Classification of CBERS-02B high resolution image using morphological features for urban areas

Urban landscapes represent one of the most challenging areas for remote sensing analysis due to high spatial and spectral diversities of surface materials involved. High Resolution images (HR, better than 5-m spatial resolution) have a potential for detailed and accurate mapping of urban environment. The objective of this study is to analyze the effectiveness of multi-scale morphological features in the purpose of classifying urban landscapes with panchromatic HR images. The experiment is performed using two CBERS HR scenes with urban landscapes characterized by different architectural styles, namely an apartment block and a peri-urban village surrounding Beijing City. Seven types of morphological features including opening (O), closing (C), opening by reconstruction(OR), closing by reconstruction(CR), opening by top-hat(OTH), closing by top hat(CTH) and derivative morphological profile(DMP) are assessed. A support vector machine classifier was also employed to handle the considerable amount of morphological features. The classification results show that with multi-scale morphological features it is possible to discriminate surfaces with mixed spectral characters such as roads, parking lots, and tents due to their different textures for each scene. According to the validation results, the overall accuracy can be improved from 50% with single band HR data to 80.2% and 76.3% respectively for each urban scene using HR-OC-DMP morphological sets. The classification of residential buildings with similar textual character but different gray scales is improved a lot with the supplement of OC sets. The integration of DMP and OC sets benefits the differentiation of bare soil and roads. The mixed sets combining simple, reconstruction and DMP filters provide the best performance.