Unsupervised change detection in SAR images using a non-local mean filter and hyperbolic tangent sigmoid function

ABSTRACT This study presents an unsupervised methodology for change detection in synthetic aperture radar (SAR) imagery, designed to address challenges in accurately identifying affected regions following natural disasters. The proposed approach integrates advanced techniques such as the Hyperbolic Tangent Sigmoid Function (HTS-F) and the Non-Local Means (NLMeans) filter to enhance noise reduction and preserve edge clarity. The architecture minimizes computational overhead through Principal Component Analysis (PCA) and $k$k-means++ clustering, ensuring efficiency while maintaining high detection accuracy. Experimental results on real-world datasets, including Yellow River, Bern, and Ottawa, demonstrate the method’s adaptability and robustness. By combining mathematical precision with operational simplicity, this approach contributes significantly to the evolving landscape of SAR-based change detection.

• Publication year

  2025

• Venue

  Remote Sensing Letters

• Publication date

  2025-03-04

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1080/2150704X.2025.2471592
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Synthetic Aperture Radar Image Change Detection Based on Principal Component Analysis and Two-Level Clustering

  2024cited by this paper
• Detection of changes in synthetic aperture radar images using Modified Gauss-Log ratio and Fuzzy Local Information C-Means clustering

  2023cited by this paper
• SAR image change detection based on Gabor wavelets and convolutional wavelet neural networks

  2023cited by this paper
• Change Detection Approach for SAR Imagery Based on Arc-Tangential Difference Image and k-Means++

  2022cited by this paper
• A saliency-guided neighbourhood ratio model for automatic change detection of SAR images

  2020cited by this paper
• High-Resolution SAR Image Despeckling Based on Nonlocal Means Filter and Modified AA Model

  2020cited by this paper
• SAR Image Change Detection Based on Data Optimization and Self-Supervised Learning

  2020cited by this paper
• SAR Image Change Detection Based on Nonlocal Low-Rank Model and Two-Level Clustering

  2020cited by this paper
• A Deep Learning Method for Change Detection in Synthetic Aperture Radar Images

  2019cited by this paper
• SAR image change detection based on deep denoising and CNN

  2019cited by this paper
• On Multiple Covariance Equality Testing with Application to SAR Change Detection

  2017cited by this paper
• Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks

  2017cited by this paper
• A Generalized Likelihood Ratio Test for Coherent Change Detection in Polarimetric SAR

  2015cited by this paper
• Fuzzy Clustering With a Modified MRF Energy Function for Change Detection in Synthetic Aperture Radar Images

  2014cited by this paper
• Using Combined Difference Image and $k$ -Means Clustering for SAR Image Change Detection

  2014cited by this paper
• Nonparametric Change Detection in Multitemporal SAR Images Based on Mean-Shift Clustering

  2013cited by this paper
• A Neighborhood-Based Ratio Approach for Change Detection in SAR Images

  2012cited by this paper
• Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering

  2009cited by this paper
• A non-local algorithm for image denoising

  2005cited by this paper
• Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery

  2005cited by this paper

• Shape Similarity based Deep Networks for Change Detection

  2025cites this paper