Object-Oriented Remote Sensing Image Classification and Road Damage Adaptive Extraction

DOI

10.2991/rsete.2013.35How to use a DOI?

Keywords

Remote sensing imagery, object-oriented, adaptive scale, road damage detection

Abstract

Quick road extraction from earthquake disaster area is very important for the earthquake emergency and rescue. For taking advantage of the multiple data sources and complexity of the contextual environments, an automatic model on the road detection is created by using a number of feature descriptors from damaged roads.The method takes advantage of effective shape, texture, spatial indices to eliminate non-road objects, and then geometry and attribute information, such as length, width, area, damage ratio, damage location of damaged roads, are calculated by registering pre-disaster road vectors and the classification results. Finaaly, the techniques are employed to extract the damaged road section for Wenchuan, China disaster area and Lushan, China disaster area are implemented as examples. The result indicates that this method can improve quickness and efficiency of road damage detection.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Liu Xiaoli
AU  - Li Xue
AU  - Li Jinggang
AU  - Wang Qiuliang
PY  - 2013/08
DA  - 2013/08
TI  - Object-Oriented Remote Sensing Image Classification and Road Damage Adaptive Extraction
BT  - Proceedings of the 2013 the International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE 2013)
PB  - Atlantis Press
SP  - 139
EP  - 142
SN  - 1951-6851
UR  - https://doi.org/10.2991/rsete.2013.35
DO  - 10.2991/rsete.2013.35
ID  - Xiaoli2013/08
ER  -