Hyperspectral Target Detection Based on Tensor Sparse Representation

Hyperspectral Target Detection Based on Tensor Sparse Representation
复制标题

基于张量稀疏表示的高光谱目标检测

DOI:
10.1109/lgrs.2019.2902629
复制
发表时间:
2019-03
影响因子:
4.8
通讯作者:
Bin Wang
Bin Wang
中科院分区:
工程技术2区
文献类型:
--
作者:
Zehao Chen;Bin Wang

文献摘要

参考文献

相似文献

基于稀疏表示的检测算法(SRD)在高光谱目标检测(TD)中已经显示出了很好的效果。然而,SRD没有利用高光谱图像(HSI)的空间信息。在这封信中,一种新的张量SRD(TSRD)算法提出了联合考虑的空间和光谱信息的HSI。TSRD将目标字典和背景字典中的每个原子扩展为三阶张量,在三阶张量中可以很好地保留局部空间邻域信息。它不仅具有SRD不需要对目标和背景分布作任何假设、可以考虑光谱变化的优点,而且还充分利用了HSI的空间信息,进一步提高了TD的精度。在合成和真实的高光谱数据上的实验结果表明,该方法在检测精度上优于传统和最先进的TD方法。
The sparse representation-based detection (SRD) algorithm has already shown the effectiveness for hyperspectral target detection (TD) recently. However, SRD does not utilize spatial information of hyperspectral imagery (HSI). In this letter, a novel tensor SRD (TSRD) algorithm is proposed to take jointly the spatial and the spectral information of HSI into account. TSRD extends each atom of both the target and the background dictionaries into a third-order tensor where the local spatial neighborhood information can be well preserved. It not only possesses the advantages of SRD that no assumptions about the target and background distributions are required and spectral variability can be considered but also exploits the spatial information of HSI to further increase the accuracy of TD. The experimental results on both synthetic and real hyperspectral data show that the proposed TSRD method outperforms traditional and state-of-the-art TD methods in terms of detection accuracy.
DOI: 10.1109/msp.2013.2278992
发表时间: 2014
影响因子: 14.9
作者:
N. Nasrabadi
通讯作者: N. Nasrabadi
DOI: 10.1109/tgrs.2008.2006364
发表时间: 2009-06-01
影响因子: 8.2
作者:
Stefanou, Marcus S.;Kerekes, John P.
通讯作者: Kerekes, John P.
DOI: --
发表时间: 1979
期刊: --
影响因子: --
作者:
T. M. Lillesand
通讯作者: T. M. Lillesand
DOI: 10.1109/jstsp.2011.2113170
发表时间: 2011-06-01
影响因子: 7.5
作者:
Chen, Yi;Nasrabadi, Nasser M.;Tran, Trac D.
通讯作者: Tran, Trac D.
DOI: 10.1109/jstars.2014.2315772
发表时间: 2014-06-01
影响因子: 5.5
作者:
Matteoli, Stefania;Diani, Marco;Theiler, James
通讯作者: Theiler, James