公开(公告)号：US09047692B1

公开(公告)日：2015-06-02

申请号：US13721607

申请日：2012-12-20

Applicant: Google Inc.

Inventor： Steven Maxwell Seitz ,  Rahul Garg

IPC: G06T11/00 ,  G06T3/40

CPC classification number: G06T3/4038

Abstract: Systems, methods, and computer storage mediums are provided for creating a scene scan from a group of photographic images. An exemplary method includes determining a set of common features for at least one pair of photographic images. The features include a portion of an object captured in each of a first and a second photographic image included in the pair. The first and second photographic images may be captured from different optical centers. A similarity transform for the at least one pair of photographic images is the determined. The similarity transform is provided in order to render the scene scan from each pair of photographic images. At least one of the rotation factor, the scaling factor, or the translation factor associated with the similarity transform is used to position each pair of photographic images such that the set of common features between a pair of, at least in part, align.

Abstract translation: 系统，方法和计算机存储介质被提供用于从一组摄影图像创建场景扫描。 一种示例性方法包括确定用于至少一对照相图像的一组共同特征。 这些特征包括在该对中包括的第一和第二摄影图像的每一个中捕获的对象的一部分。 可以从不同的光学中心捕获第一和第二摄影图像。 确定至少一对摄影图像的相似变换。 提供相似度变换以便从每对摄影图像呈现场景扫描。 使用与相似变换相关联的旋转因子，缩放因子或平移因子中的至少一个来定位每对摄影图像，使得一对至少部分对齐的一组共同特征。

公开(公告)号：US10599211B2

公开(公告)日：2020-03-24

申请号：US15228594

申请日：2016-08-04

Applicant: GOOGLE INC.

Inventor： Manuel Christian Clement ,  Alexander James Faaborg ,  Rahul Garg ,  Jonathan Tompson ,  Shiqi Chen

IPC: G06F3/01 ,  G06F3/0481 ,  G06F3/0485 ,  A63F13/428 ,  G06F3/0484 ,  A63F13/213 ,  A63F13/212 ,  G06T19/00 ,  A63F13/822 ,  A63F13/577 ,  A63F13/837

Abstract: In one aspect, a method and system are described for receiving input for a virtual user in a virtual environment. The input may be based on a plurality of movements performed by a user accessing the virtual environment. Based on the plurality of movements, the method and system can include detecting that at least one portion of the virtual user is within a threshold distance of a collision zone, the collision zone being associated with at least one virtual object. The method and system can also include selecting a collision mode for the virtual user based on the at least one portion and the at least one virtual object and dynamically modifying the virtual user based on the selected collision mode.

公开(公告)号：US20150154761A1

公开(公告)日：2015-06-04

申请号：US13721607

申请日：2012-12-20

Applicant: Google Inc.

Inventor： Steven Maxwell SEITZ ,  Rahul Garg

IPC: G06T11/00

CPC classification number: G06T3/4038

Abstract: Systems, methods, and computer storage mediums are provided for creating a scene scan from a group of photographic images. An exemplary method includes determining a set of common features for at least one pair of photographic images. The features include a portion of an object captured in each of a first and a second photographic image included in the pair. The first and second photographic images may be captured from different optical centers. A similarity transform for the at least one pair of photographic images is the determined. The similarity transform is provided in order to render the scene scan from each pair of photographic images. At least one of the rotation factor, the scaling factor, or the translation factor associated with the similarity transform is used to position each pair of photographic images such that the set of common features between a pair of, at least in part, align.

Abstract translation: 系统，方法和计算机存储介质被提供用于从一组摄影图像创建场景扫描。 一种示例性方法包括确定用于至少一对照相图像的一组共同特征。 这些特征包括在该对中包括的第一和第二摄影图像的每一个中捕获的对象的一部分。 可以从不同的光学中心捕获第一和第二摄影图像。 确定至少一对摄影图像的相似变换。 提供相似度变换以便从每对摄影图像呈现场景扫描。 使用与相似变换相关联的旋转因子，缩放因子或平移因子中的至少一个来定位每对摄影图像，使得一对之间的至少一部分共同特征的集合对齐。

公开(公告)号：US20150154736A1

公开(公告)日：2015-06-04

申请号：US13721643

申请日：2012-12-20

Applicant: Google Inc.

Inventor： Steven Maxwell SEITZ ,  Rahul Garg

IPC: G06T3/00

CPC classification number: G06T3/4038 ,  G06T3/0075

Abstract: Systems, methods, and computer storage mediums are provided for linking scene scans. A method includes creating a first scene scan from a first group of photographic images. The first scene scan is created by aligning a set of common features captured between at least two photographic images in the first group, where the at least two photographic images in the first group may each be captured from a different optical center. The set of common features is aligned based on a similarity transform determined between the at least two photographic images. An area of at least one photographic image in the first group is then defined, at least in part, based on a user selection. A second scene scan is linked with the area defined in the at least one photographic image in the first group, where the second scene scan is created from a second group of photographic images.

Abstract translation: 提供系统，方法和计算机存储介质来连接场景扫描。 一种方法包括从第一组摄影图像创建第一场景扫描。 通过对准在第一组中的至少两个摄影图像之间捕获的一组共同特征来创建第一场景扫描，其中第一组中的至少两个摄影图像可以各自从不同的光学中心捕获。 基于在所述至少两个照相图像之间确定的相似度变换来对齐所述一组共同特征。 然后至少部分地基于用户选择来定义第一组中的至少一个摄影图像的区域。 第二场景扫描与在第一组中的至少一个摄影图像中定义的区域相关联，其中从第二组摄影图像创建第二场景扫描。

公开(公告)号：US09036921B2

公开(公告)日：2015-05-19

申请号：US14189686

申请日：2014-02-25

Applicant: Google Inc.

Inventor： Steven Maxwell Seitz ,  Rahul Garg ,  Irena Kemelmaher

IPC: G06K9/68 ,  G06K9/00 ,  G06K9/32 ,  G06T7/00

CPC classification number: G06K9/00308 ,  G06K9/32 ,  G06T7/33 ,  G06T2207/20221 ,  G06T2207/30201

Abstract: Systems, methods and articles of manufacture for generating sequences of face and expression aligned images are presented. An embodiment includes determining a plurality of candidate images, computing a similarity distance between an input image and each of the candidate images based on facial features in the input image and the candidate images, comparing the computed similarity distances, selecting a candidate image based on the comparing, and adding the selected candidate image to an image sequence for real-time display. Embodiments select images from the image sequence as they are being added to the image sequence and scale, rotate and translate each image so that a face appearing in a selected image is aligned with a face appearing in a subsequently selected image from the image sequence. In this way, embodiments are able to render arbitrarily large image collections efficiently and in real time to display a face and expression aligned movie.

Abstract translation: 提出了用于生成面部和表情对齐图像序列的系统，方法和制品。 实施例包括确定多个候选图像，基于输入图像和候选图像中的面部特征，计算输入图像和每个候选图像之间的相似距离，比较计算出的相似度距离，基于 比较并将所选择的候选图像添加到用于实时显示的图像序列。 实施例从图像序列中选择图像，因为它们被添加到图像序列中并且缩放，旋转和平移每个图像，使得出现在所选择的图像中的面与来自图像序列的随后选择的图像中出现的面对齐。 以这种方式，实施例能够有效地和实时地呈现任意大的图像集合，以显示面部和表情对齐的电影。

公开(公告)号：US20190033988A1

公开(公告)日：2019-01-31

申请号：US15660216

申请日：2017-07-26

Applicant: Google Inc.

