Developments in deep learning for change detection in remote sensing: A review

Abstract

Deep learning (DL) algorithms have become increasingly popular in recent years for remote sensing applications, particularly in the field of change detection. DL has proven to be successful in automatically identifying changes in satellite images with varying resolutions. The integration of DL with remote sensing has not only facilitated the identification of global and regional changes but has also been a valuable resource for the scientific community. Researchers have developed numerous approaches for change detection, and the proposed work provides a summary of the most recent ones. Additionally, it introduces the common DL techniques used for detecting changes in satellite photos. The meta-analysis conducted in this article serves two purposes. Firstly, it tracks the evolution of change detection in DL investigations, highlighting the advancements made in this field. Secondly, it utilizes powerful DL-based change detection algorithms to determine the best strategy for monitoring changes at different resolutions. Furthermore, the proposed work thoroughly analyzes the performance of several DL approaches used for change detection. It discusses the strengths and limitations of these approaches, providing insights into their effectiveness and areas for improvement. The article also discusses future directions for DL-based change detection, emphasizing the need for further research and development in this area.