公开(公告)号：WO2015143661A9

公开(公告)日：2016-10-06

申请号：PCT/CN2014074179

申请日：2014-03-27

Applicant: INTEL CORP ,  YANG LIU ,  LI QIANG ,  WANG BIN ,  XU XIANCHAO ,  NIU BING

Inventor： YANG LIU ,  LI QIANG ,  WANG BIN ,  XU XIANCHAO ,  NIU BING

IPC: G06F19/00

CPC classification number: G06F17/5009 ,  G06F17/18 ,  G06F17/50 ,  G06F2217/16 ,  G06T7/35

Abstract: Various embodiments are generally directed to techniques for employing a hybrid of sequential and parallel processing to perform random sample and consensus (RANSAC). A device to perform RANSAC includes a derivation component to derive a first set of proposed models in parallel from a first set of minimal sample sets of a data set; and a comparison component to recalculate a required quantity of proposed models to derive an accurate model if a proposed model of the first set of proposed models better fits the data set than any proposed model derived prior to derivation of the first set of proposed models, and to determine whether to derive a second set of proposed models following derivation of the first set of proposed models based on a comparison of the required quantity to a quantity of previously derived proposed models that includes the first set. Other embodiments are described and claimed.

Abstract translation: 各种实施例通常涉及使用顺序和并行处理的混合来执行随机抽样和共同（RANSAC）的技术。 执行RANSAC的装置包括导出部件，以从数据集的第一组最小采样集合并行地导出第一组提出的模型; 以及比较组件，以重新计算所提出的模型的所需数量，以便如果所提出的第一组模型的拟议模型比在推导第一组建议模型之前导出的任何提出的模型更适合数据集，则导出精确模型，以及 基于所需数量与包括第一集合的先前导出的建议模型的数量的比较，来确定是否在推导第一组提出的模型之后导出第二组建议模型。 描述和要求保护其他实施例。

公开(公告)号：EP3008690A4

公开(公告)日：2017-05-31

申请号：EP13886672

申请日：2013-06-14

Applicant: INTEL CORP

Inventor： WANG TAO ,  FU LIANRUI ,  LI QIANG ,  LI JIANGUO ,  CHEN YURONG ,  PENG YA-TI ,  ZHANG YIMIN ,  YAO ANBANG

IPC: G06T7/00 ,  G06K9/62 ,  G06K9/68

CPC classification number: G06K9/6211 ,  G06K9/68

Abstract: Apparatuses, methods and storage medium associated with processing an image are disclosed herein. In embodiments, a method for processing one or more images may include generating a plurality of pairs of keypoint features for a pair of images. Each pair of keypoint features may include a keypoint feature from each image. Further, for each pair of keypoint features, corresponding adjoin features may be generated. Additionally, for each pair of keypoint features, whether the adjoin features are similar may be determined. Whether the pair of images have at least one similar object may also be determined, based at least in part on a result of the determination of similarity between the corresponding adjoin features. Other embodiments may be described and claimed.

Abstract translation: 本文公开了与处理图像相关联的设备，方法和存储介质。 在实施例中，用于处理一个或多个图像的方法可以包括为一对图像生成多对关键点特征。 每对关键点功能可能包含每个图像的关键点功能。 此外，对于每对关键点特征，可以生成相应的邻接特征。 另外，对于每对关键点特征，可以确定邻接特征是否相似。 至少部分地基于确定相应邻接特征之间的相似性的结果，也可以确定该对图像是否具有至少一个类似对象。 其他实施例可以被描述和要求保护。

公开(公告)号：EP2936383A4

公开(公告)日：2016-08-24

申请号：EP12890586

申请日：2012-12-20

Applicant: INTEL CORP

Inventor： XU LIN ,  DU YANGZHOU ,  LI JIANGUO ,  LI QIANG ,  PENG YA-TI ,  CHIU YI-JEN

IPC: G06K9/00 ,  G06K9/32 ,  G06K9/62 ,  G06K9/68

CPC classification number: G06K9/0055 ,  G06K9/00248 ,  G06K9/00986 ,  G06K9/3233 ,  G06K9/6201 ,  G06K9/6257 ,  G06K2009/6213

公开(公告)号：EP2553934A4

公开(公告)日：2015-04-15

申请号：EP10848689

申请日：2010-04-01

Applicant: INTEL CORP

Inventor： LI CHANGCHENG ,  DU YANGZHOU ,  LI QIANG ,  ZHANG YIMIN

IPC: H04N13/04 ,  H04N13/00

CPC classification number: H04N13/0022 ,  H04N13/0011 ,  H04N13/0018 ,  H04N13/0029

Abstract: A multi-core processor system may support 3D image rendering on an autostereoscopic display. The 3D image rendering includes pre-processing of depth map and 3D image wrapping tasks. The pre-processing of depth map may include a foreground prior depth image smoothing technique, which may perform a depth gradient detection and a smoothing task. The depth gradient detection task may detect areas with large depth gradient and the smoothing task may transform the large depth gradient into a linearly changing shape using low-strength, low-pass filtering techniques. The 3D image wrapping may include vectorizing the code for 3D image wrapping of row pixels using an efficient single instruction multiple data (SIMD) technique. After vectorizing, an API such as OpenMP may be used to parallelize the 3D image wrapping procedure. The 3D image wrapping using OpenMP may be performed on rows of the 3D image and on images of the multiple view images.

