Large Scale Asset Extraction for Urban Images

Lama Affara KAUST, KSA Liangliang Nan KAUST, KSA Bernard Ghanem KAUST, KSA Peter Wonka KAUST, KSA

Geometric Modeling and Processing mathscidoc:1608.16115

ECCV, 2016
Object proposals are currently used for increasing the computational efficiency of object detection. We propose a novel adaptive pipeline for interleaving object proposals with object classification and use it as a formulation for asset detection. We fi rst preprocess the images using a novel and efficient rectification technique. We then employ a particle filter approach to keep track of three priors, which guide proposed samples and get updated using classifier output. Tests performed on over 1000 urban images demonstrate that our rectification method is faster than existing methods without loss in quality, and that our interleaved proposal method outperforms current state-of-the-art. We further demonstrate that other methods can be improved by incorporating our interleaved proposals.
asset extraction, urban images, window extraction, facade analysis, scene understanding
[ Download ] [ 2016-08-29 14:32:32 uploaded by liangliangnan ] [ 675 downloads ] [ 0 comments ]
@inproceedings{lama2016large,
  title={Large Scale Asset Extraction for Urban Images},
  author={Lama Affara, Liangliang Nan, Bernard Ghanem, and Peter Wonka},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160829143232094458542},
  booktitle={ECCV},
  year={2016},
}
Lama Affara, Liangliang Nan, Bernard Ghanem, and Peter Wonka. Large Scale Asset Extraction for Urban Images. 2016. In ECCV. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160829143232094458542.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved