-
公开(公告)号：US09437000B2
公开(公告)日：2016-09-06
申请号：US14185616
申请日：2014-02-20
Applicant: Google Inc.
Inventor： Johnny Lee , Joel Hesch
CPC classification number: G06K9/00744 , G06T7/246 , G06T7/66 , G06T7/73 , G06T2207/10016 , G06T2207/10028 , G06T2207/30241 , G06T2207/30244 , H04W4/023 , H04W4/027 , H04W4/029
Abstract: Methods and systems for determining features of interest for following within various frames of data received from multiple sensors of a device are disclosed. An example method may include receiving data from a plurality of sensors of a device. The method may also include determining, based on the data, motion data that is indicative of a movement of the device in an environment. The method may also include as the device moves in the environment, receiving image data from a camera of the device. The method may additionally include selecting, based at least in part on the motion data, features in the image data for feature-following. The method may further include estimating one or more of a position of the device or a velocity of the device in the environment as supported by the data from the plurality of sensors and feature-following of the selected features in the images.
Abstract translation: 公开了用于确定在从设备的多个传感器接收的各种数据帧内追踪的特征的方法和系统。 示例性方法可以包括从设备的多个传感器接收数据。 该方法还可以包括基于数据确定指示设备在环境中的移动的运动数据。 该方法还可以包括当设备在环境中移动时，从设备的照相机接收图像数据。 该方法可以另外包括至少部分地基于运动数据来选择用于特征跟踪的图像数据中的特征。 该方法还可以包括估计设备的位置或环境中的设备的速度中的一个或多个，如来自多个传感器的数据所支持的，以及图像中所选特征的特征。
-
公开(公告)号：US20180033201A1
公开(公告)日：2018-02-01
申请号：US15220847
申请日：2016-07-27
Applicant: Google Inc.
Inventor： Joel Hesch , Ashish Shah , James Fung
CPC classification number: G06T19/006 , G02B27/0172 , G02B2027/0138 , G02B2027/014 , G06F3/011 , G06T7/246 , G06T7/60 , G06T7/70 , G06T7/73 , G06T2207/30244 , G09G5/18 , G09G2330/021
Abstract: A head mounted display (HMD) adjusts feature tracking parameters based on a power mode of the HMD. Examples of feature tracking parameters that can be adjusted include the number of features identified from captured images, the scale of features identified from captured images, the number of images employed for feature tracking, and the like. By adjusting its feature tracking parameters based on its power mode, the HMD can initiate the feature tracking process in low-power modes and thereby shorted the time for high-fidelity feature tracking when a user initiates a VR or AR experience at the HMD.
-
公开(公告)号：US20170046594A1
公开(公告)日：2017-02-16
申请号：US14823283
申请日：2015-08-11
Applicant: Google Inc.
Inventor： Esha Nerurkar , Joel Hesch , Simon Lynen
IPC: G06K9/62
CPC classification number: G06K9/6212 , G05D1/0268 , G06F3/011 , G06F17/30247 , G06F17/30265 , G06F17/3087 , G06K9/46 , G06K9/6267 , G06T7/246 , G06T7/521 , G06T7/593 , G06T7/70 , G06T7/73
Abstract: An electronic device reduces localization data based on feature characteristics identified from the data. Based on the feature characteristics, a quality value can be assigned to each identified feature, indicating the likelihood that the data associated with the feature will be useful in mapping a local environment of the electronic device. The localization data is reduced by removing data associated with features have a low quality value, and the reduced localization data is used to map the local environment of the device by locating features identified from the reduced localization data in a frame of reference for the electronic device.
Abstract translation: 电子设备基于从数据识别的特征特征来减少定位数据。 基于特征特征，可以向每个识别的特征分配质量值，指示与特征相关联的数据在映射电子设备的本地环境时将是有用的。 通过去除与特征相关联的数据具有低质量值来减少定位数据，并且减少的定位数据用于通过从电子设备的参考系中定位从缩小的定位数据识别的特征来映射设备的本地环境 。
-
公开(公告)号：US20170018092A1
公开(公告)日：2017-01-19
申请号：US15236881
申请日：2016-08-15
Applicant: Google Inc.
Inventor： Johnny Lee , Joel Hesch
CPC classification number: G06K9/00744 , G06T7/246 , G06T7/66 , G06T7/73 , G06T2207/10016 , G06T2207/10028 , G06T2207/30241 , G06T2207/30244 , H04W4/023 , H04W4/027 , H04W4/029
Abstract: Methods and systems for determining features of interest for following within various frames of data received from multiple sensors of a device are disclosed. An example method may include receiving data from a plurality of sensors of a device. The method may also include determining, based on the data, motion data that is indicative of a movement of the device in an environment. The method may also include as the device moves in the environment, receiving image data from a camera of the device. The method may additionally include selecting, based at least in part on the motion data, features in the image data for feature-following. The method may further include estimating one or more of a position of the device or a velocity of the device in the environment as supported by the data from the plurality of sensors and feature-following of the selected features in the images.
