吉林大学学报(地球科学版) ›› 2015, Vol. 45 ›› Issue (4): 1246-1256.doi: 10.13278/j.cnki.jjuese.201504304

• 地球探测与信息技术 • 上一篇    下一篇

利用粗糙集理论进行遥感分类信息提取

周林飞, 陈启新, 成遣, 张静   

  1. 沈阳农业大学水利学院, 沈阳 110161
  • 收稿日期:2014-10-21 发布日期:2015-07-26
  • 作者简介:周林飞(1971),女,副教授,博士,主要从事3S技术应用研究,E-mail:zlf924@163.com.
  • 基金资助:

    高等学校博士学科点专项基金(20112103120003);辽宁省水利科技指导性计划项目(〔2011〕137号-12)

Remote Sensing Classification Information Extraction Based on Rough Set Theory

Zhou Linfei, Chen Qixin, Cheng Qian, Zhang Jing   

  1. College of Water Conservancy, Shenyang Agricultural University, Shenyang 110161, China
  • Received:2014-10-21 Published:2015-07-26

摘要:

以辽宁省双台子河口湿地为研究对象,以Landsat 8和HJ-1-A/HJ-1-B的多时相遥感影像为数据源,根据研究区现状,将研究区分为旱地、芦苇、水田、碱蓬、混合植被、水面、滩涂、居民点、养殖塘九个类型.利用时间序列的归一化植被指数提取植被与非植被的分类阈值,采用粗糙集理论和多时相遥感影像,对植被和非植被分别进行分类规则的获取,建立了研究区决策树分类模型.为了进行精度评价,利用相同的训练点又进行了同样基于像元的最大似然法分类.最后利用混淆矩阵对上述两种方法进行了精度评估,基于粗糙集的决策树分类法与最大似然法总体分类精度分别为93.70%和91.62%,Kappa系数分别为0.92和0.90,两项指标值基于粗糙集理论法均比最大似然法有所提高.这为构建决策树分类模型进行湿地地表分类信息提取提供了一条新的研究思路.

关键词: 双台子河口湿地, 遥感分类, 归一化植被指数(NDVI), 粗糙集理论, 决策树

Abstract:

Using Shuangtaizi estuarine wetland as the research area, and Landsat 8 and HJ-1-A/HJ-1-B remote sensing data as the data sources, this study was conducted for land-cover information extraction. According to the status of the land, the study area was divided into 9 categories, including upland, reed, paddy field, Suaeda, mixed vegetation, water body, beach, residential land, culture pond. First, the study area was divided into vegetation and non-vegetation using the time-series normalized difference vegetation index (NDVI). Then, the classification rules of vegetation and non-vegetation were extracted based on the rough set theory and on multi-temporal remote sensing data. Finally, a decision tree classification model was established. For the purpose of an accurate evaluation, the maximum likelihood classification was conducted based on the pixels using the same training samples; and the confusion matrix and kappa coefficient were calculated. The results showed that the overall accuracy both of the deeision tree and the maximum likelihood classification reached up to 93.70% and 91.62% with a kappa coefficient of 0.92 and 0.90 respectively. The two evaluation index values were improved. It provided a novel research idea for a wetland classification information extraction based on remote sensing images.

Key words: Shuangtaizi estuarine wetlands, remote sensing classification, normalized difference vegetation index (NDVI), rough set theory, decision tree

中图分类号: 

  • TP79

[1] Ozesmi S L, Bauer M E. Satellite Remote Sensing of Wetlands[J].Wetlands Ecology Management, 2002, 10: 381-385.

[2] Chen H, Zhao Y W. Evaluating the Environmental Flows of China's Wolonghu Wetland and Land Use Changes Using a Hydrological Model, a Water Balance Model, and Remote Sensing[J]. Ecological Modelling, 2011, 222: 253-260.

[3] 王文杰,蒋卫国,王维,等.环境遥感监测与应用[M].北京:中国环境科学出版社,2011. Wang Wenjie, Jiang Weiguo, Wang Wei, et al. Environmental Remote Sensing Monitoring and Application[M]. Beijing: China Environmental Science Press,2011.

[4] 黄颖,周云轩,吴稳,等.基于决策树模型的上海城市湿地遥感提取与分类[J].吉林大学学报:地球科学版,2009,39(6):1156-1161. Huang Ying, Zhou Yunxuan, Wu Wen, et al. Shanghai Urban Wetland Extraction and Classification with Remote Sensed Imageries Based on a Decision Tree Model[J]. Journal of Jilin University: Earth Science Edition, 2009, 39(6): 1156-1161.

[5] 申文明,王文杰,罗海江,等.基于决策树分类技术的遥感影像分类方法研究[J].遥感技术与应用,2007,22(3): 333-334. Shen Wenming, Wang Wenjie, Luo Haijiang, et al. Classification Methods of Remote Sensing Image Based on Decision Tree Technologies[J]. Remote Sensing Technology and Application, 2007, 22(3): 333-334.

[6] 张玉君.Landsat 8简介[J].国土资源遥感,2013,25(1):176-177. Zhang Yujun. Landsat 8 Introduction[J]. Remote Sensing for Land & Resources, 2013,25(1),176-177.

[7] 徐涵秋,唐菲.新一代Landsat系列卫星:Landsat8遥感影像新增特征及其生态环境意义[J].生态学报,2013,33(11):3250-3257. Xu Hanqiu, Tang Fei. Analysis of New Characteristics of the First Landsat 8 Image and Their Eco-Environment Significance[J]. Acta Ecologica Sinica, 2013, 33(11), 3250-3252.

