Linear double-layered feature extraction (DFE) technique has recently appeared in radar automatic target recognition (RATR). This paper develops this technique to a nonlinear field via parallelizing a series of kernel Fisher discriminant (KFD) units, and proposes a novel kernel-based DFE algorithm, namely, multi-KFD-based linear discriminant analysis (MKFD-LDA). In the proposed method, a multi-KFD (MKFD) parallel algorithm is constructed for feature extraction, and then the projection features on the MKFD subspace are further processed by LDA. Experimental results on radar HRRP databases indicate that, compared with some classical kernel-based methods, the proposed MKFD-LDA not only performs better and more harmonious recognition, but also keeps higher robustness to kernel parameters, lower training computational cost, and competitive noise immunity.

No abstract

No abstract

Abstract-Due to the traditional recognition researches prevalently focusing on HRRP's amplitudes while almost completely neglecting the phases, this paper attempts to directly prove the discriminant availability of HRRP's phases via two proposed fusion recognition strategies. The first strategy includes three sub-processes, respectively, based on phase cosine, phase sine and their fusion. The second strategy also includes three sub-processes, respectively, based on phases, amplitudes and their fusion. Additionally, a trigonometric function couple (TFC) method is used to reduce the phase sensitivity. Several measured experimental results indicate as follows. Firstly, employing TFC can perform much better. Secondly, the two fusion recognition sub-processes apparently outperform the corresponding sub-processes constructing them. Finally, phase information usually has a better noise immunity than amplitude information, and fusing phase information into amplitudes may improve the traditional recognition performance. Therefore, the availabilities of HRRP's phases and the two fusion strategies have been experimentally proven.

No abstract