专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20110058709A1 VISUAL TARGET TRACKING USING MODEL FITTING AND EXEMPLAR 有权
标题翻译：使用模型配置和示例的视觉目标跟踪
公开(公告)号：US20110058709A1
公开(公告)日：2011-03-10
申请号：US12953069
申请日：2010-11-23
申请人： Alex Kipman , Mark Finocchio , Ryan M. Geiss , Johnny Chung Lee , Charles Claudius Marais , Zsolt Mathe
发明人： Alex Kipman , Mark Finocchio , Ryan M. Geiss , Johnny Chung Lee , Charles Claudius Marais , Zsolt Mathe
IPC分类号： G06K9/00
CPC分类号： G06K9/00362 , A63F13/10 , A63F13/213 , A63F13/428 , A63F2300/1012 , A63F2300/1093 , A63F2300/6045 , G06F3/01 , G06K9/00369 , G06K9/32 , G06T7/251 , G06T7/285 , G06T2207/10016 , G06T2207/10028 , G06T2207/30196
摘要： A method of tracking a target includes receiving an observed depth image of the target from a source and analyzing the observed depth image with a prior-trained collection of known poses to find an exemplar pose that represents an observed pose of the target. The method further includes rasterizing a model of the target into a synthesized depth image having a rasterized pose and adjusting the rasterized pose of the model into a model-fitting pose based, at least in part, on differences between the observed depth image and the synthesized depth image. Either the exemplar pose or the model-fitting pose is then selected to represent the target.
摘要翻译：跟踪目标的方法包括从源接收观察到的目标深度图像并且利用已知姿势的先前训练集合来分析所观察的深度图像，以找到表示目标观察姿势的示范姿态。该方法还包括将目标的模型光栅化成具有光栅化姿态的合成深度图像，并且至少部分地基于观察到的深度图像和合成的图像之间的差异将模型的光栅化姿态调整为模型拟合姿势深度图像。然后选择示范姿势或模型拟合姿势来表示目标。

22. 发明申请

US20100197391A1 VISUAL TARGET TRACKING 有权
标题翻译：视觉目标跟踪
公开(公告)号：US20100197391A1
公开(公告)日：2010-08-05
申请号：US12632645
申请日：2009-12-07
申请人： Ryan M. Geiss
发明人： Ryan M. Geiss
IPC分类号： A63F13/00 , A63F9/24
CPC分类号： G06T13/40 , A63F2300/1093 , A63F2300/6607 , A63F2300/8029 , G06K9/00369 , G06T7/251 , G06T2207/10028 , G06T2207/30196
摘要： A target tracking method includes representing a human target with a machine-readable model including a plurality of skeletal points. The plurality of skeletal points are adjustable into a plurality of different legal poses. The method further includes receiving an observed depth image of the human target from a source and determining proposed positions for one or more of the skeletal points of the machine-readable model based on the observed depth image. The proposed positions of the skeletal points are then adjusted to comply with one or more rules if one or more of the proposed positions violates any of the one or more rules.
摘要翻译：目标跟踪方法包括用包括多个骨架点的机器可读模型来表示人类目标。多个骨骼点可调整成多个不同的法定姿态。该方法还包括从源接收观察到的人类目标的深度图像，并且基于观察到的深度图像来确定机器可读模型的一个或多个骨架点的建议位置。然后如果所提出的一个或多个位置违反一个或多个规则中的任何一个，则调整骨架点的建议位置以符合一个或多个规则。

