We consider using the maximum-likelihood (ML)-inspired methods, such as maximum-likelihood inspired adaptive robust iterative approach (MARIA), for tomographic synthetic aperture radar (TomoSAR) imaging in scenarios with high noise level. Traditional MARIA method faces two key challenges in this case: First, the positive feedback mechanism likely leads to error propagation in high noise level; Second, the assumption of exactly known noise power is usually invalid, both of which result in significant performance degradation. Therefore, we propose a refined ML-inspired TomoSAR imaging method suitable for high noise level, improving the signal and noise estimation process of the typical MARIA. First, we derive a new iterative expression based on ML criterion without the positive feedback mechanism for signal estimation, which suppresses the error propagation in high noise level. Second, we regard noise power as a variable to be estimated and introduce an iterative method based on ML criterion for estimation. Simulation and real unmanned aerial vehicle (UAV) experiment results both verify the effectiveness of the proposed method. Finally, we theoretically give a convergence guarantee for the proposed method.

Deep learning-based disparity estimation methods have demonstrated significant potential in optical satellite stereo image applications. However, learning-based methods remain susceptible to domain shifts caused by spatiotemporal variations and stereo-sensor heterogeneity. To address these challenges, we propose a Hierarchical Domain Adaptation Disparity Estimation framework (HDADE) for optical satellite stereo images. HDADE was structured with a four-stage technique pipeline to improve the training data quality and diversity, explicitly align the spectral and stereo distribution, implicitly enhance the robustness of feature extraction and matching, directly facilitate feature alignment with the target domain. This hierarchical framework systematically mitigates disparity estimation accuracy degradation in cross-domain scenarios. Cross-spatiotemporal and cross-payload generalization experiments were conducted based on the WHU_Stereo and US3D datasets. The experimental results show that HDADE significantly outperformed other advanced methods and possessed plug-and-play versatility. Notably, greater domain shift scene transfer experiments indicated that, with limited annotation data, HDADE has the potential for large-scale automatic applications.

Conventional synthetic aperture radar (SAR) generates the imaging swath parallel to the satellite trajectory without considering about the complex orientation of scene, leading to the inefficient multiple-swaths observation of the long curved terrains, like seismic faults, railways, coastlines, etc.. Nowadays, spaceborne SAR terrain matching (TM) curved imaging is proposed to solve this problem by generating a flexible curved swath matching with the long curved terrain, improving the observing efficiency successfully. However, there is currently no suitable imaging algorithm that fully considers the complex parameters in the spaceborne SAR TM curved imaging. In this paper, we proposed a new fast back-projection algorithm for the spaceborne SAR TM curved imaging. The main technical contributions are: First, a nonuniform sub-aperture dividing method is proposed to adapt to the spatial variance of wavenumber spectrum. Second, a non-orthogonal grid meshing method is proposed to fit the complex orientation of the TM curved swath. Third, a modified spectrum compression method is proposed to accelerate processing. A spaceborne SAR TM curved imaging mission of observing the main urban area of Wuhan in China is performed with the Chinese LJ2-01 satellite. Real data results verify the effectiveness of the proposed algorithm.

Cloud detection in high-resolution remote sensing images (HRSI) is widely applied to cross-spatiotemporal domains with various scenarios change. However, cloud detection semantic segmentation models based on limited samples cannot ensure the consistency of data distribution between the source domain (SD) and the target domain (TD), resulting in a decrease in cross-domain segmentation accuracy and robust ability. Therefore, this paper proposed a two-stage domain adaptation based on the image and feature levels (TDAIF) cloud detection framework. TDAIF designs a pseudo-target domain data generator (PTDDG) at the image level to fuse the SD foreground and TD background information effectively, assisting the model in mining invariant semantic knowledge of the TD. Then, a domain discriminator and self-ensembling joint (DDSEJ) framework is explored at the feature level to implicitly handle the alignment of global features and the optimization of decision boundaries-local features. TDAIF ultimately weakens the impact of image radiation diversity and scale divergence and improves the adaptive processing capabilities for cross-spatiotemporal data. Horizontal and internal comparative experiments on TDAIF were conducted on three domain transfer data. Experimental results show that TDAIF dramatically reduces the network accuracy loss in cross-domain. Compared with CycleGAN and AdaptSegNet, the IoU is improved by about 30%. TDAIF performs better than state-of-the-art computational visual domain adaptation methods, indicating that hierarchical data alignment from the image to the feature level is very effective.

In the field of photogrammetry and remote sensing, the task of satellite stereo image disparity estimation (SSIDE) has long been recognized as both challenging and important. Currently, deep-learning methods are gaining prominence in the SSIDE domain. However, the inconsistency between stereo images and ground truth makes the fine training and accurate inference of SSIDE networks extremely difficult. Furthermore, the existence of textureless and repeated texture areas in satellite images complicates the execution of end-to-end SSIDE networks, especially in areas with variable illumination conditions. In this study, a sparse matching point-guided disparity estimation (SMP-DE) general framework was introduced to address such concerns. SMP-DE employed sparse matching point-guided data evaluation and distillation (SMP-DED) for fault-tolerant training and ensuring unbiased guidance training as well as reliable reasoning. In addition, SMP-DE executed optimization for the disparity estimation network across various feature spaces by integrating sparse matching point-guided feature contrastive registration (SMP-FCR) and matching cost uniqueness constraint (MCUC) modules. Therefore, SMP-DE can mine homogenous features and model low-entropy matching costs in challenging regions. Experimental results demonstrated that SMP-DE has outstanding disparity estimation accuracy and generalization compared with other advanced methods. Furthermore, the proposed SMP-DED exhibited excellent flexibility and generality, since it can be combined with various disparity estimating networks, giving the networks an accuracy boost on a range of datasets. In summary, SMP-DE provides a novel perspective for end-to-end SSIDE research.