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

US06911995B2 Computer vision depth segmentation using virtual surface 失效
标题翻译：计算机视觉深度分割使用虚拟表面
公开(公告)号：US06911995B2
公开(公告)日：2005-06-28
申请号：US09954770
申请日：2001-09-18
申请人： Yuri A. Ivanov , Alex P. Pentland , Christopher R. Wren
发明人： Yuri A. Ivanov , Alex P. Pentland , Christopher R. Wren
IPC分类号： H04N13/00
CPC分类号： G06T7/246 , G06T7/11 , G06T7/194 , G06T7/593 , G06T2207/10012 , H04N13/111 , H04N13/15 , H04N13/239 , H04N13/246 , H04N13/254 , H04N13/257 , H04N13/286 , H04N13/324 , H04N13/363 , H04N2013/0081 , H04N2013/0092
摘要： The location of an object in a physical scene is identified with a stereo camera. A virtual surface is identified in the physical scene, and an approximate disparity set is constructed for the virtual surface. A main and a reference image of the scene are acquired by the stereo camera. The reference image is warped according to the disparity set, and subtracted from the main image to determine a set of depth residual values. Pixels having a substantially non-zero residual are identified with a surface of the object not coincident with the virtual surface.
摘要翻译：物体场景中物体的位置用立体相机识别。在物理场景中识别虚拟表面，并为虚拟表面构建近似视差集合。场景的主要和参考图像由立体摄像机获取。参考图像根据视差设置翘曲，并从主图像中减去以确定一组深度残差值。具有基本上非零残差的像素被识别为与虚拟表面不一致的对象的表面。

2. 发明申请

US20080317332A1 System and Method for Determining Geometries of Scenes 失效
标题翻译：确定场景几何的系统和方法
公开(公告)号：US20080317332A1
公开(公告)日：2008-12-25
申请号：US11766174
申请日：2007-06-21
申请人： Yuri A. Ivanov , Jay E. Thornton , Christopher R. Wren
发明人： Yuri A. Ivanov , Jay E. Thornton , Christopher R. Wren
IPC分类号： G06K9/64 , G06F17/00 , G06K9/00 , G06K9/20
CPC分类号： G06K9/2036 , G01B11/24
摘要： A method and an apparatus determines a geometry of a scene by projecting one or more output image into the scene, in which a time to project the output image is t1. Input images are acquired of the scene, in which a time to acquire each input image is t2, and in which t1>t2 and in which the input image includes a distinguishable stripe of pixels with an edge due to t1>t2. An amount of distortion of the edge is measured from a straight line to determine a geometry of the scene.
摘要翻译：一种方法和装置通过将一个或多个输出图像投影到场景中来确定场景的几何形状，其中投影输出图像的时间为t1。获取每个输入图像的时间为t2的场景的输入图像，并且其中t1> t2，并且其中输入图像包括由于t1> t2而具有边缘的可区分的像素条。从直线测量边缘的扭曲量，以确定场景的几何形状。

3. 发明授权

US08149278B2 System and method for modeling movement of objects using probabilistic graphs obtained from surveillance data 有权
标题翻译：使用从监视数据获得的概率图来建模物体运动的系统和方法
公开(公告)号：US08149278B2
公开(公告)日：2012-04-03
申请号：US11671016
申请日：2007-02-05
申请人： Christopher R. Wren , Yuri A. Ivanov , Alexander Sorokin , Ishwinder Kaur Banga
发明人： Christopher R. Wren , Yuri A. Ivanov , Alexander Sorokin , Ishwinder Kaur Banga
IPC分类号： H04N7/18
CPC分类号： H04N7/18 , G06K9/00771 , G06K9/6296
摘要： A method and system tracks models and predict object movement in an environment. Sequences of temporally and spatially adjacent events sensed by the set of sensors are linked to form a set of tracklets. Each tracklet has an associated starting and terminating location. The tracklets are used to construct a directed graph including starting nodes, terminating nodes, and, intermediate nodes connected by edges. The intermediate nodes can be split nodes where tracklets diverge onto different tracks, and join nodes where multiple tracklets converge onto a single path. Probabilities are assigned to the edges to model and predict movement of the objects in the environment.
摘要翻译：方法和系统跟踪模型并预测环境中的物体移动。由传感器组感测的时间和空间相邻事件的序列被链接以形成一组轨迹。每个轨迹具有相关的起始和终止位置。轨迹用于构造有向图，包括起始节点，终止节点以及通过边连接的中间节点。中间节点可以是轨迹分散到不同轨道上的分割节点，并且连接多个轨迹收敛到单个路径上的节点。将概率分配给边缘以建模和预测对象在环境中的移动。

