基于自适应核方法的正交子空间投影异常检测算法

在高光谱图像的异常目标检测核方法中,高斯径向基核函数的宽度决定因子(即核参数)选择恰当与否是决定算法性能的重要因素。针对这一问题,提出了一种基于自适应核方法的正交子空间投影高光谱图像异常检测算法,有效的解决了统一的全局检测参数在复杂多变背景环境下检测性能下降的问题。这不仅提高了算法的通用性,也降低了检测的计算量。用AVIRIS高光谱数据进行了仿真实验,取得了较好的检测效果。将该算法与其他算法进行比较,结果表明,所提出算法的检测性能明显地优于传统算法,降低了虚警概率。

An orthogonal subspace projection anomaly detection algorithm based on adaptive kernel method

In the problems of anomaly detection for hyperspectral image,as for the nuclear parameter which is determined appropriately or not is an important factor in the decision algorithm performance,a new orthogonal subspace projection anomaly detection algorithm for hyperspectral image based on Adaptive Kernel Method(AKOSP) is introduced.This algorithm solves that detection parameter is difficult to adapt to complex and changing background environment which declines the detection efficiency.This algorithm not only enhanced the universality also reduces the work of testing.Numerous experiments are conducted on real hyperspectral images collected by AVIRIS.The results prove that the proposed algorithm outperforms the other algorithms,and can obtain a lower false alarm rate.