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

US20170134656A1 DEPTH CAMERA BASED IMAGE STABILIZATION 审中-公开
公开(公告)号：US20170134656A1
公开(公告)日：2017-05-11
申请号：US14935092
申请日：2015-11-06
申请人： Google Inc.
发明人： Gregory M Burgess , Thor Carpenter
IPC分类号： H04N5/232 , H04N5/262 , G06T7/00 , H04N5/272
CPC分类号： H04N5/23248 , G06T7/0024 , G06T7/30 , G06T2207/10028 , H04N5/23219 , H04N5/23254 , H04N5/23258 , H04N5/23277 , H04N5/2628 , H04N5/272
摘要： A processing device collects depth data for frames in a sequence of images of a video stream being provided by a source device to a target device as part of a communication session. The depth data is created by a depth aware camera of the source device. The processing device maps, using the depth data, feature locations of the features of an object in a frame to feature locations of the features of the object in other frames, determines overlapping frame sections between the frames using the mapped feature locations, modifies, in the sequence of images, a set of images corresponding to the frames based on the overlapping frame sections to create a stabilized stream of images for the video stream, and provides the stabilized stream of images in the video stream as part of the communication session.

2. 发明授权

US09390481B2 Enhancing content appearance 有权
标题翻译：增强内容外观
公开(公告)号：US09390481B2
公开(公告)日：2016-07-12
申请号：US13907890
申请日：2013-06-01
申请人： Google Inc.
发明人： Thor Carpenter , Anil Kokaram
IPC分类号： G06K9/40 , G06T5/00
CPC分类号： G06T5/007 , G06T7/194 , G06T2207/10016 , G06T2207/30201
摘要： Implementations generally relate to enhancing content appearance. In some implementations, a method includes receiving an image, selecting a reference object in the image. The method also includes determining one or more image parameter adjustments based on the selected reference object, and applying the one or more image parameter adjustments to the entire image.
摘要翻译：实现通常涉及增强内容外观。在一些实现中，一种方法包括接收图像，在图像中选择参考对象。该方法还包括基于所选择的参考对象来确定一个或多个图像参数调整，以及将一个或多个图像参数调整应用于整个图像。

3. 发明申请

US20150003727A1 Background detection as an optimization for gesture recognition 有权
标题翻译：背景检测作为手势识别的优化
公开(公告)号：US20150003727A1
公开(公告)日：2015-01-01
申请号：US14485186
申请日：2014-09-12
申请人： Google Inc.
发明人： Thor Carpenter , Frank Petterson , Janahan Vivekanandan
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06K9/00335 , G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20016
摘要： Methods and systems are provided allowing for background identification and gesture recognition in video images. A computer-implemented image processing method includes: receiving, using at least one processing circuit, a plurality of image frames of a video; constructing, using at feast one processing circuit, a plurality of statistical models of the plurality of image frames at a plurality of pixel granularity levels; constructing, using at least one processing circuit, a plurality of probabilistic models of an input image frame at a plurality of channel granularity levels based on the plurality of statistical models; merging at least some of the plurality of probabilistic models based on a weighted average to form a single probability image; determining background pixels, based on a probability threshold value, from the single probability image; and determining whether the plurality of image frames, when examined in a particular sequence, conveys a gesture by the object.
摘要翻译：提供了允许在视频图像中进行背景识别和手势识别的方法和系统。计算机实现的图像处理方法包括：使用至少一个处理电路接收视频的多个图像帧; 在多个像素粒度级别构建，使用一个处理电路中的多个图像帧的多个统计模型; 基于所述多个统计模型，构建使用至少一个处理电路多个信道粒度级的输入图像帧的概率模型; 基于加权平均来合并多个概率模型中的至少一些以形成单个概率图像; 基于概率阈值从单个概率图像确定背景像素; 以及当以特定顺序检查时，确定所述多个图像帧是否由所述对象传送手势。

