Title: Event-Based Vision in Space: Applications, Trends, and Future Directions

Abstract: The deployment of novel sensing technologies is driving a major transformation in Earth Observation (EO). While traditional frame-based optical sensors face significant challenges in orbital environments—such as motion blur, excessive power usage, and high data redundancy—event-based sensors, or neuromorphic cameras, offer an alternative bio-inspired asynchronous approach. These devices capture only local illumination changes, delivering microsecond temporal resolution, an exceptionally high dynamic range, and superior energy efficiency. Although the integration of these sensors is rapidly expanding from terrestrial to orbital systems, the scientific literature regarding their space-based applications remains fragmented. To address this gap, this paper provides a comprehensive review of the current state of event-based vision in space. Based on the retrieved literature, we propose a taxonomy organized around four key domains: 1) atmospheric and high-speed observation; 2) environmental monitoring and change detection; 3) operational support and onboard processing; and 4) geospatial modeling and predictive analysis. This survey underscores that neuromorphic engineering represents more than just an supplementary imaging method; it is a paradigm shift capable of directly resolving critical bottlenecks in modern remote sensing and sustainable space exploration.

Source: arXiv Generated at: 2026-06-02 00:00:00 UTC