A review of EO image information mining

TL;DR

This paper reviews current methods for content-based retrieval in Earth observation image archives, focusing on system architectures, feature processing, indexing, semantic labeling, and query execution to assess operational readiness.

Contribution

It provides a comprehensive overview of the paradigms, approaches, and challenges in EO image information mining, highlighting recent advancements and future directions.

Findings

Analyzes different system paradigms for EO image retrieval

Reviews solutions for feature simplification, indexing, and semantic labeling

Discusses methodologies for query specification and execution

Abstract

We analyze the state of the art of content-based retrieval in Earth observation image archives focusing on complete systems showing promise for operational implementation. The different paradigms at the basis of the main system families are introduced. The approaches taken are analyzed, focusing in particular on the phases after primitive feature extraction. The solutions envisaged for the issues related to feature simplification and synthesis, indexing, semantic labeling are reviewed. The methodologies for query specification and execution are analyzed.