Spatial‐spectral classification of hyperspectral images: a deep learning framework with Markov Random fields based modelling. Issue 2 (1st February 2019)

• Record Type: Journal Article
• Authors: Qing, Chunmei; Ruan, Jiawei; Xu, Xiangmin; Ren, Jinchang; Zabalza, Jaime
• Is Part Of: IET image processing. Volume 13:Issue 2(2019)
• Page Start: 235
• Page End: 245
• Publication Date: 2019-02-01
• Subjects: belief networks -- probability -- geophysical image processing -- learning (artificial intelligence) -- Markov processes -- image classification -- statistical distributions -- regression analysis -- neural nets -- hyperspectral imaging -- remote sensing; spatial‐spectral classification -- hyperspectral images -- deep learning framework -- convolutional neural networks -- Markov random fields -- CNN model -- deep spectral feature -- HSI -- class posterior probability distribution -- spatial information -- spectral features -- spatial features -- marginal probability distribution -- MRF‐based loopy belief propagation -- data classification; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5727
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : For the spatial‐spectral classification of hyperspectral images (HSIs), a deep learning framework is proposed in this study, which consists of convolutional neural networks (CNNs) and Markov random fields (MRFs). 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 utilised as a pixel‐classifier, so it only works in the spectral domain. Then, the spatial information will be encoded by MRF‐based multilevel logistic prior for regularising 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. In comparison with several state‐of‐the‐art approaches for data classification on three publicly available HSI datasets, experimental results have demonstrated the superior performance of the proposed methodology.