A Comparative Study of U-Net Architectures for Change Detection in Satellite Images

TL;DR

This paper systematically compares 18 U-Net variations for change detection in satellite images, highlighting their strengths and weaknesses, and emphasizing the importance of architecture choices for accurate remote sensing applications.

Contribution

It provides a comprehensive analysis of U-Net architectures tailored for change detection, filling a gap in remote sensing literature and guiding future research and practical implementations.

Findings

Siamese Swin-U-Net improves change detection accuracy.

Managing multi-temporal data enhances model performance.

Architectural variations significantly impact detection precision.

Abstract

Remote sensing change detection is essential for monitoring the everchanging landscapes of the Earth. The U-Net architecture has gained popularity for its capability to capture spatial information and perform pixel-wise classification. However, their application in the Remote sensing field remains largely unexplored. Therefore, this paper fill the gap by conducting a comprehensive analysis of 34 papers. This study conducts a comparison and analysis of 18 different U-Net variations, assessing their potential for detecting changes in remote sensing. We evaluate both benefits along with drawbacks of each variation within the framework of this particular application. We emphasize variations that are explicitly built for change detection, such as Siamese Swin-U-Net, which utilizes a Siamese architecture. The analysis highlights the significance of aspects such as managing data from different time periods and collecting relationships over a long distance to enhance the precision of change detection. This study provides valuable insights for researchers and practitioners that choose U-Net versions for remote sensing change detection tasks.