[8] 曲伟,路京选,李琳,等.环境减灾小卫星影像水体和湿地自动提取方法研究[J].遥感应用,2011,4(4):28. Qu Wei, Lu Jingxuan, Li Lin, et al. Research on Automatic Extraction of Water Bodies and Wetlands on HJ Satellite CCD Images[J].Remote Sensing Application,2011,4(4):28.

[9] 李鑫川,徐新刚,王纪华,等.基于时间序列环境卫星影像的作物分类识别[J].农业工程学报,2013,29(2): 169-173. Li Xinchuan, Xu Xingang, Wang Jihua, et al. Crop Classification Recognition Based on Time-Series Images from HJ Satellite[J]. Transactions of the Chinese Society of Agricultural Engineering,2013,29(2):169-173.

[10] 李小文,刘素红.遥感原理与应用[M].北京:科学出版社,2008. Li Xiaowen, Liu Suhong. Remote Sensing Principles and Applications[M]. Beijing: Science Press,2008.

[11] 张健康,程彦培,张发旺,等.基于多时相遥感影像的作物种植信息提取[J].农业工程学报,2012,28(2):134-135. Zhang Jiankang, Cheng Yanpei, Zhang Fawang, et al. Crops Planting Information Extraction Based on Multi-Temporal Remote Sensing Images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(2):134-135.

[12] 徐娜,丁建丽,刘海霞.基于NDVI和LSMM的干旱区植被信息提取研究:以新疆吐鲁番市为例[J].测绘与空间地理信息,2012,35(7):52-57. Xu Na, Ding Jianli, Liu Haixia. Extraction of Vegetation Information in Arid Area Based on NDVI and LSMM:A Case Study of Turpan[J]. Geomatics & Spatial Information Technology, 2012,35(7):52-57.

[13] 王婧,赵天忠,曾怡.基于粗糙集规则提取的面向对象树种分类方法[J].遥感信息,2013,28(4):90-96. Wang Jing, Zhao Tianzhong, Zeng Yi. Object-Oriented Classification of Tree Species Based on Rule Extraction from Rough Set[J]. Remote Sensing Information, 2013, 28(4): 90-96.

[14] 王学恩,韩崇昭,韩德强,等.粗糙集研究综述[J].控制工程,2013,20(1):1-5. Wang Xueen, Han Chongzhao, Han Deqiang, et al. A Survey of Rough sets Theory[J]. Control Engineering of China, 2013,20(1):1-5.

[15] 张树清.3S支持下中国典型沼泽湿地景观时空动态变化研究[M].长春.吉林大学出版社,2008. Zhang Shuqing. Temporal Dynamic Changes of Wetland Landscape in China Based on 3S Technology[M]. Changchun: Jilin University Press,2008.

[16] Yee Leung,Tung Fung,JuSheng Mi,et al.A Rough Set Approach to the Discovery of Classification Rules in Spatial Data[J].International Journal of Geographical Information Science,2007,21(9):1033-1058.

[17] Susmaga R, Slowinski R, Greco S, et al. Generation of Reducts and Rules in Multi-Attribute and Multi-Criteria Classification[J].Control and Cybemetics, 2000, 29(4): 969-988.

[18] 邓传辉,侍洪波.一种基于粗糙集理论的决策树分类模型的构造[J].中南工业大学学报:自然科学版,2003,34(1):85-88. Deng Chuanhui, Shi Hongbo. Construction of Decision Trees Model Based on Rough Sets Theory[J]. Journal of Central South Unitersity of Technology: Natural Science, 2003, 34(1):85-88.

[19] 郭琳,裴志远,吴全,等.面向对象的土地利用/覆盖遥感分类方法与流程应用[J].农业工程学报,2010,26(7):194-195. Guo Lin, Pei Zhiyuan,Wu Quan, et al. Application of Method and Process of Object-Oriented Land Use-Cover Classification Using Remote Sensing Images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2010,26(7);194-195.

[20] 邓书斌.ENVI遥感图像处理方法[M].北京:科学出版社,2012. Deng Shubin. Remote Sensing Image Processing Using ENVI[M]. Beijing: Science Press, 2012.

[21] Thomas M, Ralph W. Remote Sensing and Image Interpretation[M]. New York: Wiley,2000.

[22] 蔡学良,崔远来.基于异源多时相遥感数据提取灌区作物种植结构[J].农业工程学报,2009,25(8):128. Cai Xueliang, Cui Yuanlai. Crop Planting Structure Extraction in Irrigated Areas from Multi-Sensor and Multi-Temporal Remote Sensing Data[J]. Transa-tions of the Chinese Society of Agricultural Engineering, 2009, 25(8): 128.

[1] 许长福, 李雄炎, 谭锋奇, 于红岩, 李洪奇. 任务驱动数据挖掘方法的提出及在低阻油层识别中的应用[J]. J4, 2012, 42(1): 39-46.
[2] 赵安平, 王清, 张中琼. 土体微观结构对冻胀影响的灰色关联及粗糙集评价[J]. J4, 2011, 41(3): 791-798.
[3] 黄颖, 周云轩, 吴稳, 况润元, 李行. 基于决策树模型的上海城市湿地遥感提取与分类[J]. J4, 2009, 39(6): 1156-1162.
[4] 田波,周云轩,蒋云安,侯长谋. ASTER数据在深圳东部滨海地区土地利用调查中的应用[J]. J4, 2008, 38(1): 121-0128.
[5] 程彬,姜琦刚,周云轩,湛邵斌. 基于ASTER数据遥感影像的决策树分类[J]. J4, 2007, 37(1): 179-0184.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!