4. 发明授权

US09117112B2 Background detection as an optimization for gesture recognition 有权
公开(公告)号：US09117112B2
公开(公告)日：2015-08-25
申请号：US14485186
申请日：2014-09-12
申请人： Google Inc.
发明人： Thor Carpenter , Frank Petterson , Janahan Vivekanandan
IPC分类号： G06K9/00 , G06K9/48 , G06K9/40 , G06T7/00
CPC分类号： G06K9/00335 , G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20016
摘要： Methods and systems are provided allowing for background identification and gesture recognition in video images. A computer-implemented image processing method includes: receiving, using at least one processing circuit, a plurality of image frames of a video; constructing, using at feast one processing circuit, a plurality of statistical models of the plurality of image frames at a plurality of pixel granularity levels; constructing, using at least one processing circuit, a plurality of probabilistic models of an input image frame at a plurality of channel granularity levels based on the plurality of statistical models; merging at least some of the plurality of probabilistic models based on a weighted average to form a single probability image; determining background pixels, based on a probability threshold value, from the single probability image; and determining whether the plurality of image frames, when examined in a particular sequence, conveys a gesture by the object.

5. 发明申请

US20150142795A1 CONFIGURABLE MEDIA PROCESSING WITH META EFFECTS 审中-公开
标题翻译：可配置的媒体处理与元素效应
公开(公告)号：US20150142795A1
公开(公告)日：2015-05-21
申请号：US14083415
申请日：2013-11-18
申请人： Google Inc.
发明人： Thor Carpenter , Kai Ding
IPC分类号： G06F17/30
CPC分类号： G06F16/40 , G11B27/034 , H04N5/262
摘要： Systems, methods and computer readable media for configurable media processing with meta effects are disclosed. In some implementations, the systems, methods and computer readable media can process a media file based on one or more meta effects (e.g., an ordered list of effects and their corresponding parameters).
摘要翻译：公开了用于具有元效应的可配置媒体处理的系统，方法和计算机可读介质。在一些实现中，系统，方法和计算机可读介质可以基于一个或多个元效应（例如，有序的效果列表及其对应的参数）来处理媒体文件。

6. 发明授权

US09035999B2 Bandwidth reduction system and method 有权
标题翻译：带宽减少系统和方法
公开(公告)号：US09035999B2
公开(公告)日：2015-05-19
申请号：US13688959
申请日：2012-11-29
申请人： Google Inc.
发明人： Thor Carpenter , Chee Chew
IPC分类号： H04N7/14 , H04N7/15 , H04N19/169 , H04N19/103 , H04N19/162 , H04N19/164
CPC分类号： H04N7/15 , H04N7/148 , H04N19/103 , H04N19/162 , H04N19/164 , H04N19/169
摘要： A method and computing system for receiving an indication of a first user participating in a videoconference. A determination is made concerning whether bandwidth compression is preferable for the first user of the videoconference. If bandwidth compression is preferable for the first user of the videoconference: an unprocessed video stream associated with the first user is processed to generate a reduced bandwidth video stream, and the reduced bandwidth video stream is provided to a video encoder. Processing the unprocessed video stream includes performing an edge detection procedure on the unprocessed video stream.
摘要翻译：一种用于接收参与视频会议的第一用户的指示的方法和计算系统。确定对于视频会议的第一用户是否优选带宽压缩。如果针对视频会议的第一用户优选带宽压缩，则处理与第一用户相关联的未处理的视频流以生成减少带宽的视频流，并且将减少带宽的视频流提供给视频编码器。处理未处理的视频流包括对未处理的视频流执行边缘检测过程。

7. 发明授权

US08923611B2 Automatic background identification in video images 有权
标题翻译：视频图像中的自动背景识别
公开(公告)号：US08923611B2
公开(公告)日：2014-12-30
申请号：US14070412
申请日：2013-11-01
申请人： Google Inc.
发明人： Thor Carpenter
IPC分类号： G06K9/62 , G06K9/34 , G06T7/00
CPC分类号： G06K9/6212 , G06K9/34 , G06T7/11 , G06T7/136 , G06T7/143 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20076
摘要： Methods and systems are provided allowing for background identification in video images. A computer-implemented image processing method includes: receiving, using at least one processing circuit, a plurality of image frames of a video; constructing, using at least one processing circuit, a plurality of statistical models of the plurality of image frames at a plurality of pixel granularity levels; constructing, using at least one processing circuit, a plurality of probabilistic models of an input image frame at a plurality of channel granularity levels based on the plurality of statistical models; merging at least some of the plurality of probabilistic models based on a weighted average to form a single probability image; and determining background pixels, based on a probability threshold value, from the single probability image.
摘要翻译：提供了允许在视频图像中进行背景识别的方法和系统。计算机实现的图像处理方法包括：使用至少一个处理电路接收视频的多个图像帧; 使用至少一个处理电路，以多个像素粒度级构造所述多个图像帧的多个统计模型; 基于所述多个统计模型，构建使用至少一个处理电路多个信道粒度级的输入图像帧的概率模型; 基于加权平均来合并多个概率模型中的至少一些以形成单个概率图像; 以及基于概率阈值从单个概率图像确定背景像素。

