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

US20120007960A1 Video processing method for 3D display based on multi-cue process 有权
标题翻译：基于多线程过程的3D显示视频处理方法
公开(公告)号：US20120007960A1
公开(公告)日：2012-01-12
申请号：US13067465
申请日：2011-06-02
申请人： Ji Won Kim , Gengyu Ma , Haitao Wang , Xing Mei , Ji Yeun Kim , Yong Ju Jung
发明人： Ji Won Kim , Gengyu Ma , Haitao Wang , Xing Mei , Ji Yeun Kim , Yong Ju Jung
IPC分类号： H04N13/04
CPC分类号： H04N13/261 , G06K9/4671 , G11B27/28 , H04N5/147 , H04N2013/0074
摘要： A video processing method for a three-dimensional (3D) display is based on a multi-cue process. The method may include acquiring a cut boundary of a shot by performing a shot boundary detection with respect to each frame of an input video, computing a texture saliency with respect to each pixel of the input video, computing a motion saliency with respect to each pixel of the input video, computing an object saliency with respect to each pixel of the input video based on the acquired cut boundary of the shot, acquiring a universal saliency with respect to each pixel of the input video by combining the texture saliency, the motion saliency, and the object saliency, and smoothening the universal saliency of each pixel using a space-time technology.
摘要翻译：用于三维（3D）显示的视频处理方法基于多提示过程。该方法可以包括通过对输入视频的每个帧执行镜头边界检测来获取镜头的切割边界，计算相对于输入视频的每个像素的纹理显着性，计算相对于每个像素的运动显着性基于拍摄的所获取的切割边界，针对输入视频的每个像素计算对象的显着性，通过组合纹理显着性，运动显着性来获取关于输入视频的每个像素的通用显着性和物体的显着性，并利用时空技术平滑每个像素的普遍显着性。

2. 发明授权

US09148652B2 Video processing method for 3D display based on multi-cue process 有权
标题翻译：基于多线程过程的3D显示视频处理方法
公开(公告)号：US09148652B2
公开(公告)日：2015-09-29
申请号：US13067465
申请日：2011-06-02
申请人： Ji Won Kim , Gengyu Ma , Haitao Wang , Xing Mei , Ji Yeun Kim , Yong Ju Jung
发明人： Ji Won Kim , Gengyu Ma , Haitao Wang , Xing Mei , Ji Yeun Kim , Yong Ju Jung
IPC分类号： H04N9/80 , H04N13/02 , G06K9/46 , G11B27/28 , H04N5/14 , H04N13/00
CPC分类号： H04N13/261 , G06K9/4671 , G11B27/28 , H04N5/147 , H04N2013/0074
摘要： A video processing method for a three-dimensional (3D) display is based on a multi-cue process. The method may include acquiring a cut boundary of a shot by performing a shot boundary detection with respect to each frame of an input video, computing a texture saliency with respect to each pixel of the input video, computing a motion saliency with respect to each pixel of the input video, computing an object saliency with respect to each pixel of the input video based on the acquired cut boundary of the shot, acquiring a universal saliency with respect to each pixel of the input video by combining the texture saliency, the motion saliency, and the object saliency, and smoothening the universal saliency of each pixel using a space-time technology.
摘要翻译：用于三维（3D）显示的视频处理方法基于多提示过程。该方法可以包括通过对输入视频的每个帧执行镜头边界检测来获取镜头的切割边界，计算相对于输入视频的每个像素的纹理显着性，计算相对于每个像素的运动显着性基于拍摄的所获取的切割边界，针对输入视频的每个像素计算对象的显着性，通过组合纹理显着性，运动显着性来获取关于输入视频的每个像素的通用显着性和物体的显着性，并利用时空技术平滑每个像素的普遍显着性。

3. 发明申请

US20110298898A1 THREE DIMENSIONAL IMAGE GENERATING SYSTEM AND METHOD ACCOMODATING MULTI-VIEW IMAGING 审中-公开
标题翻译：三维图像生成系统和方法存储多视图成像
公开(公告)号：US20110298898A1
公开(公告)日：2011-12-08
申请号：US13100905
申请日：2011-05-04
申请人： Yong Ju Jung , Haitao Wang , Ji Won Kim , Gengyu Ma , Xing Mei , Du Sik Park
发明人： Yong Ju Jung , Haitao Wang , Ji Won Kim , Gengyu Ma , Xing Mei , Du Sik Park
IPC分类号： H04N13/02
CPC分类号： H04N13/25 , H04N13/239 , H04N13/271
摘要： Provided is a three-dimensional (3D) image generating system and method accommodating multi-view imaging. The 3D image generating system and method may generate corrected depth maps respectively corresponding to color images by merging disparity information associated with a disparity between color images and depth maps generated respectively from depth images.
摘要翻译：提供一种容纳多视点成像的三维（3D）图像生成系统和方法。 3D图像生成系统和方法可以通过合并与颜色图像和分别从深度图像生成的深度图之间的差异相关联的视差信息来生成分别对应于彩色图像的校正深度图。

