Homepage | Links | Contacts

Duration: 2019-2021
Status: Ongoing
Project Contact: jmf@uninova.pt

Financing: FCT - DSAIPA/AI/0100/2018 (national project)

Partners: UNINOVA (prime), Nova Information Management School (Magic center), Direção-Geral doTerritório (DGT)

IPSTERS (IPSentinel Terrestrial Enhanced Recognition System)
Project Summary

The main goal of this project is to explore the applications and limitations of artificial intelligence (AI) algorithms with accelerated processing hardware capabilities, as a unit of the IPSentinel for the digestion of large volumes of remotely sensed data, to produce level-3 products for land applications with the least amount of human intervention.

We propose exploring two artificial intelligence approaches, one applying active learning techniques, and another based on fuzzy logic.

1- Software Products:
- Scientific advances in the generation of land-cover land-use maps using active learning techniques in the context of Big Data for remote sensing
- Exploring the application of an intelligent data fusion algorithm for the classification of multispectral images

2- Hardware:
- Implementation on dedicated hardware (GPU and FPGA) for acceleration of the data processing.

Apoio FCT – Fundação para a Ciência e a Tecnologia no âmbito da Unidade de Investigação CTS - Centro de Tecnologia e Sistemas, referência UID/EEA/00066/2013