No abstract

No abstract

An unsupervised feature learning framework based on auto-encoder is proposed to learn sparse feature representations for remote-sensing imagery retrieval in this letter. The low-level feature descriptors are extracted and exploited to learn a set of feature extractors, which are then used to encode the low-level feature descriptors to generate new sparse features. The learned feature representations are applied to aerial images randomly selected from the University of California Merced data set. The results indicate that the performance of our proposed framework is comparable or superior to that of the state-of-the-art method. The framework is proved to be an effective approach to manage the huge volume of remote-sensing data and to retrieve the desired remote-sensing imagery.

Over the past decade, the incorporation of spatial information has drawn increasing attention in multispectral and hyperspectral data analysis. In particular, the property of spatial autocorrelation among pixels has shown great potential for improving understanding of remotely sensed imagery. In this paper, we provide a comprehensive review of the state-of-the-art techniques in incorporating spatial information in image classification and spectral unmixing. For image classification, spatial information is accounted for in the stages of pre-classification, sample selection, classifiers, post-classification, and accuracy assessment. With regards to spectral unmixing, spatial information is discussed in the context of endmember extraction, selection of endmember combinations, and abundance estimation. Finally, a perspective on future research directions for advancing spatial-spectral methods is offered.

No abstract