Radar target HRRP recognition based on reconstructive and discriminative dictionary learning
Radar target HRRP recognition based on reconstructive and discriminative dictionary learning
复制标题
DOI：
10.1016/j.sigpro.2015.12.006
复制
发表时间：
2016-09-01
影响因子：
4.4
通讯作者：
Zhou, Daiying
中科院分区：
文献类型：
--
作者：
Zhou, Daiying
提出了一种新的用于雷达目标高分辨距离像识别的字典学习算法--基于稀疏表示分类准则的重构判别字典学习算法(RDDLSRCC)。该算法的核心是在原子的更新过程中加入原子的重建力和鉴别力。通过构造基于稀疏表示分类准则(SRCC)的目标函数，可以在保持原子的同类重构能力的同时，降低原子对其他类的重构贡献，从而提高原子的判别性能。此外，利用类重构残差矩阵的类最优奇异值分解向量更新样本的稀疏编码系数，从而加快了收敛速度。与其他字典学习算法相比，RDDLSRCC算法对目标方位变化和噪声的影响具有更强的鲁棒性。大量实测数据的实验结果表明，该算法取得了良好的目标识别效果。(C)2015爱思唯尔B.V.保留所有权利。
A novel dictionary learning algorithm, namely reconstructive and discriminative dictionary learning based on sparse tepresentation classification criterion (RDDLSRCC), is proposed for radar target high resolution range profile (HRRP) recognition in this paper. The core of proposed algorithm is to incorporate the reconstructive power and discriminative power of atoms during the update of atoms. By constructing the objective function based on sparse representation classification criterion (SRCC), the discriminative performance of atoms can be improved while preserving the same-class reconstruction ability of atoms and reducing their reconstruction contribution to other classes. Moreover, the sparse coding coefficients of samples are updated using class-optimal SVD vectors of class-reconstruction residual matrix, thereby accelerating convergence. Compared with other dictionary learning algorithms, RDDLSRCC is more robust to the variation of target aspect and noise's effect. The extensive experimental results on the measured data illustrate that the proposed algorithm achieves a promising target recognition performance. (C) 2015 Elsevier B.V. All rights reserved.