An Overview of Background Modeling for Detection of Targets and Anomalies in Hyperspectral Remotely Sensed Imagery
An Overview of Background Modeling for Detection of Targets and Anomalies in Hyperspectral Remotely Sensed Imagery
复制标题
DOI：
10.1109/jstars.2014.2315772
复制
发表时间：
2014-06-01
影响因子：
5.5
通讯作者：
Theiler, James
中科院分区：
文献类型：
--
作者：
Matteoli, Stefania;Diani, Marco;Theiler, James
本文综述了从高光谱图像的杂波背景中区分目标弱信号(无论是已知的还是异常的)的著名的经典算法和最近的实验方法。作出这一区分需要对目标和背景进行定性，而我们在这次审查中的重点是背景。我们描述了各种背景建模策略--高斯和非高斯、全局和局部、生成性和区分性、参数和非参数、光谱和空间光谱--在它们如何与目标和异常检测问题相关的上下文中。我们讨论了这些算法所解决的主要问题，以及在为给定的检测应用选择有效的算法时所做的一些权衡。我们找出了这些算法之间的联系，并指出了创新的建模策略可以发展成更敏感和可靠的检测算法的方向。
This paper reviews well-known classic algorithms and more recent experimental approaches for distinguishing the weak signal of a target (either known or anomalous) from the cluttered background of a hyperspectral image. Making this distinction requires characterization of the targets and characterization of the backgrounds, and our emphasis in this review is on the backgrounds. We describe a variety of background modeling strategies-Gaussian and non-Gaussian, global and local, generative and discriminative, parametric and nonparametric, spectral and spatio-spectral-in the context of how they relate to the target and anomaly detection problems. We discuss the major issues addressed by these algorithms, and some of the tradeoffs made in choosing an effective algorithm for a given detection application. We identify connections among these algorithms and point out directions where innovative modeling strategies may be developed into detection algorithms that are more sensitive and reliable.