4. 发明授权

US08553972B2 Apparatus, method and computer-readable medium generating depth map 有权
标题翻译：仪器，方法和计算机可读介质生成深度图
公开(公告)号：US08553972B2
公开(公告)日：2013-10-08
申请号：US12830822
申请日：2010-07-06
申请人： Ji Won Kim , Gangyu Ma , Haitao Wang , Xiying Wang , Ji Yeun Kim , Yong Ju Jung
发明人： Ji Won Kim , Gangyu Ma , Haitao Wang , Xiying Wang , Ji Yeun Kim , Yong Ju Jung
IPC分类号： G06K9/00 , G06K9/32 , H04N13/00
CPC分类号： G06T7/50 , G06T2207/10016 , G06T2207/20221 , G06T2207/30196
摘要： Disclosed are an apparatus, a method and a computer-readable medium automatically generating a depth map corresponding to each two-dimensional (2D) image in a video. The apparatus includes an image acquiring unit to acquire a plurality of 2D images that are temporally consecutive in an input video, a saliency map generator to generate at least one saliency map corresponding to a current 2D image among the plurality of 2D images based on a Human Visual Perception (HVP) model, a saliency-based depth map generator, a three-dimensional (3D) structure matching unit to calculate matching scores between the current 2D image and a plurality of 3D typical structures that are stored in advance, and to determine a 3D typical structure having a highest matching score among the plurality of 3D typical structures to be a 3D structure of the current 2D image, a matching-based depth map generator; a combined depth map generator to combine the saliency-based depth map and the matching-based depth map and to generate a combined depth map, and a spatial and temporal smoothing unit to spatially and temporally smooth the combined depth map.
摘要翻译：公开了一种自动生成与视频中的每个二维（2D）图像相对应的深度图的装置，方法和计算机可读介质。该装置包括：图像获取单元，用于获取在输入视频中在时间上连续的多个2D图像，显着图生成器，用于基于人类生成与多个2D图像中的当前2D图像相对应的至少一个显着图视觉感知（HVP）模型，基于显着性的深度图生成器，三维（3D）结构匹配单元，用于计算当前2D图像与预先存储的多个3D典型结构之间的匹配分数，并且确定在所述多个3D典型结构中具有最高匹配分数以作为当前2D图像的3D结构的3D典型结构，基于匹配的深度图生成器; 组合深度图生成器，用于组合基于显着性的深度图和基于匹配的深度图并生成组合深度图，以及空间和时间平滑单元，以空间和时间平滑组合的深度图。

5. 发明申请

US20110026808A1 APPARATUS, METHOD AND COMPUTER-READABLE MEDIUM GENERATING DEPTH MAP 有权
标题翻译：装置，方法和计算机可读介质生成深度图
公开(公告)号：US20110026808A1
公开(公告)日：2011-02-03
申请号：US12830822
申请日：2010-07-06
申请人： Ji Won KIM , Gangyu Ma , Haitao Wang , Xiying Wang , Ji Yeun Kim , Yong Ju Jung
发明人： Ji Won KIM , Gangyu Ma , Haitao Wang , Xiying Wang , Ji Yeun Kim , Yong Ju Jung
IPC分类号： G06T7/00
CPC分类号： G06T7/50 , G06T2207/10016 , G06T2207/20221 , G06T2207/30196
摘要： Disclosed are an apparatus, a method and a computer-readable medium automatically generating a depth map corresponding to each two-dimensional (2D) image in a video. The apparatus includes an image acquiring unit to acquire a plurality of 2D images that are temporally consecutive in an input video, a saliency map generator to generate at least one saliency map corresponding to a current 2D image among the plurality of 2D images based on a Human Visual Perception (HVP) model, a saliency-based depth map generator, a three-dimensional (3D) structure matching unit to calculate matching scores between the current 2D image and a plurality of 3D typical structures that are stored in advance, and to determine a 3D typical structure having a highest matching score among the plurality of 3D typical structures to be a 3D structure of the current 2D image, a matching-based depth map generator; a combined depth map generator to combine the saliency-based depth map and the matching-based depth map and to generate a combined depth map, and a spatial and temporal smoothing unit to spatially and temporally smooth the combined depth map.
摘要翻译：公开了一种自动生成与视频中的每个二维（2D）图像相对应的深度图的装置，方法和计算机可读介质。该装置包括：图像获取单元，用于获取在输入视频中在时间上连续的多个2D图像，显着图生成器，用于基于人类生成与多个2D图像中的当前2D图像相对应的至少一个显着图视觉感知（HVP）模型，基于显着性的深度图生成器，三维（3D）结构匹配单元，用于计算当前2D图像与预先存储的多个3D典型结构之间的匹配分数，并且确定在所述多个3D典型结构中具有最高匹配分数以作为当前2D图像的3D结构的3D典型结构，基于匹配的深度图生成器; 组合深度图生成器，用于组合基于显着性的深度图和基于匹配的深度图并生成组合深度图，以及空间和时间平滑单元，以空间和时间平滑组合的深度图。

