| | |
Summary: NAVIGATING IN MANHATTAN: 3D ORIENTATION FROM VIDEO
WITHOUT CORRESPONDENCES
Andr´e T. Martins, Pedro M. Q. Aguiar1
, M´ario A. T. Figueiredo2
Instituto Superior T´ecnico, Technical University of Lisbon
1
Institute for Systems and Robotics, 2
Institute for Telecommunications
aftm@mega.ist.utl.pt, aguiar@isr.ist.utl.pt, mtf@lx.it.pt
ABSTRACT
The problem of inferring 3D orientation of a camera from video
sequences has been mostly addressed by first computing corre-
spondences of image features. This intermediate step is now seen
as the main bottleneck of those approaches. In this paper, we
propose a new 3D orientation estimation method for urban (in-
door and outdoor) environments, which avoids correspondences
between frames. The basic scene property exploited by our method
is that many edges are oriented along three orthogonal directions;
this is the recently introduced Manhattan world (MW) assumption.
In addition to the novel adoption of the MW assumption for
|
