Remote Sensing Scene Classification Using a Preclassification Strategy and an Improved Structural Feature

Abstract

Due to the high intraclass variability and the low interclass disparity in high-resolution remote sensing (RS) image scenes, high-resolution RS scene classification is a challenging task. The performance of scene classification not only relies on discriminative feature representation but also needs appropriate classification strategies. In this paper, a scene preclassification strategy based on unsupervised learning is proposed, which divides scenes into two groups. The division method called dynamic-sphere division method (DSDM) is based on a dynamic-sphere division and an inside-sphere membership assessment. For the group with lower membership, after introducing the spatial location and scale of the scale invariant feature transformation (SIFT) descriptor to form a transaction, frequent itemset mining and an improved feature selection criterion are implemented to reduce the redundancy from the aspects of feature quantity and feature dimension, and a more discriminative structural feature histogram FMS-hist is finally obtained. Both the radius of the dynamic-sphere and the final optimal feature dimension are automatically selected according to the inflection point of the corresponding curves. Experimental results based on two representative data sets show that the proposed DSDM can select the suitable group, the proposed FMS-hist is superior to the bag-of-SIFT-based models. The holistic procedure can further enhance the scene classification accuracy.