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

US20120263437A1 HUMAN INTERACTION TRAJECTORY-BASED SYSTEM 有权
标题翻译：人际交往路线系统
公开(公告)号：US20120263437A1
公开(公告)日：2012-10-18
申请号：US13516228
申请日：2010-12-10
申请人： Jesus Barcons-Palau , Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
发明人： Jesus Barcons-Palau , Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
IPC分类号： H04N9/80
CPC分类号： G06K9/00711 , G06K9/00335 , G06K9/00724 , G06K9/033 , G06T7/246 , G06T2207/10016 , G06T2207/30228 , G06T2207/30241
摘要： A method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence at incorporates human interaction through a user interface. The method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, eliminating incorrect trajectories through use of the interface and processing images in said video sequence responsive to the evaluating and eliminating steps.
摘要翻译：一种用于使用基于轨迹的技术来检测视频序列中的移动对象的方法和相关联的装置，其通过用户界面并入人类交互。该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量的列表，识别跨多个帧的候选轨迹，评估候选轨迹以确定所选择的轨迹通过使用界面消除不正确的轨迹，并响应于评估和消除步骤来处理所述视频序列中的图像。

2. 发明授权

US09118912B2 Object-aware video encoding strategies 有权
标题翻译：对象感知视频编码策略
公开(公告)号：US09118912B2
公开(公告)日：2015-08-25
申请号：US13508562
申请日：2010-12-08
申请人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang , Jesus Barcons-Palau
发明人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang , Jesus Barcons-Palau
IPC分类号： H04N7/26 , H04N19/103 , H04N19/172 , H04N19/115 , H04N19/14 , H04N19/154 , H04N19/20 , H04N19/176 , H04N19/147 , H04N19/46 , H04N19/124 , H04N19/137 , H04N19/167 , H04N19/85 , H04N19/177
CPC分类号： H04N19/103 , H04N19/115 , H04N19/124 , H04N19/137 , H04N19/14 , H04N19/147 , H04N19/154 , H04N19/167 , H04N19/172 , H04N19/176 , H04N19/177 , H04N19/20 , H04N19/46 , H04N19/85
摘要： A method of object-aware video coding is provided that comprises the steps of: receiving a video sequence having a plurality of frames; selecting at least two frames; determing total area of at least one object of interest in each of the at least two frames; comparing the total area to a threshold area; classifying each of the at least two frames as being a low object weighted frame or a high object weighted frame, low object weighted frames being frames having the total area exceeding the threshold area and high object weighted frames being frame having the total area not exceeding the threshold area; and encoding each low object weighted frame according to one encoding mode and encoding each high object weighted frame according to a different encoding mode.
摘要翻译：提供了一种对象感知视频编码方法，包括以下步骤：接收具有多个帧的视频序列; 选择至少两个帧; 确定所述至少两个帧中的每一个中的至少一个感兴趣对象的总面积; 将总面积与阈值区域进行比较; 将至少两个帧中的每一个分类为低对象加权帧或高对象加权帧，低对象加权帧是具有超过阈值区域的总区域的帧，并且高对象加权帧是具有不超过阈值区域的总区域的帧阈值面积并根据一个编码模式对每个低对象加权帧进行编码，并根据不同的编码模式对每个高对象加权帧进行编码。

3. 发明授权

US08977109B2 Human interaction trajectory-based system 有权
标题翻译：人类基于互动轨迹的系统
公开(公告)号：US08977109B2
公开(公告)日：2015-03-10
申请号：US13516228
申请日：2010-12-10
申请人： Jesus Barcons-Palau , Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
发明人： Jesus Barcons-Palau , Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
IPC分类号： G11B27/00 , H04N5/93 , G06K9/00 , G06K9/03 , G06T7/20
CPC分类号： G06K9/00711 , G06K9/00335 , G06K9/00724 , G06K9/033 , G06T7/246 , G06T2207/10016 , G06T2207/30228 , G06T2207/30241
摘要： A method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence at incorporates human interaction through a user interface. The method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, eliminating incorrect trajectories through use of the interface and processing images in said video sequence responsive to the evaluating and eliminating steps.
摘要翻译：一种用于使用基于轨迹的技术来检测视频序列中的移动对象的方法和相关联的装置，其通过用户界面并入人类交互。该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量的列表，识别跨多个帧的候选轨迹，评估候选轨迹以确定所选择的轨迹通过使用界面消除不正确的轨迹，并响应于评估和消除步骤来处理所述视频序列中的图像。

