Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

153 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number7919223
Pages (from-to)4520-4533
Number of pages14
Journal / PublicationIEEE Transactions on Geoscience and Remote Sensing
Volume55
Issue number8
Online published4 May 2017
Publication statusPublished - Aug 2017

Abstract

Convolutional neural network (CNN) is well known for its capability of feature learning and has made revolutionary achievements in many applications, such as scene recognition and target detection. In this paper, its capability of feature learning in hyperspectral images is explored by constructing a five-layer CNN for classification (C-CNN). The proposed C-CNN is constructed by including recent advances in deep learning area, such as batch normalization, dropout, and parametric rectified linear unit (PReLU) activation function. In addition, both spatial context and spectral information are elegantly integrated into the C-CNN such that spatial-spectral features are learned for hyperspectral images. A companion feature-learning CNN (FL-CNN) is constructed by extracting fully connected feature layers in this C-CNN. Both supervised and unsupervised modes are designed for the proposed FL-CNN to learn sensor-specific spatial-spectral features. Extensive experimental results on four benchmark data sets from two well-known hyperspectral sensors, namely airborne visible/infrared imaging spectrometer (AVIRIS) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral applications under both supervised and unsupervised modes.

Research Area(s)

  • Classification, convolutional neural network (CNN), feature learning, hyperspectral, spatial-spectral

Citation Format(s)

Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks. / Mei, Shaohui; Ji, Jingyu; Hou, Junhui; Li, Xu; Du, Qian.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 55, No. 8, 7919223, 08.2017, p. 4520-4533.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review