Institute Homepage
Institute Homepage DE Sign In

Back

Perceiving Systems Conference Paper 2015

Efficient Facade Segmentation using Auto-Context

Thumb ticker sm thumb varun
Perceiving Systems
Varun Jampani
Thumb ticker sm petergehler copy
Perceiving Systems
Peter Vincent Gehler
  • Research Group Leader
Thumb ticker sm raghudeep
Perceiving Systems
Raghudeep Gadde
Untitled

In this paper we propose a system for the problem of facade segmentation. Building facades are highly structured images and consequently most methods that have been proposed for this problem, aim to make use of this strong prior information. We are describing a system that is almost domain independent and consists of standard segmentation methods. A sequence of boosted decision trees is stacked using auto-context features and learned using the stacked generalization technique. We find that this, albeit standard, technique performs better, or equals, all previous published empirical results on all available facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test time inference.

Author(s): Varun Jampani and Raghudeep Gadde and Peter V. Gehler
Book Title: Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on
Pages: 1038--1045
Year: 2015
Month: January
Publisher: IEEE
Project(s):
Bibtex Type: Conference Paper (inproceedings)
DOI: 10.1109/WACV.2015.143
Event Name: WACV, 2015
Event Place: Waikoloa, HI, US
URL: http://wacv2015.org
Electronic Archiving: grant_archive
Organization: IEEE
Links:

BibTex 

@inproceedings{jampani15wacv,
  title = {Efficient Facade Segmentation using Auto-Context},
  booktitle = {Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on},
  abstract = {In this paper we propose a system for the problem of facade segmentation. Building facades are highly structured images and consequently most methods that have been proposed for this problem, aim to make use of this strong prior information. We are describing a system that is almost domain independent and consists of standard segmentation methods. A sequence of boosted decision trees is stacked using auto-context features and learned using the stacked generalization technique. We find that this, albeit standard, technique performs better, or equals, all previous published empirical results on all available facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test time inference.},
  pages = {1038--1045},
  publisher = {IEEE},
  organization = {IEEE},
  month = jan,
  year = {2015},
  slug = {jampani15wacv},
  author = {Jampani, Varun and Gadde, Raghudeep and Gehler, Peter V.},
  url = {http://wacv2015.org},
  month_numeric = {1}
}