Abstract translation: 公开了用于确定在从设备的多个传感器接收的各种数据帧内追踪的特征的方法和系统。 示例性方法可以包括从设备的多个传感器接收数据。 该方法还可以包括基于数据确定指示设备在环境中的移动的运动数据。 该方法还可以包括当设备在环境中移动时，从设备的照相机接收图像数据。 该方法可以另外包括至少部分地基于运动数据来选择用于特征跟踪的图像数据中的特征。 该方法还可以包括估计设备的位置或环境中的设备的速度中的一个或多个，如来自多个传感器的数据所支持的，以及图像中所选特征的特征。
-
公开(公告)号：US20160191722A1
公开(公告)日：2016-06-30
申请号：US15066105
申请日：2016-03-10
Applicant: Google Inc.
Inventor： James Fung , Joel Hesch , Johnny Lee
CPC classification number: H04N1/00204 , H04N1/2133 , H04N1/215 , H04N1/32128 , H04N5/2257 , H04N5/232 , H04N5/23229 , H04N5/772 , H04N2201/0084 , H04N2201/3247 , H04N2201/3252
Abstract: Methods and systems for communicating sensor data on a mobile device are described. An example method involves receiving, by a processor and from an inertial measurement unit (IMU), sensor data corresponding to a first timeframe, and storing the sensor data using a data buffer. The processor may also receive image data and sensor data corresponding to a second timeframe. The processor may then generate a digital image that includes at least the image data corresponding to the second timeframe and the sensor data corresponding to the first timeframe and the second timeframe. The processor may embed the stored sensor data corresponding to the first timeframe and the second timeframe in pixels of the digital image. And the processor may provide the digital image to an application processor of the mobile device.
-
Patent Agency Ranking
16.发明申请Methods and Systems for Cross-Validating Sensor Data Acquired Using Sensors of a Mobile Device 有权使用移动设备的传感器交叉验证传感器数据的方法和系统公开(公告)号：US20150237479A1
公开(公告)日：2015-08-20
申请号：US14184929
申请日：2014-02-20
Applicant: Google Inc.
Inventor： James Fung , Joel Hesch , Johnny Lee
CPC classification number: H04W4/026 , G06T7/246 , G06T2207/10004 , G06T2207/10012 , G06T2207/10028 , G06T2207/30241
Abstract: Methods and systems for cross-validating sensor data are described. An example method involves receiving image data and first timing information associated with the image data, and receiving sensor data and second timing information associated with the sensor data. The method further involves determining a first estimation of motion of the mobile device based on the image data and the first timing information, and determining a second estimation of the motion of the mobile device based on the sensor data and the second timing information. Additionally, the method involves determining whether the first estimation is within a threshold variance of the second estimation. The method then involves providing an output indicative of a validity of the first timing information and the second timing information based on whether the first estimation is within the threshold variance of the second estimation.
Abstract translation: 描述用于交叉验证传感器数据的方法和系统。 示例性方法包括接收与图像数据相关联的图像数据和第一定时信息，以及接收与传感器数据相关联的传感器数据和第二定时信息。 该方法还包括基于图像数据和第一定时信息确定移动设备的运动的第一估计，以及基于传感器数据和第二定时信息确定移动设备的运动的第二估计。 另外，该方法包括确定第一估计是否在第二估计的阈值方差内。 该方法然后包括基于第一估计是否在第二估计的阈值方差内提供指示第一定时信息和第二定时信息的有效性的输出。
-
17.发明申请公开(公告)号：US20150237269A1
公开(公告)日：2015-08-20
申请号：US14185477
申请日：2014-02-20
Applicant: Google Inc.
Inventor： Joel Hesch , Ryan Hickman , Johnny Lee
CPC classification number: H04N5/2628 , G06T15/205 , H04N5/2258 , H04N5/23229 , H04N5/23293 , H04N5/2621 , H04N2209/047 , H04W4/026 , H04W4/027
Abstract: Example methods and systems for adjusting sensor viewpoint to a virtual viewpoint are provided. An example method may involve receiving data from a first camera; receiving data from a second camera; transforming, from the first viewpoint to a virtual viewpoint within the device, frames in a first plurality of frames based on an offset from the first camera to the virtual viewpoint; determining, in a second plurality of frames, one or more features and a movement, relative to the second viewpoint, of the one or more features; and transforming, from the second viewpoint to the virtual viewpoint, the movement of the one or more features based on an offset from the second camera to the virtual viewpoint; adjusting the transformed frames of the virtual viewpoint by an amount that is proportional to the transformed movement; and providing for display the adjusted and transformed frames of the first plurality of frames.