23. 发明申请

US20100197390A1 POSE TRACKING PIPELINE 有权
标题翻译： POSE跟踪管道
公开(公告)号：US20100197390A1
公开(公告)日：2010-08-05
申请号：US12603437
申请日：2009-10-21
申请人： Robert Matthew Craig , Tommer Leyvand , Craig Peeper , Momim M. Al-Ghosien , Matt Bronder , Oliver Williams , Ryan M. Geiss , Jamie Daniel Joseph Shotton , Johnny Lee , Mark Finocchio
发明人： Robert Matthew Craig , Tommer Leyvand , Craig Peeper , Momim M. Al-Ghosien , Matt Bronder , Oliver Williams , Ryan M. Geiss , Jamie Daniel Joseph Shotton , Johnny Lee , Mark Finocchio
IPC分类号： A63F13/00
CPC分类号： G06K9/00335 , A63F13/428 , A63F2300/1006 , A63F2300/1093 , G06F3/011 , G06F3/033 , G06K9/00369 , G06T17/10 , G06T19/00
摘要： A method of tracking a target includes receiving from a source an observed depth image of a scene including the target. Each pixel of the observed depth image is labeled as either a foreground pixel belonging to the target or a background pixel not belonging to the target. Each foreground pixel is labeled with body part information indicating a likelihood that that foreground pixel belongs to one or more body parts of the target. The target is modeled with a skeleton including a plurality of skeletal points, each skeletal point including a three dimensional position derived from body part information of one or more foreground pixels.
摘要翻译：跟踪目标的方法包括从源接收包括目标的场景的观测深度图像。观察到的深度图像的每个像素被标记为属于目标的前景像素或不属于目标的背景像素。每个前景像素用身体部分信息标记，指示该前景像素属于目标的一个或多个身体部位的可能性。目标用包括多个骨骼点的骨架建模，每个骨骼点包括从一个或多个前景像素的身体部位信息导出的三维位置。

24. 发明授权

US09171264B2 Parallel processing machine learning decision tree training 有权
标题翻译：并行处理机器学习决策树训练
公开(公告)号：US09171264B2
公开(公告)日：2015-10-27
申请号：US12969112
申请日：2010-12-15
申请人： Mark Finocchio , Richard E. Moore , Ryan M. Geiss , Jamie Shotton
发明人： Mark Finocchio , Richard E. Moore , Ryan M. Geiss , Jamie Shotton
IPC分类号： G06F15/80 , G06F15/167 , G06N99/00 , G06N5/04 , G06K9/00 , G06K9/62
CPC分类号： G06N99/005 , G06K9/00986 , G06K9/6281 , G06N5/046
摘要： Embodiments are disclosed herein that relate to generating a decision tree through graphical processing unit (GPU) based machine learning. For example, one embodiment provides a method including, for each level of the decision tree: performing, at each GPU of the parallel processing pipeline, a feature test for a feature in a feature set on every example in an example set. The method further includes accumulating results of the feature tests in local memory blocks. The method further includes writing the accumulated results from each local memory block to global memory to generate a histogram of features for every node in the level, and for each node in the level, assigning a feature having a lowest entropy in accordance with the histograms to the node.
摘要翻译：本文公开的实施例涉及通过基于图形处理单元（GPU）的机器学习来生成决策树。例如，一个实施例提供一种方法，其包括对于决策树的每个级别：在并行处理流水线的每个GPU处执行在示例集合中的每个示例上的特征集中的特征的特征测试。该方法还包括在本地存储器块中积累特征测试的结果。该方法还包括将来自每个本地存储器块的累积结果写入全局存储器以产生该级别中的每个节点的特征的直方图，并且对于该级别中的每个节点，根据直方图将具有最低熵的特征分配到节点。

25. 发明授权

US08577084B2 Visual target tracking 有权
标题翻译：视觉目标跟踪
公开(公告)号：US08577084B2
公开(公告)日：2013-11-05
申请号：US12632587
申请日：2009-12-07
申请人： Ryan M. Geiss
发明人： Ryan M. Geiss
IPC分类号： G06K9/00
CPC分类号： G06K9/00369 , A63F2300/1093 , A63F2300/6607
摘要： A visual target tracking method includes representing a human target with a machine-readable model configured for adjustment into a plurality of different poses and receiving an observed depth image of the human target from a source. The observed depth image is compared to the model. A refine-z force vector is then applied to one or more force-receiving locations of the model to move a portion of the model towards a corresponding portion of the observed depth image if that portion of the model is Z-shifted from that corresponding portion of the observed depth image.
摘要翻译：视觉目标跟踪方法包括使用机器可读模型来表示人类目标，所述机器可读模型被配置为调整为多个不同的姿态并且从源接收人类目标的观察到的深度图像。将观察到的深度图像与模型进行比较。然后，将优化z力向量应用于模型的一个或多个力接收位置，以将模型的一部分朝向观察到的深度图像的对应部分移动，如果模型的该部分从该对应部分Z偏移的观察深度图像。

