Oriented object detection has become a hot topic in SAR image interpretation. Due to the unique imaging mechanism, SAR objects are represented as clusters of scattering points surrounded by coherent speckle noise, leading to blurred outlines and increased false alarms in complex scenes. To address these challenges, we propose a novel noise-to-convex detection paradigm with a hierarchical framework based on the scattering-keypoint-guided diffusion detection transformer (SKG-DDT), which consists of three levels. At the bottom level, the strong-scattering-region generation (SSRG) module constructs the spatial distribution of strong scattering regions via a diffusion model, enabling the direct identification of approximate object regions. At the middle level, the scattering-keypoint feature fusion (SKFF) module dynamically locates scattering keypoints across multiple scales, capturing their spatial and structural relationships with the attention mechanism. Finally, the convex contour prediction (CCP) module at the top level refines the object outline by predicting fine-grained convex contours. Furthermore, we unify the three-level framework into an end-to-end pipeline via a detection transformer. The proposed method was comprehensively evaluated on three public SAR datasets, including HRSID, RSDD-SAR, and SAR-Aircraft-v1.0. The experimental results demonstrate that the proposed method attains an ${\mathrm{AP}}_{50}$ of 86.5%, 92.7%, and 89.2% on these three datasets, respectively, which is an increase of 0.7%, 0.6%, and 1.0% compared to the existing state-of-the-art method. These results indicate that our approach outperforms existing algorithms across multiple object categories and diverse scenes.

Polarimetric Synthetic Aperture Radar (PolSAR) provides a more comprehensive and detailed characterization of target scattering, offering rich information both within and between image pixels. However, existing segmentation methods face challenges such as the difficulty in matching polarization characteristics with deep networks, underutilization of features, and complexity in edge segmentation. To address these issues, a segmentation framework is proposed that integrates Diffusion-based polarization parameter optimization and distribution perception, multi-scale and multi-pol feature fusion, and edge enhancement. First, it leverages Transformer and CNN to adaptively extract, analyze, and fuse features from co-polarization and cross-polarization data. Second, a POA regression and compensation module is incorporated to obtain compensated features. The segmentation results derived from these features are combined with the general results through weighted averaging, enabling mutual supervision and improving final precision by reducing misclassification in complex scattering regions. Additionally, a polarization edge-aware enhancement strategy is introduced to refine segmentation boundaries and reclassify uncertain points. Overall, the framework establishes a hybrid mapping relationship between polarization, texture, statistical properties, and label distributions, enabling effective PolSAR image segmentation. Extensive experimental results and discussion demonstrate the superior performance of our method.

The effective electromagnetic parameters of honeycomb composite structures are crucial for studying their electromagnetic properties. However, most existing homogenization methods are based on static or quasi-static equivalence, considering only the effects of the electromagnetic parameters and the volume fraction of each phase medium on the effective electromagnetic parameters, while neglecting the influence of honeycomb aperture parameters. To address this, this paper proposes a novel homogenization method systematically analyzing the influence of honeycomb structure parameters, particularly aperture parameters, on the effective electromagnetic parameters. This method enables the direct acquisition of the effective electromagnetic parameters of honeycomb structures from their geometric parameters and the material parameters of each phase medium. First, this paper uses the geometric parameters of the honeycomb structure and the material parameters of each phase medium as inputs to construct a forward neural network for predicting the reflection coefficient (S11 parameter). Subsequently, the S11 parameter matrix is rapidly constructed using the reflectance formula. Correlation analysis and global feature extraction in two-dimensional space yield the feature vector matrix, representing the transformed S11 parameters. These are used as inputs to construct an inverse neural network to predict the effective electromagnetic parameters of the honeycomb structure. Finally, this paper reconstructs reflectance curves for two-layer and three-layer honeycomb structures, with mean absolute error below 0.26, validating the proposed method's effectiveness and accuracy.

In the digital twin (DT) network, effective edge data processing is essential to meet the real-time requirements of DT models. However, edge servers (ESs) are self-interested and have limited computation resources. The virtual content operator (VCO) cannot observe their true computing capabilities, leading to participation reluctance and information asymmetry. To address these challenges, this paper proposes a contract-learning integration method for computing incentive and data offloading. A two-dimensional computation-reward contract incentive mechanism is designed to motivate ESs to provide computation resources for data pre-processing, where both continuous and discrete distributions of ES types are considered. Then, ESs upload the processed results to the VCO for DT model mapping, synchronization, and final construction. Based on the individual rationality and incentive compatibility constraints, the optimal incentive reward and computing resource allocation strategies are analytically derived to maximize the VCO’s utility. Then, based on the signed contracts, a multi-agent double deep Q-network algorithm is developed to jointly optimize the binary data offloading decision, transmission bandwidth, and transmission power for the minimal system delay. The algorithm learns adaptive strategies in the dynamic network environment and mitigates Q-value overestimation. Numerical results demonstrate that the proposed method improves system performance in terms of computing incentive and data offloading.