-
公开(公告)号：US09191705B1
公开(公告)日：2015-11-17
申请号：US13875155
申请日：2013-05-01
Applicant: Google Inc.
Inventor： Sang-Uok Kum , Meng Wang
IPC: H04H60/32 , H04N21/442 , H04N21/2743
CPC classification number: H04N21/442 , H04N21/2343 , H04N21/2743
Abstract: A system and method for managing media quality is provided. The system includes a data store with a computer readable medium storing a program of instructions for the managing of media quality; a processor that executes the program of instructions; a media analysis unit to receive transcoded media from a media store, and to detect for a phenomena affecting the transcoded media; a media quality manager, in response to the media analysis unit detection of the phenomena, determining a parameter for transcoding media; and a re-transcode unit to re-transcode the transcoded media based on the parameter.
Abstract translation: 提供了一种用于管理媒体质量的系统和方法。 该系统包括具有存储用于管理媒体质量的指令程序的计算机可读介质的数据存储器; 执行指令程序的处理器; 媒体分析单元，用于从媒体存储器接收代码转换的媒体，并且检测影响转码媒体的现象; 媒体质量管理者，响应媒体分析单元检测现象，确定用于转码媒体的参数; 以及重新转码单元，用于基于参数重新转码转码的媒体。
-
公开(公告)号：US08966179B1
公开(公告)日：2015-02-24
申请号：US13758970
申请日：2013-02-04
Applicant: Google Inc.
Inventor： Meng Wang , Arnaud Claude Weber
CPC classification number: G06F17/30876
Abstract: Computer-implemented methods for temporarily storing history of a web browsing session are provided. In one aspect, the method includes receiving a request to temporarily store session information for a web browsing session comprising at least one request to view a web page. The method also includes compressing data for the session information associated with the web browsing session, and storing the compressed data for the session information associated with the web browsing session only in a volatile memory. The compressed data for the session information stored in the volatile memory is lost when power to the volatile memory is off. A reference to the compressed data for the session information in the volatile memory is removed when the web browsing session is terminated.
Abstract translation: 提供了用于临时存储web浏览会话的历史的计算机实现的方法。 一方面，该方法包括接收临时存储用于包括至少一个查看网页的请求的网页浏览会话的会话信息的请求。 该方法还包括压缩与网络浏览会话相关联的会话信息的数据，并且将用于与web浏览会话相关联的会话信息的压缩数据仅存储在易失性存储器中。 当易失性存储器的电源关闭时，存储在易失性存储器中的会话信息的压缩数据丢失。 当Web浏览会话终止时，删除对易失性存储器中的会话信息的压缩数据的引用。
-
公开(公告)号：US08953874B2
公开(公告)日：2015-02-10
申请号：US14170335
申请日：2014-01-31
Applicant: Google Inc.
Inventor： Chen Wu , Debargha Mukherjee , Meng Wang
CPC classification number: G06K9/00201 , G06K9/00208 , G06T7/593 , G06T2207/10021 , G06T2207/10024 , G06T2207/20228
Abstract: An image converter compiles three-dimensional content into a data store, identifies a number of stereo image pairs from the three-dimensional content, computes a depth map for each of the stereo image pairs from the three-dimensional content, and partitions the stereo image pairs in the data store into multiple categories. The image converter determines a depth cue for each of the categories based on the depth map for each of the stereo image pairs in each category. The image converter computes a depth map for a category associated with a two-dimensional input image based on the determined depth cue and renders a three-dimensional output image from the two-dimensional input image using the depth map for the category.
Abstract translation: 图像转换器将三维内容编译成数据存储，从三维内容识别多个立体图像对，从三维内容计算每个立体图像对的深度图，并分割立体图像 将数据存储分成多个类别。 图像转换器基于每个类别中的每个立体图像对的深度图来确定每个类别的深度提示。 图像转换器基于所确定的深度提示来计算与二维输入图像相关联的类别的深度图，并使用该类别的深度图从二维输入图像呈现三维输出图像。
-
公开(公告)号：US20140147033A1
公开(公告)日：2014-05-29
申请号：US14170335
申请日：2014-01-31
Applicant: Google Inc.
