Mapping private gardens with remote sensing

Author(s)

Caio Hamamura

• Document type: Master's Dissertation
• Press: Piracicaba.
• Institution: Universidade de São Paulo (USP). Escola Superior de Agricultura Luiz de Queiroz (ESALA/BC)
• Defense date: 2013-05-24

Examining board members

Demóstenes Ferreira da Silva Filho; Hilton Thadeu Zarate do Couto; Ailton Luchiari

• Advisor: Demóstenes Ferreira da Silva Filho

Abstract

Urban vegetation mapping has been restricted to the public areas or the total area, not showing the contribution of the private yards to the urban greening. Some studies indicate that these areas have potential to mitigate the impacts caused by the urbanization. In this work, many methods for mapping pervious gardens were tested aiming the development of a method that could aid urban planning and investigating the contribution of these areas to the urban greening. This work achieved highly accurate results (kappa = 0.9553) and presented novel techniques for filtering and classification. We highlight the development of a simple application to perform the Kuwahara filter, which improved the results of the classification by pixel approach. The classification algorithms by pixel approach resulted in statistically more accurate products, although visually the results presented by object-oriented approach is closer to landscape features. (AU)

• FAPESP's process: 10/14602-4 - Use of the remote sensing tool for mapping permeable private gardens in the municipality of Piracicaba, SP
• Grantee: Caio Hamamura
• Support Opportunities: Scholarships in Brazil - Master