MODIS data with high spectral and temporal resolutions were used as input parameters for regional land cover classification in China. First, EVI, NDWI and NDSI were calculated as input spectral features on the basis of an annual time series of twelve MODIS 8-day composite reflectance images (MOD09) acquired during the year of 2007. The three indices were added to the image form a 10 spectral bands image. The authors employed the mean Jeffries-Matusita distance as a statistical separability criterion and classification accuracy of SVM to evaluate the contribution of different bands for land cover classification. Once the aim was achieved, the monthly three largest contribution spectral bands (EVI、B7 and B4) were dealt with. The Principal Component Analysis (PCA) method and its first three principal components were used as input parameters for SVM classification. The result shows that the three largest contribution spectral bands together with temporal information as input parameters can reach certain high classification accuracy (78.04%) at moderate spatial scales without other accessorial data.
赵德刚, 占玉林, 刘翔, 刘成林, 庄大方. 基于波段选择的MODIS全国土地覆盖分类[J]. 国土资源遥感, 2010, 22(3): 108-113.
ZHAO De-Gang, ZHAN Yu-Lin, LIU Xiang, LIU Cheng-Lin, ZHUANG Da-Fang. Land Cover Classification in China Based on Chosen Bands of MODIS. REMOTE SENSING FOR LAND & RESOURCES, 2010, 22(3): 108-113.
[2]Hugo Carro,Paulo Gonalves,Mário Caetano.Use of Intra-annual Satellite Imagery Time-series for Land Cover Characterization Purpose[J].EARSeL eProceedings,2007,6:1-11.
[3]Prasad S,Mitchell Schull,Hugh Turral.Ganges and Indus River Basin Land Use/Land Cover (LULC) and Irrigated Area Mapping Using Continuous Streams of MODIS Data[J].Remote Sensing of Environment,2005,95:317-341.
[4]Ballantine J A C,Okin G S. Mapping North African Landforms Using Continental Scale Unmixing of MODIS Imagery[J].Remote Sensing of Environment,2005,97:470-483.
[5]Wessels K J,Fries De R S,Dempewolf J.Mapping Regional Land Cover with MODIS Data for Biological Conservation:Examples from the Greater Yellowstone Ecosystem, USA and Para′State, Brazil[J].Remote Sensing of Environment,2004,92:67-83.
[6]Matsuoka M,Hayasaka T,Fukushima Y.Land Cover Classification over Yellow River Basin Using Satellite Data[J].Proceedings of the IEEE International Geoscience and Remote Sensing Symposium,2004(1):231-234.
[7]Hugo Carro,Paulo Gonalves,Mário Caetano.Contribution of Multispectral and Multitemporal Information from MODIS Images to Land Cover Classification[J].Remote Sensing of Environment,2008,112:986-997.
[8]David Landgrebe.Multispectral Land Sensing:Where from,Where to?[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):414-421.
[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.
[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.
[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.