-
公开(公告)号：US09754154B2
公开(公告)日：2017-09-05
申请号：US14559757
申请日：2014-12-03
Applicant: Microsoft Technology Licensing, LLC
Inventor： Robert M. Craig , Vladimir Tankovich , Craig Peeper , Ketan Dalal , Bhaven Dedhia , Casey Meekhof
CPC classification number: G06K9/00241 , G06F21/32 , G06T17/20 , G06T2207/10021 , G06T2207/20021 , G06T2207/30201 , G06T2210/12
Abstract: A candidate human head is found in depth video using a head detector. A head region of light intensity video is spatially resolved with a three-dimensional location of the candidate human head in the depth video. Facial recognition is performed on the head region of the light intensity video using a face recognizer.
-
公开(公告)号：US09679390B2
公开(公告)日：2017-06-13
申请号：US14143879
申请日：2013-12-30
Applicant: Microsoft Technology Licensing, LLC
Inventor： Craig Peeper , Johnny Lee , Tommer Leyvand , Szymon Stachniak
CPC classification number: G06T7/194 , G06T7/11 , G06T7/215 , G06T7/254 , G06T15/00 , G06T19/00 , G06T2207/10028
Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may then be discarded to isolate one or more voxels associated with a foreground object such as a human target and the isolated voxels associated with the foreground object may be processed.
-
公开(公告)号：US09522328B2
公开(公告)日：2016-12-20
申请号：US14477713
申请日：2014-09-04
Applicant: Microsoft Technology Licensing, LLC
Inventor： Tommer Leyvand , Johnny Chung Lee , Szymon Stachniak , Craig Peeper , Shao Liu
CPC classification number: A63F13/52 , A63F13/06 , A63F13/10 , A63F13/213 , A63F13/428 , A63F2300/1075 , A63F2300/6045 , G06F3/017 , G06K9/00342 , G06K9/00362 , G06K9/00711 , G06K9/44 , G06K9/469 , G06T7/194 , G06T7/75 , G06T2207/10028 , G06T2207/30196
Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.
-
公开(公告)号：US20160266650A1
公开(公告)日：2016-09-15
申请号：US14645220
申请日：2015-03-11
Applicant: Microsoft Technology Licensing, LLC
Inventor： Casey Meekhof , Robert M. Craig , Craig Peeper , Patrick O. Cook , Ketan Dalal , Vladimir Tankovich , Anton Rakovchuk
CPC classification number: G06F3/017 , G06F3/005 , G06K9/00335 , G06K9/00369 , G06K9/44 , G06K9/4661 , G09G5/18
Abstract: A computer system comprises a hardware interface, a computer-memory device, an update engine, and a posture-recognition engine. The hardware interface is configured to receive depth video of an environment from a camera. The computer-memory device stores a background model of the environment preservable over a reboot of the computer system, the background model including a plurality of trusted coordinates derived from the depth video. The update engine is configured to update the background model, including moving a trusted coordinate to greater depth if an observed pixel is behind the trusted coordinate over a first duration, but retaining the trusted coordinate if the observed pixel depth is in front of the trusted coordinate over the first duration. The posture-recognition engine is configured to recognize posture of a user in front of a background portion of the video, which is bounded by the trusted coordinates of the background model.
Abstract translation: 计算机系统包括硬件接口，计算机存储设备，更新引擎和姿势识别引擎。 硬件接口被配置为从相机接收环境的深度视频。 计算机存储设备存储在计算机系统的重启中可保护的环境的背景模型，背景模型包括从深度视频导出的多个可信任坐标。 更新引擎被配置为更新背景模型，包括如果观察到的像素在第一持续时间内在可信坐标之后移动可信坐标，则保持可信坐标，如果观察到的像素深度在可信坐标之前 在第一个持续时间。 姿态识别引擎被配置为识别由背景模型的可信坐标限定的视频的背景部分前面的用户的姿势。
-
公开(公告)号：US09390542B2
公开(公告)日：2016-07-12
申请号：US14076886
申请日：2013-11-11
Applicant: Microsoft Technology Licensing, LLC
Inventor： Michael V. Oneppo , Craig Peeper , Andrew L. Bliss , John L. Rapp , Mark M. Lacey
CPC classification number: G06T15/005 , G06F8/4441 , G06F9/449 , G06F9/541 , G06T1/20 , G06T15/80 , G06T2200/28
Abstract: Allocation of memory registers for shaders by a processor is described herein. For each shader, registers are allocated based on the shader's level of complexity. Simpler shader instances are restricted to a smaller number of memory registers. More complex shader instances are allotted more registers. To do so, developers' high level shading level (HLSL) language includes template classes of shaders that can later be replaced by complex or simple versions of the shader. The HLSL is converted to bytecode that can be used to rasterize pixels on a computing device.
