Object-Oriented Automatic and Accurate Shadow Detection for Very High Spatial Resolution Satellite Images

Abstract

Several existing shadow detection methods cannot keep the balance between accuracy and automaticity well. To overcome the weakness, we present a novel method to detect shadow in very high spatial resolution satellite images. First, a new shadow detection index is developed to obtain the shadow ratio map. The initial shadow mask map is then obtained by utilizing the Gaussian mixture mode and the Otsu’s method automatically. Finally, the initial shadow mask map is refined by jointly using the object spectral characteristics and the spatial-correlation relationship between objects. The experimental results performed on different images show that the accuracy and automation of the proposed method are over several state-of-the-art methods.