When the satellite signal is lost or interfered with, the traditional GNSS (Global Navigation Satellite System)/INS (Inertial Navigation System) integrated navigation will degenerate into INS, which results in the decrease in navigation accuracy. To solve these problems, this paper mainly established the PSO (particle swarm optimization) -LSTM (Long Short-Term Memory) neural network model to predict the increment of GNSS position under the condition of satellite rejection and accumulation to obtain the pseudo-GNSS signal. The signal is used to compensate for the observed value in the integrated system. The model takes the advantages of LSTM, which is good at processing time series, and uses PSO to obtain the optimal value of important hyperparameters efficiently. Meanwhile, the improved threshold function is used to denoise the IMU (inertial measurement unit) data, which improves the SNR (signal-to-noise ratio) of IMU outputs effectively. Finally, the performance of the algorithm is proved by actual road test. Compared with INS, the method can reduce the maximum errors of latitude and longitude by at least 98.78% and 99.10% while the satellite is lost for 60 s, effectively improving the accuracy of the GNSS/INS system in satellite rejection.

In high spatial resolution remote sensing imagery (HRSI), ship detection plays a fundamental role in a wide variety of applications. Despite the remarkable progress made by many methods, ship detection remains challenging due to the dense distribution, the complex background, and the huge differences in scale and orientation of ships. To address the above problems, a novel, fully deformable convolutional network (FD-Net) is proposed for dense and multiple-scale ship detection in HRSI, which could effectively extract features at variable scales, orientations and aspect ratios by integrating deformable convolution into the entire network structure. In order to boost more accurate spatial and semantic information flow in the network, an enhanced feature pyramid network (EFPN) is designed based on deformable convolution constructing bottom-up feature maps. Additionally, in considering of the feature level imbalance in feature fusion, an adaptive balanced feature integrated (ABFI) module is connected after EFPN to model the scale-sensitive dependence among feature maps and highlight the valuable features. To further enhance the generalization ability of FD-Net, extra data augmentation and training methods are jointly designed for model training. Extensive experiments are conducted on two public remote sensing datasets, DIOR and DOTA, which then strongly prove the effectiveness of our method in remote sensing field.

This article investigates the finite-time containment control for a class of second-order multiagent systems with nonlinear dynamics and external disturbances under fixed directed interaction topology. Due to the existence of nonlinear dynamics and unknown but bounded external disturbances, there is an underlying technical difficulty for the design of containment controller. Furthermore, it is a challenge for the theoretical analysis of finite-time containment control problem due to the asymmetric Laplacian matrix arising from the constraint of one-way directed communication among the agents. In response to the above-mentioned challenges, a finite-time containment control algorithm is proposed. First, the multiagent system is considered with inherent nonlinear dynamics and unknown but bounded external disturbances. Second, the desired containment control protocol is presented under a directed interaction topology. Furthermore, by adding a power-integrator technique and Lyapunov function theory, the sufficient conditions are derived for the existence of the finite-time containment controller of a class of second-order multiagent systems. Finally, a numerical example is given to verify the usefulness of the proposed finite-time containment control protocol.

Cloud detection is one of the essential procedures in optical remote sensing image processing because clouds are widely distributed in remote sensing images and cause a lot of challenges, such as climate research and object detection. In this article, a lightweight deep-learning-based framework is proposed to detect cloud in remote sensing imagery. First, a multiple features fusion strategy is designed to extract learnable manual features and convolution features from visible and near-infrared bands. Then, a lightweight fully convolutional neural network (ClouDet) with a microarchitecture named dilated separable convolutional module is used to extract the multiscale contextual information and gradually recovers segmentation results with the same size as input image, which is more effective for large-scale cloud detection with larger receptive field, less parameters, and lower compute complexity. Third, context pooling is designed to amend the possible misjudgments. Visual and quantitative comparison experiments are conducted on several public cloud detection datasets, which indicates that our proposed method can accurately detect clouds under different conditions, which is more effective and accurate than the compared state-of-the-art methods.

Graph Neural Networks (GNNs), as an effective learning framework for graph structure data representation, have been applied to hyperspectral images (HSIs) classification tasks. Among the variants of GNNs, Graph Attention Networks (GATs) have achieved state-of-the-art node prediction performance by learning to assign dense attention coefficients to all node neighbors for feature aggregation. However, due to the complexity of land distribution and the high dimension of HSIs data, it is difficult to identify different coverage categories by employing GATs directly, and the inadequacy of spectral information also affects the classification accuracy. To address the above application problems, we proposed a multi-stage superpixel-guided sparse GAT for HSI classification (named MSG-SGAT). Specifically, we create the adjacency connection graphs of different stages from the superpixel representation so as to effectively utilize the spatial topology. A sparse GAT (SGAT) module is designed to trim the graph by spectral sparsity to remove some task-irrelevant edges and assign a unique attention coefficient to each remaining edge. Sparse subgraphs are obtained by identifying the noise/task-independent edges and aggregating information. Moreover, SGAT is concatenated with the spectral branch for feature fusion and update, and pixel-level feature refinement is performed at the end of this network. MSG-SGAT mines the features of HSIs from the perspective of multi-scale hierarchy with low calculation cost and high efficiency. A series of comparative experiments on four benchmark datasets demonstrate that the performance of our proposed method is competitive with others.