4. 发明授权

US07907781B2 System and method for determining geometries of scenes 失效
标题翻译：用于确定场景几何的系统和方法
公开(公告)号：US07907781B2
公开(公告)日：2011-03-15
申请号：US11766174
申请日：2007-06-21
申请人： Yuri A. Ivanov , Jay E. Thornton , Christopher R. Wren
发明人： Yuri A. Ivanov , Jay E. Thornton , Christopher R. Wren
IPC分类号： G06K9/48
CPC分类号： G06K9/2036 , G01B11/24
摘要： A method and an apparatus determines a geometry of a scene by projecting one or more output image into the scene, in which a time to project the output image is t1. Input images are acquired of the scene, in which a time to acquire each input image is t2, and in which t1>t2 and in which the input image includes a distinguishable stripe of pixels with an edge due to t1>t2. An amount of distortion of the edge is measured from a straight line to determine a geometry of the scene.
摘要翻译：一种方法和装置通过将一个或多个输出图像投影到场景中来确定场景的几何形状，其中投影输出图像的时间为t1。获取每个输入图像的时间为t2的场景的输入图像，并且其中t1> t2，并且其中输入图像包括由于t1> t2而具有边缘的可区分的像素条。从直线测量边缘的扭曲量，以确定场景的几何形状。

5. 发明申请

US20080130951A1 System and Method for Modeling Movement of Objects Using Probabilistic Graphs Obtained From Surveillance Data 有权
标题翻译：使用从监控数据获得的概率图来建模对象运动的系统和方法
公开(公告)号：US20080130951A1
公开(公告)日：2008-06-05
申请号：US11671016
申请日：2007-02-05
申请人： Christopher R. Wren , Yuri A. Ivanov , Alexander Sorokin , Ishwinder Kaur Banga
发明人： Christopher R. Wren , Yuri A. Ivanov , Alexander Sorokin , Ishwinder Kaur Banga
IPC分类号： G06K9/00
CPC分类号： H04N7/18 , G06K9/00771 , G06K9/6296
摘要： A method and system tracks models and predict object movement in an environment. Sequences of temporally and spatially adjacent events sensed by the set of sensors are linked to form a set of tracklets. Each tracklet has an associated starting and terminating location. The tracklets are used to construct a directed graph including starting nodes, terminating nodes, and, intermediate nodes connected by edges. The intermediate nodes can be split nodes where tracklets diverge onto different tracks, and join nodes where multiple tracklets converge onto a single path. Probabilities are assigned to the edges to model and predict movement of the objects in the environment.
摘要翻译：方法和系统跟踪模型并预测环境中的物体移动。由传感器组感测的时间和空间相邻事件的序列被链接以形成一组轨迹。每个轨迹具有相关的起始和终止位置。轨迹用于构造有向图，包括起始节点，终止节点以及通过边连接的中间节点。中间节点可以是轨迹分散到不同轨道上的分割节点，并且连接多个轨迹收敛到单个路径上的节点。将概率分配给边缘以建模和预测对象在环境中的移动。

6. 发明申请

US20080130949A1 Surveillance System and Method for Tracking and Identifying Objects in Environments 审中-公开
标题翻译：监控系统和跟踪和识别环境中物体的方法
公开(公告)号：US20080130949A1
公开(公告)日：2008-06-05
申请号：US11565264
申请日：2006-11-30
申请人： Yuri A. Ivanov , Alexander Sorokin , Christopher R. Wren
发明人： Yuri A. Ivanov , Alexander Sorokin , Christopher R. Wren
IPC分类号： G06K9/00 , H04N7/18
CPC分类号： H04N7/181 , G06K9/00771 , G06K9/6296
摘要： A method and system tracks objects using a surveillance database storing events acquired by a set of sensors and sequences of images acquired by a set of cameras. Sequences of temporally and spatially adjacent events sensed by the set of sensors are linked to form a set of tracklets and stored in the database. Each tracklet has endpoints being either a track-start, track-join, tracklet-merge or tracklet-end node. A subset of sensors is selected, and a subset of tracklets associated with the subset of sensors is identified. A single starting tracklet is selected. All sequences of tracklets temporally and spatially adjacent to the starting tracklet are aggregated to construct a tracklet graph. The track-join nodes and the track-split nodes are disambiguated and eliminated from the track graph to determine a track of the object in the environment.
摘要翻译：方法和系统使用监视数据库跟踪对象，该监视数据库存储由一组传感器获取的事件和由一组相机获取的图像序列。由传感器组感测到的时间和空间相邻事件的序列被链接以形成一组轨迹并存储在数据库中。每个Tracklet都具有端点，即轨迹启动，轨迹连接，轨迹合并或轨迹结束节点。选择传感器的子集，并且识别与传感器子集相关联的轨迹的子集。选择单个起始轨迹。在时间上和空间上与起始轨迹相邻的所有轨迹序列被聚合以构成轨迹图。轨道连接节点和轨道分割节点被消除歧义，并从轨迹图中消除，以确定环境中对象的轨迹。

