期刊信息
- 刊名： 河北师范大学学报（自然科学版）Journal of Hebei Normal University (Natural Science)
- 主办： 河北师范大学
- ISSN： 1000-5854
- CN： 13-1061/N
- 中国科技核心期刊
- 中国期刊方阵入选期刊
- 中国高校优秀科技期刊
- 华北优秀期刊
- 河北省优秀科技期刊
基于数据挖掘和高光谱数据的湿地植被精细分类
- 河南省丰华工程技术有限公司, 河南 郑州 450000
-
DOI：10.13763/j.cnki.jhebnu.nse.2019.02.013
Wetland Vegetation Classification Based on Data Mining and Hyperspectral Data
摘要/Abstract
以大丰市沿海滩涂湿地区域为研究区，以机载高光谱影像为主要数据源，冠层高度模型（canopy height model，CHM）数据为辅助数据，采用数据挖掘的方法对高光谱数据进行特征规则提取，实现了湿地植被的精细分类.结果表明：3种湿地植被分类结果的总体精度为90.3%，说明数据挖掘技术在处理高维数据时不仅可以提取重要程度较高的数据，而且可以减少数据量，提高数据处理效率与分类精度；与传统的支持向量机分类法（SVM）分类结果进行对比，基于数据挖掘的湿地植被精细分类总体精度比SVM分类方法高10.8%，表明数据挖掘方法在湿地植被高光谱遥感分类问题上具有较大优势.
Taking the coastal beach wetland area in Dafeng city as the research area,the paper chooses airborne hyperspectral image as the main data source and canopy height model (CHM) data as the auxiliary.Data mining method is used to extract characteristic rules of the hyperspectral data,and fine classification of wetland vegetation is realized.The results show that the overall classification accuracy of three types of wetland vegetation is 90.3%,showing that data mining technology can not only extract data of higher importance,but also reduce data volume,improve data processing efficiency and classification accuracy.Meanwhile,compared with the classification accuracy of traditional SVM classification method,the result shows that the overall accuracy of data mining method is 10.8% higher than that of SVM classification method,which shows that data mining method has great advantages in wetland vegetation classification using hyperspectral remote sensing.
关键词
参考文献 20
- [1] 王鹏,万荣荣,杨桂山.基于多源遥感数据的湿地植被分类和生物量反演研究进展[J].湿地科学,2017,15(1):114-124.doi:10.13248/j.cnki.wetlandsci.2017.01.017 WANG Peng,WAN Rongrong,YANG Guishan.Research Progress on Wetland Vegetation Classification and Biomass Inversion Based on Multi-source Remote Sensing Data[J].Journal of Wetland Science,2017,15(1):114-124.
- [2] 孔春芳,王静,张毅,等.武汉城市湿地景观格局时空结构演化及驱动机制研究[J].中山大学学报(自然科学版),2012,51(4):119-128.KONG Chunfang,WANG Jing,ZHANG Yi,et al.Study on the Spatial and Temporal Structure Evolution and Driving Mechanism of Urban Wetland Landscape Pattern in Wuhan[J].Journal of Sun Yatsen University(Natural Science Edition),2012,51(4):119-128.
- [3] 季建万,沙晋明.基于面向对象分类方法和多源遥感数据的龙祥岛区域湿地变化检测[J].福建师范大学学报(自然科学版),2017,33(3):78-86.doi:10.12046/j.issn.1000-5277.2017.03.012 JI Jianwan,SHA Jinming.Detection of Regional Wetland Change in Longxiang Island Based on Object-oriented Classification Method and Multi-source Remote Sensing Data[J].Journal of Fujian Normal University(Natural Science),2017,33(3):78-86.
- [4] 韦玮,李增元,谭炳香.高光谱遥感技术在湿地研究中的应用[J].世界林业研究,2010,23(3):18-22.WEI Wei,LI Zengyuan,TAN Bingxiang.Application of Hyperspectral Remote Sensing Technology in Wetland Research[J].World Forestry Research,2010,23(3):18-22.
- [5] 赵子飞,江涛.基于HICO高光谱的黄河口湿地植被识别方法[J].北京测绘,2018,32(4):378-383.doi:10.19580/j.cnki.1007-3000.2018.04.002 ZHAO Zifei,JIANG Tao.Vegetation Identification Method of Wetland in Huanghekou Based on HICO Hyperspectral[J].Beijing Surveying and Mapping,2018,32(4):378-383.
