[1]张剑晨,崔 杰,程 屹,等.基于主成分变换的多光谱遥感数据的有监督可视化方法[J].南京林业大学学报(自然科学版),2018,42(05):121-128.[doi:10.3969/j.issn.1000-2006.201704017]
 ZHANG Jianchen,CUI Jie,CHENG Yi,et al.Supervised visualization of multispectral remotely sensed data based on principal component transformation[J].Journal of Nanjing Forestry University(Natural Science Edition),2018,42(05):121-128.[doi:10.3969/j.issn.1000-2006.201704017]
点击复制

基于主成分变换的多光谱遥感数据的有监督可视化方法
分享到:

《南京林业大学学报(自然科学版)》[ISSN:1000-2006/CN:32-1161/S]

卷:
42
期数:
2018年05期
页码:
121-128
栏目:
研究论文
出版日期:
2018-09-15

文章信息/Info

Title:
Supervised visualization of multispectral remotely sensed data based on principal component transformation
文章编号:
1000-2006(2018)05-0121-08
作者:
张剑晨崔 杰程 屹黄 剑杜靖媛葛宏立*
浙江农林大学环境与资源学院,浙江省森林生态系统碳循环与固碳减排重点实验室,浙江 临安 311300
Author(s):
ZHANG Jianchen CUI Jie CHENG Yi HUANG Jian DU Jingyuan GE Hongli*
School of Environmental & Resource Sciences, Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, Zhejiang A & F University, Lin'an 311300,China
关键词:
多光谱遥感数据 有监督可视化 目视解译 主成分变换 主成分变换回归重构 森林资源监测
Keywords:
multispectral remote sensing data supervised visualization visual interpretation principal component transformation(PCT) regression reconstruction of principal component transform coefficients(RRPCTC) forest resource monitoring
分类号:
TP751; S758
DOI:
10.3969/j.issn.1000-2006.201704017
文献标志码:
A
摘要:
【目的】遥感数据可视化是决定遥感数据解译质量高低的一个关键环节,目视解译是目前生产实践中遥感技术应用的一个重要方式。探讨一种基于学习样本生成可视化特征,使得可视化与目视解译应用能够有机结合,进而实现有监督可视化。【方法】采用主成分变换回归重构方法重构了针对森林资源的植被监测模型,得到3个新特征,依次赋予红绿蓝3种颜色以生成假彩色图像来实现信息可视化。【结果】基于学习样本的主成分变换回归重构方法与主成分变换法、原始近红外-短波红外-红波段组合相比,重构后的假彩色图像在一定程度上得到了改善,有利于目视解译。主成分变换回归重构后的分类精度比未重构的分类精度提高了6.20%,比原始波段组合的分类精度提高了7.82%。重构前后的一元和多元离差平方和(离差阵)构成变化分析说明,重构后类内差异缩小、类间差异增大。【结论】定量验证认为,主成分变换回归重构的可分性比未重构的主成分变换和原始波段组合的可分性都要好。
Abstract:
【Objective】Visualization of remotely sensed data is a key step to determine the interpretation quality of remotely sensed data. Visual interpretation is an important way of applying remotely sensed technology in current production practice. To exploring a method for generating visual features which based on learning samples, so that visual and visual interpreting applications can be organically combined to achieve supervised visualization. 【Method】Using the newly proposed regression reconstruction of principal component transform coefficients(RRPCTC)to constructed the model,three new features are obtained,which are respectively assigned red,green and blue three colors in order to generate false color images for visualization.【Result】The image produced by RRPCTC is improved to a certain extent compares with the ordinary principal component transformation(OPCT)method and the original near infrared-short wave infrared-red 3-band combination. It is helpful for visual interpretation. The classification accuracy of RRPCTC is improved by 6.20% compared with that of the OPCT and by 7.82% compared with that of the original 3-band combination. The changes of sums of squares of deviations of the first 3 PCs respectively and the deviation matrix before and later reconstruction show that the reconstruction makes the differences smaller inner classes and larger between classes.【Conclusion】All these quantitatively prove that the separability of the RRPCTC is better than that of OPCT and that of original 3-band combination.

参考文献/References:

