A modified multiple endmember spectral mixture analysis (MMESMA) approach is proposed for high-spatial-resolution hyperspectral imagery in the application of impervious surface mapping. Different from the original MESMA that usually selects one endmember spectral signature for each land-cover class, the proposed MMESMA allows the selection of multiple endmember signatures for each land-cover class. It is expected that the MMESMA can better accommodate within-class variations and yield better mapping results. Various unmixing models are compared, such as the linear mixing model, linear spectral mixture analysis using the original linear mixture model, original MESMA, and support vector machine using a nonlinear mixture model. Airborne 1-m resolution HySpex and ROSIS data are used in the experiments. For HySpex data, validation based on 25-cm synchronism aerial photography shows that MMESMA performs the best, with the root-mean-squared error (RMSE) of the estimated abundance fractions being 13.20% and the correlation coefficient () being 0.9656. For ROSIS data, validation based on simulation shows that MMESMA performs the best, with the RMSE of the estimated abundance fraction being 4.51% and being 0.9878. These demonstrate that the proposed MMESMA can generate more reliable abundance fractions for high-spatial-resolution hyperspectral imagery, which tends to include strong within-class spectral variations.