Inventor： Joel Hesch ,  Shiqi Chen ,  Johnny Lee ,  Rahul Garg

IPC: G06F3/0346 ,  G06T7/73 ,  G06F3/0354 ,  G06F3/01

Abstract: A method for controller tracking with multiple degrees of freedom includes generating depth data at an electronic device based on a local environment proximate the electronic device. A set of positional data is generated for at least one spatial feature associated with a controller based on a pose of the electronic device, as determined using the depth data, relative to the at least one spatial feature associated with the controller. A set of rotational data is received that represents three degrees-of-freedom (3DoF) orientation of the controller within the local environment, and a six degrees-of-freedom (6DoF) position of the controller within the local environment is tracked based on the set of positional data and the set of rotational data.

公开(公告)号：US09445048B1

公开(公告)日：2016-09-13

申请号：US14445778

申请日：2014-07-29

Applicant: Google Inc.

Inventor： Mehul Nariyawala ,  Rahul Garg ,  Navneet Dalal ,  Thor Carpenter ,  Greg Burgess ,  Tim Psiaki ,  Mark Chang ,  Antonio Bernardo Monteiro Costa ,  Christian Plagemann ,  Chee Chew

IPC: H04N7/15 ,  G06F3/01

CPC classification number: H04N7/15 ,  G06F3/017 ,  H04N7/152

Abstract: Systems and methods are disclosed for gesture-initiated actions in videoconferences. In one implementation, a processing device receives one or more content streams as part of a communication session. The processing device identifies, within the one or more content streams, a request for feedback. The processing device processes, based on an identification of a request for feedback within the one of the plurality of content streams, the one or more content streams to identify a presence of one or more gestures within at least one of the one or more content streams. The processing device initiates, based on an identification of the presence of one or more gestures within at least one of the one or more content streams, an action with respect to the communication session.

Abstract translation: 系统和方法被公开用于视频会议中的手势发起的动作。 在一个实现中，处理设备作为通信会话的一部分接收一个或多个内容流。 处理装置在一个或多个内容流中识别反馈请求。 处理设备基于对多个内容流中的一个内容流中的反馈请求的标识来处理一个或多个内容流，以识别一个或多个内容流中的至少一个内的一个或多个手势的存在 。 处理装置基于对一个或多个内容流中的至少一个内的一个或多个内容流中的一个或多个手势的存在的识别发起关于通信会话的动作。

公开(公告)号：US20140254864A1

公开(公告)日：2014-09-11

申请号：US13788900

申请日：2013-03-07

Applicant: Google Inc.

Inventor： Navneet Dalal ,  Rahul Garg ,  Varun Gulshan ,  Ankit Mohan

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/00335 ,  G06K2009/4666

Abstract: System and method for image detection that include collecting image data; at a processor, over a plurality of support regions of the image data, computing a dimensionality component of a support region of the image data, wherein the, non-nucleus pixels of a support region; calculating a normalizing factor of the dimensionality component; for at least one weighted pattern of a pattern set, applying a weighted pattern to the dimensionality component to create a gradient vector, mapping the gradient vector to a probabilistic model, and normalizing the gradient vector by the normalizing factor; condensing probabilistic models of the plurality of support regions into a probabilistic distribution feature for at least one cell of the image data; applying a classifier to at least the probabilistic distribution feature; and detecting an object in the image data according to a result of the applied classifier.

Abstract translation: 包括收集图像数据的图像检测系统和方法; 在处理器处，在图像数据的多个支持区域上，计算图像数据的支持区域的维数分量，其中支持区域的非核心像素; 计算维度分量的归一化因子; 对于图案组的至少一个加权图案，将加权图案应用于所述维度分量以创建梯度向量，将所述梯度向量映射到概率模型，以及通过所述归一化因子归一化所述梯度向量; 将所述多个支持区域的概率模型缩放为所述图像数据的至少一个单元的概率分布特征; 将分类器应用于至少概率分布特征; 以及根据应用的分类器的结果检测图像数据中的对象。