公开(公告)号：US20170262972A1

公开(公告)日：2017-09-14

申请号：US15116919

申请日：2016-03-25

Applicant: INTEL CORPORATION

Inventor： ROBERT ADAMS ,  BRADLEY JACKSON ,  IGNACIO J. ALVAREZ ,  SRIDHAR UYYALA ,  DEEPAK S. VEMBAR

IPC: G06T7/00 ,  G06T7/187 ,  G06T15/08

CPC classification number: G06T7/0002 ,  G06T7/187 ,  G06T7/55 ,  G06T15/08 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/10048 ,  G06T2215/16 ,  H04N13/20

Abstract: A mechanism is described for facilitating generation of voxel representations and assignment of trust metrics according to one embodiment. A method of embodiments, as described herein, includes detecting, by a computing device, a plurality of data sources hosting image capturing devices capable of capturing images of objects in a space, where the images are capable of being received by the computing device. The method may further include tagging trust metrics to the images based on credibility of the plurality of data sources, where a trust metrics to indicate veracity of a corresponding image. The method may further include aggregating the images into an aggregated image representation, and generating a voxel representation of the aggregated image representation such that the images are presented as voxel images, where veracities of the voxel images are secured based on tagging of the trust metrics to their corresponding images.

公开(公告)号：US20180253894A1

公开(公告)日：2018-09-06

申请号：US15771750

申请日：2016-11-02

Applicant: INTEL CORPORATION

Inventor： RANGANATH KRISHNAN ,  DEEPAK S. VEMBAR ,  ROBERT ADAMS ,  BRADLEY A. JACKSON

IPC: G06T17/00 ,  G06T15/08

CPC classification number: G06T17/00 ,  G06T7/564 ,  G06T15/04 ,  G06T15/08 ,  G06T2200/08 ,  G06T2210/52

Abstract: Techniques are provided for 3D model reconstruction of dynamic scenes using hybrid foreground-background processing. A methodology implementing the techniques according to an embodiment includes receiving multiple static images of a scene. Each static image is generated by a static camera, positioned at a fixed location and oriented at a fixed viewing angle. The method also includes receiving multiple dynamic images of the scene, each dynamic image generated by a movable camera. The method further includes performing 3D reconstruction of the scene foreground, based on the static images, and performing 3D reconstruction of the scene background, based on the static images and the dynamic images. The method further includes superimposing the reconstructed 3D foreground and 3D background, with alignment based on calibration parameters (e.g., focal length, principal point, rotation, or translation) of the static and movable cameras, to provide a hybrid 3D reconstruction of the scene for 3D rendering.