Inventor： Chen Wu , Debargha Mukherjee , Meng Wang
IPC: G06K9/00
CPC classification number: G06K9/00201 , G06K9/00208 , G06T7/593 , G06T2207/10021 , G06T2207/10024 , G06T2207/20228
Abstract: An image converter compiles three-dimensional content into a data store, identifies a number of stereo image pairs from the three-dimensional content, computes a depth map for each of the stereo image pairs from the three-dimensional content, and partitions the stereo image pairs in the data store into multiple categories. The image converter determines a depth cue for each of the categories based on the depth map for each of the stereo image pairs in each category. The image converter computes a depth map for a category associated with a two-dimensional input image based on the determined depth cue and renders a three-dimensional output image from the two-dimensional input image using the depth map for the category.
Abstract translation: 图像转换器将三维内容编译成数据存储，从三维内容识别多个立体图像对，从三维内容计算每个立体图像对的深度图，并分割立体图像 将数据存储分成多个类别。 图像转换器基于每个类别中的每个立体图像对的深度图来确定每个类别的深度提示。 图像转换器基于所确定的深度提示来计算与二维输入图像相关联的类别的深度图，并使用该类别的深度图从二维输入图像呈现三维输出图像。
-
5.发明申请公开(公告)号：US20150304630A1
公开(公告)日：2015-10-22
申请号：US14754365
申请日：2015-06-29
Applicant: Google Inc.
Inventor： Chen Wu , Debargha Mukherjee , Meng Wang
CPC classification number: H04N13/261 , G06T7/20 , G06T7/55 , G06T2207/10016 , G06T2207/10024 , G06T2207/20212
Abstract: A combined depth map is generated for a monoscopic image based on a weighted combination of a color depth map, a spatial depth map, and a motion depth map for the image, each describing the depth of pixels in the image relative to the image plane. The color depth map determines the depth of pixels according to their color, the spatial depth map determines the depth of pixels according to their location in the image, and the motion depth map determines the depth of pixels according to their motion in the image. Each of the depth maps is associated with a weight that is used to generate the weighted combination. The weights are adaptive to account for variation between different monoscopic images.
Abstract translation: 基于图像的颜色深度图，空间深度图和运动深度图的加权组合，针对单视场图像生成组合深度图，每个描述图像中像素相对于图像平面的深度。 颜色深度图根据其颜色确定像素的深度，空间深度图根据其在图像中的位置确定像素的深度，并且运动深度图根据其在图像中的运动来确定像素的深度。 每个深度图与用于生成加权组合的权重相关联。 权重适应于考虑不同单视镜图像之间的变化。
-
Patent Agency Ranking
公开(公告)号：US08982218B1
公开(公告)日：2015-03-17
申请号：US14267836
申请日：2014-05-01
Applicant: Google Inc.
Inventor： Meng Wang , Sang-Uok Kum , Chen Wu
CPC classification number: H04N19/00909 , H04N17/004 , H04N21/23418
Abstract: A system and method for detecting media source quality are provided. The system includes a data store comprising a computer readable medium storing a program of instructions for the detection of media source quality; a processor that executes the program of instructions; a video data receiver to receive video raw data, the video raw data corresponding to an uploaded and transcoded video; a video improver to apply a video improvement technique to the received video raw data to produce a modified version of the video raw data; and a video quality assessor to compare the received video raw data and the modified version of the video raw data, and based on the modified version of the video raw data improving on a factor associated with the video improvement technique, the video quality assessor indicates a phenomenon affecting the quality of the uploaded and transcoded video.
Abstract translation: 提供了一种用于检测媒体源质量的系统和方法。 该系统包括数据存储器，其包括存储用于检测媒体源质量的指令程序的计算机可读介质; 执行指令程序的处理器; 视频数据接收器，用于接收视频原始数据，视频原始数据对应于上传和转码视频; 视频改进器，用于将视频改进技术应用于所接收的视频原始数据，以产生视频原始数据的修改版本; 以及视频质量评估者，用于比较所接收的视频原始数据和视频原始数据的修改版本，并且基于与视频改进技术相关联的因素改进的视频原始数据的修改版本，视频质量评估者指示 影响上传和转码视频质量的现象。
-
7.发明申请公开(公告)号：US20140118494A1
公开(公告)日：2014-05-01
申请号：US13666566
申请日：2012-11-01
Applicant: Google Inc.
