融合微分重排与匹配的高光谱快速目标检测

王含宇; 杨名宇; 王浩; 孟令通; 王檬檬

doi:10.3788/YJYXS20193408.0793

您当前的位置：

首页 >

文章列表页 >

融合微分重排与匹配的高光谱快速目标检测

图像处理 | 更新时间：2020-12-14

- 融合微分重排与匹配的高光谱快速目标检测
- A fast hyperspectral target detection fused on spectral derivative and recomposition and SAM
- 液晶与显示 2019年34卷第8期页码：793-802
- 作者机构：
  
  1.中国科学院航空光学成像与测量重点实验室, 吉林长春 130033
  2.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
- 作者简介：
  
  [ "王含宇(1991-), 女, 吉林长春人, 助理研究员, 硕士, 2017年于天津大学获得硕士学位, 主要从事高光谱图像处理方面的研究。Email:wanghany123@163.com" ]
- 基金信息：
  
  国家重点研发计划(2017YFC0822403);吉林省技术攻关项目(20190303074SF);National Key Research and Development Program of China(2017YFC0822403);Key Technological Program of JiLin Province(20190303074SF)
- DOI：10.3788/YJYXS20193408.0793
  中图分类号： TP751;O433.4
- 收稿日期：2019-04-22，
  
  录用日期：2019-5-8，
  
  纸质出版日期：2019-08-05
- 稿件说明：
移动端阅览
王含宇, 杨名宇, 王浩, 等. 融合微分重排与匹配的高光谱快速目标检测[J]. 液晶与显示, 2019,34(8):793-802.

Han-yu WANG, Ming-yu YANG, Hao WANG, et al. A fast hyperspectral target detection fused on spectral derivative and recomposition and SAM[J]. Chinese journal of liquid crystals and displays, 2019, 34(8): 793-802.
王含宇, 杨名宇, 王浩, 等. 融合微分重排与匹配的高光谱快速目标检测[J]. 液晶与显示, 2019,34(8):793-802. DOI： 10.3788/YJYXS20193408.0793.

Han-yu WANG, Ming-yu YANG, Hao WANG, et al. A fast hyperspectral target detection fused on spectral derivative and recomposition and SAM[J]. Chinese journal of liquid crystals and displays, 2019, 34(8): 793-802. DOI： 10.3788/YJYXS20193408.0793.

摘要

为滤除大量冗余背景信息，提升目标检测速度，解决目标光谱获取困难等问题，提出一种融合光谱微分重排与光谱角匹配的高光谱快速目标检测算法。首先，对已知背景光谱信息微分重排，筛选出背景特征较少的谱段集；然后，计算相应谱段下，高光谱图像各像素点的光谱微分值与背景光谱微分值的差值，并对所得各谱段微分差值加权求和阈值化，粗提取出目标位置；最后，计算提取出的目标位置光谱与先验背景光谱角匹配的反余弦值，实现目标背景差异精细判别。通过自行拍摄的草地上黄、绿伪装网及AVIRIS获取的San Diego机场飞机高光谱图像进行实验，与RX、CEM、OSP、ACE、SAM等算法比较。实验结果表明，所提算法在保证检测精度的同时，具有较低的虚警率和较好的时效性：ROC曲线下面积AUC均高于0.98，虚警率分别为3%和1.6%，处理时间仅为0.36 s和0.077 s。

Abstract

In order to filter a large amount of redundant background information

improve the speed of target detection and solve the difficult access problem of target spectrum

a fast hyperspectral target detection algorithm which is fused on spectral derivative

recomposition and spectral angle mapper is proposed. Firstly

the derivative of background spectrum is calculated and reordered to find a spectral set with less background information. Secondly

each pixel of the spectral image in the corresponding spectral set are used to calculate the spectral derivative results subtracting the spectral derivative results of background

then the threshold derivative difference of each spectrum is weighted and summed to extract the target location roughly. Finally

spectral angle mapper algorithm is utilized to calculate the arccosine values of target points and priori background to distinguish the difference between targets and background precisely. Two hyperspectral images of yellow and green camouflage nets on the grass and the planes on the San Diego airport captured by AVIRIS were selected in the experiment for comparing the proposed algorithm with RX

CEM

OSP

ACE

SAM algorithms. The experimental results indicate that the proposed algorithm has a good detection precision

low false alarm rate and high efficiency with AUC higher than 0.98

false alarm rate 3% and 1.6% respectively

the processing time only 0.36 s and 0.077 s.

关键词

Keywords

references

王岩, 杨小虎, 王金玲, 等.空间遥感光谱仪器光学性能地面检测系统[J].液晶与显示, 2017, 32(3):206-212.

