This project funded by CNPq proposes developing methods based on machine learning for mapping tree species protected by law in Mato Grosso do Sul (MS) from images collected by UAVs (Unmanned Aerial Vehicles) and for mapping native vegetation throughout the state from orbital images. Continue reading
The project is funded by FAPERJ and investigates methods based on deep learning (deep learning-DL) for semantic segmentation of remote sensing (SR) images. Continue reading
The project is funded by FAPERJ and investigates signal processing and machine learning techniques and their applications in remote sensing and sensor systems and wireless communications. Continue reading
The project aims to evaluate and develop domain adaptation methods to the generalization improvement of deforestation detection techniques in remote sensing images. Read more at project site.
The present project aims to investigate different strategies to handle the insufficient availability of labeled training data, towards fully exploiting the potential of deep architectures for remote sensing image analysis.
Regarding the application domain, the project aims to employ the solutions to be developed in relevant, concrete problems:
The project aims to evaluatie and compare state-of-the-ate Deep Learning techinques for crop mapping in tropical and a temperate regions. It is done using multi-temporal SAR image sequences.
Read more at the Project’s site.
This project aims to evaluate deep learning techniques applied to Deforestation Detection in the Brazilian Amazon. You can find more information at the Project Site
This project aims to evaluate and propose deep learning techniques applied to the semantic segmentation of sequences of satellite images applied to agricultural crop recognition in tropical regions from Brazil. Specifically, the project focuses on unique, end-to-end architectures capable of producing the segmentation outcome of entire image sequences. Read more at the Project Site