专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明申请

WO2022021217A1 MULTI-CAMERA PERSON ASSOCIATION VIA PAIR-WISE MATCHING IN CONTINUOUS FRAMES FOR IMMERSIVE VIDEO 审中-公开
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
申请人： INTEL CORPORATION , FANG, Longwei , LI, Qiang , LI, Wenlong , FANG, Yikai , ZHENG, Hang
发明人： FANG, Longwei , LI, Qiang , LI, Wenlong , FANG, Yikai , ZHENG, Hang
IPC分类号： G06K9/00 , G06T7/20
摘要： 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.

62. 发明申请

WO2021237610A1 LOW-POWER DATA SCHEDULING AND RECEPTION TECHNIQUES 审中-公开
公开(公告)号：WO2021237610A1
公开(公告)日：2021-12-02
申请号：PCT/CN2020/093018
申请日：2020-05-28
申请人： QUALCOMM INCORPORATED , ZHU, Yuankun , ZHANG, Hao , LIU, Gang , HUI, Chaofeng , JIANG, Pan , ZHANG, Fojian , LI, Jian , LI, Qiang , YU, Bo
发明人： ZHU, Yuankun , ZHANG, Hao , LIU, Gang , HUI, Chaofeng , JIANG, Pan , ZHANG, Fojian , LI, Jian , LI, Qiang , YU, Bo
IPC分类号： H04W72/04
摘要： Wireless communication techniques that include low-power data scheduling and reception techniques for wireless communication systems are discussed. A UE may receive from a base station control information in a first slot. The control information may include an indication of where data scheduled by the control information is located. The UE may determine that data is located in at least one second slot based, at least in part, on the received control information. The UE may receive from the base station the data in the at least one second slot. Other aspects and features are also claimed and described.

63. 发明申请

WO2021232329A1 VIRTUAL CAMERA FRIENDLY OPTICAL TRACKING 审中-公开
公开(公告)号：WO2021232329A1
公开(公告)日：2021-11-25
申请号：PCT/CN2020/091490
申请日：2020-05-21
申请人： INTEL CORPORATION , LING, Chen , LI, Wenlong , LI, Qiang , LIN, Haihua , TONG, Xiaofeng
发明人： LING, Chen , LI, Wenlong , LI, Qiang , LIN, Haihua , TONG, Xiaofeng
IPC分类号： G06K9/00
摘要： A method for player and ball tracking post processing is described herein. The method includes optically tracking a trajectory of a player and ball and determining at least one affinity player for the currently tracked player. Additionally, the method includes completing the optical trajectory for the currently tracked player based on an estimated trajectory from the affinity player and stabilizing ball tracking during game break. The method further includes calculating virtual camera movement.

64. 发明申请

WO2020097750A1 AUTOMATED FIELD OF VIEW ESTIMATION FROM GAME PARTICIPANT PERSPECTIVES 审中-公开
公开(公告)号：WO2020097750A1
公开(公告)日：2020-05-22
申请号：PCT/CN2018/114989
申请日：2018-11-12
申请人： INTEL CORPORATION , TONG, Xiaofeng , TURIEL, Eli , LI, Qiang , LI, Wenlong , FANG, Yikai , HOUMINER, Doron , SHILONI, Asaf
发明人： TONG, Xiaofeng , TURIEL, Eli , LI, Qiang , LI, Wenlong , FANG, Yikai , HOUMINER, Doron , SHILONI, Asaf
IPC分类号： H04N21/6587
摘要： Methods, systems and apparatuses may provide for technology that identifies a player captured in a multi-camera video feed of a game that involves the identified player and estimates a first field of view from the perspective of the identified player for a selected from of the multi-camera video feed. Additionally, the technology automatically generates, based on the first field of view, a camera path for a replay of the selected frame from the perspective of the identified player. In one example, the technology also determines a trajectory of a projectile captured in the multi-camera video feed, estimates, based on the trajectory, a second field of view from the perspective of the projectile, and automatically generates, based on the second field of view, a replay of one or more selected frames of the multi-camera video feed from the perspective of the projectile.

