Deep Learning Meets Object-Based Image Analysis: Tasks, challenges, strategies, and perspectives

Abstract

Deep learning (DL) has gained significant attention in remote sensing, especially in pixel- or patch-level applications. Despite initial attempts to integrate DL into object-based image analysis (OBIA), its full potential remains largely unexplored. In this article, as OBIA usage becomes more widespread, we conduct a comprehensive review and expansion of its task subdomains, with or without the integration of DL. Furthermore, we identify and summarize five prevailing strategies to address the challenge of DL’s limitations in directly processing unstructured object data within OBIA, and this review also recommends some important future research directions. Our goal with these endeavors is to inspire more exploration in this fascinating yet overlooked area and facilitate the integration of DL into OBIA processing workflows.