[1] 钱乐祥. 遥感数字影像处理与地理特征生成 [M]. 北京:科学出版社, 2004.
QIAN L X. Remote sensing digital image processing and geographical feature generation[M]. Beijing: Science Press, 2004.
[2] 苏红军, 盛业华, 杜培军. 自动子空间划分在高光谱影像波段选择中的应用[J].地球信息科学学报, 2007, 9(4): 123-128.
SU H J, SHENG Y H, DU P J. Application of automatic subspace partitioning in hyperspectral image band selection[J]. Journal of Earth Information Science, 2007, 9(4): 123-128.
[3] STEFANO B, ANDREA E,FABRIZIO S. Feature selection for ordinal text classification[J]. Neural Computation, 2014,26(3):557-591.
[4] 孙华,鞠洪波,张怀清,等. Hyperion高光谱影像波段选择方法比较研究[J]. 红外, 2013, 34(2): 27-34.
SUN H,JU H B,ZHANG H Q,et al. Comparative study of band selection methods for hyperspectral imagery Hyperion[J]. Infra-red,2013, 34(2): 27-34.
[5] CHANG C I, DU Q, SUN T L, et al. A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification [J]. IEEE Transactions on Geoscience & Remote Sensing, 1999, 37(6): 2631-2641.
[6] LI W, PRASAD S, FOWLER J E, et al. Locality-preserving dimensionality reduction and classification for hyperspectral image analysis [J]. IEEE Transactions on Geoscience & Remote Sensing, 2012, 50(4): 1185-1198.
[7] 刘翔.基于光谱维变换的高光谱图像目标检测研究[D].北京:中国科学院遥感应用研究所,2008.
LIU X. Research on hyperspectral image target detection bases on spectral dimension transform[D]. Beijing: Institute of Remote Sensing Applications, Chinese Academy of Sciences,2008.
[8] GREENA A, BERMAN M, SWITZER P, et al. A transformation for ordering multispectral data in terms of image quality with implications for noise removal[J]. IEEE Transactions on Geoscience & Remote Sensing,1988,26(1):65-74.
[9] FRITZ R, FRECH I, KOCH B, et al.Sensor fused images for visual interpretation of forest stand borders [J]. International Archives of Photogrammetry and Remote Sensing, 1999(32):7-13.
[10] 林辉, 熊育久, 孙华, 等. 湖南省森林资源连续清查遥感应用研究 [J]. 中南林业科技大学学报, 2007, 27(4): 33-38.DOI:10.14067/J.CNKI.1673-923x.2007.04.020.
LIN H, XIONG Y J, SUN H, et al. Institute of remote sensing applications of continuous forest inventory in Hunan Province[J]. Journal of Central South University of Forestry and Technology,2007,27(4):33-38.
[11] 许筱阳, 李元科, 赵鹏祥. TM影像森林类型解译中若干问题的探讨 [J]. 西北林学院学报, 1993(1): 100-104.
XU X Y, LI Y K, ZHAO P X. Discussion on some problems in interpretation of forest types by TM images[J]. Journal of Northwest Forestry College,1993(1):100-104.
[12] 王晓晶, 王蓉, 郑团结, 等. 面向森林资源调查应用的天绘一号数据影像融合算法评价分析 [J]. 林业资源管理, 2013(3): 138-142.DOI:10.13466/j.cnki.lyzygl.2013.03.005.
WANG X J, WANG R, ZHENG T J, et al. Sky painting NO. 1 for forest resources investigation and application for evaluation and analysis of data fusion algorithms for forest resources survey[J]. Forestry Resource Management,2013(3):138-142.
[13] 熊立伟, 吴湘滨, 谭红伟. 遥感影像元数据多维可视化方法的设计与实现[J]. 遥感信息, 2016,31(2):60-63.DOI:10.3969/j.issn.1000-3177.2016.02.011.
XIONG L W, WU X B, TAN H W. Design and implementation of remote sensing image metadata multidimensional visualization method[J]. Remote Sensing Information,2016,31(2):60-63.
[14] 修珍珍,王斌,杨校生,等.庙山坞自然保护区森林生态系统服务功能评价[J]. 南京林业大学学报(自然科学版), 2015,39(4):81-87.DOI:10.3969/j.issn.1000-2006.2017.01.001.
XIU Z Z, WANG B, YANG X S,et al. Evaluation on service function of forest ecosystem in Miaoshanwu Nature Reserve[J]. Journal of Nanjing Forestry University(Natural Sciences Edition),2015,39(4):81-87.
[15] 李盛阳, 于海军, 韩洁, 等. 基于三维地球的海量遥感影像高效可视化管理系统的设计与实现[J]. 遥感技术与应用, 2016,31(1):170-176.DOI:10.11873/j.issn.1004-0323.2016.1.0170.
LI S Y, YU H J, HAN J, et al. Design and implementation of efficient visualization management system of massive remote sensing images based on 3D earth[J]. Remote Technology and Application,2016,31(1):170-176.
[16] PEARSON K. On lines and planes of closest fit to systems of points in space[J]. Philosophical Magazine,1901,2(11):559-572.
[17] HOTELLING H. Analysis of a complex of statistical variables into principal components [J]. British Journal of Educational Psychology, 1932, 24(6): 417-520.
[18] 朱建平. 应用多元统计分析[M]. 北京:科学出版社,2012:34-37.

备注/Memo

备注/Memo:
收稿日期:2017-04-12 修回日期:2018-03-05 基金项目:国家自然科学基金项目(41371411); 浙江省大学生科技创新项目(2016R412033) 第一作者:张剑晨(diezhu2626@qq.com)。*通信作者:葛宏立(jhghlhxl@163.com),教授。
更新日期/Last Update: 2018-09-15