Search

The emerging technology of rotating synthetic aperture (RSA) presents a promising solution for the development of lightweight, large-aperture, and high-resolution optical remote sensing systems in geostationary orbit. However, the rectangular shape of the primary mirror and the distinctive imaging mechanism involving the continuous rotation of the mirror lead to a pronounced decline in image resolution along the shorter side of the rectangle compared to the longer side. The resolution also exhibits periodic time-varying characteristics. To address these limitations and enhance image quality, we begin by analyzing the imaging mechanism of the RSA system. Subsequently, we propose a single-image super-resolution method that utilizes a rotated varied-size window attention mechanism instead of full attention, based on the Vision Transformer architecture. We employ a two-stage training methodology for the network, where we pre-train it on images masked with stripe-shaped masks along the shorter side of the rectangular pupil. Following that, we fine-tune the network using unmasked images. Through the strip-wise mask sampling strategy, this two-stage training approach effectively circumvents the interference of lower confidence (clarity) information and outperforms training the network from scratch using the unmasked degraded images. Our digital simulation and semi-physical imaging experiments demonstrate that the proposed method achieves satisfactory performance. This work establishes a valuable reference for future space applications of the RSA system. [ABSTRACT FROM AUTHOR]

The novel rotating synthetic aperture (RSA) is a new optical imaging system that uses the method of rotating the rectangular primary mirror for dynamic imaging. It has the advantage of being lightweight, with no need for splicing and real-time surface shape maintenance on orbit. The novel imaging method leads to complex image quality degradation characteristics. Therefore, it is vital to use the image quality improvement method to restore and improve the image quality to meet the application requirements. For the RSA system, a new system that has not been applied in orbit, it is difficult to construct suitable large datasets. Therefore, it is necessary to study and establish the dynamic imaging characteristic model of the RSA system, and on this basis provide data support for the corresponding image super resolution and restoration method through simulation. In this paper, we first analyze the imaging characteristics and mathematically model the rectangular rotary pupil of the RSA system. On this basis, combined with the analysis of the physical interpretation of the blur kernel, we find that the optimal blur kernel is not the point spread function (PSF) of the imaging system. Therefore, the simulation method of convolving the input image directly with the PSF is flawed. Furthermore, the weights of a convolutional neural network (CNN) are the same for each input. This means that the normal convolutional layer is not only difficult to accurately estimate the time-varying blur kernel, but also difficult to adapt to the change in the length–width ratio of the primary mirror. To that end, we propose a blur kernel estimation conditional convolutional neural network (CCNN) that is equivalent to multiple normal CNNs. We extend the CNN to a conditional model by taking an encoding as an additional input and using conditionally parameterized convolutions instead of normal convolutions. The CCNN can simulate the imaging characteristics of the rectangular pupil with different length–width ratios and different rotation angles in a controllable manner. The results of semi-physical experiments show that the proposed simulation method achieves a satisfactory performance, which can provide data and theoretical support for the image restoration and super-resolution method of the RSA system. [ABSTRACT FROM AUTHOR]

The novel rotating synthetic aperture imaging system has the advantages of short processing cycle, light weight, low cost, and convenient transport, which is a potential development direction for future optical satellite payloads with ultra-large aperture. However, influenced by the coupling effects of the rectangular primary mirror, rotating imaging, and link perturbation, images from this system may have unique spatial and temporal variability with resolution anisotropy, resulting in the dynamics and weak features of targets. The insufficient recognition of system characteristics seriously restricts the application ability of corresponding target interpretation methods. To address this problem, we start with the analysis of system imaging characteristics and target interpretation mechanisms. Considering calculating texture, grayscale, and edge feature parameters in evaluation regions of different sizes, we propose a degradation assessment method based on multi-scale feature characterization. Then, combined with the theoretical calculation and practical target detection experiments, the influence of crucial parameters such as the aspect ratio and rotation angle of the primary mirror on the target interpretation capability is analyzed. The results will provide guidance for the integrated design and optimization of optical imaging systems and intelligent image processing methods. • A degradation assessment method based on multi-scale feature characterization is proposed. • The effect of rotating synthetic aperture system on image target characteristic degradation is analyzed. • The impacts of key system parameters on target detection performance are analyzed. [ABSTRACT FROM AUTHOR]

