Impervious Surface Extraction From Multispectral Images via Morphological Attribute Profiles Based on Spectral Analysis

Impervious surfaces exhibit unique spatial characteristics in urban environments. The estimation of impervious surfaces is critical for the analysis of these environments. In this paper, we propose a new technique based on morphological attribute profiles for mapping impervious surfaces under a spectral mixture analysis model. A main feature of our newly developed method is that it can model different kinds of structural information, which represents an important competitive advantage over existing techniques. As a result, considering the special characteristics of urban environments, our new method for impervious surface extraction exhibits the potential to model complex urban backgrounds. Four kinds of remotely sensed data, including Landsat ETM+, GF-1, IKONOS and sentinel-2 collected over Guangzhou, China, are used in this work to test the performance of our approach in the task of extracting imperviousness from images with different spatial resolution. Our experimental results illustrate that the proposed method exhibits very good performance in the task of estimating the impervious surface distribution, with relatively high precision. Root-mean-square error (RMSE) was 10.89%, mean absolute error (MAE) was 8.37% and Bias was 1.4% for the ETM+ data. RMSE was 11.49%, MAE was 6.25% and Bias was 2.34% for the GF-1 data. The RMSE was 7.72%, MAE was 7.67% and Bias was 3.91% for the IKONOS data, respectively. These results are superior to those provided by other state-of-the-art methods. Furthermore, our results also show the effectiveness of the method in distinguishing bright impervious surface from the dark impervious surface, especially in high resolution remotely sensed images.