吉林大学学报(地球科学版) ›› 2017, Vol. 47 ›› Issue (3): 907-915.doi: 10.13278/j.cnki.jjuese.201703304

• 地球探测与信息技术 • 上一篇    下一篇

吉林西部多时相遥感数据分类方案的构建及应用

李晓东1,2, 姜琦刚1   

  1. 1. 吉林大学地球探测科学与技术学院, 长春 130026;
    2. 白城师范学院旅游与地理科学学院, 吉林 白城 137000
  • 收稿日期:2016-09-08 出版日期:2017-05-26 发布日期:2017-05-26
  • 通讯作者: 姜琦刚(1965),男,博士,教授,博士生导师,主要从事地学信息工程研究,E-mail:sky_0013@163.com E-mail:sky_0013@163.com
  • 作者简介:李晓东(1977-),男,博士,讲师,主要从事资源环境遥感研究,E-mail:xiaodonglee@126.com
  • 基金资助:
    中国地质调查局项目(12120115063701)

Land Cover Classification Method Based on Multi-Temporal Satellite Images: Taking Western Jilin Region as an Example

Li Xiaodong1,2, Jiang Qigang1   

  1. 1. College of GeoExploration Science and Technology, Jilin University, Changchun 130026, China;
    2. School of Tourism and Geography Science, Baicheng Normal College, Baicheng 137000, Jilin, China
  • Received:2016-09-08 Online:2017-05-26 Published:2017-05-26
  • Supported by:
    Supported by the Project of China geological Survey (12120115063701)

摘要: 为了深化遥感监测方法在生态环境调查中的应用,本文以吉林西部为试验区,设计了一种多时相遥感数据分类方案。该方案以物候信息为主,结合地物特征变量(植被、水体和土地信息)构建的多维特征空间数据集用于土地覆被分类。该遥感分类方案提取了9种地表覆被类型,结果表明:地表植被季节变化信息和土地利用信息的引入能明显改善土地覆被的分类精度;与基于原始波段的分类方案相比,多时相遥感数据分类方案的分类精度最好,总体分类精度为95.50%,Kappa系数为95.04%。

关键词: 吉林西部, 多时相遥感数据, 土地覆被分类, 物候信息

Abstract: With the rapid development of 3S (remote sensing (RS), geographical information system (GIS), global positioning system (GPS)) technology, the satellite image data used for monitoring the surface vegetation cover is vast. Western Jilin region was selected as the experimental zone. Using various functions, the land cover classification scheme was proposed to quickly and accurately extract the land cover information in the test area based on multi-temporal satellite images, coupled with the main classified variables including the seasonal variation information of vegetation, the water information and the land use information. Furthermore, the extracted data were statistically analyzed to verify the feasibility and rationality of the method. Finally, the results are as follows: 1) The way combined these classification features for extracting land cover type effectively improved the overall classification accuracy. Especially, the introduction of the changed information, including the seasonal variation of vegetation cover and the land-use and land-cover information, could significantly improve the classification accuracy of land cover; 2) The overall classification accuracy of the algorithm was 95.5%, the Kappa coefficient of classification was 95.04%.

Key words: western of Jilin, multi-temporal satellite images, land cover types, phenological information

中图分类号: 

