发明名称 Mechanism for facilitating dynamic simulation of avatars corresponding to changing user performances as detected at computing devices
摘要 A mechanism is described for facilitating dynamic simulation of avatars based on user performances according to one embodiment. A method of embodiments, as described herein, includes capturing, in real-time, an image of a user, the image including a video image over a plurality of video frames. The method may further include tracking changes in size of the user image, the tracking of the changes may include locating one or more positions of the user image within each of the plurality of video frames, computing, in real-time, user performances based on the changes in the size of the user image over the plurality of video frames, and dynamically scaling an avatar associated with the user such that the avatar is dynamically simulated corresponding to the user performances.
申请公布号 US9489760(B2) 申请公布日期 2016.11.08
申请号 US201314358394 申请日期 2013.11.14
申请人 Intel Corporation 发明人 Li Wenlong;Tong Xiaofeng;Du Yangzhou;Sachson Thomas
分类号 G06K9/00;G06T13/40;G06T7/00;G06T7/20;G06T1/00;G06T3/40;G06F3/01 主分类号 G06K9/00
代理机构 Blakely, Sokoloff, Taylor & Zafman LLP 代理人 Blakely, Sokoloff, Taylor & Zafman LLP
主权项 1. An apparatus comprising: reception and capturing logic to capture, in real-time, a live image of a user, wherein the live image includes a live video image over a plurality of video frames, wherein the live image is being communicated, in real-time, for facilitating live viewing of a live avatar corresponding to the live image using one or more display screens of the apparatus or one of more computing devices; detection/tracking logic to track changes in size of the live image, wherein tracking the changes includes locating one or more positions of the live image within each of the plurality of video frames; computation engine to compute, in real-time, user performances based on the changes in the size of the live image over the plurality of video frames, wherein the use performances are further computed based on the user's gestures including facial expressions as interpreted from tracking of a plurality of facial point on the user's face; and scaling logic to dynamically scale the live avatar associated with the user and corresponding to the live image such that the live avatar is dynamically simulated corresponding to the user performances.
地址 Santa Clara CA US