Conditional Random Field and Deep Feature Learning for Hyperspectral Image Classification

Image classification is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, a convolutional neural network (CNN) has established itself as a powerful model in classification by demonstrating excellent performances. The use of a graphical model such...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2019-03, Vol.57 (3), p.1612-1628
Main Authors: Alam, Fahim Irfan, Zhou, Jun, Liew, Alan Wee-Chung, Jia, Xiuping, Chanussot, Jocelyn, Gao, Yongsheng
Format: Article
Language:English
Subjects:
Artificial neural networks
Classification
Conditional random field (CRF)
Conditional random fields
Convolution
convolutional neural network (CNN)
Cubes
Data
Data models
deep learning
Feature extraction
Frameworks
Hyperspectral imaging
Image classification
Image processing
Information processing
Kernel
Methods
Neural networks
Performance evaluation
Remote sensing
Spatial data
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image classification is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, a convolutional neural network (CNN) has established itself as a powerful model in classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the classification performance. In this paper, we propose a method to classify hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral band groups to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of 3-D data cubes. Furthermore, we introduce a deep deconvolution network that improves the final classification performance. We also introduced a new data set and experimented our proposed method on it along with several widely adopted benchmark data sets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2018.2867679