Biological Vision for Urban Vegetation Detection in Color Remote Sensing Imagery

DOI

10.2991/rsete.2013.93How to use a DOI?

Keywords

urban vegetation; color remote sensing; visual attention; fuzzy ART

Abstract

Urban vegetation, which scatters in gardens, settlements and streets etc., appears small, often fragmented, linear patches. Automatic vegetation detection in color remote sensing imagery is useful for obtaining more timely and accurate information. In this paper, a new biological vision methodology based on visual attention theory and adaptive resonance theory (ART) is presented to automatic detect urban vegetation in color remote sensing imagery. The central rationale of the method is that vegetation information is from the double-opponent saliency map and then gets object-based classification. Without a priori knowledge of image content, the image can be segmented into vegetation and other object through the unsupervised learning and self-organization fuzzy ART neural network. Experimental results indicate that our method performs much better than eCognitionR.

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  - Xu Fang
AU  - Jiang Weiwei
PY  - 2013/08
DA  - 2013/08
TI  - Biological Vision for Urban Vegetation Detection in Color Remote Sensing Imagery
BT  - Proceedings of the 2013 the International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE 2013)
PB  - Atlantis Press
SP  - 380
EP  - 383
SN  - 1951-6851
UR  - https://doi.org/10.2991/rsete.2013.93
DO  - 10.2991/rsete.2013.93
ID  - Fang2013/08
ER  -