4. 发明申请

US20120224629A1 OBJECT-AWARE VIDEO ENCODING STRATEGIES 有权
标题翻译：对象识别视频编码策略
公开(公告)号：US20120224629A1
公开(公告)日：2012-09-06
申请号：US13508562
申请日：2010-12-08
申请人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang , Jesus Barcons-Palau
发明人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang , Jesus Barcons-Palau
IPC分类号： H04N7/26
CPC分类号： H04N19/103 , H04N19/115 , H04N19/124 , H04N19/137 , H04N19/14 , H04N19/147 , H04N19/154 , H04N19/167 , H04N19/172 , H04N19/176 , H04N19/177 , H04N19/20 , H04N19/46 , H04N19/85
摘要： A method of object-aware video coding is provided that comprises the steps of: receiving a video sequence having a plurality of frames; selecting at least two frames; determing total area of at least one object of interest in each of the at least two frames; comparing the total area to a threshold area; classifying each of the at least two frames as being a low object weighted frame or a high object weighted frame, low object weighted frames being frames having the total area exceeding the threshold area and high object weighted frames being frame having the total area not exceeding the threshold area; and encoding each low object weighted frame according to one encoding mode and encoding each high object weighted frame according to a different encoding mode.
摘要翻译：提供了一种对象感知视频编码方法，包括以下步骤：接收具有多个帧的视频序列; 选择至少两个帧; 确定所述至少两个帧中的每一个中的至少一个感兴趣对象的总面积; 将总面积与阈值区域进行比较; 将至少两个帧中的每一个分类为低对象加权帧或高对象加权帧，低对象加权帧是具有超过阈值区域的总区域的帧，并且高对象加权帧是具有不超过阈值区域的总区域的帧阈值面积并根据一个编码模式对每个低对象加权帧进行编码，并根据不同的编码模式对每个高对象加权帧进行编码。

5. 发明申请

US20120114184A1 TRAJECTORY-BASED METHOD TO DETECT AND ENHANCE A MOVING OBJECT IN A VIDEO SEQUENCE 审中-公开
标题翻译：基于TRAJECTORY的方法来检测和增强视频序列中的移动对象
公开(公告)号：US20120114184A1
公开(公告)日：2012-05-10
申请号：US13386145
申请日：2010-07-20
申请人： Jesus Barcons-Palau , Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
发明人： Jesus Barcons-Palau , Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
IPC分类号： G06K9/68
CPC分类号： G06K9/00711 , G06T7/246 , G06T2207/10016 , G06T2207/30224 , G06T2207/30241
摘要： The present invention concerns a method and associated apparatus for using a trajectory-based technique to detect a moving object in a video sequence, such as the ball in a soccer game. In one embodiment, the method comprises steps of identifying and evaluating sets of connected components in a video frame, filtering the list of connected components by comparing features of the connected components to predetermined criteria, identifying candidate trajectories across multiple frames, evaluating the candidate trajectories to determine a selected trajectory, and processing images in the video sequence based at least in part upon the selected trajectory.
摘要翻译：本发明涉及一种使用基于轨迹的技术来检测诸如足球游戏中的球的视频序列中的移动物体的方法和相关装置。在一个实施例中，该方法包括以下步骤：识别和评估视频帧中的连接分量集合，通过将所连接分量的特征与预定标准进行比较来过滤所连接分量列表，识别跨多个帧的候选轨迹，评估候选轨迹确定所选择的轨迹，以及至少部分地基于所选择的轨迹来处理视频序列中的图像。

