Shape feature-assisted discrimination of cloud and snow in GF-1 spectral images of mountainous areas

摘要

In this study, we propose a new method for cloud and snow discrimination, which is based on spectral, texture, and shape features and combined with support vector machine multi-classification strategy. A new feature called curvature histogram is designed to describe edge shape. First, the region of interest test is applied to extract cloud and snow area. Then, the extracted area is combined with the segmentation results using the mean shift algorithm to obtain the object of interest while calculating the feature values. The complexity of surfaces in the cloud and snow area is classified into four types, namely, thick cloud, thin cloud, snow, and snow-covered land, such that six kinds of classifiers are obtained by designing a classifier between every two categories. Through six classifiers and calculating the sum of confidence coefficients for each category, every superpixel is classified into the class with the highest confidence coefficient and a rough cloud and snow mask is obtained. Finally, the GrabCut algorithm is applied to optimize the classification results at the pixel level. The experiments on the images of China's GF-1 satellite, indicate that the proposed method is effective for cloud and snow discrimination on multispectral high-resolution satellites images in mountainous area.