SAR Target Recognition via Joint Sparse Representation of Monogenic Signal
SAR Target Recognition via Joint Sparse Representation of Monogenic Signal
复制标题
基于单基因信号联合稀疏表示的 SAR 目标识别
DOI：
10.1109/jstars.2015.2436694
复制
发表时间：
2015-07-01
影响因子：
5.5
通讯作者：
Lu, Jun
中科院分区：
文献类型：
--
作者：
Dong, Ganggang;Kuang, Gangyao;Lu, Jun
本文提出了通过表示和多任务学习进行分类，用于 SAR 图像中的目标识别。为了捕获SAR图像的特征，采用了分析信号（即单基因信号）的多维概括。然后原始信号可以正交分解为三个分量：1）局部幅度； 2）局部阶段； 3）本地化定位。由于组件代表不同类型的信息，因此在统一框架中共同考虑它们是有益的。然而，这些组件由于高维和冗余而无法直接利用。为了解决这个问题，一个直观的想法是通过连接组件来定义增强特征向量。这种策略通常会产生一些信息丢失。为了弥补这一不足，本文考虑了不同学习任务的三个组成部分，其中一些公共信息可以共享。具体来说，首先生成每个单基因成分的特定成分特征描述符。受多任务学习最近成功的启发，所得特征被输入到联合稀疏表示模型中，以利用多个任务之间的相互关联。根据所有任务累积的总重建误差得出推断。本文的新颖之处包括1）开发了三个特定于组件的特征描述符； 2）将多任务学习引入稀疏表示模型； 3）所提出方法的数值实现； 4）对MSTAR SAR数据集进行广泛的对比实验研究，包括标准操作条件下的目标识别、扩展操作条件下的目标识别以及异常值剔除的能力。
In this paper, the classification via sprepresentation and multitask learning is presented for target recognition in SAR image. To capture the characteristics of SAR image, a multidimensional generalization of the analytic signal, namely the monogenic signal, is employed. The original signal can be then orthogonally decomposed into three components: 1) local amplitude; 2) local phase; and 3) local orientation. Since the components represent the different kinds of information, it is beneficial by jointly considering them in a unifying framework. However, these components are infeasible to be directly utilized due to the high dimension and redundancy. To solve the problem, an intuitive idea is to define an augmented feature vector by concatenating the components. This strategy usually produces some information loss. To cover the shortage, this paper considers three components into different learning tasks, in which some common information can be shared. Specifically, the component-specific feature descriptor for each monogenic component is produced first. Inspired by the recent success of multitask learning, the resulting features are then fed into a joint sparse representation model to exploit the intercorrelation among multiple tasks. The inference is reached in terms of the total reconstruction error accumulated from all tasks. The novelty of this paper includes 1) the development of three component-specific feature descriptors; 2) the introduction of multitask learning into sparse representation model; 3) the numerical implementation of proposed method; and 4) extensive comparative experimental studies on MSTAR SAR dataset, including target recognition under standard operating conditions, as well as extended operating conditions, and the capability of outliers rejection.