Classification of roof covering in urban areas using aerial imagery is a challenging task. In this work we present a preliminary mapping of roofs using the high-resolution Skysat multispectral images. The classification is performed using a two-stage machine learning approach: the first stage includes a supervised classification for land use, while the second stage includes the classification of terraces and roofs with one or more pitches in those areas previously recognized as edifices. The methodology has been tested to classify the roofs in the north-east part of the Stromboli Island (Sicily, Italy). Our preliminary results are promising and encourage us to pursue further developments as ways to improve accuracy and reliability of the classification.

Roof covering classification using Skysat multispectral imagery

Giuseppe Bilotta;Michele Mangiameli;Giuseppe Mussumeci;
2022

Abstract

Classification of roof covering in urban areas using aerial imagery is a challenging task. In this work we present a preliminary mapping of roofs using the high-resolution Skysat multispectral images. The classification is performed using a two-stage machine learning approach: the first stage includes a supervised classification for land use, while the second stage includes the classification of terraces and roofs with one or more pitches in those areas previously recognized as edifices. The methodology has been tested to classify the roofs in the north-east part of the Stromboli Island (Sicily, Italy). Our preliminary results are promising and encourage us to pursue further developments as ways to improve accuracy and reliability of the classification.
File in questo prodotto:
File Dimensione Formato  
Ganci_ICNAMM.pdf

non disponibili

Tipologia: Documento in Pre-print
Dimensione 643.73 kB
Formato Adobe PDF
643.73 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/523123
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact