Fine-tuning contextual-based optimum path forest for land cover classification

• Grant number: 16/05093-5
• Support Opportunities: Regular Research Grants - Publications - Scientific article
• Start date: May 01, 2016
• End date: October 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: João Paulo Papa
• Grantee: João Paulo Papa
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil

Abstract

Contextual-based learning aims at considering neighboring pixels in order to improve pixel-wise-oriented classification techniques. In this work, we presented a meta-heuristic framework for the optimization of non-discrete Markovian models considering the Optimum-Path Forest (OPF) classifier, as well as we proposed a post-processing procedure to avoid overcorrection over high-frequency regions. The proposed approach outperformed previous results obtained with standard OPF in satellite imagery. (AU)