6. 发明授权

US09602814B2 Methods and apparatus for sampling-based super resolution video encoding and decoding 有权
公开(公告)号：US09602814B2
公开(公告)日：2017-03-21
申请号：US13574428
申请日：2011-01-20
申请人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
发明人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
IPC分类号： H04N7/12 , H04N11/02 , H04N11/04 , H04N19/577 , H04N19/51 , H04N19/527 , H04N19/119 , H04N19/132 , H04N19/12 , H04N19/59 , H04N19/137 , H04N19/172 , H04N19/20 , H04N19/46 , H04N19/33
CPC分类号： H04N19/577 , H04N19/119 , H04N19/12 , H04N19/132 , H04N19/137 , H04N19/172 , H04N19/20 , H04N19/33 , H04N19/46 , H04N19/527 , H04N19/537 , H04N19/573 , H04N19/59
摘要： Methods and apparatus are provided for sampling-based super resolution video encoding and decoding. The encoding method receives high resolution pictures and generates low resolution pictures and metadata there from, the metadata for guiding post-decoding post-processing of the low resolution pictures and the metadata; and then encodes the low resolution pictures and the metadata using at least one encoder. The corresponding decoding method receives a bitstream and decodes low resolution pictures and metadata there from using a decoder; and then reconstructs high resolution pictures respectively corresponding to the low resolution pictures using the low resolution pictures and the metadata.

7. 发明授权

US09420291B2 Methods and apparatus for reducing vector quantization error through patch shifting 有权
标题翻译：减少矢量量化误差的方法和装置
公开(公告)号：US09420291B2
公开(公告)日：2016-08-16
申请号：US13576848
申请日：2011-02-01
申请人： Dong-Qing Zhang , Joan Llach , Sitaram Bhagavathy
发明人： Dong-Qing Zhang , Joan Llach , Sitaram Bhagavathy
IPC分类号： H04N7/12 , H04N19/105 , G06T1/00 , H04N19/139 , H04N19/593 , H04N19/14 , H04N19/94 , H04N19/59
CPC分类号： H04N19/105 , G06T1/00 , H04N19/139 , H04N19/14 , H04N19/59 , H04N19/593 , H04N19/94
摘要： Methods and apparatus are provided for reducing vector quantization error through patch shifting. A method generates, from an input video sequence, one of more high resolution replacement patches, the one or more high resolution replacement patches for replacing one or more low resolution patches during a reconstruction of the input video sequence. This generating step generates the one or more high resolution replacement patches using data corresponding to a patch spatial shifting process, the patch spatial shifting process for reducing jittery artifacts caused by a motion-induced vector quantization error in the one or more high resolution replacement patches, the data for at least deriving a patch size of the one or more high resolution replacement patches such that the one or more high resolution replacement patches are generated to have the patch size greater than a patch size of the one or more low resolution patches in order to be suitable for use in the patch spatial shifting process.
摘要翻译：提供了通过补片移位来减少矢量量化误差的方法和装置。一种方法从输入视频序列生成更多高分辨率替换贴片之一，该一个或多个高分辨率替换贴片用于在重建输入视频序列期间替换一个或多个低分辨率贴片。该生成步骤使用与贴片空间移位处理对应的数据来生成一个或多个高分辨率替换贴片，该贴片空间移位处理用于减少由一个或多个高分辨率替换贴片中的运动引起的矢量量化误差引起的抖动伪像，所述数据用于至少导出所述一个或多个高分辨率替换补丁的补丁大小，使得生成所述一个或多个高分辨率替换补丁以使所述补丁大小大于所述一个或多个低分辨率补丁的补丁大小顺序适用于贴片空间位移过程。

8. 发明申请

US20120288015A1 DATA PRUNING FOR VIDEO COMPRESSION USING EXAMPLE-BASED SUPER-RESOLUTION 有权
标题翻译：使用基于示例的超分辨率进行视频压缩的数据预处理
公开(公告)号：US20120288015A1
公开(公告)日：2012-11-15
申请号：US13522024
申请日：2011-01-21
申请人： Dong-Qing Zhang , Sitaram Bhagavathy , Joan Llach
发明人： Dong-Qing Zhang , Sitaram Bhagavathy , Joan Llach
IPC分类号： H04N7/12
CPC分类号： H04N19/105 , H04N7/0125 , H04N7/54 , H04N19/139 , H04N19/14 , H04N19/146 , H04N19/149 , H04N19/152 , H04N19/154 , H04N19/46 , H04N19/59 , H04N19/94
摘要： Methods and apparatuses for data pruning for video compression using example-based super resolution are provided. A method and apparatus for encoding is provided in which patches of video are extracted from input video, grouped together using a clustering method, and representative patches are packed into patch frames. The original video is downsized and sent either along with, or in addition to, the patch frames. At a decoder, the method and apparatus provided extract patches from the patch frames and create a patch library. The regular video frames are upsized and the low resolution patches are replaced by patches from the patch library by searching the library using the patches in the decoded regular frames as keywords. If there are no appropriate patches, no replacement is made. A post processing procedure is used to enhance the spatiotemporal smoothness of the recovered video.
摘要翻译：提供了使用基于示例的超分辨率进行视频压缩的数据剪枝的方法和装置。提供了一种用于编码的方法和装置，其中使用聚类方法从输入视频中提取视频片段，将其分组在一起，并将代表性的片段打包到片段中。原始视频被缩小，并且或者与补丁帧一起发送。在解码器中，所提供的方法和装置从补丁帧提取补丁并创建补丁库。常规视频帧大小，低分辨率补丁由补丁库中的补丁替换，通过使用解码的常规帧中的补丁作为关键字搜索库。如果没有适当的补丁，则不进行更换。后处理程序用于增强恢复的视频的时空平滑度。