  • P407.8
[1] 周永章,王正海,侯卫生. 数学地球科学[M].广州:中山大学出版社,2012. Zhou Yongzhang, Wang Zhenghai, Hou Weisheng.Mathematical Geoscience[M]. Guangzhou:Sun Yat-Sen University Press, 2012.
[2] 王宗明,国志兴,宋开山,等. 2000—2005年三江平原土地利用/覆被变化对植被净初级生产力的影响研究[J].自然资源学报,2009,24(1):136-146. Wang Zongming, Guo Zhixing, Song Kaishan, et al. Effects of Land Use/Cover Change on Net Primary Productivity of Sanjiang Plain, During 2000-2005[J]. Journal of Natural Resources, 2009, 24(1): 136-146.
[3] 赵锐锋,陈亚宁,李卫红,等. 塔里木河干流区土地覆被变化与景观格局分析[J].地理学报,2009,64(1):95-106. Zhao Ruifeng, Chen Yaning, Li Weihong, et al. Land Cover Change and Landscape Pattern in the Mainstream of the Tarim River[J]. Acta Geographica Sinica, 2009, 64(1): 95-106.
[4] 戴竹红,塔西甫拉提·特依拜,马勇刚. 土地利用/土地覆被变化遥感监测研究[J].沙漠与绿洲气象,2007,1(6):17-19. Dai Zhuhong, Tashfulati·Teyibai, Ma Yonggang. The Research of Land Use/Cover Change Using Remote Sensing Monitoring[J]. Desert and Oasis Meteorology, 2007, 1(6): 17-19.
[5] 王芳芳,吴世新,杨涵. 基于3S的近15a新疆LUCC时空变化研究及分析[J].中国沙漠,2009,29(4):636-640. Wang Fangfang, Wu Shixin, Yang Han. Study on Spatiotemporal Variations of Land Use/Cover in Xinjiang Based on 3S Technology[J]. Journal of Desert Research, 2009, 29(4): 636-640.
[6] Jonsson P, Eklundh L. Seasonality Extraction by Function Fitting to Time-Series of Satellite Sensor Data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002,40(8): 1824-1832.
[7] Defries R S, Townshend J R G. NDVI Derived Land Cover Classifications at a Global-Scale[J]. International Journal of Remote Sensing, 1994, 15(17): 3567-3586.
[8] 汪权方,李家永.基于时序NDVI数据的中国红壤丘陵区土地覆被分类研究[J]. 农业工程学报,2005,21(2):72-77. Wang Quanfang, Li Jiayong. Land Cover Classification in Redsoil Hilly Region of China Using Multi-Temporal VEGETATION/NDVI Data: A Case Study of Poyang Basin[J]. Transactions of the CSAE, 2005, 21(2): 72-77.
[9] 左玉珊,王卫,郝彦莉,等. 基于MODIS影像的土地覆被分类研究:以京津冀地区为例[J]. 地理科学进展,2014,33(11):1556-1565. Zuo Yushan, Wang Wei, Hao Yanli, et al. Land Cover Classification Based on MODISImages: Taking the Beijing-Tianjin-Hebei Region as an Example[J]. Progress in Geography, 2014,33(11):1556-1565.
[10] 张景,姚凤梅,徐永明,等. 基于MODIS的土地覆盖遥感分类特征的评价与比较[J]. 地理科学,2010,30(2):249-253. Zhang Jing, Yao Fengmei, Xu Yongming, et al. Comparison and Evaluation of Classification Features in Land Cover Based on Remote Sensing[J]. Scientia Geographica Sinica, 2010, 30(2): 249-253.
[11] 谭磊,赵书河,罗云霄,等. 基于对象特征的山东省丘陵地区多时相遥感土地覆被自动分类[J].生态学报,2014,34(24):7251-7260. Tan Lei, Zhao Shuhe, Luo Yunxiao, et al. Application of Object-Oriented Image Analysis to Land-Cover Classification in Hilly Areas[J]. Acta Ecologica Sinica, 2014, 34(24): 7251-7260.
[12] James M E, Kalluri S N V. Pathfinder AVHRR Land Dataset:An Improved Coarse Resolution Dataset for Terrestrial Monitoring[J]. International Journal of Remote Sensing, 1994, 15(17): 3347-3363.
[13] Loveland T R, Reed B C, Brown J F, et al. Development of a Global Land Cover Characteristics Data Base and IGBPDIS Cover from 1 km AVHRR Data[J]. International Journal of Remote Sensing, 2000, 21(6/7):1303-1330.
[14] Ross S L, Joseph F K, Jayantha E, et al. Land Cover Change Detection Using Multi-Temporal MODIS NDVI Data[J]. Remote Sensing Environment, 2006, 105: 142-154.
[15] Wardlow B D, Egbert S L, Kastens J H. Analysis of Time-Series MODIS 250 m Vegetation Index Data for CropClassification in the US Central Great Plain[J]. Remote Sensing of Environment, 2007, 108: 290-310.
