University of Twente
Hallenweg 8,
7522 NH Enschede
The Netherlands
Hallenweg 8,
7522 NH Enschede
The Netherlands
Presentation
The Faculty ITC in University of Twente is leading institute in Earth observation and dedicated to advancing geospatial solutions for real-world challenges and addressing societal needs in life-long learning and remote sensing.
Since 1950, University of Twente and its faculty of ITC has successfully conducted research and consultancy projects in over 70 countries, demonstrating extensive experience. ITC leverages geo-information, Earth observation, and spatio-temporal analytics for land surface monitoring, planning, and management. Its contributions include SAR method development, tools for converting external geospatial data (e.g., cadastral data) into radar reference coordinates, and enrichment of the SAR Benchmark database for machine/deep learning analysis. Expertise spans polarimetric SAR feature extraction, forest monitoring, classification, PolInSAR and TomoSAR, and multi-temporal SAR processing. Published tools are available on platforms like GitHub and integrated into systems such as PolSARpro. ITC’s 'Remote Sensing and GIS Lab' ensures access to critical remote sensing data while adhering to Open Science and FAIR principles for data sharing and open policy. Additionally, ITC’s CRIB provides a cloud computing platform to support these activities.
Role in the project
The University of Twente is specifically the manager of Tasks 5.1 and 5.2, and also contributes to other tasks defined within WP5, as well as all other work packages (WPs) from WP1 through WP10. In Task 5.1, they oversee and manage the generation of benchmark datasets derived from space-based Copernicus radar data, applicable for large-scale, near-real-time infrastructure damage assessment. This task includes essential activities such as data preprocessing, cleaning, georeferencing, and noise suppression to ensure data consistency and accuracy. In Task 5.2, they are in charge of managing the development of AI and deep learning models for cross-modal analysis, enabling real-time identification and assessment of structural damage through the monitoring of urban areas using real-time UAV imagery.
