header

Discovering Favorite Views of Popular Places with Iconoid Shift


Tobias Weyand, Bastian Leibe
International Conference on Computer Vision (ICCV'11). (Oral)
pubimg

In this paper, we propose a novel algorithm for automatic landmark building discovery in large, unstructured image collections. In contrast to other approaches which aim at a hard clustering, we regard the task as a mode estimation problem. Our algorithm searches for local attractors in the image distribution that have a maximal mutual homography overlap with the images in their neighborhood. Those attractors correspond to central, iconic views of single objects or buildings, which we efficiently extract using a medoid shift search with a novel distance measure. We propose efficient algorithms for performing this search. Most importantly, our approach performs only an efficient local exploration of the matching graph that makes it applicable for large-scale analysis of photo collections. We show experimental results validating our approach on a dataset of 500k images of the inner city of Paris.

» Show BibTeX

@inproceedings{DBLP:conf/iccv/WeyandL11,
author = {Tobias Weyand and
Bastian Leibe},
title = {Discovering favorite views of popular places with iconoid shift},
booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2011, Barcelona,
Spain, November 6-13, 2011},
pages = {1132--1139},
year = {2011},
crossref = {DBLP:conf/iccv/2011},
url = {http://dx.doi.org/10.1109/ICCV.2011.6126361},
doi = {10.1109/ICCV.2011.6126361},
timestamp = {Thu, 19 Jan 2012 18:05:15 +0100},
biburl = {http://dblp.uni-trier.de/rec/bib/conf/iccv/WeyandL11},
bibsource = {dblp computer science bibliography, http://dblp.org}
}




Disclaimer Home Visual Computing institute RWTH Aachen University