Advances and Opportunities in Remote Sensing Image Geometric Registration: A systematic review of state-of-the-art approaches and future research directions

• Published in: IEEE geoscience and remote sensing magazine Vol. 9; no. 4; pp. 120 - 142
• Main Authors: Feng, Ruitao, Shen, Huanfeng, Bai, Jianjun, Li, Xinghua
• Format: Journal Article
• Language: English
• Published: IEEE 01.12.2021
• Subjects: Feature extraction; Image fusion; Image registration; Learning systems; Measurement; Optical flow; Remote sensing; Time series analysis
• ISSN: 2473-2397; 2168-6831
• DOI: 10.1109/MGRS.2021.3081763

Geometric registration is often an accuracy assurance for most remote sensing image processing and analysis, such as image mosaicking, image fusion, and time-series analysis. In recent decades, geometric registration has attracted considerable attention in the remote sensing community, leading to a large amount of research on the subject. However, few studies have systematically reviewed its current status and deeply investigated its development trends. Moreover, new approaches are constantly emerging, and some issues still need to be solved. Thus, this article presents a survey of state-of-the-art approaches for remote sensing image registration in terms of intensity-based, feature-based, and combination techniques. Optical flow estimation and deep learning-based methods are summarized, and software-operated registration and registration evaluation are introduced. Building on recent advances, promising opportunities are explored.