Feature Extraction in the Remote Sensing Data Value Chain: A Systematic Review of Methods and Applications

TL;DR

This paper systematically reviews feature extraction techniques in remote sensing, introducing a framework to analyze their evolution and future directions amid the shift towards unified models and representation learning.

Contribution

It provides a comprehensive framework for understanding FE in RS, tracing its evolution, and offering insights into future research directions in the foundation model era.

Findings

FE techniques reduce data redundancy and improve ML tasks in RS.

The landscape of FE in RS is diverse and rapidly evolving.

Future FE research should focus on robustness, interpretability, and bridging classical methods with modern learning.

Abstract

Earth observation involves collecting, analyzing, and processing an ever-growing mass of data. This planetary data is crucial for addressing relevant societal, economic, and environmental challenges, ranging from environmental monitoring to urban planning and disaster management. However, its high dimensionality entails significant feature redundancy and computational overhead, limiting the effectiveness of machine learning models. Feature extraction (FE) techniques address these challenges by preserving essential data properties while reducing redundancy and enhancing tasks in Remote Sensing (RS). The landscape of FE for RS is diverse, disorganized, and rapidly evolving. We offer a practical guide for this landscape by introducing a framework of FE. Using this framework, we trace the evolution of FE across the data value chain in RS. Finally, we synthesize these trends and offer perspectives for the future of FE in RS by first characterizing this shift from single-task models to unified representations, then identifying two perspectives in the foundation model era: the need for robust and interpretable FE and the potential of bridging classical FE with modern representation learning.