Micro-variation monitoring radar based on the differential interference principle can monitor objects prone to micro deformation. However, it is easily affected by human and environmental factors to cause the radar image to loss coherence in the long-term monitoring work, thus affecting the normal monitoring of radar. Therefore, it is of great significance to study the change detection method of micro-variation monitoring radar images, which can provide reference information and quantitative analysis for monitoring work. In this paper, a method of landslide area identification and detection based on micro-variation radar image is proposed. Based on the radar coherence coefficient image of time series, the difference image is produced by logarithmic ratio cumulation. The difference map is decomposed and denoised by wavelet transform, and then the final difference map is produced by reconstructing the processed wavelet coefficients. Finally, the improved K-means is used to cluster the difference map to get the change detection result image. The actual monitoring data of a mining area is used for variation detection. The results show that the proposed method retains the detailed information of the change area and removes a lot of noise. The difference map is easier to cluster, and the clustering result is more accurate.
1. Wang, Y., L. Du, and H. Dai, "Unsupervised SAR image change detection based on SIFT keypoints and region information," IEEE Geoscience and Remote Sensing Letters, Vol. 13, No. 7, 931-935, July 2016. doi:10.1109/LGRS.2016.2554606
2. Ren, H., P. Huang, W. Tan, W. Xu, F. Liu, and M. Zhang, "Unsupervised image change detection based on ground-based imaging radar," 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), 1-5, 2019.
3. Zhuang, H. Fan, H. Deng, K. Yao, and B. Guo, "A spatial-temporal adaptive neighborhood-based ratio approach for change detection in SAR images," Remote Sensing, Vol. 10, No. 8, 2018. doi:10.3390/rs10081295
4. Zhang, X., W. Liu, and S. He, "Urban change detection in TerraSAR image using the difference method and sar coherence coefficient," Journal of Engineering Science And Technology Review, Vol. 11, No. 3, 18-23, 2018. doi:10.25103/jestr.113.03
5. Bovolo, F. and L. Bruzzone, "A detail-preserving scale-driven approach to change detection in multitemporal SAR images," IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, No. 12, 2963-2972, Dec. 2005. doi:10.1109/TGRS.2005.857987
6. Sumaiya, M., N. Kumari, R. Shantha, and Selva, "Logarithmic mean-based thresholding for SAR image change detection," IEEE Geoscience and Remote Sensing Letters, Vol. 13, No. 11, 1726-1728, 2016. doi:10.1109/LGRS.2016.2606119
7. Arai and Kohei, "Change detection method with multi-temporal satellite images based on wavelet decomposition and tiling," International Journal of Modern Physics A, Vol. 12, No. 3, 56-61, 2021.
8. Zhou, Y., L. Zhang, and P. Hua, "Combined simulated annealing and soft-threshold wavelet denoising of SAR image," Journal of Beijing University of Aeronautics and Astronautics, Vol. 32, No. 3, 293-296, 2006.
9. Yetgin, Z., "Unsupervised change detection of satellite images using local gradual descent," IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 5, 1919-1929, May 2012. doi:10.1109/TGRS.2011.2168230
10. Liu, L., Z. Jia, J. Yang, and N. K. Kasabov, "SAR image change detection based on mathematical morphology and the K-means clustering algorithm," IEEE Access, Vol. 7, 43970-43978, 2019. doi:10.1109/ACCESS.2019.2908282