Recently, remote sensing image super-resolution (RSISR) has drawn considerable attention and made great breakthroughs based on convolutional neural networks (CNNs). Due to the scale and richness of texture and structural information frequently recurring inside the same remote sensing images (RSIs) but varying greatly with different RSIs, state-of-the-art CNN-based methods have begun to explore the multi-scale global features in RSIs by using attention mechanisms. However, they are still insufficient to explore significant content attention clues in RSIs. In this paper, we present a new Hybrid Attention-based U-shaped Network (HAUNet) for RSISR to effectively explore the multi-scale features and enhance the global feature representation by hybrid convolution-based attention. It contains two kinds of convolutional attention-based Single-scale feature Extraction Modules (SEM) to explore the global spatial context information and abstract content information, and a Cross-scale Interaction Module (CIM) as the skip connection between different scale feature outputs of encoders to bridge the semantic and resolution gaps between them. Considering the existence of equipment with poor hardware facilities, we further design a lighter HAUNet-S with about 596K parameters. Experimental attribution analysis method LAM results demonstrate that our HAUNet is a more efficient way to capture meaningful content information and quantitative results can show that our HAUNet can significantly improve the performance of RSISR on four remote sensing test datasets. Meanwhile, HAUNET-S also maintains competitive performance. Our code is available at https://github.com/likakakaka/HAUNet_RSISR.

An adaptive unscented Kalman filtering (UKF) algorithm with noise statistic estimator is designed to solve the problem that the conventional UKF declines in accuracy and further diverges when the prior noise statistic is unknown and time-varying. Firstly, a constant noise statistic estimator which is suboptimal and unbiased is deduced based on maximum a posterior (MAP) estimation. Then, the recursive equations of time-varying noise statistic estimator are given through exponential weighting of the constant noise statistic estimator. Finally, performance analysis of the adaptive UKF algorithm is done. Under the condition of unknown and time-varying noise statistic, the proposed adaptive UKF algorithm still converges, moreover its filtering precision and stability are better than those of the conventional UKF. And an adaptive capability to deal with variable noise statistic is performed by the presented UKF. The simulation examples show its effectiveness.

Super-resolution neural networks have recently achieved great progress in restoring high-quality remote sensing images at low zoom-in magnitude. However, these networks often struggle with challenges like shape distortion and blurring effects due to the severe absence of structure and texture details in large-factor remote sensing image super-resolution. Addressing these challenges, we propose a novel Two-Stage Spatial-Frequency Joint Learning Network (TSFNet). TSFNet innovatively merges insights from both spatial and frequency domains, enabling a progressive refinement of super-resolution results from coarse to fine. Specifically, different from existing frequency feature extraction approaches, we design a novel amplitude-guided-phase adaptive filter module to explicitly disentangle and sequentially recover both the global common image degradation and specific structural degradation in the frequency domain. Additionally, we introduce the cross-stage feature fusion design to enhance feature representation and selectively propagate useful information from stage one to stage two. Quantitative and qualitative experimental results demonstrate that our proposed method surpasses state-of-the-art techniques in large-factor remote sensing image super-resolution. Our code is available at https://github.com/likakakaka/TSFNet_RSISR.

The precise calibration and compensation of detetion, drive, system phase, and resonator errors in whole-angle (WA) hemispherical resonator gyroscope (HRG) are essential to improve performance. This paper comprehensively considers the influences of four kinds of errors, including the gain mismatch and angle misalignment of detection and drive electrodes; the nonlinearity of capacitance detection and electrostatic drive; the phase delay of each module in the measurement and control system; the anisodamping and anisoelasticity of resonator. A novel self-excitation enabled decoupling, calibration, and compensation (SE-DCC) process is proposed based on the analysis and modeling of these errors. The detection errors are first calibrated and compensated under high-speed turntable excitation. The drive and system phase errors are then self-calibrated and self-compensated under self-excitation operation. Finally, the characteristics of resonator appear, and the self-calibration and force-compensation of anisodamping are completed. Experimental results demonstrate that the angle-dependent errors under high-speed rotation are effectively suppressed, the peak-to-peak value of angle-dependent bias (ADB) is reduced by more than two orders from 31.44°/h to 0.25°/h, the scale factor (SF) nonlinearity in ±500°/s range is reduced by 85 times from 74.6ppm to 0.879ppm, the bias stability (1σ) is reduced from 0.7740°/h to 0.0134°/h, and the bias instability (BI) is reduced by one order from 0.0991°/h to 0.0092°/h. The SE-DCC process is proven to push the accuracy of the tested WA HRG to inertial-level and shows promise for expanding to all types of WA gyroscopes with high Q factor and low frequency spilt.

The optimality of Bayesian filtering relies on the completeness of prior models, while deep learning holds a distinct advantage in learning models from offline data. Nevertheless, the current fusion of these two methodologies remains largely ad hoc, lacking a theoretical foundation. This paper presents a novel solution, namely an explainable gated Bayesian recurrent neural network specifically designed to state estimation under model mismatches. Firstly, we transform the non-Markov state-space model into an equivalent first-order Markov model with memory. It is a generalized transformation that overcomes the limitations of the first-order Markov property and enables recursive filtering. Secondly, by deriving a data-assisted joint state-memory-mismatch Bayesian filtering, we design a Bayesian gated framework that includes a memory update gate for capturing the temporal regularities in state evolution, a state prediction gate with the evolution mismatch compensation, and a state update gate with the observation mismatch compensation. The Gaussian approximation implementation of the filtering process within the gated framework is derived, taking into account the computational efficiency. Finally, the corresponding internal neural network structures and end-to-end training methods are designed. The Bayesian filtering theory enhances the interpretability of the proposed gated network, enabling the effective integration of offline data and prior models within functionally explicit gated units. In comprehensive experiments, including simulations and real-world datasets, the proposed gated network demonstrates superior estimation performance compared to benchmark filters and state-of-the-art deep learning filtering methods.