Zehao Li

Aeromagnetic interference is one of the important factors limiting the application of aeromagnetic data on aircraft platforms. Therefore, magnetic compensation is necessary for aeromagnetic data processing, which is of great significance to improve the accuracy of geomagnetic navigation. In recent years, aeromagnetic compensation methods can be mainly divided into two categories: linear regression methods based on the Tolles-Lawson (T-L) model and data-driven methods based on machine learning. However, the accuracy of linear regression methods is subject to the complexity of the model and the problem of multicollinearity, while data-driven methods require the quantity and quality of aeromagnetic measurement data. To solve this problem, we proposed an aeromagnetic compensation method taking advantage of both the T-L model and neural network. The T-L model parameters are trained through our network, while the attention mechanism is applied in the hidden layer to enhance the feature extraction ability of the model for time series. We validate our method by applying it to an open-access dataset. The Experimental results demonstrate that our method has higher compensation accuracy and generalization performance than the classical algorithms.

Infrared small and dim target detection is a difficult task in many fields, such as navigation, guidance, early warning. The main challenges are inapparent target and complicated background. The low-rank and sparse model has been developed to address this problem, which provides a feasible and effective approach. In this paper, the practicability of strengthened local feature-based spatial-temporal tensor model is considered to improve the optimization procedure of solution. A more consistent spatial-temporal tensor is designed, which helps to sustain the function for non-Gaussian like targets. A strengthened local feature map is acquired by the temporal-constrained Gaussian curvature filter and 3D structure tensor, which accelerates the converge of iteration. Non-convex approximation high-order singular value decomposition model with adaptive total variation regularization is adopted, achieving better results of optimization. The proposed strengthened local feature-based spatial-temporal tensor model can realize precise infrared small target detection with high efficiency, and it is robust for different scenes. A comprehensive test is carried out on open datasets to verify the performance of the proposed model, which shows its great advantages over other state-of-the-art methods.

Infrared small target detection is a popular issue in the field of computer vision. Traditional methods have been researched until now, and can basically deal with target detection in usual scenarios. However, small and dim targets do not have obvious characteristics and are easily interfered by clutter in a complex background. This letter studied common target detection methods like low-rank and sparse representation and local contrast measure, a new method called strengthened robust local contrast measure algorithm (SRLCM) is proposed here. By solving non-convex problem more rigorously and analyzing small target features carefully, SRLCM can achieve a better detection and segmentation performance in an irregular background.