Deep neural network-based approaches for change detection via remote sensing image series

• Grant number: 24/01610-1
• Support Opportunities: Regular Research Grants
• Start date: January 01, 2025
• End date: December 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Rogério Galante Negri
• Grantee: Rogério Galante Negri
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Estadual Paulista (UNESP). Campus de São José dos Campos. São José dos Campos , SP, Brazil
• Associated researchers: Alejandro César Frery Orgambide ; Aluísio de Souza Pinheiro ; Avik Bhattacharya ; Paolo Ettore Gamba ; Wallace Correa de Oliveira Casaca

Abstract

Brazil has faced significant impacts on the environment and society, highlighting the need for effective tools to monitor and understand environmental risk phenomena. Change detection techniques in images obtained through remote sensing, which identify altered areas over time, play a vital role in environmental monitoring. Artificial Intelligence, especially deep neural networks, offers a promising perspective for innovative approaches in change detection. This project, based on deep neural network concepts, aims to develop advanced change detection techniques, with an emphasis on unsupervised and multiclass approaches, applied to the analysis of extensive time series. Furthermore, the advancements of this research will be applied to national issues such as deforestation and hydrological extreme events. (AU)