Abstract
Understanding the scenes provided by remote sensing (RS) images has drawn increasing attention in the last decade. It is to automatically classify a RS scene image by feature extraction and label assignment. Although much effort has been dedicated to developing discriminative feature extraction as well as automatic classification techniques, it is still very challenging owing to the complex distributions of the ground objects in high spatial resolution scenes. To enhance the ability to represent the RS scenes, an integration of multiple types of features for remote sensing scenes is considered as an effective way. Nevertheless, different kinds of features possess different characteristics, and how to fuse them together is a critical problem. In this paper, to fuse three different but complementary types of features that are extracted to characterize global attributes of scenes together, a discriminant correlation analysis based feature-level fusion approach is proposed, which maximizes the correlation of corresponding features across the two feature sets and in addition de-correlates features that belong to different classes within each feature set. In addition, to further improve the scene classification performance, another kind of information fusion form, called decision-level fusion is adopted in the classification stage. In our proposed decision-level fusion technique, the final results of multiple classifiers are combined via majority voting. Extensive experiments results conducted on the well-known SIRI-WHU dataset, the WHU-RS dataset and the UC Merced Land Use dataset have demonstrated that the proposed remote sensing scene classification method based on heterogeneous feature extraction and multi-level fusion is superior to many state-of-the-art scene classification algorithms.
Highlights
Remote sensing (RS) scene classification, aiming at classifying scene images into various semantic categories, has been a subject of increased interest in recent years, and widely used in remote sensing image retrieval, segmentation, especially for image understanding
The combined feature is directly fed into a support vector machine (SVM) classifier without dimensionality reduction
The heterogeneous features are reduced according to our method, the overall accuracy of ours is still superior to the method without feature reduction
Summary
Remote sensing (RS) scene classification, aiming at classifying scene images into various semantic categories, has been a subject of increased interest in recent years, and widely used in remote sensing image retrieval, segmentation, especially for image understanding. Compared with classifying pixels or targets, scene classification is a challenging task due to highly complex geometrical structures, spatial patterns, and the existences of various objects inherent in the scenes [1,2,3,4]. Good features that have good discriminability for different categories of image scenes can maximize inter-class differences and at the same time, minimize intra-class variations [6]. Histogram of oriented gradients (HOG) and scale invariant feature transform (SIFT) are two most widely used descriptors for shape information extraction [7, 8]. The representations, the first-order and second-order statistics, are used to extract spectral information [12]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have