8. 发明授权

US10033926B2 Depth camera based image stabilization 有权
公开(公告)号：US10033926B2
公开(公告)日：2018-07-24
申请号：US14935092
申请日：2015-11-06
申请人： Google Inc.
发明人： Gregory M Burgess , Thor Carpenter
IPC分类号： H04N5/228 , H04N5/232 , H04N5/272 , H04N5/262 , G06T7/00
摘要： A processing device collects depth data for frames in a sequence of images of a video stream being provided by a source device to a target device as part of a communication session. The depth data is created by a depth aware camera of the source device. The processing device maps, using the depth data, feature locations of the features of an object in a frame to feature locations of the features of the object in other frames, determines overlapping frame sections between the frames using the mapped feature locations, modifies, in the sequence of images, a set of images corresponding to the frames based on the overlapping frame sections to create a stabilized stream of images for the video stream, and provides the stabilized stream of images in the video stream as part of the communication session.

9. 发明授权

US09105088B1 Image blur with preservation of detail 有权
标题翻译：图像模糊与保存细节
公开(公告)号：US09105088B1
公开(公告)日：2015-08-11
申请号：US14046919
申请日：2013-10-04
申请人： Google Inc.
发明人： Ryan Petrie , Thor Carpenter
IPC分类号： G06K9/40 , G06T5/00
CPC分类号： G06T5/003 , G06T5/002 , G06T5/004 , G06T5/50 , G06T2207/10004 , G06T2207/20012 , G06T2207/20192 , G06T2207/20221 , G06T2207/30201
摘要： Implementations relate to blurring an image while preserving details in the image. In some implementations, a method includes receiving an input image and creating a blurred image from the input image by averaging pixel intensities of a plurality of pixels in the input image. The method creates a transparency mask from the input image, where the transparency mask indicates transparency values for pixel positions of the input image based on edges detected in the input image. The pixel intensities of the input image and pixel intensities of the blurred image are composited based on the transparency values of the transparency mask to create an output image having greater blur than the input image in areas outside the detected edges.
摘要翻译：实现涉及模糊图像同时保留图像中的细节。在一些实现中，一种方法包括通过对输入图像中的多个像素的像素强度进行平均来从输入图像接收输入图像并创建模糊图像。该方法从输入图像创建透明度掩码，其中透明掩码基于输入图像中检测到的边缘来指示输入图像的像素位置的透明度值。基于透明度掩模的透明度值来合成输入图像的像素强度和模糊图像的像素强度，以在检测到的边缘之外的区域中产生具有比输入图像更大的模糊的输出图像。

10. 发明授权

US09060095B2 Modifying an appearance of a participant during a video conference 有权
标题翻译：在视频会议期间修改与会者的外观
公开(公告)号：US09060095B2
公开(公告)日：2015-06-16
申请号：US13802241
申请日：2013-03-13
申请人： GOOGLE INC.
发明人： Frank Petterson , Janahan Vivekanandan , Thor Carpenter
IPC分类号： H04N7/14 , H04N7/15 , G06K9/00
CPC分类号： H04N7/157 , G06K9/00228
摘要： Implementations generally relate to modifying an appearance of a participant during a video conference. In some implementations, a method includes obtaining at least one frame from a media stream, where the at least one frame includes a first face, and where the first face is an image of a face associated with a user. The method also includes determining a plurality of coordinates within the at least one frame. The method also includes obtaining at least one media content item. The method also includes adding the at least one media content item to the at least one frame based on the plurality of coordinates.
摘要翻译：实现通常涉及在视频会议期间修改参与者的外观。在一些实施方式中，一种方法包括从媒体流获得至少一个帧，其中所述至少一个帧包括第一面，并且其中所述第一面是与用户相关联的面部的图像。该方法还包括确定至少一个帧内的多个坐标。该方法还包括获得至少一个媒体内容项目。该方法还包括基于多个坐标将至少一个媒体内容项添加到至少一个帧。

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