26. 发明授权

US08565485B2 Pose tracking pipeline 有权
公开(公告)号：US08565485B2
公开(公告)日：2013-10-22
申请号：US13615269
申请日：2012-09-13
申请人： Robert Matthew Craig , Tommer Leyvand , Craig Peeper , Momin M. Al-Ghosien , Matt Bronder , Oliver Williams , Ryan M. Geiss , Jamie Daniel Joseph Shotton , Johnny Lee , Mark Finocchio
发明人： Robert Matthew Craig , Tommer Leyvand , Craig Peeper , Momin M. Al-Ghosien , Matt Bronder , Oliver Williams , Ryan M. Geiss , Jamie Daniel Joseph Shotton , Johnny Lee , Mark Finocchio
IPC分类号： G06K9/00 , H04N11/02
CPC分类号： G06K9/00335 , A63F13/428 , A63F2300/1006 , A63F2300/1093 , G06F3/011 , G06F3/033 , G06K9/00369 , G06T17/10 , G06T19/00
摘要： A method of tracking a target includes receiving from a source a depth image of a scene including the human subject. The depth image includes a depth for each of a plurality of pixels. The method further includes identifying pixels of the depth image that belong to the human subject and deriving from the identified pixels of the depth image one or more machine readable data structures representing the human subject as a body model including a plurality of shapes.

27. 发明授权

US08488888B2 Classification of posture states 有权
标题翻译：姿势状态分类
公开(公告)号：US08488888B2
公开(公告)日：2013-07-16
申请号：US12979897
申请日：2010-12-28
申请人： Alexandru Balan , Matheen Siddiqui , Ryan M. Geiss , Alex Aben-Athar Kipman , Oliver Michael Christian Williams , Jamie Shotton
发明人： Alexandru Balan , Matheen Siddiqui , Ryan M. Geiss , Alex Aben-Athar Kipman , Oliver Michael Christian Williams , Jamie Shotton
IPC分类号： G06K9/00 , G06K9/46 , H04N9/47
CPC分类号： G06F3/011 , G06F3/017 , G06K9/00342 , G06K9/00369 , G06K9/00375
摘要： Systems and methods for estimating a posture of a body part of a user are disclosed. In one disclosed embodiment, an image is received from a sensor, where the image includes at least a portion of an image of the user including the body part. The skeleton information of the user is estimated from the image, a region of the image corresponding to the body part is identified at least partially based on the skeleton information, and a shape descriptor is extracted for the region and the shape descriptor is classified based on training data to estimate the posture of the body part.
摘要翻译：公开了用于估计用户的身体部位的姿势的系统和方法。在一个公开的实施例中，从传感器接收图像，其中图像包括包括身体部分的用户的图像的至少一部分。从图像估计用户的骨架信息，至少部分地基于骨骼信息来识别对应于身体部位的图像的区域，并且针对该区域提取形状描述符，并且基于训练数据来估计身体部位的姿势。

28. 发明授权

US08267781B2 Visual target tracking 有权
标题翻译：视觉目标跟踪
公开(公告)号：US08267781B2
公开(公告)日：2012-09-18
申请号：US12363604
申请日：2009-01-30
申请人： Ryan M. Geiss
发明人： Ryan M. Geiss
IPC分类号： A63F13/00
CPC分类号： G06T7/2046 , A63F13/213 , A63F13/428 , A63F2300/1093 , A63F2300/6607 , G06T7/251 , G06T2207/10021 , G06T2207/10028 , G06T2207/30196
摘要： A method of tracking a target includes receiving an observed depth image of the target from a source and obtaining a posed model of the target. The model is rasterized into a synthesized depth image, and the pose of the model is adjusted based, at least in part, on differences between the observed depth image and the synthesized depth image.
摘要翻译：跟踪目标的方法包括从源接收目标的观测深度图像并获得目标的姿态模型。该模型被光栅化为合成深度图像，并且至少部分地基于观察到的深度图像和合成深度图像之间的差异来调整模型的姿态。

