Integrated Deep Learning Solutions for Image Segmentation and Deforestation Detection

• Grant number: 24/04492-0
• Support Opportunities: Regular Research Grants
• Start date: November 01, 2025
• End date: October 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Wallace Correa de Oliveira Casaca
• Grantee: Wallace Correa de Oliveira Casaca
• Host Institution: Instituto de Biociências, Letras e Ciências Exatas (IBILCE). Universidade Estadual Paulista (UNESP). Campus de São José do Rio Preto. São José do Rio Preto , SP, Brazil
• City of the host institution: São José do Rio Preto
• Associated researchers: Lucas Correia Ribas ; Marilaine Colnago ; Rogério Galante Negri

Abstract

This project focuses on developing new methodologies and tools based on deep learning in two branches of the Computer Vision field: (i) interactive image segmentation and (ii) detection of deforestation occurrences in the Brazilian Amazon. This multifaceted project aims to advance the forefront of knowledge in the aforementioned branches through ongoing investigations and research efforts. In the branch of image segmentation, the goal is to develop new AI-driven frameworks by combining deep learning neural networks for semantic segmentation and image graph-based strategies. Additionally, it involves unifying graph diffusion models with specific convolutional networks, such as contour and fine learning. In the deforestation detection front, the proposal is to formulate new deep learning-driven approaches from time series of remote sensing images. In addition to identifying occurrences concisely and with temporal consistency, the proposed approach allows for automatic mapping of deforested portions, resulting in a method that is both accurate and fully unsupervised. For this task, combinations of classic neural networks, such as LSTM, with change detection architectures, such as Early Fusion and CSVM-based networks, will be implemented. (AU)

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

FERREIRA, RAFAELLA S.; COLNAGO, MARILAINE; CASACA, WALLACE. Predictive and interpretable machine learning for COVID-19 resurgences: the role of SARS-CoV-2 variants in the post-pandemic era. BMC INFECTIOUS DISEASES, v. 25, n. 1, p. 21-pg., 2025-12-29. (24/04718-8, 24/04492-0, 23/14427-8)