7. 发明申请

US20150105908A1 ROBOTIC PLACEMENT AND MANIPULATION WITH ENHANCED ACCURACY 有权
标题翻译：机器人配置和操纵与增强精度
公开(公告)号：US20150105908A1
公开(公告)日：2015-04-16
申请号：US14511718
申请日：2014-10-10
申请人： Yuri A. Ivanov , Rodney Brooks
发明人： Yuri A. Ivanov , Rodney Brooks
IPC分类号： B25J9/10
CPC分类号： B25J9/1697 , G05B2219/36414 , G05B2219/39101 , G05B2219/40562 , G05B2219/49113 , Y10S901/47
摘要： Systems and methods for providing precise robotic operations without the need for special or task-specific components utilize, in one implementation, a spatial adjustment system, physically separate from the robotic manipulator, supports the target workpiece and works in concert with the robotic manipulator to perform tasks with high spatial precision.
摘要翻译：在一个实施方式中，用于提供精确的机器人操作而不需要特殊或任务特定部件的系统和方法在与机器人操纵器物理分离的空间调节系统中使用，支撑目标工件并与机器人操纵器一起工作以执行空间精度高的任务

8. 发明授权

US08280839B2 Nearest neighbor methods for non-Euclidean manifolds 失效
标题翻译：非欧几里得歧管的最近邻方法
公开(公告)号：US08280839B2
公开(公告)日：2012-10-02
申请号：US12712791
申请日：2010-02-25
申请人： Yuri A. Ivanov , Rizwan Choudhry
发明人： Yuri A. Ivanov , Rizwan Choudhry
IPC分类号： G06F17/00
CPC分类号： G06K9/6252
摘要： Embodiments of the invention disclose a system and a method for determining a nearest neighbor to an input data point on a non-Euclidean manifold. The data points on the non-Euclidean manifold are clustered, projected into Euclidean sub-space nearest to the cluster and mapped from the Euclidean sub-space into a Hamming space such that neighboring data points of the Hamming space corresponds to neighboring data points on the non-Euclidean manifold. The method maps the input data point to the Hamming space corresponding to a particular Euclidean sub-space, wherein the particular Euclidean sub-space is the nearest to the input data point, and selects a data point corresponding to a nearest data point to the input data point in the Hamming space as the nearest neighbor for the input data point on the non-Euclidean manifold.
摘要翻译：本发明的实施例公开了一种用于确定非欧几里得歧管上的输入数据点的最近邻的系统和方法。非欧几里得歧管上的数据点被聚类，投影到最接近簇的欧几里德子空间中，并从欧几里得子空间映射成汉明空间，使得汉明空间的相邻数据点对应于非欧几里得歧管。该方法将输入数据点映射到与特定欧几里德子空间对应的汉明空间，其中特定欧几里得子空间最接近输入数据点，并且选择对应于最近数据点的数据点到输入 Hamming空间中的数据点作为非欧几里德流形上输入数据点的最近邻。

9. 发明申请

US20080247599A1 Method for Detecting Objects Left-Behind in a Scene 有权
标题翻译：检测场景中左后方的对象的方法
公开(公告)号：US20080247599A1
公开(公告)日：2008-10-09
申请号：US11697052
申请日：2007-04-05
申请人： Fatih M. Porikli , Yuri A. Ivanov
发明人： Fatih M. Porikli , Yuri A. Ivanov
IPC分类号： G06K9/74
CPC分类号： G06K9/00771
摘要： A method detects an object left-behind in a scene by updating a set of background models using a sequence of images acquired of the scene by a camera. Each background model is updated at a different temporal scales ranging from short term to long term. A foreground mask is determined from each background model after the updating for a particular image of the sequence. A motion image is updated from the set of foreground masks. In the motion, image, each pixel has an associated evidence value. The evidence values are compared with a evidence threshold to detect and signal an object left behind in the scene.
摘要翻译：一种方法通过使用由相机拍摄的场景的图像序列来更新一组背景模型来检测场景中的遗留物体。每个背景模型以不同的时间尺度更新，从短期到长期。在对序列的特定图像进行更新之后，从每个背景模型确定前景蒙版。运动图像从前景蒙版组更新。在运动，图像中，每个像素都具有相关的证据值。将证据值与证据阈值进行比较，以检测并发出场景中留下的物体。

10. 发明申请

US20080122589A1 Tactile Output Device 审中-公开
标题翻译：触觉输出设备
公开(公告)号：US20080122589A1
公开(公告)日：2008-05-29
申请号：US11563760
申请日：2006-11-28
申请人： Yuri A. Ivanov
发明人： Yuri A. Ivanov
IPC分类号： G08B6/00 , G09B21/00
CPC分类号： G06F3/016 , A61F9/08 , G09B21/003
摘要： A tactile output device including an electro-active polymer layer and first and second sets of coplanar conductors arranged proximate to the layer. The first and second sets of conductors are approximately at right angles to each other, and the conductors in each set are spaced apart and parallel to each other. The conductors can be selected individually to convey current to expand and contract the electro-active polymer in vicinities where the conductors intersect. The selection can be according to pixels in an image to product a three-dimensional contoured surface corresponding to the image.
摘要翻译：一种触觉输出装置，包括电活性聚合物层和靠近层布置的第一和第二组共面导体。第一和第二组导体大致彼此成直角，并且每组中的导体间隔开并且彼此平行。可以单独选择导体以传送电流以在电导体相交的附近扩展和收缩电活性聚合物。选择可以根据图像中的像素来产生对应于图像的三维轮廓表面。

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