Vol. 9, No. 2, 42-51, 2010
Javier Sánchez, Estíbaliz Martínez, Agueda Arquero, and Diego Renza
Abstract
Remote sensing information from spaceborne and airborne platforms continues to provide valuable data for different environmental monitoring applications. In this sense, high spatial resolution imagery is an important source of information for land cover mapping. For the processing of high spatial resolution images, the object-based methodology is one of the most commonly used strategies. However, conventional pixel-based methods, which only use spectral information for land cover classification, are inadequate for classifying this type of images. This research presents a methodology to characterise Mediterranean land covers in high resolution aerial images by means of an object-oriented approach. It uses a self-calibrating multi-band region growing approach optimised by pre-processing the image with a bilateral filtering. The obtained results show promise in terms of both segmentation quality and computational efficiency.
Submitted: 27 May 2010
Revised: 1 Dec 2010
Accepted: 21 Dec 2010
Published: 29 Dec 2010
Responsible editor: Bogdan Zagajewski Citation
Sánchez J, E Martínez, A Arquero & D Renza, 2010. Land cover mapping by an optimised object-oriented approach. Case of study: Mediterranean landscapes. EARSeL eProceedings, 9(2): 42-51
 |
EARSeL European Association of Remote Sensing Laboratories, Strasbourg, France |
 |
BIS-Verlag |