公开(公告)号：WO2020132784A1

公开(公告)日：2020-07-02

申请号：PCT/CN2018/123029

申请日：2018-12-24

Applicant: INTEL CORPORATION ,  TONG, Xiaofeng ,  LI, Qiang ,  LI, Wenlong ,  FANG, Yikai ,  SHKEDI, Ofer

Inventor： TONG, Xiaofeng ,  LI, Qiang ,  LI, Wenlong ,  FANG, Yikai ,  SHKEDI, Ofer

IPC: H04N7/18 ,  G06T7/00

Abstract: Methods and apparatus to detect collision of a virtual camera with objects in a three-dimensional volumetric model are disclosed herein. An example virtual camera system disclosed herein includes cameras to obtain images of a scene in an environment. The example virtual camera system also includes a virtual camera generator to create a 3D volumetric model of the scene based on the images, identify a 3D location of a virtual camera to be disposed in the 3D volumetric model, and detect whether a collision occurs between the virtual camera and one or more objects in the 3D volumetric model.

公开(公告)号：WO2019047135A1

公开(公告)日：2019-03-14

申请号：PCT/CN2017/100976

申请日：2017-09-08

Applicant: INTEL CORPORATION ,  FANG, Yikai ,  TONG, Xiaofeng ,  ZHANG, Lidan ,  LI, Qiang Eric ,  LI, Wenlong

Inventor： FANG, Yikai ,  TONG, Xiaofeng ,  ZHANG, Lidan ,  LI, Qiang Eric ,  LI, Wenlong

IPC: G09B19/00

CPC classification number: G09B19/0038

Abstract: Systems and techniques for sensor-derived swing hit and direction detection are described herein. A set of sensor values may be compressed into a first lower dimension (2105). Features may be extracted from the compressed set of sensor values (2110). The features may be clustered into a set of clusters (2115). A swing action may be detected based on a distance between members of the set of clusters (2120).

公开(公告)号：WO2016101131A1

公开(公告)日：2016-06-30

申请号：PCT/CN2014/094618

申请日：2014-12-23

Applicant: INTEL CORPORATION ,  FANG, Yikai ,  DU, Yangzhou ,  LI, Qiang, Eric ,  TONG, Xiaofeng ,  LI, Wenlong ,  PARK, Minje ,  JU, Myung-Ho ,  YI, Jihyeon Kate ,  KIM, Tae-Hoon Pete

Inventor： FANG, Yikai ,  DU, Yangzhou ,  LI, Qiang, Eric ,  TONG, Xiaofeng ,  LI, Wenlong ,  PARK, Minje ,  JU, Myung-Ho ,  YI, Jihyeon Kate ,  KIM, Tae-Hoon Pete

IPC: G06T13/40

CPC classification number: G06T13/40 ,  G06K9/00255 ,  G06K9/00315 ,  G06K9/00355 ,  G06T5/002 ,  G06T2207/10016 ,  G06T2207/20092 ,  G06T2207/20182 ,  G06T2207/30201

Abstract: Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.

Abstract translation: 这里通常描述用于增强面部动画的系统和方法的示例。 用于将面部表情映射到替代化身表情的方法可以包括捕获脸部的一系列图像，以及从该系列图像中检测面部的面部表情的序列。 该方法可以包括确定映射到面部表情序列的替代化身表达，以及使用替代化身表达来动画化身化身。

公开(公告)号：WO2010076622A1

公开(公告)日：2010-07-08

申请号：PCT/IB2009/007751

申请日：2009-12-14

Applicant: NOKIA CORPORATION ,  CHAI, Xiujuan ,  FANG, Yikai ,  WANG, Hao ,  WANG, Kong Qiao

Inventor： CHAI, Xiujuan ,  FANG, Yikai ,  WANG, Hao ,  WANG, Kong Qiao

IPC: G06K9/00

CPC classification number: G06K9/00389

Abstract: A method for providing hand segmentation for gesture analysis may include determining a target region based at least in part on depth range data corresponding to an intensity image. The intensity image may include data descriptive of a hand. The method may further include determining a point of interest of a hand portion of the target region, determining a shape corresponding to a palm region of the hand, and removing a selected portion of the target region to identify a portion of the target region corresponding to the hand. An apparatus and computer program product corresponding to the method are also provided.

Abstract translation: 用于提供用于手势分析的手分割的方法可以包括至少部分地基于对应于强度图像的深度范围数据来确定目标区域。 强度图像可以包括描述手的数据。 该方法还可以包括确定目标区域的手部分的兴趣点，确定与手掌区域相对应的形状，以及移除目标区域的选定部分，以识别对应于该区域的目标区域的一部分 手。 还提供了一种与该方法对应的装置和计算机程序产品。

公开(公告)号：WO2023087164A1

公开(公告)日：2023-05-25

申请号：PCT/CN2021/131079

申请日：2021-11-17

Applicant: INTEL CORPORATION ,  FANG, Longwei ,  FANG, Yikai ,  TAO, Hongzhi ,  LI, Qiang ,  ZHENG, Hang

Inventor： FANG, Longwei ,  FANG, Yikai ,  TAO, Hongzhi ,  LI, Qiang ,  ZHENG, Hang

IPC: G06T17/00

Abstract: A method and system of multi-view image processing with accurate skeleton reconstruction uses joint confidence values.

