Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network

• Published in: IEEE transactions on image processing Vol. 27; no. 5; pp. 2354 - 2367
• Main Authors: Xiangyong Cao, Feng Zhou, Lin Xu, Deyu Meng, Zongben Xu, Paisley, John
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Bayes methods; Bayesian analysis; Classification; convolutional neural networks; Data mining; Feature extraction; Hyperspectral image classification; Hyperspectral imaging; Image classification; Labels; Machine learning; Markov processes; Markov random fields; Neural networks; Remote sensing; Smoothness; Spatial data; Stochastic processes; Task analysis
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2018.2799324

This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent and update the class labels of all pixel vectors using α-expansion mincut-based algorithm. Compared with the other state-of-the-art methods, the classification method achieves better performance on one synthetic data set and two benchmark HSI data sets in a number of experimental settings.