Object Based Image Analysis Technique for Distinguishing Tropical Native Forest from Plantations: A Landcover Classification Analysis of Patches Surrounding the Serra do Brigadeiro State Park, Minas Gerais, Brazil
Date
2016-04-29
Authors
Advisors
Journal Title
Journal ISSN
Volume Title
Abstract
The Brazilian Atlantic forest is regarded as one of the hottest biodiversity hotspots in the world. Nonetheless, this area has experienced massive deforestation and significant fragmentation as a result of encroaching pasture, coffee, and eucalyptus plantations. Satellite remote sensing is one of the primary methods of monitoring forest health and extent; yet, distinguishing native forest from plantations, such as eucalyptus, remains a significant challenge in most of the tropics. This study explores the use of moderately priced, high-resolution satellite imagery and identifies the algorithms and training parameters that successfully separate eucalyptus plantations from Atlantic forest patches for future conservation prioritization.
Type
Description
Provenance
Citation
Permalink
Citation
Meehan, Kelly (2016). Object Based Image Analysis Technique for Distinguishing Tropical Native Forest from Plantations: A Landcover Classification Analysis of Patches Surrounding the Serra do Brigadeiro State Park, Minas Gerais, Brazil. Master's project, Duke University. Retrieved from https://hdl.handle.net/10161/11941.
Collections
Dukes student scholarship is made available to the public using a Creative Commons Attribution / Non-commercial / No derivative (CC-BY-NC-ND) license.