Spatial‐spectral classification of hyperspectral images: a deep learning framework with Markov Random fields based modelling

Abstract

This version is available at https://strathprints.strath.ac.uk/65510/ Strathprints is designed to allow users to access the research output of the University of Strathclyde. Unless otherwise explicitly stated on the manuscript, Copyright © and Moral Rights for the papers on this site are retained by the individual authors and/or other copyright owners. Please check the manuscript for details of any other licences that may have been applied. You may not engage in further distribution of the material for any profitmaking activities or any commercial gain. You may freely distribute both the url (https://strathprints.strath.ac.uk/) and the content of this paper for research or private study, educational, or not-for-profit purposes without prior permission or charge.Any correspondence concerning this service should be sent to the Strathprints administrator: strathprints@strath.ac.ukThe Strathprints institutional repository (https://strathprints.strath.ac.uk) is a digital archive of University of Strathclyde research outputs. It has been developed to disseminate open access research outputs, expose data about those outputs, and enable the management and persistent access to Strathclyde's intellectual output. Abstract: For spatial-spectral classification of hyperspectral images (HSI), a deep learning framework is proposed in this paper, which consists of convolutional neural networks (CNN) and Markov random fields (MRF). Firstly, a CNN model to learn the deep spectral feature from the HSI is built and the class posterior probability distribution is estimated. The CNN with a dropout layer can relieve the overfitting in classification. The CNN is utilized as a pixel-classifier, so it only works in the spectral domain. Then, the spatial information will be encoded by MRF-based multilevel logistic (MLL) prior for regularizing the classification. To derive the correlation of both spectral and spatial features for improving algorithm performance, the marginal probability distribution in HSI is learned using MRF-based loopy belief propagation (LBP). In comparison with several state-of-the-art approaches for data classification on 3 publicly available HSI datasets, experimental results have demonstrated the superior performance of the proposed methodology. Keywords Hyperspectral image (HSI); spatial-spectral classification; convolutional neural networks (CNN); Markov random fields (MRF); loopy belief propagation (LBP). IntroductionHyperspectral remote sensing, a technology of acquiring remote sensing image in high-resolution spectrum, is capable of simultaneously collecting spectral and spatial information for earth observation, especially land cover analysis [1]. As an emerging field, hyperspectral remote sensing has been introduced in a wide range of scenes increasingly. Even for hyperspectral image (HSI)-based classification and target detection, the technology has been successfully applied in aerospace, agriculture, forestry, mineral, atmospheric sciences, military and so on [2] [3]. Apart from these conventional applicati...

Effect of pooling strategy on convolutional neural network for classification of hyperspectral remote sensing images

“…The traditional classification algorithms such as support vector machine [18], multinomial logistic regression (LR) [19], minimum spanning forest [20] and so on are used in classification of HSI. Recently, deep learning (DL) [21] has produced encouraging results on HSI classification [22–29] because of its ability to automatically learn representative features from the data. Various DL methods have been proposed in literature such as stacked autoencoder, deep belief network and convolutional neural network (CNN) [30].…”

Spatial Residual Blocks Combined Parallel Network for Hyperspectral Image Classification

“…Due to the increase attention to the spatial information of HSI, CNN has become the popular method for the HSI classification [24]- [29]. It has been proved that CNNs can simultaneously extract both spatial and spectral features of HSI to produce precise classification results.…”

Superpixel based Feature Specific Sparse Representation for Spectral-Spatial Classification of Hyperspectral Images

“…However, the aforementioned methods focus more on the spectral information only, where the spatial information has not been adequately considered. Recently, some improved approaches have also been proposed, such as the composite kernel SVM [15], the ensemble-based random forest [16], and the random field-based method [17,18]. Furthermore, effective feature extraction techniques have developed for HSI classification, such as the principal component analysis (PCA) and its variations [19,20].…”