BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION

Christophe Simler, Charles Beumier

2010

Abstract

A method is proposed for building and road detection on very high spatial resolution multispectral aerial image of dense urban areas. First, objects are extracted with a segmentation algorithm in order to use both spectral and spatial information. Second, a spectral-spatial object-level pattern is formed, and then classification is performed using a 3-class SVM classifier, followed by a post-processing using contextual information to handle conflicts. However, in the particular case where many building roofs are grey like the roads and have similar geometry, classification accuracy is inevitably limited. In order to overcome this limitation, different classifiers are combined and different patterns used, improving the accuracy of 10%.

Paper Citation

in Harvard Style

Simler C. and Beumier C. (2010). BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 451-457. DOI: 10.5220/0002851104510457

in Bibtex Style

@conference{visapp10,
author={Christophe Simler and Charles Beumier},
title={BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={451-457},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002851104510457},
isbn={978-989-674-029-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - BUILDING AND ROAD EXTRACTION ON URBAN VHR IMAGES USING SVM COMBINATIONS AND MEAN SHIFT SEGMENTATION
SN - 978-989-674-029-0
AU - Simler C.
AU - Beumier C.
PY - 2010
SP - 451
EP - 457
DO - 10.5220/0002851104510457