Estimation of impervious surface based on integrated analysis of classification and regression by using SVM

Impervious surface percentage(ISP) is the key parameter for urban regional environment research. This paper proposes the method of ISP estimation by using support vector machine(SVM) on TM image: (1) extract the ISA pixels which occupies any portion of the constructed impervious class based on SVM classification for spatial inputs of ISP estimation (2) estimate ISP of ISA pixels by using SVM regression model, build sample-ISP regression model based on various spectral features inputs and apply ISP-model for regional imperviousness mapping. On the TM image of Tianjin urban area, select high resolution image(Quickbird) classification result of college, industrial and residential districts as training sample(7500 items) and testing sample(2000 items), the mean square error(RMSE) of SVM model is 15.4%; adding "greenness" of tasseled cap transform as SVM feature, the RMSE decrease to 12%. The results of the study indicate that SVM model is suitable for large area ISP mapping without insufficient sample because of the non-linear characteristic and good performance of small-sample generalization. Additionally, to build a typical sample library for large-area ISP mapping will be our future research directions.