Abstract translation: 提供了将传感器视点调整到虚拟视点的示例性方法和系统。 示例性方法可以涉及从第一相机接收数据; 从第二相机接收数据; 基于从第一摄像机到虚拟视点的偏移，从设备内的第一视点到虚拟视点转换第一多个帧中的帧; 在第二多个帧中确定所述一个或多个特征的一个或多个特征和相对于所述第二视点的运动; 并且从第二观点向虚拟视点将基于从第二照相机的偏移到所述虚拟视点的所述一个或多个特征的移动; 将所述虚拟视点的变换帧调整与所述变换的运动成比例的量; 以及提供用于显示所述第一多个帧的已调整和变换的帧。
-
18.发明申请公开(公告)号：US20150237223A1
公开(公告)日：2015-08-20
申请号：US14185091
申请日：2014-02-20
Applicant: Google Inc.
Inventor： James Fung , Joel Hesch , Johnny Lee
CPC classification number: H04N1/00204 , H04N1/2133 , H04N1/215 , H04N1/32128 , H04N5/2257 , H04N5/232 , H04N5/23229 , H04N5/772 , H04N2201/0084 , H04N2201/3247 , H04N2201/3252
Abstract: Methods and systems for communicating sensor data on a mobile device are described. An example method involves receiving, by a processor and from an inertial measurement unit (IMU), sensor data corresponding to a first timeframe, and storing the sensor data using a data buffer. The processor may also receive image data and sensor data corresponding to a second timeframe. The processor may then generate a digital image that includes at least the image data corresponding to the second timeframe and the sensor data corresponding to the first timeframe and the second timeframe. The processor may embed the stored sensor data corresponding to the first timeframe and the second timeframe in pixels of the digital image. And the processor may provide the digital image to an application processor of the mobile device.
Abstract translation: 描述了用于在移动设备上传送传感器数据的方法和系统。 一种示例性方法包括由处理器和惯性测量单元（IMU）接收对应于第一时间帧的传感器数据，以及使用数据缓冲器存储传感器数据。 处理器还可以接收对应于第二时间帧的图像数据和传感器数据。 然后，处理器可以生成至少包括对应于第二时间帧的图像数据和对应于第一时间帧和第二时间帧的传感器数据的数字图像。 处理器可以将对应于第一时间帧和第二时间帧的存储的传感器数据嵌入数字图像的像素中。 并且处理器可以将数字图像提供给移动设备的应用处理器。
-
公开(公告)号：US20150235335A1
公开(公告)日：2015-08-20
申请号：US14185027
申请日：2014-02-20
Applicant: Google Inc.
Inventor： James Fung , Joel Hesch , Johnny Lee
CPC classification number: G06T1/0021 , G03B19/00 , H04N5/23229
Abstract: Methods and systems for detecting frame tears are described. As one example, a mobile device may include at least one camera, a sensor, a co-processor, and an application processor. The co-processor is configured to generate a digital image including image data from the at least one camera and sensor data from the sensor. The co-processor is further configured to embed a frame identifier corresponding to the digital image at least two corner pixels of the digital image. The application processor is configured to receive the digital image from the co-processor, determine a first value embedded in a first corner pixel of the digital image, and determined a second value embedded in a second corner pixel of the digital image. The application processor is also configured to provide an output indicative of a validity of the digital image based on a comparison between the first value and the second value.
Abstract translation: 描述了用于检测框架撕裂的方法和系统。 作为一个示例，移动设备可以包括至少一个相机，传感器，协处理器和应用处理器。 协处理器被配置为生成包括来自至少一个照相机的图像数据和来自传感器的传感器数据的数字图像。 协处理器还被配置为将与数字图像相对应的帧标识符嵌入数字图像的至少两个角落像素。 应用处理器被配置为从协处理器接收数字图像，确定嵌入在数字图像的第一角落像素中的第一值，并且确定嵌入在数字图像的第二角落像素中的第二值。 应用处理器还被配置为基于第一值和第二值之间的比较来提供指示数字图像的有效性的输出。
-
公开(公告)号：US09990547B2
公开(公告)日：2018-06-05
申请号：US15236881
申请日：2016-08-15
Applicant: Google Inc.
Inventor： Johnny Lee , Joel Hesch
CPC classification number: G06K9/00744 , G06T7/246 , G06T7/66 , G06T7/73 , G06T2207/10016 , G06T2207/10028 , G06T2207/30241 , G06T2207/30244 , H04W4/023 , H04W4/027 , H04W4/029
Abstract: Methods and systems for determining features of interest for following within various frames of data received from multiple sensors of a device are disclosed. An example method may include receiving data from a plurality of sensors of a device. The method may also include determining, based on the data, motion data that is indicative of a movement of the device in an environment. The method may also include as the device moves in the environment, receiving image data from a camera of the device. The method may additionally include selecting, based at least in part on the motion data, features in the image data for feature-following. The method may further include estimating one or more of a position of the device or a velocity of the device in the environment as supported by the data from the plurality of sensors and feature-following of the selected features in the images.
-
-
-
-
-
-
-
-
-
Search Results
28
records
(took 0.022 seconds)