• A combined network structure based on the image degradation process that includes three stages of "denoising, deblurring, and detail enhancement". • An interstage information transfer method based on the idea of differentiated intermediate supervision. • A loss function group based on remote sensing imaging modulation transfer function. High-definition remote sensing images have been widely used in many fields such as urban planning and resource exploration. Due to the impact of imaging links, the quality of images produced by remote sensing platforms often deteriorates. Therefore, high-performance remote sensing image restoration processing methods are of great significance for improving their application efficiency. However, existing deep learning methods have not been matched and adjusted based on the imaging characteristics and degradation mechanism of remote sensing systems, and lack representation and constraints on various prior information of remote sensing platforms, which leads to false information easily and is not conducive to interpretation application. To overcome these problems, in this work, we conduct research on a multi-stage remote sensing image restoration network. First, we propose a multi-stage network framework of "denoising deblurring detail enhancement", in which structures at different stages are designed to address the multi-scale characteristics of remote sensing images. Secondly, in order to avoid the degradation of the multi-stage network, we design a differentiated intermediate supervision module and an adaptive structural adjustment module. Finally, based on the degradation characteristics of the remote sensing platform imaging system, we propose a loss function from the prior term of the modulation transfer function. We verify our method by conducting comprehensive comparisons on a new dataset by the full-link imaging simulation. Experiments show that our method is superior to other comparison methods in remote sensing image restoration, and shows competitive performance in terms of restoration performance and speed. Compared with the basic network, the proposed modules improve PSNR and SSIM by 7.18 % and 4.74 % respectively. [ABSTRACT FROM AUTHOR]

Due to the complexity of scene interference and the variability of ship scale and position, automatic ship detection in remote sensing images makes for challenging research. The existing deep networks rarely design receptive fields that fit the target scale based on training data. Moreover, most of them ignore the effective retention of position information in the feature extraction process, which reduces the contribution of features to subsequent classification. To overcome these limitations, we propose a novel ship detection framework combining the dilated rate selection and attention-guided feature representation strategies, which can efficiently detect ships of different scales under the interference of complex environments such as clouds, sea clutter and mist. Specifically, we present a dilated convolution parameter search strategy to adaptively select the dilated rate for the multi-branch extraction architecture, adaptively obtaining context information of different receptive fields without sacrificing the image resolution. Moreover, to enhance the spatial position information of the feature maps, we calculate the correlation of spatial points from the vertical and horizontal directions and embed it into the channel compression coding process, thus generating the multi-dimensional feature descriptors which are sensitive to direction and position characteristics of ships. Experimental results on the Airbus dataset demonstrate that the proposed method achieves state-of-the-art performance compared with other detection models. [ABSTRACT FROM AUTHOR]

Rotating Synthetic Aperture (RSA) technology is one of the distinctly advantageous Earth geostationary orbit optical remote sensing technologies. However, the continuous rotation of the RSA system's rectangular primary mirror results in a discernible drop in resolution along the shorter side of the mirror. Additionally, the captured images exhibit periodic and time-varying characteristics. To improve the image quality to meet interpretation needs, we first delineate the imaging process of the rotating primary mirror and analyze the characteristics of image degradation based on the system's imaging mechanism. Then, we propose a dual super-resolution (SR) framework based on Swin Transformer and introduce a self-supervised learning method for jointly training the unified SR network using wavelet fusion. The self-supervised learning method effectively utilizes the spatiotemporal correlation of the information contained in images captured at different rotation directions of the rectangular pupil. Moreover, the attention mechanism in Transformer can adopt a global perspective and utilize content-based interactions between image content and attention weights to model strong long-range dependencies in remote sensing images. This approach significantly enhances image quality along the pupil's shorter side, consequently yielding superior results. Extensive digital and semi-physical imaging experiments, involving six aspect ratios of the primary mirror, demonstrate that our SR method surpasses state-of-the-art methods. The work in this paper can serve as a valuable reference for future space applications of the RSA technology. • Analyzing the imaging mechanisms of the rotating synthetic aperture system. • Self-supervised learning enhances the utilization of image internal information. • Designing a dual framework that can be trained jointly for image super resolution. • Interactions between image content and attention weights improve performance. • Performance is evaluated through digital and semi-physical experiments. [ABSTRACT FROM AUTHOR]