基于特征层融合的高光谱图像异常检测算法研究

李智勇; 匡纲要; 邹焕新; 吴昊

doi:10.11834/jrs.20030412

浏览量 : 0 下载量: 639 CSCD: 4

PDF
导出
分享
收藏
专辑

基于特征层融合的高光谱图像异常检测算法研究
Research of Anomaly Detection Approaches Based on Feature Fusion in Hyperspectral Imagery
2003年第4期页码：304-308
纸质出版：2003
DOI： 10.11834/jrs.20030412
稿件说明：

移动端阅览

[1]李智勇,匡纲要,邹焕新,吴昊.基于特征层融合的高光谱图像异常检测算法研究[J].遥感学报,2003(04):304-308. DOI： 10.11834/jrs.20030412.

LI Zhi-yong, KUNAG Gang-yao, ZOU Huan-xin, et al. Research of Anomaly Detection Approaches Based on Feature Fusion in Hyperspectral Imagery[J]. Journal of Remote Sensing, 2003, (4): 304-308. DOI： 10.11834/jrs.20030412.

摘要

介绍了一种基于特征层融合的异常检测算法。目前

其他的目标检测算法都需要知道有确定类别标记的样本

而一般的异常检测则是利用统计特征差异分割出图像中不同于背景的点。此方法减少了对先验信息的依赖

但是其结果存在较大虚警。提出的异常检测算法是利用低概率检测算法对高光谱数据先进行特征层融合

再进行分割、提取异常点

其结果降低了虚警和漏警。用这一方法对OMIS系统产生的数据进行了处理

取得了较好的结果。

Abstract

An anomaly detection approach based on feature fusion is presented in this paper.All the detection algorithms

aside from anomaly detection

require training pixels of the desired class.Anomaly detection is the detection of scene elements that appear unlikely with respect to a probabilistic feature of the scene.The method needs on prior information

but the result has much false alarm.In this paper

we use low probability detection to fuse the data in feature level;then segment the image and detect anomaly elements.The result eliminates much false alarm and improves the detectability.We apply the method to the data produced by OMIS system and achieve satisfying results.