公开(公告)号：WO2014063278A1

公开(公告)日：2014-05-01

申请号：PCT/CN2012/083275

申请日：2012-10-22

Applicant: NOKIA CORPORATION ,  LI, Jiangwei ,  XU, Lei ,  FANG, Yikai ,  WANG, Kongqiao

Inventor： LI, Jiangwei ,  XU, Lei ,  FANG, Yikai ,  WANG, Kongqiao

IPC: G06T7/00

CPC classification number: G06T7/408 ,  G06K9/00355 ,  G06K9/4652 ,  G06K9/6262 ,  G06K9/6267 ,  G06K9/6278 ,  G06K9/6282 ,  G06T2207/10024

Abstract: It is inter alia disclosed to classify samples of a set of samples of an image regarding whether or not a respective sample comprises optical information on a specific object type based on classification information. Therein, the classification information comprises a plurality of classifiers, each classifier being associated exclusively with one colour channel of a plurality of colour channels.

Abstract translation: 公开的是对图像的一组样本的样本进行分类，以便相应的样本是否包含基于分类信息的特定对象类型的光学信息。 其中，分类信息包括多个分类器，每个分类器仅与多个颜色通道中的一个颜色通道相关联。

公开(公告)号：WO2008038096A1

公开(公告)日：2008-04-03

申请号：PCT/IB2007/002766

申请日：2007-09-24

Applicant: NOKIA CORPORATION ,  WANG, Kong, Qiao ,  TAKALA, Roope ,  FANG, Yikai ,  LU, Hanqing ,  LIU, Qingshan

Inventor： WANG, Kong, Qiao ,  TAKALA, Roope ,  FANG, Yikai ,  LU, Hanqing ,  LIU, Qingshan

IPC: G06F3/01

CPC classification number: G06F3/017 ,  G06K9/00375

Abstract: The present invention relates to a method for invoking an operation of a communication terminal in response to registering and interpreting a predetermined motion or pattern of an object. It further relates to a computer-readable medium in which the present invention is implemented.

Abstract translation: 本发明涉及一种用于响应于注册和解释对象的预定运动或图案来调用通信终端的操作的方法。 本发明还涉及实现本发明的计算机可读介质。

公开(公告)号：WO2023044663A1

公开(公告)日：2023-03-30

申请号：PCT/CN2021/119876

申请日：2021-09-23

Applicant: INTEL CORPORATION ,  LIU, Chenning ,  LI, Qiang ,  LI, Wenlong ,  FANG, Yikai ,  ZHENG, Hang ,  CHEN, Jiansheng

Inventor： LIU, Chenning ,  LI, Qiang ,  LI, Wenlong ,  FANG, Yikai ,  ZHENG, Hang ,  CHEN, Jiansheng

IPC: G06K9/62

Abstract: An example apparatus includes processor circuitry to extract features from image data obtained from a plurality of cameras, the extraction of features performed using a plurality of sequential neural network layers; in response to each of the plurality of sequential neural network layer extracting the features, identify the extracted features in a torso region of the image data via a plurality of attention modules; estimate body landmarks from image data to localize an area; generate an upper heatmap mask based on a geometric center of the image data; calculate a loss function for the image data based on a cross-entropy loss, a pixel-wise loss, and a triplet loss determined from the extracted features and the generated heatmap mask; select lowest correlated classes based on calculated correlations between pairs of a plurality of classes; and calculate voting scores for groups associated with the lowest correlated classes.

公开(公告)号：WO2022226724A1

公开(公告)日：2022-11-03

申请号：PCT/CN2021/089941

申请日：2021-04-26

Applicant: INTEL CORPORATION ,  TAO, Hongzhi ,  FANG, Yikai ,  FANG, Longwei

Inventor： TAO, Hongzhi ,  FANG, Yikai ,  FANG, Longwei

IPC: G06T17/00

Abstract: A method and system of image processing with multi-skeleton tracking uses a temporal object key point loss metric.

公开(公告)号：WO2022021217A1

公开(公告)日：2022-02-03

申请号：PCT/CN2020/105816

申请日：2020-07-30

Applicant: INTEL CORPORATION ,  FANG, Longwei ,  LI, Qiang ,  LI, Wenlong ,  FANG, Yikai ,  ZHENG, Hang

Inventor： FANG, Longwei ,  LI, Qiang ,  LI, Wenlong ,  FANG, Yikai ,  ZHENG, Hang

IPC: G06K9/00 ,  G06T7/20

Abstract: Techniques related to performing object or person association or correspondence in multi-view video are discussed. Such techniques include determining correspondences at a particular time instance based on separately optimizing correspondence sub-matrices for distance sub-matrices based on two-way minimum distance pairs between frame pairs, generating and fusing tracklets across time instances, and adjusting correspondence, after such tracklet processing, via elimination of outlier object positions and rearrangement of object correspondence.