In the realm of artificial intelligence, the emergence of foundation models, backed by high computing capabilities and extensive data, has been revolutionary. Segment Anything Model (SAM), built on the Vision Transformer (ViT) model with millions of parameters and trained on its corresponding large-scale dataset SA-1B, excels in various segmentation scenarios relying on its significance of semantic information and generalization ability. Such achievement of visual foundation model stimulates continuous researches on specific downstream tasks in computer vision. The ClassWise-SAM-Adapter (CWSAM) is designed to adapt the high-performing SAM for landcover classification on space-borne Synthetic Aperture Radar (SAR) images. The proposed CWSAM freezes most of SAM's parameters and incorporates lightweight adapters for parameter efficient fine-tuning, and a classwise mask decoder is designed to achieve semantic segmentation task. This adapt-tuning method allows for efficient landcover classification of SAR images, balancing the accuracy with computational demand. In addition, the task specific input module injects low frequency information of SAR images by MLP-based layers to improve the model performance. Compared to conventional state-of-the-art semantic segmentation algorithms by extensive experiments, CWSAM showcases enhanced performance with fewer computing resources, highlighting the potential of leveraging foundational models like SAM for specific downstream tasks in the SAR domain. The source code is available at: https://github.com/xypu98/CWSAM.

To monitor a space target, 3-D reconstruction from a multiview sequence of the inverse synthetic aperture radar (ISAR) imaging is developed. Scattering of a complex electric-large target, e.g., the ENVISAT satellite model, is numerically calculated, and multiview 2-D ISAR imaging can be simulated. Under the sparse sampling ISAR imaging via compressed sensing, the Kanade-Lucas-Tomasi feature tracker is applied to extraction of target feature points. Then, using the orthographic factorization method, 3-D reconstruction of those feature points is produced. A simple hexagonal frustum is first tested for the feasibility analysis. Two sequences of multiview ISAR imaging, one is the ENVISAT model and another real measurements of a space shuttle, are then presented for 3-D reconstruction. Furthermore, a complex multistructure model of the International Space Station is also studied from multiview ISAR imaging under different sparse sampling rates. All results demonstrate good feasibility of the 3-D reconstruction for those target components, e.g., solar panel and antenna.

Land cover classification with SAR images mainly focuses on the utilization of fully polarimetric SAR (PolSAR) images. The conventional task of PolSAR classification is single-pixel-based region-level classification using polarimetric target decomposition. In recent years, a large number of high-resolution SAR images have become available, most of which are single-polarization. This article explores the potential of object-level semantic segmentation of high-resolution single-pol SAR images, in particular tailored for the Gaofen-3 (GF-3) sensor. First, a well-annotated GF-3 segmentation dataset “FUSAR-Map” is presented for SAR semantic segmentation. It is based on four data sources: GF-3 single-pol SAR images, Google Earth optical remote sensing images, Google Earth digital maps, and building footprint vector data. It consists of 610 high-resolution GF-3 single-pol SAR images with the size of 1024 × 1024. Second, an encoder-decoder network based on transfer learning is employed to implement semantic segmentation of GF-3 SAR images. For the FUSAR-Map dataset, an optical image pretrained deep convolution neural network (DCNN) is fine-tuned with the SAR training dataset. Experiments on the FUSAR-Map dataset demonstrate the feasibility of object-level semantic segmentation with high-resolution GF-3 single-pol SAR images. Also, our algorithm obtains fourth place about the PolSAR image semantic segmentation on the “2020 Gaofen Challenge on Automated High-Resolution Earth Observation Image Interpretation.” The new dataset and the encoder-decoder network are intended as the benchmark data and baseline algorithm for further development of semantic segmentation with high-resolution SAR images. The FUSAR-Map and our algorithm are available at github.com/fudanxu/FUSAR-Map/.

Simulation of inverse synthetic aperture radar (ISAR) imaging of a space target and reconstruction under sparse sampling via compressed sensing (CS) are developed. The numerical bidirectional analytic ray tracing (BART) method is employed to compute the polarized scattering from an electrically large target. With multiorbit and multistation imaging modes, 2-D and 3-D ISAR images are acquired, leading to information retrieval of the space target, such as shape, structure, attitude, etc. CS is introduced into the reconstruction of ISAR images under sparse sampling. As an example, the models of the Aura satellite and the X-37B orbital test vehicle are presented for ISAR imaging and reconstruction.

SAR images are highly sensitive to observation configurations, and exhibit significant variations across different viewing angles, making it challenging to represent and learn their anisotropic features. As a result, deep learning methods often generalize poorly across different view angles. Inspired by the concept of neural radiance fields (NeRF), this study combines SAR imaging mechanisms with neural networks to propose a novel NeRF model for SAR image generation. Following the mapping and projection principles, a set of SAR images is modeled implicitly as a function of attenuation coefficients and scattering intensities in the 3D imaging space through a differentiable rendering equation. SAR-NeRF is then constructed to learn the distribution of attenuation coefficients and scattering intensities of voxels, where the vectorized form of the 3D voxel SAR rendering equation and the sampling relationship between the 3D space voxels and the 2D view ray grids are analytically derived. Through quantitative experiments on various datasets, we thoroughly assess the multi-view representation and generalization capabilities of SAR-NeRF. Additionally, this paper includes few-shot classification performance improvement as a metric for generation performance. The study found that using 12 images per class resulted in an accuracy improvement of nearly 10% for the classification algorithm.

Hyperspectral data has been widely used in species discrimination of plants with rich spectral information in hundreds of spectral bands, while the availability of hyperspectral data has hindered its applications in many specific cases. The successful operation of the Chinese satellite, Gaofen-5 (GF-5), provides potentially promising new hyperspectral dataset with 330 spectral bands in visible and near infrared range. Therefore, there is much demand for assessing the effectiveness and superiority of GF-5 hyperspectral data in plants species mapping, particularly mangrove species mapping, to better support the efficient mangrove management. In this study, mangrove forest in Mai Po Nature Reserve (MPNR), Hong Kong was selected as the study area. Four dominant native mangrove species were investigated in this study according to the field surveys. Two machine learning methods, Random Forests and Support Vector Machines, were employed to classify mangrove species with Landsat 8, Simulated Hyperion and GF-5 data sets. The results showed that 97 more bands of GF-5 over Hyperion brought a higher over accuracy of 87.12%, in comparison with 86.82% from Hyperion and 73.89% from Landsat 8. The higher spectral resolution of 5 nm in GF-5 was identified as making the major contribution, especially for the mapping of Aegiceras corniculatum. Therefore, GF-5 is likely to improve the classification accuracy of mangrove species mapping via enhancing spectral resolution and thus has promising potential to improve mangrove monitoring at species level to support mangrove management.