[16] Wardlow B D, Egbert S L. Large-Area Crop Mapping Using Time-Series MODIS 250 m NDVI Data: An Assessment for the US Central Great Plains[J]. Remote Sensing of Environment, 2008, 112: 1096-1116.
[17] Lambin E F, Strahlers A H. Change-Vector Analysis in Multi-Temporal Space: A Tool to Detect and Categorize Land Cover Change Processes Using High Temporal-Resolution Satellite Data[J]. Remote Sensing of Environment, 1994, 48(2): 231-244.
[18] Ludeke M K B, Ramge P H, Kohlmaierg H. The Use of Satellite NDVI Data for the Validation of Global Vegetation Phenology Models: Application to the Frankfurt Biosphere Model[J]. Ecological Modelling, 1996, 91: 255-270.
[19] Pieter S A, Beck C, Kjellarild H, et al. Improved Monitoring of Vegetation Dynamics at Very High Latitudes: A New Method Using MODIS NDVI[J]. Remote Sensing of Environment, 2006, 100: 321-324.
[20] Geerken R, Zaitchik B, Evans J P. Classifying Rangeland Vegetation Type and Coverage Using a Fourier Component Based Similarity Measure[J]. International Journal of Remote Sensing,2005,26(24): 5535-5554.
[21] Geerken R, Batikha N, Celis D, et al. Differentiation of Rangeland Vegetation and Assessment of Its Status: Field Investigations and MODIS and SPOT VEGETATION Data Analyses[J]. International Journal of Remote Sensing, 2005, 26(20): 4499-4526.
[22] Evans J P, Geerken R. Classifying Rangeland Vegetation Type and Coverage Using a Fourier Component Based Similarity Measure[J]. Remote Sensing of Environment, 2006, 105: 1-8.
[23] Piao S L, Fang J Y, Zhou L, et al. Interannual Variations of Monthly and Seasonal Normalized Difference Vegetation Index (NDVI) in China from 1982 to 1999[J]. Journal of Geophysical Research, 2003, 108: 4401–4413.
[24] 李忠峰,李雪梅,蔡运龙,等.基于SPOT VEGE-TATION数据的榆林地区土地覆盖变化研究[J].干旱区资源与环境,2007,21(2):56-59. Li Zhongfeng, Li Xuemei, Cai Yunlong, et al. Study of Land Cover Change in Yulin District Based on Spot Vegetation[J]. Journal of Arid Land Resources and Environment, 2007, 21(2): 56-59.
[25] 刘殿伟,宋开山,王丹丹,等.近50年来松嫩平原西部土地利用变化及驱动力分析[J]. 地理科学,2006,26(3):277-283. Liu Dianwei, Song Kaishan, Wang Dandan, et al. Dynamic Change of Land-Use Patterns in West Part of Songnen Plain[J]. Sicentia Geographica Sinica, 2006, 26(3): 277-283.
[26] 李晓东,姜琦刚. 基于多时相遥感数据的农田分类提取[J].农业工程学报,2015,31(7):145-150. Li Xiaodong, Jiang Qigang. Extraction of Farmland Classification Based on Multi-Temporal Remote Sensing Data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(7): 145-150.
[27] 黄方,王平,刘权. 松嫩平原西部植被覆盖动态变化研究[J].东北师大学报(自然科学版),2008,40(4):115-120. Huang Fang, Wang Ping, Liu Quan. Analysis of Vegetation Change in West Songnen Plain Since 1998[J]. Journal of Northeast Normal University (Natural Science Edition),2008, 40(4): 115-120.
[28] 姜琦刚,贾大成,李远华,等. 东北地区生态地质环境遥感监测[M].北京:地质出版社,2013. Jiang Qigang, Jia Dacheng, Li Yuanhua, et al. Remote Sensing Monitoring of Ecological Geological Environment in Northeast China[M]. Beijing: Geological Publishing House, 2013.
[29] 李晓东,姜琦刚. 吉林西部农业生态资源调查及其时空分布特征[J]. 白城师范学院学报,2016(2):10-19. Li Xiaodong, Jiang Qigang. Investigation on Agroecological Resources and the Temporal as well as Spatial Distribution in the West of Jilin[J]. Journal of Baicheng Normal University, 2016(2): 10-19.
