-
公开(公告)号：US11354879B1
公开(公告)日：2022-06-07
申请号：US16733724
申请日：2020-01-03
Applicant: Amazon Technologies, Inc.
Abstract: Techniques are described for detecting a periphery of a surface based on a point set representing the surface. The surface may correspond to a display medium upon which content is projected. A shape model may be matched and aligned to a contour of the point set. A periphery or edge of the surface and corresponding display medium may be determined based on the aligned shape model.
-
公开(公告)号：US10198823B1
公开(公告)日：2019-02-05
申请号：US16110767
申请日：2018-08-23
Applicant: Amazon Technologies, Inc.
Inventor： Amit Kumar Agrawal , Abhishek Singh , Visesh Uday Kumar Chari , Lelin Zhang , Qiang Liu , Rohith Mysore Vijaya Kumar , David Ting-Yu Wu
Abstract: Devices and techniques are generally described for segmentation of object image data from background image data. In some examples, the segmentation of object image data may comprise capturing image data comprising color data and depth data. In some examples, the segmentation of object image data may further include separating the depth data into a plurality of clusters of image data, wherein each cluster is associated with a respective range of depth values. In various examples, the segmentation of object image data may comprise selecting a main cluster of image data as corresponding to an object of interest in the image data. In various other examples, the segmentation of object image data may comprise identifying pixels of the main cluster that correspond to the object of interest.
-
公开(公告)号：US09959480B1
公开(公告)日：2018-05-01
申请号：US15611403
申请日：2017-06-01
Applicant: Amazon Technologies, Inc.
Inventor： Amit Kumar Agrawal , Qiang Liu , David Ting-Yu Wu
CPC classification number: G06K9/00369 , G06K9/38 , G06K9/42 , G06K9/469
Abstract: Features are disclosed for classifying pixels included in a digital image. Distance information from a pixel to structural reference points, such as skeletal joints, is generated. The distance information is then applied to a pixel classifier to identify one or more classifications for the pixel.
-
公开(公告)号：US09996573B1
公开(公告)日：2018-06-12
申请号：US14222377
申请日：2014-03-21
Applicant: Amazon Technologies, Inc.
Inventor： Akshat Vig , Wei Xiao , Somasundaram Perianayagam , Timothy Andrew Rath , Barry Bailey Hunter, Jr. , Kiran-Kumar Muniswamy-Reddy , Yijun Lu , Qiang Liu , Ying Lin , Stuart Henry Seelye Marshall
IPC: G06F17/30
CPC classification number: G06F17/30584
Abstract: A hosted service may limit access to a table initially comprising one or more partitions. Access to the table may be limited to a provisioned capacity. A client of the service may request an increased capacity. A minimum number of partitions for providing the increased capacity may be determined. Proportions of the increased capacity may be allocated among members of successive generations of partitions to be provided by a member of a generation or its descendants. The proportions may be allocated to minimize the costs associated with splitting partitions based on the minimum number of partitions.
-
公开(公告)号：US09965865B1
公开(公告)日：2018-05-08
申请号：US15473334
申请日：2017-03-29
Applicant: Amazon Technologies, Inc.
Inventor： Amit Kumar Agrawal , Abhishek Singh , Visesh Uday Kumar Chari , Prakash Ramu , Lelin Zhang , Qiang Liu , Yadunandana Nagaraja Rao , Rohith Mysore Vijaya Kumar , Weijian Wang
CPC classification number: G06T7/194 , G06K9/00201 , G06K9/00234 , G06K9/00369 , G06K9/2027 , G06K9/22 , G06K9/4652 , G06K9/6218 , G06K9/6257 , G06K9/6267 , G06T2207/10024 , G06T2207/10028 , G06T2207/30196 , H04N13/204
Abstract: Devices and techniques are generally described for segmentation of image data using depth data. In various examples, color image data may be received from a digital camera. In some examples, depth image data may be received from a depth sensor. In various examples, the depth image data may be separated into a plurality of clusters of depth image data, wherein each cluster is associated with a respective range of depth values. In some further examples, a determination may be made that a first cluster of image data corresponds to an object of interest, such as a human subject, in the image data. In various examples, pixels of the first cluster may be encoded with foreground indicator data. In some further examples, segmented image data may be generated. The segmented image data may comprise pixels encoded with the foreground indicator data.
-
Patent Agency Ranking
公开(公告)号：US09562966B1
公开(公告)日：2017-02-07
申请号：US14742218
申请日：2015-06-17
Applicant: Amazon Technologies, Inc.
