Multisource synthetic aperture radar (SAR) image registration is a difficult task in remote sensing due to the influence of speckle noise and geometric distortions between the images. The SAR scale-invariant feature transform (SAR-SIFT) is a prior option to extract features for automatic registration of SAR images. However, most registration methods based on the SAR-SIFT operator only use the image information (the geometric distribution of the pixels making up the feature) and do not consider the influences of the side-looking imagery mode and the topographic relief. In this article, we propose a novel registration method to address the above problems, which combines the optimized SAR-SIFT features and the imaging geometry of the SAR system. The major improvement of the algorithm is the use of the range–Doppler (RD) model in feature matching and geometric transformation estimation. A new local matching method aided by the RD model, transforming the global matching mode to the local one, is first introduced to avoid the gross errors and improve the matching efficiency. Then, an RD-model-based geometric transformation model is presented for multisource SAR images with obvious geometric distortions. In addition, the stationary wavelet transform (SWT) is brought in the feature extraction to optimize the SAR-SIFT keypoints to extract reliable and uniformed features. The experimental results fully demonstrate the applicability of the proposed method for registration of multisource SAR images in different acquiring configurations, especially with different passes.
9 June 2022 in IEEE Transactions on Geoscience and Remote Sensing
For multitemporal synthetic aperture radar (SAR) images, the change detection methods based on nonlocal theory can well suppress the adverse effects of coherent speckle noise over the change detection results. However, effectively retaining the edge information of the changed area is still a challenging task. To overcome this problem, this study proposes a change detection method based on progressive nonlocal theory. First, the progressive nonlocal theory is used to extract the spatial–temporal nonlocal information from multitemporal SAR images. Compared with the traditional nonlocal theory, the progressive nonlocal theory proposed in this study has three distinctive characteristics: 1) the progressive nonlocal neighborhood from the matching window to the search window; 2) the progressive optimization of matching window weight from the isotropic Gaussian distribution to the irregular distribution; and 3) the progressive increase of noise level from the 2 sigma principle to the 4/3 sigma principle (the noise level corresponding to the 4/3 sigma principle is 1.5 times the noise level corresponding to the 2 sigma principle). The difference image is then obtained by using the spatial–temporal nonlocal information and the ratio operator. Finally, the change map is obtained by applying a threshold segmentation method to the difference image. Two data sets were used for the testing, and it was shown that compared with other advanced methods, the method proposed in this study can better retain the edge information of the changed area and improve the Kappa coefficient and F1 score of the change map.
3 June 2022 in IEEE Transactions on Geoscience and Remote Sensing
Synthetic aperture radar (SAR) coherent change detection (CCD) predominantly uses the degree of coherence or similar change metrics as a measurement of the changes that have occurred between two data collections. Many existing coherence estimators have shown some performances for change detection, but are still relatively limited, because the change areas do not stand out well from all decorrelation areas due to low clutter-to-noise ratio (CNR) and volume scattering. Besides, many estimators require the equal-variance assumption between two SAR images of the same scene. However, the assumption is less likely to be met in areas with significant intensity differences, especially in change regions. In this article, a novel weighted coherence estimator is proposed to address these problems. The estimator is derived based on the statistical characteristics of SAR images using the maximum-likelihood (ML) principle. The introduction of weight parameters not only makes the estimator no longer need to satisfy the equal-variance assumption but also combines the advantages of coherent and noncoherent algorithms to a certain extent, because the weights are closely related to the ratio change statistic. Experiments on simulated and real SAR image pairs demonstrate the effectiveness of the proposed estimator in highlighting change areas and the boundaries between change and other areas in theory and practice.
2 May 2022 in IEEE Transactions on Geoscience and Remote Sensing
Synthetic aperture radar (SAR) change detection (CD) can be broadly classified into two categories: noncoherent intensity CD and coherent change detection (CCD). The former methods, belonging to the field of image processing, are theoretically suitable for all SAR images since they only utilize the information of SAR magnitude; however, the detection precision cannot be guaranteed. The latter methods can show effective performances for most SAR image pairs using identical collection geometrics because of the basis of the probability and statistics theory. In this article, we propose a novel change estimator to combine the advantages of the two kinds of algorithms in a theoretical derivation way. An intensity-based estimator, inspired by the derivation of the coherence estimator in CCD, is first proposed. It is a new maximum-likelihood (ML) change estimator maximizing the probability distribution function (pdf) of the ratio change statistic instead of SAR complex data. In addition, the simple linear iterative cluster (SLIC) algorithm is introduced to make the new estimator adjustable because changes at different degrees can be extracted with varying settings of the superpixels number, which is further demonstrated in real SAR images. Finally, experiments in SAR image pairs of different statistical characteristics show that the proposed estimator can yield higher contrast SAR CD images than the other five common change statistics and obtain better CD maps than the other four classic thresholding methods.
19 February 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning-based change detection (CD) methods have become an important means of synthetic aperture radar (SAR) images to identify changes. To generate an accurate change map, these methods typically require a high-quality training set. As a frequently adopted way to extract training samples, preclassification has a crucial effect on CD precision. However, preclassification images are often generated using intensity-based CD algorithms that rely on SAR magnitude images without considering phase information. Additionally, the statistical characteristics of SAR images are seldom considered. When designing the artificial intelligence CD models, it is expected to account for speckle noise inherent in SAR images while detecting more small-scale changes to obtain a high-accuracy CD map. Thus, we introduce a new CD approach for single-polarization SAR images based on image standardization and the improved residual network (I-ResNet). Firstly, a strategy of fusing the coherent and noncoherent intensity changes for preclassification image generation is introduced to retain large-scale and small-scale changes. The noncoherent change acquisition part of the strategy involves an image standardization algorithm which is derived from the Gaussian speckle model and is especially effective for images with different statistical characteristics. Then the I-ResNet model combining the dual-tree complex wavelet transform (DT-CWT) with residual learning is presented, which aims at taking advantage of the wavelet transform in reducing the influence of speckle noise and ResNet in easy training and preservation of information integrity. Finally, experiments with different SAR image pairs demonstrate that the proposed method produces better CD maps than other related methods.