The convolution 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.
The conventional frequency diversity array (FDA) can generate arcsine form of continuous direction modulation (DM) waveforms which can automatically scan the entire space range. However, the single waveform and time varying phase of FDA cannot meet the requirements of practical security communication application scenarios. Thus, a new transmit diversity technique, called time frequency direction modulation (TFDM), is proposed to improve azimuth security. In this paper, unique timefrequency information at a given azimuth was formed by designing the beam steering term and the frequency term of each array element on the basis of the time varying characteristics of the FDA. In a transmit duration , DM can be divided into linear DM (LDM) and nonlinear DM (NDM) according to the beam shape. For LDM, for a specific observation direction, the frequency reaches the set value when the beam energy reaches the maximum value when the beam scans to this direction, but the uniqueness of time frequency information no longer exists in other directions. For NDM, the beam can pass through a given azimuth multiple times and form multiple pairs of time-frequency information, which provides a new idea for realizing multi-directional communication and solving communication rate problems. Finally, the uni-directional and multi-directional communication based on three different safe communication methods: time-direction modulation (TDM), frequency-direction modulation (FDM), and time-frequency-direction modulation (TFDM) are realized and the validity of the proposed method and the corresponding theory are verified by extensive numerical results.INDEX TERMS Frequency diversity array(FDA), frequency modulated (FM), time frequency direction modulation(TFDM), security communication.
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).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.