公开(公告)号：EP3216008A4

公开(公告)日：2018-06-27

申请号：EP14905549

申请日：2014-11-05

Applicant: INTEL CORP

Inventor： DU YANGZHOU ,  LI WENLONG ,  LI QIANG ,  TONG XIAOFENG ,  KIM TAE-HOON ,  PARK MINJE

IPC: G06K9/00 ,  G06T13/20 ,  G06T13/40

CPC classification number: G06T13/40 ,  G06F17/2785 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00308 ,  G06T13/205 ,  G10L25/48

Abstract: Apparatuses, methods and storage medium associated with creating an avatar video are disclosed herein. In embodiments, the apparatus may one or more facial expression engines, an animation-rendering engine, and a video generator. The one or more facial expression engines may be configured to receive video, voice and/or text inputs, and, in response, generate a plurality of animation messages having facial expression parameters that depict facial expressions for a plurality of avatars based at least in part on the video, voice and/or text inputs received. The animation-rendering engine may be configured to receive the one or more animation messages, and drive a plurality of avatar models, to animate and render the plurality of avatars with the facial expression depicted. The video generator may be configured to capture the animation and rendering of the plurality of avatars, to generate a video. Other embodiments may be described and/or claimed.

公开(公告)号：EP3198560A4

公开(公告)日：2018-05-09

申请号：EP14902693

申请日：2014-09-24

Applicant: INTEL CORP

Inventor： LI QIANG ,  TONG XIAOFENG ,  DU YANGZHOU ,  LI WENLONG ,  OZER CALEB J ,  LORENZO JOSE ELMER S

IPC: G06T13/40

CPC classification number: G06T13/40 ,  A63F13/2145 ,  A63F13/428 ,  A63F2300/6607 ,  G06F3/011 ,  G06F3/04883 ,  G06T15/005 ,  G06T15/503

Abstract: Apparatuses, methods and storage medium associated with animating and rendering an avatar are disclosed herein. In embodiments, the apparatus may include a gesture tracker and an animation engine. The gesture tracker may be configured to detect and track a user gesture that corresponds to a canned facial expression, the user gesture including a duration component corresponding to a duration the canned facial expression is to be animated. Further, the gesture tracker may be configured to respond to a detection and tracking of the user gesture, and output one or more animation messages that describe the detected/tracked user gesture or identify the canned facial expression, and the duration. The animation engine may be configured to receive the one or more animation messages, and drive an avatar model, in accordance with the one or more animation messages, to animate the avatar with animation of the canned facial expressions for the duration. Other embodiments may be described and/or claimed.

公开(公告)号：EP3123369A4

公开(公告)日：2018-01-03

申请号：EP14886965

申请日：2014-03-27

Applicant: INTEL CORP

Inventor： YANG LIU ,  LI QIANG ,  WANG BIN ,  XU XIANCHAO ,  NIU BING

IPC: G06F17/18 ,  G06F17/50 ,  G06F19/00 ,  G06T7/35

CPC classification number: G06F17/5009 ,  G06F17/18 ,  G06F17/50 ,  G06F2217/16 ,  G06T7/35

Abstract: Various embodiments are generally directed to techniques for employing a hybrid of sequential and parallel processing to perform random sample and consensus (RANSAC). A device to perform RANSAC includes a derivation component to derive a first set of proposed models in parallel from a first set of minimal sample sets of a data set; and a comparison component to recalculate a required quantity of proposed models to derive an accurate model if a proposed model of the first set of proposed models better fits the data set than any proposed model derived prior to derivation of the first set of proposed models, and to determine whether to derive a second set of proposed models following derivation of the first set of proposed models based on a comparison of the required quantity to a quantity of previously derived proposed models that includes the first set. Other embodiments are described and claimed.

公开(公告)号：DE112009005074T8

公开(公告)日：2012-12-27

申请号：DE112009005074

申请日：2009-05-21

Applicant: INTEL CORP

Inventor： CHEN YURONG ,  LI JIANGUO ,  LI QIANG ,  ZHENG YING

IPC: G06T15/00

公开(公告)号：SG175393A1

公开(公告)日：2011-12-29

申请号：SG2011079506

申请日：2009-05-21

Applicant: INTEL CORP

Inventor： LI JIANGUO ,  ZHENG YING ,  LI QIANG ,  CHEN YURONG

Abstract: Stereo image reconstruction techniques are described. An image from a root viewpoint is translated to an image from another viewpoint. Homography fitting is used to translate the image between viewpoints. Inverse compositional image alignment is used to determine a homography matrix and determine a pixel in the translated image.

公开(公告)号：GB2482447B

公开(公告)日：2014-08-27

申请号：GB201118808

申请日：2009-05-21

Applicant: INTEL CORP

Inventor： LI JIANGUO ,  ZHENG YING ,  LI QIANG ,  CHEN YURONG

IPC: G06T7/00 ,  H04N13/00

Abstract: Stereo image reconstruction techniques are described. An image from a root viewpoint is translated to an image from another viewpoint. Homography fitting is used to translate the image between viewpoints. Inverse compositional image alignment is used to determine a homography matrix and determine a pixel in the translated image.