Robust SAR Image Registration Based on Edge Matching and Refined Coherent Point Drift

As synthetic aperture radar (SAR) data is more and more popular in recent days, the fusion of SAR and optical image become inevitable and desirable problem. Image Registration is the fundamental for data fusion, and has been wildly studied. However, literature on registration between SAR and optical image remain little, which means the problem is still challenge and open. On one hand, the SAR and optical image are from totally different sensor with variant imaging mechanism. On the other hand, Simple features could not enough to maintain the accuracy and efficiency of multi-modal registration. We propose a new method for SAR and optical image registration. Different from current methods mainly based on intensity feature or point feature, our method matches two images by their boundary features. A globalized boundary detection algorithm are used for feature extraction. The extracted boundaries were then matched by coherence point drift algorithm. Experiments prove that our method could achieve pixel-level precision, and perform robust for different resolutions.

For Synthetic Aperture Radar (SAR) image registration, successive processes following feature extraction are required by both the traditional feature-based method and the deep learning method. Among these processes, the feature matching process—whose time and space complexity are related to the number of feature points extracted from sensed and reference images, as well as the dimension of feature descriptors—proves to be particularly time consuming. Additionally, the successive processes introduce data sharing and memory occupancy issues, requiring an elaborate design to prevent memory leaks. To address these challenges, this paper introduces the OptionEM-based reinforcement learning framework to achieve end-to-end SAR image registration. This framework outputs registered images directly without requiring feature matching and the calculation of the transformation matrix, leading to significant processing time savings. The Transformer architecture is employed to learn image features, while a correlation network is introduced to learn the correlation and transformation matrix between image pairs. Reinforcement learning, as a decision process, can dynamically correct errors, making it more-efficient and -robust compared to supervised learning mechanisms such as deep learning. We present a hierarchical reinforcement learning framework combined with Episodic Memory to mitigate the inherent problem of invalid exploration in generalized reinforcement learning algorithms. This approach effectively combines coarse and fine registration, further enhancing training efficiency. Experiments conducted on three sets of SAR images, acquired by TerraSAR-X and Sentinel-1A, demonstrated that the proposed method’s average runtime is sub-second, achieving subpixel registration accuracy.

The traditional template matching strategy of optical and synthetic aperture radar (SAR) is sensitive to the nonlinear transformation between two images. In some cases, the optical and SAR image pairs do not conform to the affine transformation condition. To address this issue, this study presents a novel template matching strategy which uses the One-Class Support Vector Machine (SVM) to remove outliers. First, we propose a method to construct the similarity map dataset using the SEN1-2 dataset for training the One-Class SVM. Second, a four-step strategy for optical and SAR image registration is presented in this paper. In the first step, the optical image is divided into some grids. In the second step, the strongest Harris response point is selected as the feature point in each grid. In the third step, we use Gaussian pyramid features of oriented gradients (GPOG) descriptor to calculate the similarity map in the search region. The trained One-Class SVM is used to remove outliers through similarity maps in the fourth step. Furthermore, the number of improve matches (NIM) and the rate of improve matches (RIM) are designed to measure the effect of image registration. Finally, this paper designs two experiments to prove that the proposed strategy can correctly select the matching points through similarity maps. The experimental results of the One-Class SVM in dataset show that the One-Class SVM can select the correct points in different datasets. The image registration results obtained on the second experiment show that the proposed strategy is robust to the nonlinear transformation between optical and SAR images.

Synthetic Aperture Radar (SAR) images are efficient and reliable source of information in extraction of damaged regions in case of floods. In assessment of damage accurately due to floods, image registration of optical (before-flood) and SAR images (after-flood) has to be carried out efficiently. In this paper, we discuss a robust multi-sensor image registration algorithm using scale invariant feature points for keypoint extraction. For matching the keypoints, a multi-objective genetic algorithm is developed with angle, distance and vicinity criterion as the fitness functions. This optimization process helps in matching the scale invariant feature points. From the obtained results, the performance of the image registration is evaluated and it is concluded that the proposed approach is efficient.

