Theconvolution neural network (CNN) has recently shown the good performance in hyperspectral image (HSI) classification tasks. Many CNN-based methods crop image patches from original HSI as inputs. However, the input HSI cubes usually contain background and many hyperspectral pixels with different land-cover labels. Therefore, the spatial context information on objects of the same category is diverse in HSI cubes, which will weaken the discrimination of spectral–spatial features. In addition, CNN-based methods still face challenges in dealing with the spectral similarity between HSI cubes of spatially adjacent categories, which will limit the classification accuracy. To address the aforementioned issues, we propose a cascade residual capsule network (CRCN) for HSI classification. First, a residual module is designed to learn high-level spectral features of input HSI cubes in the spectral dimension. The residual module is employed to solve the problem of the spectral similarity between HSI cubes of spatially adjacent categories. And then two 3-D convolution layers are exploited to extract high-level spatial–spectral features. Finally, a capsule structure is developed to characterize spatial context orientation representations of objects, which can effectively deal with the diverse spatial context information on objects of the same category in HSI cubes. The capsule module is composed of two 3-D convolution layers and the capsule structure, which is connected to the residual module in series to construct the proposed CRCN. Experimental results on four public HSI datasets demonstrate the superiority of the proposed CRCN over six state-of-the-art models.

For the purpose of simultaneously estimating and locating the linear frequency modulation (LFM) emitter with unknown parameters, an innovative approach, i.e., Fast Direct Position Determination (FDPD), is introduced. The proposed algorithm is based on maximum likelihood estimation (MLE) and spectrum detection. To improve the accuracy and overcome the dramatic complexity of plain maximum likelihood formulation, we further derive the objective function equation of Direct Position Determination (DPD) algorithm and present an enhanced strategy to solve the highly nonlinear optimization problem. By combining the two-step localization method, one-step localization method, and short-time Fourier transform (STFT), our approach realizes jointly estimation of the transmitted signal parameters and emitter localization. Simulation results show that the proposed method is superior compared to the existing DPD, and two-step localization algorithms in terms of localization error and computational complexity, especially for low signal-to-noise ratio (SNR).

In this article, the problem of simultaneously estimating and localizing multiple-input multiple-output (MIMO) radar emitters is considered for a distributed multi-station passive localization system, wherein the transmitted signal is unknown for receiver stations. To achieve highly accurate and robust localization performance, a novel algorithm based on the direct position determination (DPD) algorithm, Karhunen–Loève (KL) transform, and feature matching (FM) is addressed to jointly estimate the emitter position and the unknown signal waveform. First, we further derive the objective function of the DPD method and present an enhanced strategy to exploit as much waveform information as possible without any prior knowledge. By applying KL transform and FM techniques, the proposed method achieves MIMO radar emitter identification and emitter localization. The numerical results show that the proposed algorithm outperforms the existing DPD approaches which ignore the transmitted signals, especially for a low signal-to-noise ratio (SNR).

Unlike phased array, frequency diverse array (FDA) applies a tiny frequency offset across the antenna elements to generate a range-angle-dependent beampattern. However, due to the range-angle coupling property, the emitter position cannot be obtained directly from conventional FDA beamforming peaks. This paper proposes a novel passive localization approach based on direction modulation (DM) and Chan algorithm. By applying DM, the angle-range coupling can be wiped off well, which has a significant influence on the emitter localization. Simulation results are implemented to verify the validity and superiority of the proposed technique.