65. 发明申请

WO2020061986A1 MULTI-CAM BALL LOCATION METHOD AND APPARATUS 审中-公开
公开(公告)号：WO2020061986A1
公开(公告)日：2020-04-02
申请号：PCT/CN2018/108189
申请日：2018-09-28
申请人： INTEL CORPORATION , TONG, Xiaofeng , LING, Chen , LU, Ming , LI, Qiang , LI, Wenlong , FANG, Yikai , WANG, Yumeng
发明人： TONG, Xiaofeng , LING, Chen , LU, Ming , LI, Qiang , LI, Wenlong , FANG, Yikai , WANG, Yumeng
IPC分类号： H04N5/232 , G06T7/20
摘要： A multi-camera architecture for detecting and tracking a ball in real-time. The multi-camera architecture includes network interface circuitry to receive a plurality of real-time videos taken from a plurality of high-resolution cameras. Each of the high-resolution cameras simultaneously captures a sports event, wherein each of the plurality of high-resolution cameras includes a viewpoint that covers an entire playing field where the sports event is played. The multi-camera architecture further includes one or more processors coupled to the network interface circuity and one or more memory devices coupled to the one or more processors. The one or more memory devices includes instructions to determine the location of the ball for each frame of the plurality of real-time videos, which when executed by the one or more processors, cause the multi-camera architecture to simultaneously perform one of a detection scheme or a tracking scheme on a frame from each of the plurality of real-time videos to detect the ball used in the sports event and perform a multi-camera build to determine a location of the ball in 3D for the frame from each of the plurality of real-time videos using one of detection or tracking results for each of the cameras.

66. 发明申请

WO2020061792A1 REAL-TIME MULTI-VIEW DETECTION OF OBJECTS IN MULTI-CAMERA ENVIRONMENTS 审中-公开
公开(公告)号：WO2020061792A1
公开(公告)日：2020-04-02
申请号：PCT/CN2018/107498
申请日：2018-09-26
申请人： INTEL CORPORATION , LI, Qiang , TONG, Xiaofeng , FANG, Yikai , LING, Cheng , LI, Wenlong
发明人： LI, Qiang , TONG, Xiaofeng , FANG, Yikai , LING, Cheng , LI, Wenlong
IPC分类号： H04N5/232 , G06T7/60
摘要： A mechanism is described for facilitating real-time multi-view detection of objects in multi-camera environments, according to one embodiment. A method of embodiments, as described herein, includes mapping first lines associated with objects to a ground plane; and forming clusters of second lines corresponding to the first lines such that an intersection point in a cluster represents a position of an object on the ground plane.

67. 发明申请

WO2018053682A1 ANIMATION SIMULATION OF BIOMECHANICS 审中-公开
标题翻译：生物力学的动画模拟
公开(公告)号：WO2018053682A1
公开(公告)日：2018-03-29
申请号：PCT/CN2016/099442
申请日：2016-09-20
申请人： INTEL CORPORATION , TONG, Xiaofeng , CHANG, Yuanzhang , LI, Qiang , LI, Wenlong
发明人： TONG, Xiaofeng , CHANG, Yuanzhang , LI, Qiang , LI, Wenlong
IPC分类号： G06T13/40
CPC分类号： G06T13/40 , A63B69/00 , G06F3/011 , G06F3/017 , G06T3/4007 , G06T7/20 , G06T2215/16
摘要： Methods, systems, and storage media for generating and displaying animations of simulated biomechanical motions are disclosed. In embodiments, a computer device may obtain sensor data of a sensor affixed to a user's body or equipment used by the user, and may use inverse kinematics to determine desired positions and orientations of an avatar based on the sensor data. In embodiments, the computer device may adjust or alter the avatar based on the inverse kinematics, and generate an animation for display based on the adjusted avatar. Other embodiments may be disclosed and/or claimed.
摘要翻译：公开了用于生成和显示模拟生物力学运动的动画的方法，系统和存储介质。在实施例中，计算机设备可以获得固定到用户使用的身体或设备的传感器的传感器数据，并且可以使用逆向运动学来基于传感器数据确定化身的期望位置和取向。在实施例中，计算机设备可基于逆向运动学来调整或改变化身，并且基于调整后的化身生成用于显示的动画。其他实施例可以被公开和/或要求保护。