Inventor： Chen Wu , Debargha Mukherjee , Meng Wang
IPC: H04N13/00
CPC classification number: H04N13/261 , G06T7/20 , G06T7/55 , G06T2207/10016 , G06T2207/10024 , G06T2207/20212
Abstract: A combined depth map is generated for a monoscopic image based on a weighted combination of a color depth map, a spatial depth map, and a motion depth map for the image, each describing the depth of pixels in the image relative to the image plane. The color depth map determines the depth of pixels according to their color, the spatial depth map determines the depth of pixels according to their location in the image, and the motion depth map determines the depth of pixels according to their motion in the image. Each of the depth maps is associated with a weight that is used to generate the weighted combination. The weights are adaptive to account for variation between different monoscopic images.
Abstract translation: 基于图像的颜色深度图，空间深度图和运动深度图的加权组合，针对单视场图像生成组合深度图，每个描述图像中像素相对于图像平面的深度。 颜色深度图根据其颜色确定像素的深度，空间深度图根据其在图像中的位置确定像素的深度，并且运动深度图根据其在图像中的运动来确定像素的深度。 每个深度图与用于生成加权组合的权重相关联。 权重适应于考虑不同单视镜图像之间的变化。
-
8.发明申请公开(公告)号：US20190037197A1
公开(公告)日：2019-01-31
申请号：US15295944
申请日：2016-10-17
Applicant: Google Inc.
Inventor： Debargha Mukherjee , Chen Wu , Meng Wang
Abstract: A two-dimensional image to be converted to a first three-dimensional image may be received. A second three-dimensional image that is visually similar to the two-dimensional image that is to be converted may be identified. A feature-to-depth mapping function may be computed for the first three-dimensional image by using an approximate depth map of the second three-dimensional image that is visually similar to the two-dimensional image that is to be converted. The feature-to-depth mapping function may be applied to a plurality of pixels of the two-dimensional image to determine a depth value for the plurality of pixels of the two-dimensional image. The first three-dimensional image may be generated based on the depth values for the plurality of pixels of the two-dimensional image.
-
公开(公告)号：US09769460B1
公开(公告)日：2017-09-19
申请号：US14805326
申请日：2015-07-21
Applicant: Google Inc.
Inventor： Debargha Mukherjee , Meng Wang , Chen Wu
CPC classification number: H04N13/261 , G06T7/40 , G06T15/00 , G06T2207/10028 , H04N2013/0081
Abstract: A request to convert a two-dimensional image to a three-dimensional image may be received. A feature-to-depth mapping function associated with another three-dimensional image that shares a characteristic with the two-dimensional image that is to be converted to the three-dimensional image may be identified. A depth value for a plurality of pixels of the two-dimensional image may be determined based on the feature-to-depth mapping function associated with the other three-dimensional image. The three-dimensional image may be generated based on the depth value for the plurality of pixels of the two-dimensional image.
-
公开(公告)号：US09224211B2
公开(公告)日：2015-12-29
申请号：US14140440
申请日：2013-12-24
Applicant: Google Inc.
Inventor： Meng Wang , Yushi Jing
CPC classification number: G06T7/2006 , G06T7/269 , G06T2207/10016
Abstract: Embodiments for moving object detection in an image are disclosed. These include detecting a moving object in an input image by selecting video frames that are visually similar to the input image, generating a model motion image by estimating motion for each selected video frame, and detecting, using the model motion image, a moving object in the input image based on differences between the model motion image and the input image.
Abstract translation: 公开了用于在图像中移动物体检测的实施例。 这些包括通过选择与输入图像在视觉上类似的视频帧来检测输入图像中的运动对象，通过估计每个所选视频帧的运动来生成模型运动图像，以及使用模型运动图像检测运动对象 基于模型运动图像和输入图像之间的差异的输入图像。
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.016 seconds)
