Welcome to RSiM
Remote Sensing Image Analysis Group

About

The Remote Sensing Image Analysis (RSiM) group at the Faculty of EECS, TU Berlin and the Big Data Analytics for Earth Observation (BigEarth) group at BIFOLD are led by Prof. Begüm Demir. Our groups perform research in the field of processing and analysis of remote sensing images for Earth observation with interdisciplinary approaches associated to remote sensing, machine learning, signal & image processing and big data management.

Latest News

Post thumb
  • 2025-04-01

Talking to Earth: a First-Generation AI Digital Assistant

As a part of the ESA funded DA4DTE project, together with the National and Kapodistrian University of Athens and and e-GEOS, we developed AI powered digital assistant that allows users to access and explore complex EO data through a natural language interface. For details, please click here.

Post thumb
  • 2025-03-28

GAIA: A Vision-Language Dataset for Earth Observation

GAIA is a new dataset designed to overcome the limitations of existing vision-language models and datasets in the field of Earth observation. For details, please click here.

Post thumb
  • 2025-03-25

Learning-Based Compression and Compressed Domain Analysis in Remote Sensing

A new website that reflects years of research and development at RSiM in advancing learning based compression and compressed domain analysis in RS.

Post thumb
  • 2025-02-01

MORSE @CVPR

We organize the First Workshop on Foundation and Large Vision Models in Remote Sensing (MORSE) at the IEEE/CVF CVPR in collaboration with Prof. Prasad, Prof. Chanussot, Prof. Banerjee and Prof. Hong. For details, visit MORSE.

Post thumb
  • 2024-11-02

Berlin Science Week

At the Berlin Science Week, we demonstrated EarthQube that is a system we developed to efficiently query satellite image archives. For more information, please visit: bifold.berlin.

Post thumb
  • 2024-09-13

BigEarth News @CORDIS

The BigEarth Project, led by Prof. Dr. Demir, has been honored by CORDIS for advancing AI in remote sensing image search and retrieval. For details, visit cordis.europa.eu.

Supported by

logo logo logo logo logo