Advanced

Detecting windows in city scenes

Johansson, Björn LU and Kahl, Fredrik LU (2002) Pattern Recognition with Support Vector Machines. First International Workshop, SVM 2002 In Pattern Recognition with Support Vector Machines. First International Workshop, SVM 2002. Proceedings (Lecture Notes in Computer Science Vol.2388) 2388. p.388-396
Abstract
In this paper we present an object detection system for city environments. We focus on the problem of automatically detecting windows on buildings. Several possible applications for the detection system are given, such as recognition of buildings, pose estimation, rectification and 3D reconstruction. Experimental validations on real images are also provided. The system is capable of detecting windows in images at several different orientations and scales. The approach is based on learning from examples using support vector machines. Since the system is trainable, the extension to detect other objects in the scene is straightforward. The performance of the system has been evaluated on an independent training set and the results show that... (More)
In this paper we present an object detection system for city environments. We focus on the problem of automatically detecting windows on buildings. Several possible applications for the detection system are given, such as recognition of buildings, pose estimation, rectification and 3D reconstruction. Experimental validations on real images are also provided. The system is capable of detecting windows in images at several different orientations and scales. The approach is based on learning from examples using support vector machines. Since the system is trainable, the extension to detect other objects in the scene is straightforward. The performance of the system has been evaluated on an independent training set and the results show that the object category "window" can be reliably detected under various poses and lighting conditions. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Pattern Recognition with Support Vector Machines. First International Workshop, SVM 2002. Proceedings (Lecture Notes in Computer Science Vol.2388)
volume
2388
pages
388 - 396
publisher
Springer
conference name
Pattern Recognition with Support Vector Machines. First International Workshop, SVM 2002
external identifiers
  • wos:000187252200030
  • scopus:84958773131
ISSN
1611-3349
0302-9743
ISBN
3-540-44016-X
language
English
LU publication?
yes
id
2fc1242d-a077-4e0e-95f8-2f8205083082 (old id 292313)
alternative location
http://www.springerlink.com/content/1hu44k9b0qlmxngm/fulltext.pdf
date added to LUP
2007-11-27 15:47:28
date last changed
2017-10-01 03:47:18
@inproceedings{2fc1242d-a077-4e0e-95f8-2f8205083082,
  abstract     = {In this paper we present an object detection system for city environments. We focus on the problem of automatically detecting windows on buildings. Several possible applications for the detection system are given, such as recognition of buildings, pose estimation, rectification and 3D reconstruction. Experimental validations on real images are also provided. The system is capable of detecting windows in images at several different orientations and scales. The approach is based on learning from examples using support vector machines. Since the system is trainable, the extension to detect other objects in the scene is straightforward. The performance of the system has been evaluated on an independent training set and the results show that the object category "window" can be reliably detected under various poses and lighting conditions.},
  author       = {Johansson, Björn and Kahl, Fredrik},
  booktitle    = {Pattern Recognition with Support Vector Machines. First International Workshop, SVM 2002. Proceedings (Lecture Notes in Computer Science Vol.2388)},
  isbn         = {3-540-44016-X},
  issn         = {1611-3349},
  language     = {eng},
  pages        = {388--396},
  publisher    = {Springer},
  title        = {Detecting windows in city scenes},
  volume       = {2388},
  year         = {2002},
}