During ESA Φ-week 2018, our team presented the outcomes of our research in the field of Earth Observation, with a particular focus on utilizing Deep Learning techniques for remote sensing image segmentation.
Remote sensing image segmentation holds significant importance in the realm of Earth Observation, prompting numerous methods to be explored and proposed. Our study specifically concentrates on Deep Learning network architectures for semantic image segmentation. While many existing solutions overlook image preprocessing and primarily emphasize network topologies and hyperparameters, our work introduces a comprehensive suite of tools tailored to Earth Observation data. These tools are designed to facilitate seamless experimentation and integration of various Deep Learning models, preprocessing techniques, and model ensemble methods.
Our group is excited to participate to the conference “Copernicus and Space Applications, 2018 edition” organized by the Romanian Space Agency together with European Space Agency, European Commission, Romanian Parliament – Chamber of Deputies – SPACE Subcommision and Eursys.
Our group is delighted to announce that between 3-4 May 2018 we participated in the OGC’s Earth Observation Exploitation Platform Hackathon. Our team was represented by Marian Neagul, Silviu Panica and Teodora Selea.
As part of the ACM womENcourage 2017 event our PhD Student Teodora Selea presented a poster outlining her work in developing programable and scallable Remote Sensing processing software. Teodora leveraged the already existing experience inside our group in the area of GRID Computing and High Throughput Computing in order to propose a new backend for standards compliant OGC processing service.
The work is based in the ongoing ESA Pathfinder EO4SEE Project.
We are delighted to announce that our group is participating in the ESA Earth Observation for South East Europe Pathfinder project.
EO4SEE stands for Earth Observation for South East Europe and it represents a pathfinder assessment for regional high volume data access, process and information service delivery platform within the region.
subscribe via RSS