Cloud classification of ground-based images is a challenging task due to extreme variations in the appearance of clouds under different atmospheric conditions. Recent research has focused on extracting discriminative image features, which play an important role in achieving competitive classification performance. In this paper, an novel feature extraction algorithm, pyramid salient LBP (PSLBP), is proposed for ground-based cloud classification. The proposed PSLBP descriptors take texture resolution variations into account by cascading the SLBP information of hierarchical spatial pyramids. PSLBP descriptors show their effectiveness for cloud representation. Experimental results using ground-based cloud images demonstrate that the proposed method can achieve better results than current state-of-the-art methods.
展开▼