68. 发明申请

WO2017101094A1 AVATAR ANIMATION SYSTEM 审中-公开
标题翻译：阿凡达动画系统
公开(公告)号：WO2017101094A1
公开(公告)日：2017-06-22
申请号：PCT/CN2015/097826
申请日：2015-12-18
申请人： INTEL CORPORATION , PARK, Minje , KIM, Tae-Hoon , JU, Myung-Ho , YI, Jihyeon , SHEN, Xiaolu , ZHANG, Lidan , LI, Qiang
发明人： PARK, Minje , KIM, Tae-Hoon , JU, Myung-Ho , YI, Jihyeon , SHEN, Xiaolu , ZHANG, Lidan , LI, Qiang
IPC分类号： G06T13/40
CPC分类号： G06T13/40 , G06T7/73 , G06T17/20 , G06T2207/20084 , G06T2207/30201 , G06T2210/44
摘要： Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. The real-time provision of high quality avatar animation is enabled, at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.
摘要翻译：这里公开的头像动画系统提供基于人脸的变化的人脸的高质量实时头像动画。高质量化身动画的实时提供至少部分地由多帧回归器实现，该多帧回归器配置成将描述两幅或多幅图像中描绘的面部表情的信息映射到描述单个化身混合形状的信息。该两个或更多个图像可以是时间上连续的图像。该多帧回归器实现机器学习组件，其从描述主体的脸部的信息和/或描述先前由多帧回归器生成的化身动画帧的信息来生成高质量化身动画。机器学习组件可以使用一组描述人类面部表情的训练图像和由专业动画师创作的化身动画来反映在该组训练图像中描绘的面部表情。

69. 发明申请

WO2016044968A1 MOVING AN OBJECT ON DISPLAY 审中-公开
标题翻译：移动对象在显示
公开(公告)号：WO2016044968A1
公开(公告)日：2016-03-31
申请号：PCT/CN2014/087047
申请日：2014-09-22
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , LI, Qiang , CHEN, Fan
发明人： LI, Qiang , CHEN, Fan
IPC分类号： G06F3/048
CPC分类号： G06F3/04883 , G06F2203/04808
摘要： Examples disclosed herein relate, among other things, to a computing system. The computing system may include, for example, a display, a touch-sensitive surface, and a detection engine to detect a movement of at least one object moving at a first rate along a first path on the touch-sensitive surface, determine a number of objects involved in the movement, convert the first rate into a second rate based at least on the number of objects, and move a display object on the display at the second rate along a second path corresponding to the first path.
摘要翻译：除其他之外，本文公开的示例涉及计算系统。计算系统可以包括例如显示器，触敏表面和检测引擎，以检测沿着触敏表面上的第一路径以第一速率移动的至少一个物体的移动，确定数字涉及运动的物体，至少基于物体数量将第一速率转换成第二速率，并沿着与第一路径对应的第二路径以第二速率在显示器上移动显示对象。

70. 发明申请

WO2014094275A1 ACCELERATED OBJECT DETECTION FILTER USING A VIDEO MOTION ESTIMATION MODULE 审中-公开
标题翻译：加速对象检测过滤器使用视频运动估计模块
公开(公告)号：WO2014094275A1
公开(公告)日：2014-06-26
申请号：PCT/CN2012/087017
申请日：2012-12-20
申请人： INTEL CORPORATION , XU, Lin , DU, Yangzhou , LI, Jianguo , LI, Qiang , PENG, Ya-Ti , CHIU, Yi-Jen
发明人： XU, Lin , DU, Yangzhou , LI, Jianguo , LI, Qiang , PENG, Ya-Ti , CHIU, Yi-Jen
IPC分类号： G06K9/00
CPC分类号： G06K9/0055 , G06K9/00248 , G06K9/00986 , G06K9/3233 , G06K9/6201 , G06K9/6257 , G06K2009/6213
摘要： Systems, apparatus and methods are described related to accelerated object detection filter using a video estimation module.
摘要翻译：与使用视频估计模块的加速对象检测滤波器相关的系统，装置和方法被描述。

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