- [6] 李兴.高光谱数据库及数据挖掘研究[D].北京:中国科学院研究生院(遥感应用研究所),2006.LI Xing.Research on Hyperspectral Database and Data Mining[D].Beijing:Graduate School of Chinese Academy of Sciences(Institute of Remote Sensing Applications),2006.
- [7] 于莉莉.基于数据仓库的决策支持系统[J].佳木斯大学学报(自然科学版),2003,21(1):11-14.YU Lili.Decision Support System Based on Data Warehouse[J].Journal of Jiamusi University(Natural Science Edition),2003,21(1):11-14.
- [8] 肖利,金远平.一个新的挖掘广义关联规则算法[J].东南大学学报(自然科学版),1997,27(6):76-81.XIAO Li,JIN Yuanping.A New Mining Algorithm for Generalized Association Rules[J].Journal of Southeast University(Natural Science Edition),1997,27(6):76-81.
- [9] 杜培军,高松洁.高光谱遥感数据挖掘若干基本问题的研究[J].遥感信息,2005(3):53-57.DU Peijun,GAO Songjie.Research on Some Basic Problems of Hyperspectral Remote Sensing Data Mining[J].Remote Sensing Information,2005(3):53-57.
- [10] SCHMID T,KOCH M,GUMUZZIO J,et al.A Spectral Library for a Semi-arid Wetland and Its Application to Studies of Wetland Degradation Using Hyperspectral and Multispectral Data[J].International Journal of Remote Sensing,2004,25(13):2485-2496.
- [11] VAIPHASA C,SKIDMRE A K,BOER W F D,et al.A Hyperspectral Band Selector for Plant Species Discrimination[J].Isprs Journal of Photogrammetry & Remote Sensing,2007,62(3):225-235.
- [12] VYAS D,KRISHNAYYA N S R,MANJUNATH K R,et al.Evaluation of Classifiers for Processing Hyperion (EO-1) Data of Tropical Vegetation[J].International Journal of Applied Earth Observation & Geoinformation,2011,13(2):228-235.
- [13] 马超飞,刘建强.遥感图像多维量化关联规则挖掘[J].遥感技术与应用,2003,18(4):243-247.doi:10.11873/j.issn.1004-0323.2003.4.243 MA Chaofei,LIU Jianqiang.Multidimensional Quantization Association Rules Mining for Remote Sensing Images[J].Remote Sensing Technology and Application,2003,18(4):243-247.
- [14] 叶静,蔡之华.遥感图像中的数据挖掘应用概述[J].计算机与现代化,2003(10):36-38.YE Jing,CAI Zhihua.Overview of Data Mining Applications in Remote Sensing Images[J].Computer and Modernization,2003(10):36-38.
- [15] 崔小芳,刘正军.基于随机森林分类方法和多源遥感数据的湿地植被精细分类[J].测绘与空间地理信息,2018,41(8):113-116.CUI Xiaofang,LIU Zhengjun.Detailed Classification of Wetland Vegetation Based on Random Forest Classification Method and Multi-source Remote Sensing Data[J].Mapping and Spatial Geographic Information,2008,41(8):113-116.
- [16] 王霄鹏. 黄河三角洲湿地典型植被高光谱遥感研究[D].大连:大连海事大学,2014.WANG Xiaopeng.Study on Hyperspectral Remote Sensing of Typical Vegetation in Yellow River Delta Wetland[D].Dalian:Dalian Maritime University,2014.
- [17] 艾金勇.图书馆读者借阅行为的关联规则挖掘研究[J].情报探索,2017,1(1):40-43.doi:10.3969/j.issn.1005-8095.2017.01.007 AI Jinyong.Research on Association Rules Mining of Library Reader Borrowing Behavior[J].Information Exploration,2017,1(1):40-43.
- [18] HAN Jiawei,KAMBER Micheline.数据挖掘概念与技术[M].范明,孟小峰译.北京:科学出版社,2010.HAN Jiawei,KAMBER Micheline.Data Mining Concepts and Techniques[M].FAN Ming,MENG Xiaofeng Translation.Beijing:Science Press,2010.
- [19] SMYTH P,GOOFMAN R M.An Information Theoretic Approach to Rule Induction from Databases[J].IEEE Transactions on Knowledge & Data Engineering,1992,4(4):301-316.
- [20] 潘琛,杜培军,罗艳,等.一种基于植被指数的遥感影像决策树分类方法[J].计算机应用,2009,29(3):777-780.PAN Chen,DU Peijun,LUO Yan,et al.A Classification Method for Remote Sensing Image Decision Tree Based on Vegetation Index[J].Journal of Computer Applications,2009,29(3):777-780.