9 October 2006 Land use/cover classification through multiresolution segmentation and object oriented neural networks classification
Author Affiliations +
Abstract
In this paper is presented a land use/cover classification methodology of the rural/urban fringe, by means of the application of a neuronal network, with resource to the multiresolution image segmentation, construction of complex elements through object oriented analysis and integration of not spectral (ancillary) information. The study area is the municipality of Almada, located in the south bank of Tagus River and corresponding to one of the core regions of the Lisbon Metropolitan Area (Portugal). The data used was 2004 HRVIR SPOT images fused with supermode panchromatic image and the Portuguese urban quarter statistical data. The developed procedure is based in five steps: 1) Legend creation; 2) deriving statistical ancillary data; 3) deriving object (texture) data; 4) deriving spectral data and 5) neural network classification.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jorge Rocha, Jorge Rocha, José A. Tenedório, José A. Tenedório, Sara Encarnação, Sara Encarnação, Paulo Morgado, Paulo Morgado, } "Land use/cover classification through multiresolution segmentation and object oriented neural networks classification", Proc. SPIE 6366, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology VI, 63660A (9 October 2006); doi: 10.1117/12.690762; https://doi.org/10.1117/12.690762
PROCEEDINGS
11 PAGES


SHARE
Back to Top