Urban Impervious Surface Estimation from Remote Sensing and Social Data

We propose an inspiring approach for accurate impervious surface estimation based on the integration of remote sensing and social data. The proposed approach exploits the strengths of two kind of heterogeneous features, i.e., physical features and social features, where the former ones are derived by a morphological attribute profiles-guided spectral mixture analysis model using remote sensing imagery, and the latter ones are obtained from the normalized kernel density of point of interest and vector road datasets. These two features are then integrated using a multivariable linear regression model to estimate impervious surfaces. The proposed method has been tested in the main urban area of Guangzhou, China, in pixel level and parcel level, respectively. The obtained results, with the overall RAISE of 10.98% and 10.90% for pixel level and parcel level, respectively, demonstrate the good performance of integrating remote sensing imagery and social data for mapping of urban impervious surface.