DocumentCode :
3835888
Title :
Stages as Models of Scene Geometry
Author :
Vladimir Nedovic;Arnold W.M. Smeulders;Andre Redert;Jan-Mark Geusebroek
Author_Institution :
University of Amsterdam, Amsterdam
Volume :
32
Issue :
9
fYear :
2010
Firstpage :
1673
Lastpage :
1687
Abstract :
Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, image retrieval, and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify geometric scene categorization as the first step toward robust and efficient depth estimation from single images. We introduce 15 typical 3D scene geometries called stages, each with a unique depth profile, which roughly correspond to a large majority of broadcast video frames. Stage information serves as a first approximation of global depth, narrowing down the search space in depth estimation and object localization. We propose different sets of low-level features for depth estimation, and perform stage classification on two diverse data sets of television broadcasts. Classification results demonstrate that stages can often be efficiently learned from low-dimensional image representations.
Keywords :
"Solid modeling","Layout","Computational geometry","Image reconstruction","Multimedia communication","TV broadcasting","Remotely operated vehicles","Mobile robots","Navigation","Image retrieval"
Journal_Title :
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2009.174
Filename :
5282498
Link To Document :
بازگشت