发明名称 |
SYSTEM AND METHOD OF LIMITING PROCESSING BY A 3D RECONSTRUCTION SYSTEM OF AN ENVIRONMENT IN A 3D RECONSTRUCTION OF AN EVENT OCCURRING IN AN EVENT SPACE |
摘要 |
A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective sub-volume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes. |
申请公布号 |
US2016189421(A1) |
申请公布日期 |
2016.06.30 |
申请号 |
US201514909660 |
申请日期 |
2015.04.01 |
申请人 |
REPLAY TECHNOLOGIES INC. |
发明人 |
Haimovitch-Yogev Oren;Shapira Matteo;Shapira Aviv;Prilusky Diego;Ben Zvi Yaniv;Gilat Adi |
分类号 |
G06T15/20;G06T7/00;H04N13/02;G06T11/00 |
主分类号 |
G06T15/20 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event occurring in an event space; the method comprising the steps of:
(a) determining by a user a volume of the event space; (b) defining by a user the volume for a system, the system comprising a subdivision module and a plurality of cameras, the plurality of cameras for recording the event in a plurality of imaging frames; (c) dividing by the subdivision module the volume into a plurality of sub-volumes, the volume comprising the plurality of sub-volumes; (d) projecting from each camera by the subdivision module each of the sub-volumes to create a plurality of sub-volume masks relative to each camera; (e) recording the event by the system; (f) creating by the subdivision module an imaging mask for each camera; (g) comparing for each camera by the subdivision module the respective imaging mask to the respective sub-volume mask and extracting by the subdivision module at least one feature from at least one imaging mask, the at least one feature related to the event; (h) saving by the subdivision module the at least one feature to a subspace division mask; (i) cropping by the system of the at least one feature from the imaging frames using the subspace division mask; and (j) processing by the system only the at least one feature for a 3D reconstruction. |
地址 |
Newark CA US |