This paper investigates the safety risks associated with sea ice along the Arctic Route by using polar sea ice images obtained by Gaofen-3 (GF3) Synthetic Aperture Radar (SAR) satellites. We collected three SAR datasets, representative of GF3 satellites' operational modes, and constructed semantic segmentation datasets through meticulous annotation using concurrent optical satellite imagery obtained by Landsat satellites to ensure precision. We propose SI-CTFNet, an innovative sea ice semantic segmentation model that integrates Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for enhanced multi-scale feature extraction. SI-CTFNet features a dual-pathway architecture designed to optimize feature extraction, complemented by the BiAFusion module, which effectively merges local and global features to improve decoding accuracy. Additionally, we introduce the MSDAM module to facilitate a comprehensive multi-scale contextual analysis, addressing the diverse distribution of ice types in the imagery. The model incorporates advanced decoding techniques, including a progressive upsampling (PUP) approach for the CNN-fusion branch and an efficient All-MLP module for the Transformer branch. Performance evaluations across three distinct datasets reveal that SI-CTFNet significantly outperforms existing methods in key metrics and maintains efficacy with supplementary Sentinel1A C-band satellite data. Furthermore, we present a streamlined variant of SI-CTFNet, which achieves a threefold increase in inference speed with minimal reduction in classification accuracy. The ultimate objective of this work is to advance a precise sea ice forecasting and navigation system for polar regions, aimed at automating sea ice classification within a smart polar shipping framework.

Weakly supervised semantic segmentation in aerial images has attracted growing research attention due to the significant saving in annotation cost. Most of the current approaches are based on one specific pseudo label. These methods easily overfit the wrongly labeled pixels from noisy label and limit the performance and generalization of the segmentation model. To tackle these problems, we propose a novel joint multi-label learning network (JMLNet) to help the model learn common knowledge from multiple noisy labels and prevent the model from overfitting one specific label. Our combination strategy of multiple proposals is that we regard them all as ground truth and propose three new multi-label losses to use the multi-label guide segmentation model in the training process. JMLNet also contains two methods to generate high-quality proposals, which further improve the performance of the segmentation task. First we propose a detection-based GradCAM (GradCAM${}^D$) to generate segmentation proposals from object detectors. Then we use GradCAM${}^D$ to adjust the GrabCut algorithm and generate segmentation proposals (GrabCut${}^C$). We report the state-of-the-art results on the semantic segmentation task of iSAID and mapping challenge dataset when training with bounding boxes annotations.

Interferometric synthetic aperture radar (InSAR) products may be significantly distorted by microwave signals traveling through the ionosphere, especially with long wavelengths. The split-spectrum method (SSM) is used to separate the ionospheric and the nondispersive phase terms with lower and higher spectral sub-band interferogram images. However, the ionospheric path delay phase is very delicate to the synthetic aperture radar (SAR) parameters including orbit vectors, slant range, and target height. In this paper, we get the impact of SAR parameter errors on the ionospheric phase by two steps. The first step is getting the derivates of geolocation with reference to SAR parameters based on the range-Doppler (RD) imaging model and the second step is calculating the derivates of the ionospheric phase delay with respect to geometric positioning. Through the numerical simulation, we demonstrate that the deviation of ionospheric phase has a linear relationship with SAR parameter errors. The experimental results show that the estimation of SAR parameters should be accurate enough since the parameter errors significantly affect the performance of ionospheric correction. The root mean square error (RMSE) between the corrected differential interferometric SAR (DInSAR) phase with SAR parameter errors and the corrected DInSAR phase without parameter errors varies from centimeter to decimeter level with the L-band data acquired by the Advanced Land Observing Satellite (ALOS) Phased Array type L-band SAR (PALSAR) over Antofagasta, Chile. Furthermore, the effectiveness of SSM can be improved when SAR parameters are accurately estimated.

In recent years, with the development of micro-satellite clusters and large-scale satellite constellations, the likelihood of multiple spacecraft engaging in orbital pursuit–evasion games has increased. This paper establishes a novel interception domain theory for planar orbital multi-player “encirclement-capture” differential games, and it proves the partitioned structure and classification properties of Nash equilibrium solutions. The main contributions of our study are the following: (1) Proposing the first rigorous definition of interception domains in orbital pursuit–evasion games, proving their convexity, developing computational methods for domain intersections, and establishing a complete classification of equilibrium for planar multi-pursuer interception games, which establishes a theoretical foundation for analyzing multi-spacecraft orbital pursuit–evasion games. (2) Analyzing Nash equilibrium properties for “encirclement-capture” differential games with two, three, or more pursuers, classifying degenerate/non-degenerate scenarios via spatial inclusion relationships. The equilibrium results indicate that as the number of pursuers increases, the game tends toward a degenerate scenario where the likelihood of redundant pursuers (whose actions do not affect the game outcome) rises.

Synthetic aperture radar (SAR) automatic target recognition (ATR) has been widely applied in multiple fields. However, the special imaging mechanism of SAR results in different visual features of the same target at different azimuth angles, so single-aspect SAR target recognition has the limitation of observing the target from a single perspective. Multi-aspect SAR target recognition technology can overcome this limitation by utilizing information from different azimuths and effectively improve target recognition performance. Considering the order dependency and data limitation of existing methods, this paper proposes a multi-aspect SAR recognition method based on Non-Local, which applies a self-attention calculation to feature maps to learn the correlation between multi-aspect SAR images. Meanwhile, in order to improve the generalization ability of the proposed method under limited data, a network based on contrastive learning was designed to pre-train the feature extraction part of the whole network. The experimental results using the MSTAR dataset show that the proposed method has excellent recognition accuracy and good robustness.

Recent advancements in satellite optical reconnaissance have elevated the sun angle to a critical factor in orbital pursuit-evasion games. The stringent imaging constraints imposed by sun angle and relative distance induce non-smoothness in the terminal region of such differential games, significantly complicating equilibrium-solution derivation. To address this challenge, we formulated a novel differential game model where the pursuer minimizes the time-to-entry into the evader’s effective imaging region. We first constructed a sequence of low-dimensional manifolds that collectively cover the terminal region, solving the differential game with this sequence to yield the Nash equilibrium. Subsequently, we approximated the terminal region using a smooth manifold of identical dimensions, enabling a computationally efficient approximate solution. Both methodologies demonstrate broad applicability to orbital differential games featuring non-smooth terminal regions. Simulation results confirm that the approximation error becomes pronounced only under extreme initial sun angles, though this error remains acceptable for practical space reconnaissance applications.