6. 发明申请

US20110268422A1 Method, system, and medium for providing broadcasting service using home server and mobile phone 审中-公开
标题翻译：使用家庭服务器和手机提供广播服务的方法，系统和媒介
公开(公告)号：US20110268422A1
公开(公告)日：2011-11-03
申请号：US13067948
申请日：2011-07-08
申请人： Jin Guk Jeong , Sang Kyun Kim , Yong Ju Jung , Eul Hyeon Hwang , Doo Sun Hwang , Ji Yeun Kim , San Ko , Cheol Kon Jung , Yong Lee
发明人： Jin Guk Jeong , Sang Kyun Kim , Yong Ju Jung , Eul Hyeon Hwang , Doo Sun Hwang , Ji Yeun Kim , San Ko , Cheol Kon Jung , Yong Lee
IPC分类号： H04N5/915
CPC分类号： H04N9/8042 , H04N5/775 , H04N9/8205 , H04N9/8227 , H04N21/4126 , H04N21/42204 , H04N21/43615 , H04N21/43637 , H04N21/4667
摘要： A method, system, and medium of providing various types of broadcast services such as a record, a summary, a navigation and a real-time event service with respect to a broadcast content, utilizing a home server, according to a user's request. A broadcast service providing method includes: storing broadcast summary data, navigation data and real-time event data which is generated by analyzing received broadcast data according to a broadcast record request from a user's portable device, in a database; and providing the user's portable device with a streaming service with respect to the stored broadcast summary data, the navigation data and the real-time event data, according to a summary selection request from the user's portable device.
摘要翻译：根据用户的要求，使用家庭服务器，提供关于广播内容的记录，摘要，导航和实时事件服务的各种类型的广播服务的方法，系统和媒体。广播服务提供方法包括：根据来自用户的便携式设备的广播记录请求，在数据库中存储广播摘要数据，导航数据和实时事件数据，该数据是通过分析接收到的广播数据而生成的; 以及根据来自用户的便携式设备的摘要选择请求，向用户的便携式设备提供关于存储的广播摘要数据，导航数据和实时事件数据的流服务。

7. 发明申请

US20090123021A1 System, method, and medium indexing photos semantically 审中-公开
标题翻译：系统，方法和中等索引照片语义
公开(公告)号：US20090123021A1
公开(公告)日：2009-05-14
申请号：US11698203
申请日：2007-01-26
申请人： Yong Ju Jung , Jae Won Lee , Ji Yeun Kim , Sang Kyun Kim , Ick Sang Han
发明人： Yong Ju Jung , Jae Won Lee , Ji Yeun Kim , Sang Kyun Kim , Ick Sang Han
IPC分类号： G06K9/00 , G06F7/00 , G06F17/00
CPC分类号： G11B27/28 , H04N5/77 , H04N9/8205
摘要： A system, method and medium indexing a plurality of photos semantically based on a user's annotation. The method includes analyzing the user's annotation and extracting a shared index from the user's annotation, detecting a situation change in the plurality of photos, and indexing the plurality of photos according to the situation change based on the shared index.
摘要翻译：一种系统，方法和媒体，用于基于用户的注释来语义地索引多个照片。该方法包括分析用户的注释并从用户的注释中提取共享的索引，检测多张照片中的情况变化，以及根据共享索引的情况变化对多张照片进行索引。