[30] 徐言,姜琦刚. 基于6S模型的MODIS影像逐像元大气校正及其应用[J].吉林大学学报(地球科学版),2015,45(5):1547-1553. Xu Yan, Jiang Qigang. A Pixel by Pixel Atmospheric Correction Algorithm and Its Application for MODIS Data Based on 6S Model[J]. Journal of Jilin University (Earth Science Edition), 2015, 45(5): 1547-1553.
[31] 刘纪远.国家资源环境遥感宏观调查与动态监测研究[M]. 北京:中国科学技术出版社,1996. Liu Jiyuan. The Macro Investigation and Dynamic Research of the Resource and Environment[M]. Beijing:Science and Technology of China Press, 1996.
[32] 徐爱萍, 舒红. 空间数据分析与R语言实践[M]. 北京: 清华大学出版社, 2013. Xu Aiping, Shu Hong. Applied Spatial Data Analysis with R[M]. Beijing: Tsinghua University Press, 2013.
[33] 李晓东,姜琦刚. 基于多时相遥感数据的吉林西部土地覆被分类提取[J]. 农业工程学报,2016,32(9):173-178. Li Xiaodong, Jiang Qigang. Extracting Land Cover Types in Western Jilin Based on Multi-Temporal Remote Sensing Data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(9): 173-178.
[34] 吴际通,谭伟,喻理飞. 基于TM/ETM+影像的不同水体指数对比研究[J]. 测绘科学,2013,38(4):192-194. Wu Jitong, Tan Wei, Yu Lifei. Comparative Study of Different Water Indexes Based on TM/ETM+ Imagery[J]. Science of Surveying and Mapping, 2013, 38(4): 192-194.
[35] 连懿,陈圣波,王亚楠,等. 基于决策树模型的吉林西部居民地分布信息提取[J].安徽农业科学,2010,38(10):5241-5243. Lian Yi, Chen Shengbo, Wang Yanan, et al. Extraction to the Residential Distribution Information in West Jilin Based on Decision Tree Model[J]. Anhui Agriculture Science, 2010, 38(10): 5241-5243.
[36] Muchoney D, Borak J. Application of the MODIS Global Supervised Classification Refel to Vegetation and Land Cover Mapping of Central America[J]. Intel Remote Sensing, 2000, 21(1): 1115-1138.
[37] 张斌,王继尧,吕一河,等. ALOS影像数据土地覆盖分类及景观特征研究[J].计算机工程与应用,2012,48(24):216-221. Zhang Bin, Wang Jiyao, Lü Yihe, et al. Study on Land Cover Classification and Landscape Characteristics of ALOS Images[J]. Computer Engineering and Applications, 2012, 48(24): 216-221.
[38] 李晓东,李相坤,姜琦刚. 基于空间变异理论的地表覆被时空变化监测方法[J].草业科学,2015,32(6):877-885. Li Xiaodong, Li Xiangkun, Jiang Qigang. The Monitoring Method of the Surface Vegetation Based on the Spatial Variation Analysis[J]. Pratacultural Science,2015, 32(6): 877-885.
[39] Richards J A, Jia X P. Remote Sensing Digital (Digital Number)Image Analysis Introduction[M]. 4th ed. Berlin: Springer-Verlag, 2006.
[40] 赵英时. 遥感应用分析原理与方法[M]. 北京:科学出版,2003. Zhao Yingshi. The Principle and Method of Analysis of Remote Sensing Application[M]. Beijing: Science Press, 2003.
[1] 王清, 刘宇峰, 刘守伟, 张旭东, 彭玮, 李超月, 徐新川, 范建华. 吉林西部盐渍土多场作用下物质特性演化规律[J]. 吉林大学学报(地球科学版), 2017, 47(3): 807-817.
[2] 卢文喜, 安永凯, 宋文博, 于婷. 吉林西部季节性气象干旱的时空演化特征[J]. 吉林大学学报(地球科学版), 2016, 46(2): 543-551.
[3] 王宇, 卢文喜, 卞建民, 侯泽宇. 三种地下水位动态预测模型在吉林西部的应用与对比[J]. 吉林大学学报(地球科学版), 2015, 45(3): 886-891.
[4] 汤洁,梁爽,张豪,吴佳曦,娄云. 吉林西部盐碱水田区冻融期土壤水盐运移特征及酶活性变化[J]. 吉林大学学报(地球科学版), 2014, 44(2): 636-644.
[5] 陈社明,卢文喜,罗建男,康柱. 吉林西部气象干旱的多标度分形特征[J]. 吉林大学学报(地球科学版), 2013, 43(1): 245-250.
[6] 赵娟,李育松,卞建民,张丽姝,杨占梅. 吉林西部地区高砷地下水砷的阈值分析及风险评价[J]. 吉林大学学报(地球科学版), 2013, 43(1): 251-258.
[7] 汤洁, 张楠, 李昭阳, 毛子龙, 李娜, 徐小明, 韩维峥. 吉林西部不同土地利用类型的土壤有机碳垂向分布和碳密度[J]. J4, 2011, 41(4): 1151-1156.
[8] 卞建民, 查恩爽, 汤洁, 马力, 陈刚. 吉林西部砷中毒区高砷地下水反向地球化学模拟[J]. J4, 2010, 40(5): 1098-1103.
[9] 杨俊鹏,胡 克,刘玉英. 吉林西部盐碱化土壤碳酸盐的碳稳定同位素特征[J]. J4, 2006, 36(02): 245-0249.
[10] 周云轩,王黎明,陈圣波,万 力,尹 楠. 吉林西部陆面遥感蒸散模型研究[J]. J4, 2005, 35(06): 812-0817.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!