No abstract

Polarimetric high resolution range profile (HRRP) contains the geometrical structural information along radar line-of-sight and has shown great potentials in target recognition. In existing researches, H /α decomposition has been applied to exploit global polarimetric features of a single HRRP from its spatially averaged coherent matrix, which loses target local scattering information. In this paper, we propose to apply the H /α decomposition along the slow time dimension in a dual polarimetric HRRP sequence. The H and α features are extracted for each target scattering center by averaging its samples in different observations of the HRRP sequence, which provides both target local high resolution and polarimetric scattering characteristics. We also design a novel six-zone H -α plane for geometrical structure classification of target scattering centers. Simulation and experimental results show the effectiveness of the proposed method and display its good potentials for practical applications.

No abstract

Polarimetric high‐resolution range profile (HRRP) holds great potential for radar automatic target recognition (RATR) owing to its capability of providing both polarimetric and spatial scattering information. In recent years, deep learning (DL) has obtained state‐of‐the‐art results in many classification tasks and has drawn great attention in the RATR field. However, as one of the most challenging tasks in RATR, small training sample case will restrict the application of DL because its superior performance generally depends on a large number of training samples. A feature‐guided deep model based on Transformer framework is proposed for polarimetric HRRP recognition with limited training samples. In the proposed model, artificial features are introduced to the attention module to guide the model focus on the range cells of HRRP with more target scattering information so as to reduce the dependence of the model on the number of training samples. Several different approaches are also studied to measure the similarity between artificial features and HRRP data to further improve the learning capacity of the model. Experimental results demonstrate that the proposed feature‐guided Transformer model modifying by Cosine similarity measure is able to achieve a better performance for polarimetric HRRP recognition with limited training samples.

In this paper, a multi-aperture multiplexing multiple-input multiple-output (MAM-MIMO) sparse array is presented for cooperative automotive radars (CARs). The proposed sparse array composed of multiple subarrays can simultaneously cover a wide field-of-view (FOV) and achieve the required azimuth resolution at different ranges. To validate this idea, an optimization model for the MAM-MIMO sparse array is derived based on the example of CARs. This optimization model has been found by combining the peak-to-sidelobe ratio (PSLR) at all beams pointing within the constraints of different detection ranges. In addition, a hierarchical genetic algorithm based on the multi-objective decomposition method has been developed to obtain the optimized sparse array. The proposed method has been evaluated through both simulations and experiments. It is demonstrated that the optimized MAM-MIMO sparse array can effectively suppress sidelobes of its subarrays, yet with reasonably high azimuth resolutions and large FOVs.