8. 发明申请

US20080212932A1 SYSTEM FOR MANAGING VIDEO BASED ON TOPIC AND METHOD USING THE SAME AND METHOD FOR SEARCHING VIDEO BASED ON TOPIC 审中-公开
标题翻译：基于主题管理视频的系统及使用该方法的方法和基于主题搜索视频的方法
公开(公告)号：US20080212932A1
公开(公告)日：2008-09-04
申请号：US11769355
申请日：2007-06-27
申请人： Yong Lee , Doo Sun Hwang , Ji Yeun Kim , Jeong Mi Cho , Sang Kyun Kim , Yong Ju Jung
发明人： Yong Lee , Doo Sun Hwang , Ji Yeun Kim , Jeong Mi Cho , Sang Kyun Kim , Yong Ju Jung
IPC分类号： H04N5/91
CPC分类号： H04N5/76 , G06F16/7844 , G11B27/11 , G11B27/34
摘要： A video management method and system based on a topic, and a video search method based on a topic. The video management system includes: a video topic management unit extracting a topic from information associated with a video, storing the extracted topic, and monitoring the video associated with the stored topic; a video storage management unit storing the video and information associated with the video, and managing a storage space based on the topic which is stored in the video topic management unit; and a topic video management unit generating a topic video of the monitored video when the video associated with the stored topic is monitored, and providing a search function and a navigation function of the video which is stored in the video storage management unit.
摘要翻译：基于主题的视频管理方法和系统，以及基于主题的视频搜索方法。视频管理系统包括：视频主题管理单元，从与视频关联的信息中提取主题，存储所提取的主题，以及监视与所存储的主题相关联的视频; 视频存储管理单元，存储与视频相关联的视频和信息，并且基于存储在视频主题管理单元中的主题来管理存储空间; 以及主题视频管理单元，当与所存储的主题相关联的视频被监视时，生成被监视视频的主题视频，并且提供存储在视频存储管理单元中的视频的搜索功能和导航功能。

9. 发明申请

US20080013940A1 Method, system, and medium for classifying category of photo 审中-公开
标题翻译：方法，系统和介质，用于分类照片类别
公开(公告)号：US20080013940A1
公开(公告)日：2008-01-17
申请号：US11605281
申请日：2006-11-29
申请人： Yong Ju Jung , Sang Kyun Kim , Ji Yeun Kim
发明人： Yong Ju Jung , Sang Kyun Kim , Ji Yeun Kim
IPC分类号： G03B17/00
CPC分类号： G03D15/001
摘要： A photo category classification method including dividing a region of a photo based on content of the photo and extracting a visual feature from the segmented region of the photo, modeling at least one local semantic concept included in the photo according to the extracted visual feature, acquiring a posterior probability value from confidence values acquired from the modeling of the at least one local semantic concept by normalization using regression analysis, modeling a global semantic concept included in the photo by using the posterior probability value of the at least one local semantic concept; and removing classification noise from a confidence value acquired from the modeling the global semantic concept.
摘要翻译：一种照片类别分类方法，包括基于照片的内容划分照片的区域并从照片的分割区域提取视觉特征，根据所提取的视觉特征对包括在照片中的至少一个局部语义概念进行建模，获取通过使用回归分析的归一化从所述至少一个局部语义概念的建模获得的置信度值的后验概率值，通过使用所述至少一个局部语义概念的后验概率值来对包含在所述照片中的全局语义概念进行建模; 以及从对全局语义概念的建模获得的置信度值中去除分类噪声。

10. 发明授权

US08000578B2 Method, system, and medium for providing broadcasting service using home server and mobile phone 有权
公开(公告)号：US08000578B2
公开(公告)日：2011-08-16
申请号：US11651565
申请日：2007-01-10
申请人： Jin Guk Jeong , Sang Kyun Kim , Yong Ju Jung , Eui Hyeon Hwang , Doo Sun Hwang , Ji Yeun Kim , San Ko , Cheol Kon Jung , Yong Lee
发明人： Jin Guk Jeong , Sang Kyun Kim , Yong Ju Jung , Eui Hyeon Hwang , Doo Sun Hwang , Ji Yeun Kim , San Ko , Cheol Kon Jung , Yong Lee
IPC分类号： H04N5/91
CPC分类号： H04N9/8042 , H04N5/775 , H04N9/8205 , H04N9/8227 , H04N21/4126 , H04N21/42204 , H04N21/43615 , H04N21/43637 , H04N21/4667
摘要： A method, system, and medium of providing various types of broadcast services such as a record, a summary, a navigation and a real-time event service with respect to a broadcast content, utilizing a home server, according to a user's request. A broadcast service providing method includes: storing broadcast summary data, navigation data and real-time event data which is generated by analyzing received broadcast data according to a broadcast record request from a user's portable device, in a database; and providing the user's portable device with a streaming service with respect to the stored broadcast summary data, the navigation data and the real-time event data, according to a summary selection request from the user's portable device.

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