一种改进的快速N-FINDR端元提取算法

赵春晖; 郭蕴霆

doi:doi:10.3788/gzxb20154410.1011002

光子学报, 2015, 44 (10): 1011002, 网络出版: 2015-11-30

一种改进的快速N-FINDR端元提取算法

An Improved Fast N-FINDR Endmember Extraction Algorithm

论文大纲

赵春晖 ^*郭蕴霆

作者单位

哈尔滨工程大学信息与通信工程学院,哈尔滨 150001

摘要

为了解决传统N-FINDR算法计算量大,提取结果对噪声和初始端元选取敏感,且容易将异常点作为端元而造成误提取的问题,提出一种改进的快速N-FINDR端元提取算法.该方法通过光谱距离提取并去除高光谱图像中的冗余信息,减少N-FINDR提取端元的搜索范围,平滑噪声影响,并自适应剔除异常点,通过最大化光谱距离选取N-FINDR的初始端元,避免了随机选择的盲目性.采用合成数据和真实高光谱数据进行仿真分析并与现有算法进行对比,结果表明,本文算法能在噪声与奇异点干扰下正确提取端元,其提取效率和鲁棒性均优于现有算法.

Abstract

Traditional N-FINDR algorithm suffers from complicated calculations,and is sensitive to noise and initial endmembers,resulting in wrong extraction by outliers. In order to solve these problems,an improved fast N-FINDR endmember extraction algorithm was proposed,which gets rid of the redundant information and reduces the search area of commonly used N-FINDR algorithm by spectral distance,then smoothes the spectral noise and gets rid of the outliers adaptively. In addition,the initial endmembers of N-FINDR are selected by maximizing the spectral distance,avoiding the blindness of random selection. The synthetic data and real hyperspectral data were used for simulation analysis,and the proposed method was compared with existing algorithms. The experiment results show that the proposed method is able to extract the endmembers correctly in the noise,and has higher extraction efficiency and robustness than existing algorithms.

参考文献

[1] SCHOWENGERDT A R. Remote sensing: models and methods for image processing［M］. San Diego: Academic Press,1997: 120-121.

[2] WINTER E M. N-finder: an algorithm for fast autonomous spectral endmember determination in hyperspectral data［C］. SPIE: Conference on Imaging Spectrometry V,1999,3753: 266-275.

[3] PLAZA A,CHANG Chein-I. An improved N-FINDR algorithm in implementation. Algorithms and Technologies for Multispectral［C］,Hyperspectral and Ultraspectral Imagery XI,2005,5806: 298-306.

[4] NASCIMENTO J M P,DIAS J M B. Vertex component analysis: a fast algorithm to unmix hyperspectral data［J］. IEEE Transactions on Geoscience and Remote Sensing,2005,43(4): 898-910.

[5] FANG Ling-jiang,NIAN Yong-jian,LEI Shu-tao,et al. Endmembers extraction for hyperspectral images based on vertex component analysis［J］. Ship Electronic Engineering,2014,34(8): 154-157.方凌江,粘永健,雷树涛,等. 基于顶点成分分析的高光谱图像端元提取算法［J］.舰船电子工程,2014,34(8): 154-157.

[6] CHANG Chein-i,WU Chao-cheng,LIU Wei-min,et al. A new growing method for simplex-based endmember extraction algorithm［J］. IEEE Transactions Geosciences and Remote Sensing,2006,44(10): 2804-1819.

[7] WANG Li-jiao,LI Xiao-run,ZHAO Liao-ying. Fast implement of the simplex growing algorithm for endmember extraction［J］. Acta Optica Sinica,2014,34(11): 1-7.王丽姣,历小润,赵辽英. 快速实现基于单形体体积生长的端元提取算法［J］. 光学学报,2014,34(11): 1-7.

[8] LI Na,ZHAO Hui-jie. Endmember extraction method based on morphology and orthogonal subspace projection［J］. Journal of Beijing University of Aeronautics and Astronautics,2010,36(12): 1457-1460.李娜,赵慧洁. 基于形态学与正交子空间投影的端元提取方法［J］. 北京航空航天大学学报,2010,36(12): 1457-1460.

[9] CUI Jian-tao,WANG Jing,LI Xiao-run,et al. Endmember extraction algorithm based on spatial pixel purity index［J］. Journal of Zhejiang University (Engineering Science),2013,47(9): 1524-1530.崔建涛,王晶,厉小润,等. 基于空间像素纯度指数的端元提取算法［J］. 浙江大学学报,2013,47(9): 1524-1530.

[10] SETOAIN J,PRIETO M,TENLLADO C,et al. Parallel morphological endmember extraction using commodity graphics hardware ［J］. Geoscience and Remote Sensing Letters,IEEE,2007,4(3): 441-445.

[11] WANG Ying,LIANG Nan,GUO Lei. A hyperspectral remote sensing image endmember extraction algorithm based on modified extended-morphological operator［J］. Acta Photonica Sinica,2012,41(6): 672-677.王瀛,梁楠,郭雷. 一种基于修正扩展形态学算子的高光谱遥感图像端元提取算法［J］. 光子学报,2012,41(6): 672-677.

[12] BOARDMAN J W,KRUSE F A,GREEN R O. Mapping target signatures via partial unmixing of AVIRIS data: in Summaries ［C］. Fifth JPL Airborne Earth Science Workshop. 1995,23-26.

[13] XIONG Wei,CHANG Chein-i,WU Chao-cheng,et al. Fast algorithms to implement N-FINDR for Hyperspectral endmember extraction［C］. Proceedings of the SPIE,2010,76951Q: 1-12.

[14] DING Hai-yong,SHI Wen-zhong. Fast N-FINDR algorithm for endmember extraction based on chi-square distribution［J］. Journal of Remote Sensing,2013,17(1): 122-129.

[15] WANG Li-guo,ZHANG Ye. Speed-up for N-FINDR algorithm［J］. Journal of Harbin Institute of Technology,2008,15(1): 141-144.

[16] ZHAO Chun-hui,QI Bin,WANG Yu-lei. An improved N-FINDR hyperspectral endmember extraction algorithm［J］. Journal of Electronics & Information Technology,2012,34(2): 499-503.赵春晖,齐滨,王玉磊. 一种改进的N-FINDR高光谱端元提取算法［J］,电子与信息学报,2012,34(2): 499-503.

[17] 耿修瑞,赵永超,周冠华. 一种利用单形体体积自动提取高光谱图像端元的算法［J］. 自然科学进展,2006,16(9): 1196-1200.GENG Xiu-rui,ZHAO Yong-chao,ZHOU Guan-hua. An automatic extraction algorithon of hyperspectral image endmember using single volume form［J］. Progress in Natural Science,2006,16(9):1196-1200.

赵春晖, 郭蕴霆. 一种改进的快速N-FINDR端元提取算法[J]. 光子学报, 2015, 44(10): 1011002. ZHAO Chun-hui, GUO Yun-ting. An Improved Fast N-FINDR Endmember Extraction Algorithm[J]. ACTA PHOTONICA SINICA, 2015, 44(10): 1011002.

一种改进的快速N-FINDR端元提取算法

关于本站 Cookie 的使用提示

全站搜索

一种改进的快速N-FINDR端元提取算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索