Aims and Scope

Earth Observation (EO) is a rapidly growing research field that brings together computer vision, machine learning, and signal/image processing to provide valuable information about processes occurring at the Earth's surface. EO utilizes data from airborne and spaceborne sensors to capture detailed information on materials and biophysical properties across a wide range of the electromagnetic spectrum, with varying spatial, temporal, and spectral resolutions.

This assumes particular importance in view of the environmental challenges our Planet is facing, including climate change, habitat destruction, pollution and loss of biodiversity. By combining advanced image processing techniques, machine learning algorithms, and big data analysis, computer vision can be used to automate the process of monitoring and analysing environmental data.

EO has a wide range of applications, including online mapping services, large-scale surveillance, urban modelling, navigation systems, natural hazard forecast and response, climate change monitoring, virtual habitat modelling, and more. The integration with other kinds of data necessitates the application of multiple pattern recognition tasks for analysis and offers immense potential for advancing our understanding of Earth's dynamics, thanks to an interdisciplinarity which allows to address complex societal and environmental challenges.

The primary goal of this workshop is to foster collaboration and idea exchange among the Computer Vision, Remote Sensing and Environmental Monitoring communities, both nationally and internationally. We aim to bring together researchers and experts from the three fields to promote interdisciplinary research, encourage innovative computer vision approaches for automated interpretation of Earth observation and other correlated data, and enhance knowledge within the vision community for this rapidly evolving and highly impactful area of research. The implications of this research are far-reaching, affecting human society, economy, industry, and the environment.

Precisely, a non-exhaustive list of topics of interest includes the following:

• Methods: Data-centric machine learning; remote sensing data + language processing (such as Large Language Models) models; open-set, open-world, and open long-tailed recognition; multi-resolution, multi-temporal, multi-sensor, multi-modal approaches; generative models (GANs, stable diffusion, etc); self-, weakly, semi-, and unsupervised approaches; human-in-the-loop and active learning; etc.
• Tasks: Classification; object detection; segmentation (universal, semantic, panoptic, and/or instance); data augmentation and improvement; deep fake; domain adaptation and concept drift; super-resolution; explainability and interpretability; multi and hyperspectral, optical and radar image processing; and so on.
• Applications: Disaster relief; urban planning; sustainable and intelligent agriculture; coast, sea, and marine monitoring; pollution monitoring and air/water quality analysis; circular economy; Cultural Heritage documentation and preservation; climate change; sustainable development goals; geoscience; phenological studies; and so on.