Pseudo-Zernike Moments Based Sparse Representations for SAR Image Classification
Pseudo-Zernike Moments Based Sparse Representations for SAR Image Classification
复制标题
DOI：
10.1109/taes.2018.2856321
复制
发表时间：
2019-04-01
影响因子：
4.4
通讯作者：
Mulgrew, Bernard
中科院分区：
文献类型：
--
作者：
Gishkori, Shahzad;Mulgrew, Bernard
我们提出了雷达图像分类通过伪Zernike矩的稀疏表示。我们利用伪Zernike矩的不变性，通过引入辅助原子来增加稀疏代表字典中的冗余。我们使用复杂的雷达信号。我们证明了我们提出的方法的有效性公开可用的运动和静止目标的采集和识别数据集。
We propose radar image classification via pseudo-Zernike moments based sparse representations. We exploit invariance properties of pseudo-Zernike moments to augment redundancy in the sparsity representative dictionary by introducing auxiliary atoms. We employ complex radar signatures. We prove the validity of our proposed methods on the publicly available moving and stationary target acquisition and recognition dataset.