WANG Y, YANG X H, WANG J L, et al . Ground testing system for detecting optical performance of space remote sensing spectrometer[J]. Chinese Journal of Liquid Crystals and Displays , 2017, 32(3):206-212. (in Chinese)

BACHER R, MEILLIER C, CHATELAIN F, et al . Robust control of varying weak hyperspectral target detection with sparse nonnegative representation[J]. IEEE Transactions on Signal Processing , 2017, 65(13):3538-3550.

梅风华, 李超, 张玉鑫.光谱成像技术在海域目标探测中的应用[J].中国光学, 2017, 10(6):708-718.

MEI F H, LI C, ZHANG Y X. Application of spectral imaging technology in maritime target detection[J]. Chinese Optics , 2017, 10(6):708-718. (in Chinese)

REED I S, YU X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE Transactions on Acoustics , Speech , and Signal Processing , 1990, 38(10):1760-1770.

耿修瑞.高光谱遥感图像目标探测与分类技术研究[D].北京: 中国科学院研究生院, 2005. http://cdmd.cnki.com.cn/Article/CDMD-80070-2005121828.htm

GENG X R. Target detection and classification for hyperspectral imagery[D]. Beijing: University of Chinese Academy of Sciences, 2005. (in Chinese)

张宁, 赵睿, 白郁, 等.基于集成学习约束能量最小化的高光谱目标检测算法研究[J].上海航天, 2018, 35(1):23-29.

ZHANGN, ZHAO R, BAI Y, et al . Research on hyperspectral target detection algorithm based on ensemble learning constraint energy minimization[J]. Aerospace Shanghai , 2018, 35(1):23-29. (in Chinese)

YANG S, SHI Z W. SparseCEM and SparseACE for hyperspectral image target detection[J]. IEEE Geoscience and Remote Sensing Letters , 2014, 11(12):2135-2139.

LIU C, LI J W. Hyperspectral subpixel target detection based on extended mathematical morphology[J]. Infrared and Laser Engineering , 2015, 44(10):3141-3147.

杜小平, 刘明, 夏鲁瑞, 等.基于光谱角累加的高光谱图像异常检测算法[J].中国光学, 2016, 6(3):325-331.

DU X P, LIU M, XIA L R, et al . Anomaly detection algorithm for hyperspectral imagery based on summation of spectral angles[J]. Chinese Optics , 2013, 6(3):325-331. (in Chinese)

王晗, 王阿川, 苍圣.基于压缩感知的高光谱遥感影像重构方法研究[J].液晶与显示, 2017, 32(3):219-226.

WANG H, WANG A C, CANG S. Hyperspectral remote sensing image reconstruction method based on compressive sensing[J]. Chinese Journal of Liquid Crystals and Displays , 2017, 32(3):219-226. (in Chinese)

闫敬文, 陈宏达, 刘蕾.高光谱图像分类的研究进展[J].光学精密工程, 2019, 27(3):680-693.

YAN J W, CHEN H D, LIU L. Overview of hyperspectral image classification[J]. Optics and Precision Engineering , 2019, 27(3):680-693. (in Chinese)

吕利利.基于光谱微分法的荒漠稀疏植被提取及变化分析——以疏勒河流域走廊平原地区为例[D].兰州: 兰州大学, 2018. http://cdmd.cnki.com.cn/Article/CDMD-10730-1018979557.htm

LYU L L. Sparse vegetation extraction and change analysis based on spectral differentiation——an example in the Shule River basin plain[D]. Lanzhou: Lanzhou University, 2018. (in Chinese)

WETTLE M, FERRIER G, LAWRENCE A J, et al . Fourth derivative analysis of red sea coral reflectance spectra[J]. International Journal of Remote Sensing , 2003, 24(19):3867-3872.

施英妮, 张亭禄, 魏雅利, 等.光谱微分技术在高光谱遥感浅海海底底质中的应用初探[J].遥感信息, 2010(3):21-25.

SHI Y N, ZHANG T L, WEI Y L, et al . Preliminary study on the seafloor type classification by using spectral derivative method[J]. Remote Sensing Information , 2010(3):21-25. (in Chinese)

刘志刚, 卢云龙, 魏一苇.有监督的高光谱图像伪装目标检测方法[J].红外与激光工程, 2013, 42(11):3076-3081.

LIU Z G, LU Y L, WEI Y W. Supervised method for hyperspectral image camouflage target detection[J]. Infrared and Laser Engineering , 2013, 42(11):3076-3081. (in Chinese)

QU Y F, LIU Z Y. Dimensionality reduction and derivative spectral feature optimization for hyperspectral target recognition[J] . Optik , 2017, 130:1349-1357.

刘恂, 华文深, 杨佳.面向高光谱探测的伪装效果评价方法[J].红外与激光工程, 2014, 43(10):3228-3232.

LIUX, HUA W S, YANG J. Camouflage effect evaluation based on hyperspectral detecting technology[J]. Infrared and Laser Engineering , 2014, 43(10):3228-3232. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据