An Improved Anisotropic Gaussian-Scale Invariant Feature Transform (IAG-SIFT) algorithm is proposed to register the Synthetic Aperture Radar (SAR) images. The standard SIFT algorithm generates isotropic Gaussian scale space which blurs lots of details in the image. The Anisotropic Scale Space (ASS) can preserve more details than the isotropic one. However, in many SAR registration methods, the gradient calculation of the ASS is performed by using the simple differential equation which is not appropriate for SAR images. As the SAR images contain multiplicative speckle noise, simple difference operation is not suitable for gradient calculation. It can reduce the number of correct matches in SAR image registration. So, in this paper, a Gaussian-Gamma-Shaped Bi-Window (GGS-BW) is used for ratio based gradient computation which is very effective for SAR images. The proposed IAG-SIFT method significantly improves the matching performance between the SAR images. The Experimental results show the effectiveness of proposed IAG-SIFT algorithm in SAR image registration.

Synthetic aperture radar (SAR) imaging has been widely applied in drones for its consistent surveillance capability and invulnerability to smoke or cloud. Yet drone platform is unstable and observing distance is much shorter than satellite. As a consequence, the SAR image registration, which is a crucial process in SAR imaging, is influenced by sparkling scattering spots and coherent speckle noise. In this paper, we propose a multi-layer method to improve SAR registration performance on drones. ORB method is applied to mitigate sparkle scattering spot. Multi-layer feature clustering can eliminate the error matches by coherent speckle noise. Experiments were carried out to valid the proposed method. Results demonstrate that the proposed method can improve SAR image registration performance on unstable aerial platforms.

Common feature representation in optical and synthetic aperture radar (SAR) image registration is one of the most challenging tasks due to the significant geometric and radiometric differences. This letter proposed a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Prominent structure-guided feature (PSGF)</i> representation for SAR and optical image registration. Firstly, the prominent structure of the image is highlighted based on windowed inherent variations, which is conducive to identifying more accurate and reliable corresponding points. Secondly, the maximum response index filter banks are proposed to extract structure features with multi-orientation convolution results. Then the structure feature-guided representation generated from this filtering map is quantized in histograms. Finally, the descriptor with radiation invariance is employed for feature matching, enabling automatic image registration with high accuracy. Comparative analysis with state-of-the-art methods on diverse terrain data demonstrates the superiority of the proposed PSGF method for SAR and optical image registration.

We address the application of model-supported exploitation techniques to synthetic aperture radar (SAR) imagery. The emphasis is on monitoring SAR imagery using wide area 2D and/or 3D site models along with contextual information. We consider here the following tasks useful in monitoring: (a) site model construction using segmentation and labeling techniques, (b) target detection, (c) target classification and indexing, and (d) SAR image-site model registration. The 2-D wide area site models used here for SAR image exploitation differ from typical site models developed for RADIUS applications, in that they do not model specific facilities, but constitute wide area site models of cultural features such as urban clutter areas, roads, clearings, fields, etc. These models may be derived directly from existing site models, possibly constructed from electro-optical (EO) observations. When such models are not available, a set of segmentation and labeling techniques described here can be used for the construction of 2D site models. The use of models can potentially yield critical information which can disambiguate target signatures in SAR images. We address registration of SAR and EO images to a common site model. Specific derivations are given for the case of registration within the RCDE platform. We suggest a constant false alarm rate (CFAR) detection scheme and a topographic primal sketch (TPS) based classification scheme for monitoring target occurrences in SAR images. The TPS of an observed target is matched against candidate targets TPSs synthesized for the preferred target orientation, inferred from context (e.g. road or parking lot targets). Experimental results on real and synthetic SAR images are provided.

The low information consistency and serious interference caused by synthetic aperture radar (SAR) imaging characteristics and target attributes affect the accuracy of SAR image information description, which reduces the performance of SAR image registration. In this work, the polar speeded up robust features (PSURF) descriptor is proposed for SAR image registration. In PSURF, according to the advantages of pole space in the relationship between pixels, a quantitative model of information change based on pole space is established to improve the integrity, consistency, and separability of image features. Firstly, the support region is transformed into polar coordinates. Then, the image gray level changes in the radial and angular directions are quantified with different scales. Finally, the PSURF descriptor based on the scale of keypoints is constructed covering the omnidirectional space.

