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. 发明授权

US08350850B2 Using photo collections for three dimensional modeling 有权
公开(公告)号：US08350850B2
公开(公告)日：2013-01-08
申请号：US12059794
申请日：2008-03-31
申请人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
发明人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
IPC分类号： G06T17/00 , G06T15/00
CPC分类号： G06T17/00 , G06T7/536 , G06T7/564 , G06T15/205 , G06T2200/08 , G06T2207/10016
摘要： A collection of photos and a three-dimensional reconstruction of the photos are used to construct and texture a mesh model. In one embodiment, a first digital image of a first view of a real world scene is analyzed to identify lines in the first view. Among the lines, parallel lines are identified. A three-dimensional vanishing direction in a three-dimensional space is determined based on the parallel lines and an orientation of the digital image in the three-dimensional space. A plane is automatically generated by fitting the plane to the vanishing direction. A rendering of a three-dimensional model with the plane is displayed. Three-dimensional points corresponding to features common to the photos may be used to constrain the plane. The photos may be projected onto the model to provide visual feedback when editing the plane. Furthermore, the photos may be used to texture the model.

2. 发明申请

US20090244062A1 USING PHOTO COLLECTIONS FOR THREE DIMENSIONAL MODELING 有权
标题翻译：使用三维建模的照片集
公开(公告)号：US20090244062A1
公开(公告)日：2009-10-01
申请号：US12059794
申请日：2008-03-31
申请人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
发明人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
IPC分类号： G06T17/00 , G09G5/00
CPC分类号： G06T17/00 , G06T7/536 , G06T7/564 , G06T15/205 , G06T2200/08 , G06T2207/10016
摘要： A collection of photos and a three-dimensional reconstruction of the photos are used to construct and texture a mesh model. In one embodiment, a first digital image of a first view of a real world scene is analyzed to identify lines in the first view. Among the lines, parallel lines are identified. A three-dimensional vanishing direction in a three-dimensional space is determined based on the parallel lines and an orientation of the digital image in the three-dimensional space. A plane is automatically generated by fitting the plane to the vanishing direction. A rendering of a three-dimensional model with the plane is displayed. Three-dimensional points corresponding to features common to the photos may be used to constrain the plane. The photos may be projected onto the model to provide visual feedback when editing the plane. Furthermore, the photos may be used to texture the model.
摘要翻译：使用照片的集合和照片的三维重建来构造和纹理网格模型。在一个实施例中，分析现实世界场景的第一视图的第一数字图像以识别第一视图中的线。在行中，确定了平行线。基于三维空间中的数字图像的平行线和取向来确定三维空间中的三维消失方向。通过将平面装配到消失方向，自动生成平面。显示用平面渲染三维模型。对应于照片共同特征的三维点可以用于约束平面。照片可以投影到模型上，以便在编辑飞机时提供视觉反馈。此外，照片可以用于纹理模型。

3. 发明申请

US20120321175A1 LOCATION-AIDED RECOGNITION 有权
标题翻译：位置识别
公开(公告)号：US20120321175A1
公开(公告)日：2012-12-20
申请号：US13162591
申请日：2011-06-17
申请人： Varsha Hedau , Sudipta Sinha , Charles Lawrence Zitnick , Richard Szeliski
发明人： Varsha Hedau , Sudipta Sinha , Charles Lawrence Zitnick , Richard Szeliski
IPC分类号： G06K9/62
CPC分类号： G06K9/6227 , G06K9/6231
摘要： A mobile device having the capability of performing real-time location recognition with assistance from a server is provided. The approximate geophysical location of the mobile device is uploaded to the server. Based on the mobile device's approximate geophysical location, the server responds by sending the mobile device a message comprising a classifier and a set of feature descriptors. This can occur before an image is captured for visual querying. The classifier and feature descriptors are computed during an offline training stage using techniques to minimize computation at query time. The classifier and feature descriptors are used to perform visual recognition in real-time by performing the classification on the mobile device itself.
摘要翻译：提供了具有从服务器的协助执行实时位置识别能力的移动设备。移动设备的近似地球物理位置被上传到服务器。基于移动设备的近似地球物理位置，服务器通过向移动设备发送包括分类器和一组特征描述符的消息来进行响应。这可能在捕获图像以进行视觉查询之前发生。分类器和特征描述符在离线训练阶段使用技术来计算，以最小化查询时间的计算。分类器和特征描述符用于通过在移动设备本身上执行分类来实时执行视觉识别。