9. 发明申请

US20120294369A1 METHODS AND APPARATUS FOR SAMPLING-BASED SUPER RESOLUTION VIDEO ENCODING AND DECODING 有权
标题翻译：基于采样的超分辨率视频编码和解码的方法和装置
公开(公告)号：US20120294369A1
公开(公告)日：2012-11-22
申请号：US13574428
申请日：2011-01-20
申请人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
发明人： Sitaram Bhagavathy , Joan Llach , Dong-Qing Zhang
IPC分类号： H04N7/26 , H04N7/46 , H04N7/32
CPC分类号： H04N19/577 , H04N19/119 , H04N19/12 , H04N19/132 , H04N19/137 , H04N19/172 , H04N19/20 , H04N19/33 , H04N19/46 , H04N19/527 , H04N19/537 , H04N19/573 , H04N19/59
摘要： Methods and apparatus are provided for sampling-based super resolution video encoding and decoding. The encoding method receives high resolution pictures and generates low resolution pictures and metadata there from, the metadata for guiding post-decoding post-processing of the low resolution pictures and the metadata; and then encodes the low resolution pictures and the metadata using at least one encoder. The corresponding decoding method receives a bitstream and decodes low resolution pictures and metadata there from using a decoder; and then reconstructs high resolution pictures respectively corresponding to the low resolution pictures using the low resolution pictures and the metadata.
摘要翻译：提供了基于采样的超分辨率视频编码和解码的方法和装置。编码方法接收高分辨率图像，并从其中生成低分辨率图像和元数据，用于引导低分辨率图像的后解码后处理的元数据和元数据; 然后使用至少一个编码器对低分辨率图像和元数据进行编码。相应的解码方法接收比特流并且使用解码器解码低分辨率图像和元数据; 然后使用低分辨率图像和元数据重建分别对应于低分辨率图像的高分辨率图像。

10. 发明授权

US09813707B2 Data pruning for video compression using example-based super-resolution 有权
公开(公告)号：US09813707B2
公开(公告)日：2017-11-07
申请号：US13522024
申请日：2011-01-21
申请人： Dong-Qing Zhang , Sitaram Bhagavathy , Joan Llach
发明人： Dong-Qing Zhang , Sitaram Bhagavathy , Joan Llach
IPC分类号： H04N7/12 , H04N19/105 , H04N7/54 , H04N19/146 , H04N19/152 , H04N19/149 , H04N19/154 , H04N7/01 , H04N19/139 , H04N19/46 , H04N19/14 , H04N19/94 , H04N19/59
CPC分类号： H04N19/105 , H04N7/0125 , H04N7/54 , H04N19/139 , H04N19/14 , H04N19/146 , H04N19/149 , H04N19/152 , H04N19/154 , H04N19/46 , H04N19/59 , H04N19/94
摘要： Methods and apparatuses for data pruning for video compression using example-based super resolution are provided. A method and apparatus for encoding is provided in which patches of video are extracted from input video, grouped together using a clustering method, and representative patches are packed into patch frames. The original video is downsized and sent either along with, or in addition to, the patch frames. At a decoder, the method and apparatus provided extract patches from the patch frames and create a patch library. The regular video frames are upsized and the low resolution patches are replaced by patches from the patch library by searching the library using the patches in the decoded regular frames as keywords. If there are no appropriate patches, no replacement is made. A post processing procedure is used to enhance the spatiotemporal smoothness of the recovered video.

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