Inventor： Ronald Joseph Degges, Jr. , Qiang Liu
CPC classification number: G01S7/4865 , G01C3/00 , G01S7/481 , G01S7/4915 , G01S7/493 , G01S17/003 , G01S17/08 , G01S17/36 , G01S17/88 , G01S17/89
Abstract: A distance between a light source and a surface may be determined by emitting pulses of light from the light source and measuring an intensity of the light after the light reaches the surface. To determine a true distance, aliased distances, which are outside of a known distance segment, are disregarded. The distance segment may be defined by a modulation period of light emitted by the light source. The distance segment may be determined based on a ratio of a measured intensity of light captured during a first time interval and a second time interval, and a comparison of other types of evidence data that identifies a correct distance segment. The evidence data may include data associated with the amplitude (intensity) of the light captured, temporal variations in data, and/or analysis data collected from other surfaces that are adjacent to the surface.
Abstract translation: 光源和表面之间的距离可以通过发射来自光源的光的脉冲来确定，并且在光到达表面之后测量光的强度。 为了确定一个真正的距离，忽略了已知距离段以外的混叠距离。 距离段可以由光源发出的光的调制周期来定义。 距离段可以基于在第一时间间隔和第二时间间隔期间捕获的光的测量强度的比率以及识别正确距离段的其他类型的证据数据的比较来确定。 证据数据可以包括与捕获的光的振幅（强度），数据的时间变化和/或从与表面相邻的其它表面收集的分析数据相关联的数据。
-
公开(公告)号：US09753119B1
公开(公告)日：2017-09-05
申请号：US14167813
申请日：2014-01-29
Applicant: Amazon Technologies, Inc.
Inventor： Kavitha Velusamy , Ning Yao , Wai Chung Chu , Sowmya Gopalan , Qiang Liu , Rahul Agrawal , Manika Puri
IPC: G01S5/20
CPC classification number: G01S5/20 , G01S5/18 , G01S5/22 , G01S17/023 , G01S17/36 , G01S17/42 , G01S17/46 , G01S17/89
Abstract: A system may utilize sound localization techniques, such as time-difference-of-arrival techniques, to estimate an audio-based sound source position from which a sound originates. An optical image or depth map of an area containing the sound source location may then captured and analyzed to detect an object that is known or expected to have produced the sound. The position of the object may also be determined based on the analysis of the optical image or depth map. The position of the sound source may then be determined based at least in part on the position of the detected object or on a combination of the audio-based sound source position and the determined position of the object.
-
公开(公告)号：US09632592B1
公开(公告)日：2017-04-25
申请号：US14563229
申请日：2014-12-08
Applicant: Amazon Technologies, Inc.
Inventor： Qiang Liu , Samuel Henry Chang
CPC classification number: G06F3/0325 , G06F3/017 , G06F3/0425 , H04N5/74
Abstract: Systems and techniques for detecting gestures of a user based on analysis of acquired depth maps as well as identified distortion within one or more acquired color images. For instance, a system may project content onto a display surface within an environment. A user may then interact with the content via gestures, which may include hand gestures, gestures with a stylus or the like. In some instances, the content includes multiple selection portions, such as soft buttons, icons, and the like, that a user may select by pointing or touching with a finger or other type of selection tool. For instance, the projected content may include one or more projected icons and the user may select one of the icons by touching the display surface onto which the respective display icon is being projected.
-
公开(公告)号：US10096122B1
公开(公告)日：2018-10-09
申请号：US15472041
申请日：2017-03-28
Applicant: Amazon Technologies, Inc.
Inventor： Amit Kumar Agrawal , Abhishek Singh , Visesh Uday Kumar Chari , Lelin Zhang , Qiang Liu , Rohith Mysore Vijaya Kumar , David Ting-Yu Wu
Abstract: Devices and techniques are generally described for segmentation of object image data from background image data. In some examples, the segmentation of object image data may comprise capturing image data comprising color data and depth data. In some examples, the segmentation of object image data may further include separating the depth data into a plurality of clusters of image data, wherein each cluster is associated with a respective range of depth values. In various examples, the segmentation of object image data may comprise selecting a main cluster of image data as corresponding to an object of interest in the image data. In various other examples, the segmentation of object image data may comprise identifying pixels of the main cluster that correspond to the object of interest.
-
公开(公告)号：US09697433B1
公开(公告)日：2017-07-04
申请号：US14729894
申请日：2015-06-03
Applicant: Amazon Technologies, Inc.
Inventor： Amit Kumar Agrawal , Qiang Liu , David Ting-Yu Wu
CPC classification number: G06K9/00369 , G06K9/38 , G06K9/42 , G06K9/469
Abstract: Features are disclosed for classifying pixels included in a digital image. Distance information from a pixel to structural reference points, such as skeletal joints, is generated. The distance information is then applied to a pixel classifier to identify one or more classifications for the pixel.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.016 seconds)
