全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于波段选择的MODIS全国土地覆盖分类

DOI: 10.6046/gtzyyg.2010.03.22, PP. 108-113

Keywords: ?MODIS,J-M距离,土地覆盖分类,SVM

Full-Text   Cite this paper   Add to My Lib

Abstract:

?以MODIS多光谱和多时相数据为输入参数进行了全国土地覆盖分类研究。从试验区2007年MODIS8d数据的合成影像(MOD09)中提取EVI、NDWI和NDSI3个指数,并将其作为特征波段与原有的7波段(B1~B7)形成10波段影像。以统计分类J-M距离平均值和SVM分类总精度为标准评价不同波段对土地覆盖分类的贡献。在全国范围内,选择贡献最大的EVI、B7和B4这3个波段的月合成值,并分别对其作PCA变换,选取各PCA变换后的前3个波段进行分类运算。研究结果表明,在没有其他辅助信息的境况下,基于MODIS贡献最大的前3个波段结合多时相信息能够在中分辨率区域土地覆盖分类中取得较好的分类结果,其精度为78.04%。

References

[1]  [9]Bruzzone L, Roli F, Serpico S B. An Extension to Multiclass Cases of the Jeffries-Matusita Distance[J]. IEEE Transactions on Geoscience and Remote Sensing, 1995(33), 1318-1321.
[2]  [12]刘勇洪,牛铮,徐永明,等.基于MODIS数据设计的中国土地覆盖分类系统与应用研究[J].农业工程学报,2006,22(5):99-104.
[3]  [13]王正兴,刘闯,HUETE Alfredo.植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J]. 生态学报,2003,23(5):979-987.
[4]  [11]Sharma R K,Ixen T K,Pavel M. Probabilistic Image Sensor Fusion [J]. Advances in Neural Information Processing Systems,1999(11):203-207.
[5]  [14]Huang C, Davis L S,Townshend J R G. An Assessment of Support Vector Machines for Land Cover Classification[J]. International Journal of Remote Sensing,2002,23:725-749.
[6]  [12]Wright W A,Bristol F. Quick Markov Random Field Image Fusion [C]// Proceedings of the Conference on Signal Processing, Sensor Fusion and Target Recognition VII. Orlando, 1998:302-308.
[7]  [13]Broussard R P,Roges S K, Oxley M E,et al. Physiologically Motivated Image Fusion for Object Detection Using a Pulse Coupled Neural Network [J]. Neural Networks,1999 (3):554-563.
[8]  [15]Townshend J R, Justice C R,Kalb V.Characterization and Classification of South American Land Cover Types Using Satellite Data[J].International Journal of Remote Sensing,1987(8):1189-1207.
[9]  [16]2007年中国国土资源公报[EB/OL]. http://www.gov.cn/gzdt/2008-04/17/content_947023.htm
[10]  [8]David Landgrebe.Multispectral Land Sensing:Where from,Where to?[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):414-421.
[11]  [1]Daily M I,Farr T,Elachi C. Geologic Interpretation from Composited Radar and Landsat Imagery [J]. Photogram Eng Remote Sensing, 1979,45(8):1109-1116.
[12]  [2]Ray P K,Roy A K,Prabhakaran B. Evaluation and Integration of ERS-1 ASAR and Optical Sensor Data (TM and IRS) for Geological Investigations Photon Irvachak [J]. Journal of Indian Society of Remote Sensing,1995,23:77-86.
[13]  [3]Demargne L,Nezry E,Yakam S F,et al. Use of SPOT and Radar Data for Forestry Inventory in Sarawak, Malaysia [C]// Proceedings of the Conference on Data Management and Modeling Using Remote Sensing and GIS for Tropical Forest Land Inventory. Jakarta,1998:111-119.
[14]  [4]王峰,荆燕, 陈志军. 运用Radarsat与ETM数据融合探测隐伏断裂[J]. 地震研究, 2004, 27(4):369-373.
[15]  [5]郭广猛,曹云刚,马龙. ENVISAT-ASAR数据处理介绍[J]. 遥感信息,2006(4):61-63.
[16]  [6]余钧辉,张万昌,乐通潮. 基于小波变换的MODIS与ETM数据融合研究[J]. 遥感信息,2004 (4):39-43.
[17]  [7]Reed J M,Hutchinson S. Image Fusion and Subpixel Parameter Estimation for Automated Optical Inspection of Electronic Components [J]. Industrial Electronics,1996,43(3):346-354.
[18]  [8]Richards J A. Thematic Mapping from Multitemporal Image Data Using the Principal Component Transformation [J]. Remote Sensing of Environment,1984,16:36-46.
[19]  [9]Therrien C W,Scrofani J W,Krebs W K. An Adaptive Technique for the Enhanced Fusion of Low Light Visible with Uncooled Thermal Infrared Imagery [C]//International Conference on Imaging Processing.Washington,1997:405-412.
[20]  [10]Toet A,Ijspeert J K,Wanan A M. Fusion of Visible and Thermal Imagery Improves Situational Awareness [J]. Displays,1997,18(2):85-95.
[21]  [10]Cortes C,Vapnik V.Support Vector Networks[J].Machine Learning, 1995(20):273-297.
[22]  [11]李淼,张继贤,张永红.支持向量机在MODIS影像分类中的方法研究[J].测绘与空间地理信息,2007,30(3):177-179.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133