摘要
针对高光谱目标检测中复杂背景的影响,提出一种基于期望最大化聚类的亚像素目标检测方法,利用背景分解来描述复杂背景.首先,采用期望最大化聚类法实现高光谱图像的背景分解.然后,将背景子空间模型应用于分解得到的场景.由于分解得到的场景更加单一,因此该方法更适合于复杂背景下的亚像素目标检测.将提出的方法应用于实际的高光谱图像,实验结果表明这种方法具有更好的检测性能.
Background is a key interferene in target detection. To avoid the interferene of complex background, an expectation-maximization cluster based approach to subpixel detection in hyperspectral is presented that incorporates background segmentation to model complex background. First, the expectation-maximization cluster model is employed to segment whole background into homogenous regions. Then the adaptive matched subspace detection algorithm （AMSD） is applied in each homogenous region. Since the segmented regions are more homogenous than the whole complex background, our new approach can have a better performance. Experimental result with a real hyperspectral image has proved the validity of the new approach.
出处
《西安电子科技大学学报》
EI
CAS
CSCD
北大核心
2009年第3期512-516,共5页
Journal of Xidian University
基金
国家自然科学基金资助(60777042)
关键词
遥感
高光谱
亚像素目标
目标检测
图像分割
remote sensing
hyperspectral
subpixel target
target detector
image segmentation