Availability of the sufficient number of matching pairs is the major challenge for optical to SAR (Synthetic Aperture Radar) image registration. Recently, a distinctive order based self-similarity operator (DOBSS) has been proposed to register the optical images. In this paper, a modified version of the distinctive order based self-similarity (M-DOBSS) is proposed to register the optical and SAR images. The proposed M-DOBSS provides more distinctiveness than the standard DOBSS operator. It can significantly increase the number of matching pairs between the optical and SAR images. Experiments on different sets of optical-SAR image pairs demonstrates the effectiveness of the proposed method.

Synthetic Aperture Radar (SAR) is an active remote sensing system which can be installed on aircraft, satellite and other carriers with the advantages of all day and night and all-weather ability. It is the important problem that how to deal with SAR and extract information reasonably and efficiently. Particularly SAR image geometric correction is the bottleneck to impede the application of SAR. In this paper we introduces image registration and the Susan algorithm knowledge firstly, then introduces the process of SAR image registration based on Susan algorithm and finally presents experimental results of SAR image registration. The Experiment shows that this method is effective and applicable, no matter from calculating the time or from the calculation accuracy.

In this paper, to address the problem in the registration of synthetic aperture radar (SAR), the speeded up robust features (SURF) approach based on multi-level FAST and improved random sampling consistency is proposed. This approach is used to address the high mismatch rate in SAR image registration, and it is based on the characteristics of SAR images. We construct a new corner detection by combining with the hierarchical theory of the system, which is referred to as multi-level FAST (MFAST). The contribution of MFAST algorithm mainly lies in the efficiency of SURF algorithm, which determines the main direction and feature descriptor. And improving the random sampling consistency (RANSAC) to remove mismatched feature points and ameliorate the registration effectiveness. The proposed algorithm is suitable for multi-sensor images with large gray differences and significant edge features. The experimental results show that the registration efficiency of the proposed algorithm is more than three times of the SURF algorithm, and the registration accuracy also is better than traditional SURF algorithm, which can reach 0.39 pixels.

Precise registration of synthetic aperture radar (SAR) images is a nontrivial task since a change in radar-acquisition geometry generates image shifts. In existing system, either the transformation functions are oversimplified, or external measures such as digital elevation model and flight track are required to be precise. In this paper, we proposed a generative Bayesian approach to modelling the displacement vectors that map the position of each pixel in the image, thus avoiding degradation of the transformation function. Rather than providing a point estimate for the transformation function, the proposed method yields a full posterior density function of the transformation function. Especially, the Bayesian model learns all the parameters adaptively, and the procedure is fully automatic. The proposed model is comparable in accuracy to state-of-the-art optical flow methods on the challenging Sintel benchmarks, and outperforms currently published SAR image registration methods on some real SAR data with critical scenes.

In this paper, to address problems in the registration of synthetic aperture radar (SAR) and optical images due to large gray differences, the scale-invariant feature transform (SIFT) approach based on phase congruency (PC-SIFT) is proposed. This approach is used to address the gradient inversion in multi-source images, and it is based on optimizing the dominant direction interval of the descriptors. We construct a new descriptor by combining phase consistency and the gradient amplitude, which is referred to as PCG-SIFT descriptor. The proposed algorithm is suitable for multi-sensor images with large gray differences and significant edge features The results of experiments show that compared to the traditional gradient-based SIFT descriptor, the PC-SIFT descriptor and PCG-SIFT descriptor improve the robustness and matching probability of the registration algorithm for multi-source images.

Synthetic Aperture Radar (SAR) is one of the most widely utilized methods to extract elevation information and identify large-scale deformations in mountainous areas. Homologous points in stereo SAR image pairs are difficult to identify due to complex geometric and radiometric distortions. In this paper, a new approach for mountainous area images is suggested. Firstly, a simulated SAR image and a look-up table based on DEM data are generated by a range-Doppler model and an empirical formula. Then, a point matching RPM-L2E algorithm is used to match images obtained by the simulation and in real-time to indirectly obtain the feature points of the real SAR images. Finally, the accurate registration of mountainous areas in the SAR images is achieved by a polynomial transform. Experimental verification is performed by using the data of mountainous SAR images from the same sensor and different sensors. When the registration accuracy of the method is compared with that of two state-of-the-art image registration algorithms, better outcomes are experimentally shown. The suggested approach can effectively solve the registration problem of SAR images of mountainous areas, and can overcome the disadvantages of poor adaptability and low accuracy of traditional SAR image registration methods for mountainous areas.