计算机科学 ›› 2018, Vol. 45 ›› Issue (6): 259-264.doi: 10.11896/j.issn.1002-137X.2018.06.046

• 图形图像与模式识别 • 上一篇    下一篇

基于逐像素递归处理的高光谱实时亚像元目标检测

林伟俊1, 赵辽英1, 厉小润2   

  1. 杭州电子科技大学计算机学院 杭州3100181;
    浙江大学电气工程学院 杭州3100272
  • 收稿日期:2017-04-12 出版日期:2018-06-15 发布日期:2018-07-24
  • 作者简介:林伟俊(1993-),男,硕士生,主要研究方向为高光谱图像目标检测,E-mail:jum05768@foxmail.com;赵辽英(1970-),女,博士,教授,主要研究方向为图像处理与模式识别,E-mail:zhaoly@hdu.edu.cn(通信作者);厉小润(1970-),男,博士,研究员,主要研究方向为图像处理与模式识别、嵌入式控制与信息系统,E-mail:605641977@qq.com
  • 基金资助:
    本文受国家自然科学基金资助项目(61571170),教育部联合基金项目(6141A02022314),上海航天科技创新基金资助项目(SAST2015033)资助

Real-time Sub-pixel Object Detection for Hyperspectral Image Based on Pixel-by-pixel Processing

LIN Wei-jun1, ZHAO Liao-ying1, LI Xiao-run2   

  1. School of Computer Science and Technology,Hangzhou Dianzi University,Hangzhou 310018,China1;
    College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China2
  • Received:2017-04-12 Online:2018-06-15 Published:2018-07-24

摘要: 亚像元目标检测是高光谱图像应用的关键技术。由于高光谱数据的高维度增加了存储空间和数据处理的复杂度,实时处理成为了目标检测面临的重要问题。自适应匹配滤波算法(AMF)是一种有效的亚像元目标检测算法。在基于Woodbury引理实现以逐像素排列格式传输和存储的高光谱数据协方差矩阵实时求逆的基础上,以AMF为高光谱图像亚像元目标检测算法,推导出了基于逐像素递归处理的高光谱图像实时AMF目标检测流程。通过仿真数据和真实高光谱图像实验证明,相比于非实时AMF,实时AMF只需少量的存储空间便可得到同样甚至更高的检测精度。

关键词: 高光谱图像处理, 实时检测, 亚像元目标检测, 逐像素排列, 自适应匹配滤波

Abstract: Sub-pixel target detection is one of the key technologies in the applications of hyperspectral images.Since the high dimensions of hyperspectral data increase apparently the storage space and complexity of data processing,real-time processing has become a crucial problem for target detection.Adaptive matched filter (AMF) is an effective algorithm for sub-pixel target detection.This paper derived the real-time AMF target detection procedure of hyperspectral images by using AMF as the sub-pixel target detection algorithm,based on the realization of real-time inversing of hyperspectral data’s covariance matrix with the pixel-by-pixel format transmission and storage by using Woodbury lemma.Expe-riments were conducted on synthetic data and real hyperspectral images.The results demonstrate that compared with non-real time AMF,real-time AMF needs less storage space and can achieve the same or slightly better detection accuracy.

Key words: Adaptive matched filter, Causal processing, Hyperspectral image processing, Pixel-by-pixel processing, Sub-pixel target detection

中图分类号: 

  • TP391
[1]姜志侠,孟品超,李延忠.矩阵分析[M].北京:清华大学出版社,2015.
[2]CHEN S Y,WANG Y L,WU C C,et al.Real-Time Causal Processing of Anomaly Detection for Hyperspectral Imagery [J].IEEE Transactions on Geoscience and Remote Sensing,2014,50(2):1513-1534.
[3]CHANG C I,LI H C,SONG M P,et al.Real-Time Constrained Energy Minimization for Subpixel Detection [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2545-2559.
[4]CHANG C I,SCHULTZ R C,HOBBS M C,et al.Progressive Band Processing of Constrained Energy Minimization for Subpixel Detection[J].IEEE Transactions on Geoscience and Remote Sensing,2015,50(3):1626-1637.
[5]ZHAO C H,WANG Y L,LI X H.A real-time anomaly detection algorithm for hyperspectral imagery based on causal processing [J].Journal of Infrared and Millimeter Waves,2015,34(1):114-121.(in Chinese)
赵春晖,王玉磊,李晓慧.一种新型高光谱实时异常检测算法[J].红外与毫米波学报,2015,34(1):114-121.
[6]ZHAO C H,YOU W.Real-Time Anomaly Detection Algorithm for Hyperspectral Remote Sensing by Using Recursive Polynomial Kernel Function [J].Acta Optica Sinica,2016(2):257-265.(in Chinese)
赵春晖,尤伟.采用多项式递归核的高光谱遥感异常实时检测算法[J].光学学报,2016(2):257-265.
[7]YANG B M,PLAZA A,GAO L,et al.Dual-Mode FPGA Implementation of Target and Anomaly Detection Algorithms for Real-Time Hyperspectral Imaging[J].IEEE Journal of Selected To-pics in Applied Earth Observations and Remote Sensing,2015,8(6):2950-2961.
[8]ZHANG L P.Advance and Future Challenges in Hyperspectral Target Detection [J].Geomatics and Information Science of Wuhan University,2014,39(12):1387-1394.(in Chinese)
张良培.高光谱目标探测的进展与前沿问题[J].武汉大学学报(信息科学版),2014,39(12):1387-1394.
[9]MANOLAKIS D,SHAW G.Detection algorithms forhyper-spectral imaging applications[J].IEEE Signal Process Maga-zing,2002,19(1):29-43.
[10]ROBEY F C,FUHRMANN D R,KELLY E J,et al.CFAR adaptive matched filter detector [J].IEEE Trans.on Aerospace and Electronic Systems,1992,28(1):208-218.
[11]GENG X R,JI L Y,SUN K.Clever eye algorithm for target detection of remote sensing imagery[J].Isprs Journal of Photogrammetry and Remote Sensing,2016,114:32-39.
[12]张兵,高连如.高光谱图像分类与目标检测[M].北京:科学出版社,2011.
[13]赵文吉,段福州,刘晓萌,等.ENVI遥感影像处理专题与实践 [M].北京:中国环境科学出版社,2007.
[14]CUI J T.Research on hyper spectral remote sensing image mixing technology [D].Hangzhou:Zhejiang University,2014.(in Chinese)
崔建涛.高光谱遥感图像解混技术研究[D].杭州:浙江大学,2014.
[1] 陈连栋,张蕾,曲武,孔明.
一种分布式的僵尸网络实时检测算法
Distributed Real-time Botnet Detection Algorithm
计算机科学, 2016, 43(3): 127-136. https://doi.org/10.11896/j.issn.1002-137X.2016.03.026
[2] 安国成,张凤军.
利用检测特征空间的目标实时跟踪
Target Tracking Based on Feature Space of Detection
计算机科学, 2013, 40(Z11): 309-313.
[3] .
一种基于Hurst参数的SYN Flooding攻击实时检测方法

计算机科学, 2008, 35(12): 109-113.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!