作为三维（3D）纹理; 以及图形处理器单元，用于生成对应于所发送的3D纹理的体元单元的视觉外壳，将所生成的视觉外观变换为网格单元，执行数据对齐和像素变换，使用所确定的屏幕显示值确定屏幕显示值以执行呈现。

9. 发明授权

US09076219B2 Space segmentation method for 3D point clouds 有权
标题翻译： 3D点云的空间分割方法
公开(公告)号：US09076219B2
公开(公告)日：2015-07-07
申请号：US13601851
申请日：2012-08-31
申请人： Youngmi Cha , Chang Woo Chu , Il Kyu Park , Ji Hyung Lee , Bonki Koo
发明人： Youngmi Cha , Chang Woo Chu , Il Kyu Park , Ji Hyung Lee , Bonki Koo
IPC分类号： G06K9/34 , G06T7/00 , G06K9/00
CPC分类号： G06T7/0081 , G06K9/00664 , G06K9/00697 , G06T7/11 , G06T7/136 , G06T7/194 , G06T2200/04 , G06T2207/10028 , G06T2207/20021
摘要： A space segmentation method for 3D point clouds is disclosed. A space segmentation method for 3D point clouds includes equally segmenting a space of the 3D point clouds into a plurality of grid cells; establishing a base plane corresponding to a ground part of the space of the 3D point clouds; accumulating points of all grid cells located perpendicular to the base plane in a grid cell of the base plane; and segmenting the grid cell in which the points are accumulated into an object part and a ground part according to the number of accumulated points.
摘要翻译：公开了一种用于3D点云的空间分割方法。用于3D点云的空间分割方法包括将3D点云的空间均匀分割成多个网格单元; 建立对应于3D点云的空间的地面部分的基础平面; 在基本平面的网格单元中积累垂直于基础平面的所有网格单元的点; 并且根据累积点的数量将点累积的网格单元分割成对象部分和接地部分。

10. 发明申请

US20130089259A1 SPACE SEGMENTATION METHOD FOR 3D POINT CLOUDS 有权
标题翻译：三维点云空间分割方法
公开(公告)号：US20130089259A1
公开(公告)日：2013-04-11
申请号：US13601851
申请日：2012-08-31
申请人： Youngmi CHA , Chang Woo Chu , Il Kyu Park , Ji Hyung Lee , Bonki Koo
发明人： Youngmi CHA , Chang Woo Chu , Il Kyu Park , Ji Hyung Lee , Bonki Koo
IPC分类号： G06K9/34
CPC分类号： G06T7/0081 , G06K9/00664 , G06K9/00697 , G06T7/11 , G06T7/136 , G06T7/194 , G06T2200/04 , G06T2207/10028 , G06T2207/20021
摘要： A space segmentation method for 3D point clouds is disclosed. A space segmentation method for 3D point clouds includes equally segmenting a space of the 3D point clouds into a plurality of grid cells; establishing a base plane corresponding to a ground part of the space of the 3D point clouds; accumulating points of all grid cells located perpendicular to the base plane in a grid cell of the base plane; and segmenting the grid cell in which the points are accumulated into an object part and a ground part according to the number of accumulated points.
摘要翻译：公开了一种用于3D点云的空间分割方法。用于3D点云的空间分割方法包括将3D点云的空间均匀分割成多个网格单元; 建立对应于3D点云的空间的地面部分的基础平面; 在基本平面的网格单元中积累垂直于基础平面的所有网格单元的点; 并且根据累积点的数量将点累积的网格单元分割成对象部分和接地部分。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式