-
Patent Agency Ranking
公开(公告)号：US10552666B2
公开(公告)日：2020-02-04
申请号：US15666113
申请日：2017-08-01
Applicant: Microsoft Technology Licensing, LLC
Inventor： Robert M. Craig , Vladimir Tankovich , Craig Peeper , Ketan Dalal , Bhaven Dedhia , Casey Meekhof
Abstract: A candidate human head is found in depth video using a head detector. A head region of light intensity video is spatially resolved with a three-dimensional location of the candidate human head in the depth video. Facial recognition is performed on the head region of the light intensity video using a face recognizer.
-
公开(公告)号：US20180075288A1
公开(公告)日：2018-03-15
申请号：US15666113
申请日：2017-08-01
Applicant: Microsoft Technology Licensing, LLC
Inventor： Robert M. Craig , Vladimir Tankovich , Craig Peeper , Ketan Dalal , Bhaven Dedhia , Casey Meekhof
CPC classification number: G06K9/00241 , G06F21/32 , G06T17/20 , G06T2207/10021 , G06T2207/20021 , G06T2207/30201 , G06T2210/12
Abstract: A candidate human head is found in depth video using a head detector. A head region of light intensity video is spatially resolved with a three-dimensional location of the candidate human head in the depth video. Facial recognition is performed on the head region of the light intensity video using a face recognizer.
-
公开(公告)号：US09821226B2
公开(公告)日：2017-11-21
申请号：US14602333
申请日：2015-01-22
Applicant: Microsoft Technology Licensing, LLC
Inventor： Tommer Leyvand , Johnny Lee , Craig Peeper , Szymon Stachniak , Shao Liu
IPC: G06K9/00 , A63F13/52 , G06F3/01 , A63F13/213 , A63F13/20 , A63F13/40 , G06T7/73 , G06T7/194 , A63F13/428 , G06K9/44 , G06K9/46
CPC classification number: A63F13/52 , A63F13/06 , A63F13/10 , A63F13/213 , A63F13/428 , A63F2300/1075 , A63F2300/6045 , G06F3/017 , G06K9/00342 , G06K9/00362 , G06K9/00711 , G06K9/44 , G06K9/469 , G06T7/194 , G06T7/75 , G06T2207/10028 , G06T2207/30196
Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.
-
公开(公告)号：US09639166B2
公开(公告)日：2017-05-02
申请号：US14645220
申请日：2015-03-11
Applicant: Microsoft Technology Licensing, LLC
Inventor： Casey Meekhof , Robert M. Craig , Craig Peeper , Patrick O. Cook , Ketan Dalal , Vladimir Tankovich , Anton Rakovchuk
CPC classification number: G06F3/017 , G06F3/005 , G06K9/00335 , G06K9/00369 , G06K9/44 , G06K9/4661 , G09G5/18
Abstract: A computer system comprises a hardware interface, a computer-memory device, an update engine, and a posture-recognition engine. The hardware interface is configured to receive depth video of an environment from a camera. The computer-memory device stores a background model of the environment preservable over a reboot of the computer system, the background model including a plurality of trusted coordinates derived from the depth video. The update engine is configured to update the background model, including moving a trusted coordinate to greater depth if an observed pixel is behind the trusted coordinate over a first duration, but retaining the trusted coordinate if the observed pixel depth is in front of the trusted coordinate over the first duration. The posture-recognition engine is configured to recognize posture of a user in front of a background portion of the video, which is bounded by the trusted coordinates of the background model.
-
公开(公告)号：US09824484B2
公开(公告)日：2017-11-21
申请号：US15208328
申请日：2016-07-12
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Michael V. Oneppo , Craig Peeper , Andrew L. Bliss , John L. Rapp , Mark M. Lacey
CPC classification number: G06T15/005 , G06F8/4441 , G06F9/449 , G06F9/541 , G06T1/20 , G06T15/80 , G06T2200/28
Abstract: Allocation of memory registers for shaders by a processor is described herein. For each shader, registers are allocated based on the shader's level of complexity. Simpler shader instances are restricted to a smaller number of memory registers. More complex shader instances are allotted more registers. To do so, developers' high level shading level (HLSL) language includes template classes of shaders that can later be replaced by complex or simple versions of the shader. The HLSL is converted to bytecode that can be used to rasterize pixels on a computing device.
-
-
-
-
-
-
-
-
-
Search Results
18
records
(took 0.027 seconds)