4. 发明授权

US09152882B2 Location-aided recognition 有权
标题翻译：位置辅助识别
公开(公告)号：US09152882B2
公开(公告)日：2015-10-06
申请号：US13162591
申请日：2011-06-17
申请人： Varsha Hedau , Sudipta Sinha , Charles Lawrence Zitnick , Richard Szeliski
发明人： Varsha Hedau , Sudipta Sinha , Charles Lawrence Zitnick , Richard Szeliski
IPC分类号： G06K9/62
CPC分类号： G06K9/6227 , G06K9/6231
摘要： A mobile device having the capability of performing real-time location recognition with assistance from a server is provided. The approximate geophysical location of the mobile device is uploaded to the server. Based on the mobile device's approximate geophysical location, the server responds by sending the mobile device a message comprising a classifier and a set of feature descriptors. This can occur before an image is captured for visual querying. The classifier and feature descriptors are computed during an offline training stage using techniques to minimize computation at query time. The classifier and feature descriptors are used to perform visual recognition in real-time by performing the classification on the mobile device itself.
摘要翻译：提供了具有从服务器的协助执行实时位置识别能力的移动设备。移动设备的近似地球物理位置被上传到服务器。基于移动设备的近似地球物理位置，服务器通过向移动设备发送包括分类器和一组特征描述符的消息来进行响应。这可能在捕获图像以进行视觉查询之前发生。分类器和特征描述符在离线训练阶段使用技术来计算，以最小化查询时间的计算。分类器和特征描述符用于通过在移动设备本身上执行分类来实时执行视觉识别。

5. 发明申请

US20140037218A1 THREE-DIMENSIONAL OBJECT BROWSING IN DOCUMENTS 有权
标题翻译：文件中的三维对象浏览
公开(公告)号：US20140037218A1
公开(公告)日：2014-02-06
申请号：US13567105
申请日：2012-08-06
申请人： Geoffrey G. Zweig , Eric J. Stollnitz , Richard Szeliski , Sudipta Sinha , Johannes Kopf
发明人： Geoffrey G. Zweig , Eric J. Stollnitz , Richard Szeliski , Sudipta Sinha , Johannes Kopf
IPC分类号： G06K9/68
CPC分类号： G06F17/30268
摘要： A document that includes a representation of a two-dimensional (2-D) image may be obtained. A selection indicator indicating a selection of at least a portion of the 2-D image may be obtained. A match correspondence may be determined between the selected portion of the 2-D image and a three-dimensional (3-D) image object stored in an object database, the match correspondence based on a web crawler analysis result. A 3-D rendering of the 3-D image object that corresponds to the selected portion of the 2-D image may be initiated.
摘要翻译：可以获得包括二维（2-D）图像的表示的文档。可以获得指示选择2-D图像的至少一部分的选择指示符。可以在2-D图像的所选部分和存储在对象数据库中的三维（3-D）图像对象之间确定匹配对应关系，该匹配对应基于网络爬行器分析结果。可以启动对应于2-D图像的所选部分的3-D图像对象的3-D渲染。

6. 发明授权

US09025860B2 Three-dimensional object browsing in documents 有权
标题翻译：文件中的三维对象浏览
公开(公告)号：US09025860B2
公开(公告)日：2015-05-05
申请号：US13567105
申请日：2012-08-06
申请人： Geoffrey G. Zweig , Eric J. Stollnitz , Richard Szeliski , Sudipta Sinha , Johannes Kopf
发明人： Geoffrey G. Zweig , Eric J. Stollnitz , Richard Szeliski , Sudipta Sinha , Johannes Kopf
IPC分类号： G06K9/00 , G06F17/30
CPC分类号： G06F17/30268
摘要： A document that includes a representation of a two-dimensional (2-D) image may be obtained. A selection indicator indicating a selection of at least a portion of the 2-D image may be obtained. A match correspondence may be determined between the selected portion of the 2-D image and a three-dimensional (3-D) image object stored in an object database, the match correspondence based on a web crawler analysis result. A 3-D rendering of the 3-D image object that corresponds to the selected portion of the 2-D image may be initiated.
摘要翻译：可以获得包括二维（2-D）图像的表示的文档。可以获得指示选择2-D图像的至少一部分的选择指示符。可以在2-D图像的所选部分和存储在对象数据库中的三维（3-D）图像对象之间确定匹配对应关系，该匹配对应基于网络爬行器分析结果。可以启动对应于2-D图像的所选部分的3-D图像对象的3-D渲染。