29. 发明申请

US20120154373A1 PARALLEL PROCESSING MACHINE LEARNING DECISION TREE TRAINING 有权
标题翻译：平行加工机器学习决策树培训
公开(公告)号：US20120154373A1
公开(公告)日：2012-06-21
申请号：US12969112
申请日：2010-12-15
申请人： Mark Finocchio , Richard E. Moore , Ryan M. Geiss , Jamie Shotton
发明人： Mark Finocchio , Richard E. Moore , Ryan M. Geiss , Jamie Shotton
IPC分类号： G06F15/80 , G06T15/00
CPC分类号： G06N99/005 , G06K9/00986 , G06K9/6281 , G06N5/046
摘要： Embodiments are disclosed herein that relate to generating a decision tree through graphical processing unit (GPU) based machine learning. For example, one embodiment provides a method including, for each level of the decision tree: performing, at each GPU of the parallel processing pipeline, a feature test for a feature in a feature set on every example in an example set. The method further includes accumulating results of the feature tests in local memory blocks. The method further includes writing the accumulated results from each local memory block to global memory to generate a histogram of features for every node in the level, and for each node in the level, assigning a feature having a lowest entropy in accordance with the histograms to the node.
摘要翻译：本文公开的实施例涉及通过基于图形处理单元（GPU）的机器学习来生成决策树。例如，一个实施例提供一种方法，其包括对于决策树的每个级别：在并行处理流水线的每个GPU处执行在示例集合中的每个示例上的特征集中的特征的特征测试。该方法还包括在本地存储器块中积累特征测试的结果。该方法还包括将来自每个本地存储器块的累积结果写入全局存储器以产生该级别中的每个节点的特征的直方图，并且对于该级别中的每个节点，根据直方图将具有最低熵的特征分配到节点。

30. 发明授权

US07932914B1 Storing high dynamic range data in a low dynamic range format 有权
标题翻译：以低动态范围格式存储高动态范围数据
公开(公告)号：US07932914B1
公开(公告)日：2011-04-26
申请号：US11254385
申请日：2005-10-20
申请人： Ryan M. Geiss , Mehmet Cem Cebenoyan
发明人： Ryan M. Geiss , Mehmet Cem Cebenoyan
IPC分类号： G09G5/00
CPC分类号： G09G5/393 , G09G5/395 , G09G2340/02 , G09G2360/12
摘要： Systems and methods for storing high dynamic range image data in a low dynamic range format may be used to store the high dynamic range image data in less memory. The memory bandwidth needed to access the high dynamic range data is reduced and processing performance may be improved when performance is limited by memory bandwidth. The high dynamic range image data is scaled and compressed into a low dynamic range format for storage in a render target. If the compressed high dynamic range image data contains multiple data samples per pixel, the data may be processed to produce filtered compressed high dynamic range image data with only one sample per pixel. The high dynamic range image may be reconstructed from the low dynamic range format data and further processed as high dynamic range format data for a range of applications.
摘要翻译：用于以低动态范围格式存储高动态范围图像数据的系统和方法可用于在较少存储器中存储高动态范围图像数据。降低访问高动态范围数据所需的存储器带宽，并且当性能受到存储器带宽的限制时，可以提高处理性能。高动态范围图像数据被缩放并压缩成低动态范围格式以存储在渲染目标中。如果压缩的高动态范围图像数据包含每像素多个数据样本，则可以处理数据以产生仅具有每像素一个采样的滤波压缩的高动态范围图像数据。高动态范围图像可以从低动态范围格式数据重建，并且作为用于一系列应用的高动态范围格式数据被进一步处理。

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