Sorry, you need to enable JavaScript to visit this website.

Three-dimensional Reconstruction from Heterogeneous Video Devices With Camera-In-View Information

Citation Author(s):
Submitted by:
Simone Milani
Last updated:
23 February 2016 - 1:38pm
Document Type:
Poster
Event:
Presenters:
Simone Milani
 

In this work, a 3D modelization of the surrounding environment is enabled with an improvised ad-hoc camera networks of both static and mobile devices (cloud vision network).

The estimation can be significantly improved whenever one or more cameras (named here camera-in-views) can be
localized within the field of view of other devices. The locations of camera-in-views (CIV) correspond to both scene points and extrinsic parameters. Image points and synchronization associated to CIV are obtained via a VLC signaling.
As a matter of fact, it is possible to modify a standard bundle adjustment algorithm to improve the accuracy and reduce the amount of iterations.

Experimental results show that this additional information can improve the accuracy of the system up to 17 %.

up
0 users have voted: