Share Email Print
cover

Proceedings Paper

Robust recognition of urban patterns using a two-stage soft-hard neural classification
Author(s): Elisabetta Binaghi; Pietro Alessandro Brivio; Ignazio Gallo; Monica Pepe; Anna Rampini
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The aim of the work is to propose a methodology for spatial/spectral analysis of urban patterns using neural network. To address the problem of spectral ambiguity and spatial complexity related to built-up patterns a two-stage classification procedure based on Multi-Layer Perceptron, is proposed. The first stage is devoted to generate discriminating features for problematic patterns by a supervised soft classification It uses a moving window to evaluate the neighbouring influences during the classification. The spatial relationships among the window pixels to be classified are not explicitly formalised, but the corresponding window is directly presented as input to the neural network classifier. The generated features are used in the second stage for complete land cover mapping. For an experimental evaluation the strategy has been applied to the classification of natural colour aerial photographs acquired over heterogeneous landscape, including urban patterns, and characterised by high spatial resolution and low spectral information. The proposed methodology for the extraction of urban patterns proved to be accurate and robust besides transferable.

Paper Details

Date Published: 19 January 2001
PDF: 8 pages
Proc. SPIE 4170, Image and Signal Processing for Remote Sensing VI, (19 January 2001); doi: 10.1117/12.413880
Show Author Affiliations
Elisabetta Binaghi, Istituto per le Tecnologie Informatiche Multimediali (Italy)
Pietro Alessandro Brivio, Istituto di Ricerca sul Rischio Sismico (Italy)
Ignazio Gallo, Istituto per le Tecnologie Informatiche Multimediali (Italy)
Monica Pepe, Istituto per le Tecnologie Informatiche Multimediali (Italy)
Anna Rampini, Istituto per le Tecnologie Informatiche Multimediali (Italy)


Published in SPIE Proceedings Vol. 4170:
Image and Signal Processing for Remote Sensing VI
Sebastiano Bruno Serpico, Editor(s)

© SPIE. Terms of Use
Back to Top