Estimation of impervious surface based on integrated analysis of classification and regression by using SVM
作者： Xi Cheng , Jiancheng Luo , Zhanfeng Shen , Changming Zhu , Xin Zhang
DOI: 10.1109/IGARSS.2011.6049864
关键词:
摘要: Impervious surface percentage(ISP) is the key parameter for urban regional environment research. This paper proposes method of ISP estimation by using support vector machine(SVM) on TM image: (1) extract ISA pixels which occupies any portion constructed impervious class based SVM classification spatial inputs (2) estimate regression model, build sample-ISP model various spectral features and apply ISP-model imperviousness mapping. On image Tianjin area, select high resolution image(Quickbird) result college, industrial residential districts as training sample(7500 items) testing sample(2000 items), mean square error(RMSE) 15.4%; adding “greenness” tasseled cap transform feature, RMSE decrease to 12%. The results study indicate that suitable large area mapping without insufficient sample because non-linear characteristic good performance small-sample generalization. Additionally, a typical library large-area will be our future research directions.
irgrid.ac.cn参考文章(16)
Xuling Luo, G. Mirchandani, An integrated framework for image classification international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 620- 623 ,(2000) , 10.1109/ICASSP.2000.862058
Giorgos Mountrakis, Li Luo, Enhancing and replacing spectral information with intermediate structural inputs: A case study on impervious surface detection Remote Sensing of Environment. ,vol. 115, pp. 1162- 1170 ,(2011) , 10.1016/J.RSE.2010.12.018
Dengsheng Lu, Qihao Weng, Use of impervious surface in urban land-use classification Remote Sensing of Environment. ,vol. 102, pp. 146- 160 ,(2006) , 10.1016/J.RSE.2006.02.010
George Xian, Collin Homer, Updating the 2001 National Land Cover Database Impervious Surface Products to 2006 using Landsat Imagery Change Detection Methods Remote Sensing of Environment. ,vol. 114, pp. 1676- 1686 ,(2010) , 10.1016/J.RSE.2010.02.018
S. Lee, R. G. Lathrop, Sub-pixel estimation of urban land cover components with linear mixture model analysis and Landsat Thematic Mapper imagery International Journal of Remote Sensing. ,vol. 26, pp. 4885- 4905 ,(2005) , 10.1080/01431160500300222
Changshan Wu, Alan T. Murray, Estimating impervious surface distribution by spectral mixture analysis Remote Sensing of Environment. ,vol. 84, pp. 493- 505 ,(2003) , 10.1016/S0034-4257(02)00136-0
Changshan Wu, Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery Remote Sensing of Environment. ,vol. 93, pp. 480- 492 ,(2004) , 10.1016/J.RSE.2004.08.003
Xiaojun Yang, Zhi Liu, Use of satellite-derived landscape imperviousness index to characterize urban spatial growth Computers, Environment and Urban Systems. ,vol. 29, pp. 524- 540 ,(2005) , 10.1016/J.COMPENVURBSYS.2005.01.005
Soe W. Myint, Patricia Gober, Anthony Brazel, Susanne Grossman-Clarke, Qihao Weng, Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery Remote Sensing of Environment. ,vol. 115, pp. 1145- 1161 ,(2011) , 10.1016/J.RSE.2010.12.017
R POWELL, D ROBERTS, P DENNISON, L HESS, Sub-pixel mapping of urban land cover using multiple endmember spectral mixture analysis: Manaus, Brazil Remote Sensing of Environment. ,vol. 106, pp. 253- 267 ,(2007) , 10.1016/J.RSE.2006.09.005