7. 发明申请

US20150242680A1 POLARIZED GAZE TRACKING 有权
标题翻译：极化高差跟踪
公开(公告)号：US20150242680A1
公开(公告)日：2015-08-27
申请号：US14191305
申请日：2014-02-26
申请人： Vaibhav Thukral , Sudipta Sinha , Vivek Pradeep , Timothy Andrew Large , Nigel Stuart Keam , David Nister
发明人： Vaibhav Thukral , Sudipta Sinha , Vivek Pradeep , Timothy Andrew Large , Nigel Stuart Keam , David Nister
IPC分类号： G06K9/00 , H04N5/235 , G06F3/01 , H04N5/232
CPC分类号： G06K9/00335 , G06F3/013 , G06K9/00604 , G06K9/2027 , H04N5/23219 , H04N5/2354
摘要： Embodiments that relate to determining gaze locations are disclosed. In one embodiment a method includes shining light along an outbound light path to the eyes of the user wearing glasses. Upon detecting the glasses, the light is dynamically polarized in a polarization pattern that switches between a random polarization phase and a single polarization phase, wherein the random polarization phase includes a first polarization along an outbound light path and a second polarization orthogonal to the first polarization along a reflected light path. The single polarization phase has a single polarization. During the random polarization phases, glares reflected from the glasses are filtered out and pupil images are captured. Glint images are captured during the single polarization phase. Based on pupil characteristics and glint characteristics, gaze locations are repeatedly detected.
摘要翻译：公开了与确定凝视位置有关的实施例。在一个实施例中，一种方法包括沿着出射光路将光照射到佩戴眼镜的用户的眼睛。在检测到眼镜时，光以在随机偏振相位和单极化相位之间切换的偏振图案中被动态偏振，其中随机偏振相位包括沿着出射光路的第一偏振和与第一偏振正交的第二偏振沿反射光路。单极化相具有单极化。在随机极化阶段期间，从眼镜反射的眩光被滤出并且捕获瞳孔图像。在单极化阶段期间捕获闪烁图像。基于瞳孔特征和闪光特征，重复检测注视位置。

8. 发明授权

US08675049B2 Navigation model to render centered objects using images 有权
标题翻译：使用图像渲染中心对象的导航模型
公开(公告)号：US08675049B2
公开(公告)日：2014-03-18
申请号：US13156975
申请日：2011-06-09
申请人： Johannes Kopf , Eric Stollnitz , Sudipta Sinha , Rick Szeliski
发明人： Johannes Kopf , Eric Stollnitz , Sudipta Sinha , Rick Szeliski
IPC分类号： H04N13/02
CPC分类号： H04N13/194 , H04N13/221 , H04N13/264 , H04N13/296
摘要： A 3D model of an object is rendered using centered images of the object. An algorithm executed locally or in a distributed manner calculates camera positions for the images and determines a virtual camera path based on the camera positions. The application adjusts the images to fit the plane of the virtual camera path and fills in the gaps between the images using transition renderings. To improve user experience, the application also calculates resting positions for navigation stop points using a spring system. Upon constructing the 3D model, the application can transmit the 3D model to a variety of user devices including the network connected device having a camera module that captured the images.
摘要翻译：使用对象的中心图像渲染对象的3D模型。本地或以分布式方式执行的算法计算图像的相机位置，并基于相机位置确定虚拟相机路径。应用程序调整图像以适应虚拟相机路径的平面，并使用过渡渲染填充图像之间的间隙。为了提高用户体验，应用程序还使用弹簧系统计算导航停止点的静止位置。在构建3D模型时，应用可以将3D模型发送到各种用户设备，包括具有拍摄图像的相机模块的网络连接设备。

9. 发明申请

US20120314040A1 NAVIGATION MODEL TO RENDER CENTERED OBJECTS USING IMAGES 有权
标题翻译：使用图像渲染中心对象的导航模型
公开(公告)号：US20120314040A1
公开(公告)日：2012-12-13
申请号：US13156975
申请日：2011-06-09
申请人： Johannes Kopf , Eric Stollnitz , Sudipta Sinha , Rick Szeliski
发明人： Johannes Kopf , Eric Stollnitz , Sudipta Sinha , Rick Szeliski
IPC分类号： H04N13/02
CPC分类号： H04N13/194 , H04N13/221 , H04N13/264 , H04N13/296
摘要： A 3D model of an object is rendered using centered images of the object. An algorithm executed locally or in a distributed manner calculates camera positions for the images and determines a virtual camera path based on the camera positions. The application adjusts the images to fit the plane of the virtual camera path and fills in the gaps between the images using transition renderings. To improve user experience, the application also calculates resting positions for navigation stop points using a spring system. Upon constructing the 3D model, the application can transmit the 3D model to a variety of user devices including the network connected device having a camera module that captured the images.
摘要翻译：使用对象的中心图像渲染对象的3D模型。本地或以分布式方式执行的算法计算图像的相机位置，并基于相机位置确定虚拟相机路径。应用程序调整图像以适应虚拟相机路径的平面，并使用过渡渲染填充图像之间的间隙。为了提高用户体验，应用程序还使用弹簧系统计算导航停止点的静止位置。在构建3D模型时，应用可以将3D模型发送到各种用户设备，包括具有拍摄图像的相机模块的网络连接设备。

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