TY - GEN
T1 - Using CNN to classify hyperspectral data based on spatial-spectral information
AU - Lin, Lianlei
AU - Song, Xinyi
N1 - Publisher Copyright:
© Springer International Publishing AG 2017.
PY - 2017
Y1 - 2017
N2 - Currently, the dimensionality of hyperspectral images is increasing, and the images have the characteristics of nonlinearity and spatial correlation, making it more and more difficult to classify these data. In this study, convolutional neural network (CNN) which has been successfully applied in image recognition and language detection is introduced. The spectral and spatial information is combined and used for hyperspectral image classification. According to the character of CNN that its input is two-dimensional image data, two methods are proposed converting the spectral and spatial information of hyperspectral images into two dimensional images. One of them converts the spatial-spectral information into gray level images and uses the varying texture features between spectral bands. The other converts the spatial-spectral information into waveforms and uses the wave characteristics of the spectral bands. Experiments on KSC and Pavia U data sets demonstrate the feasibility and efficacy of CNN in hyperspectral image classification.
AB - Currently, the dimensionality of hyperspectral images is increasing, and the images have the characteristics of nonlinearity and spatial correlation, making it more and more difficult to classify these data. In this study, convolutional neural network (CNN) which has been successfully applied in image recognition and language detection is introduced. The spectral and spatial information is combined and used for hyperspectral image classification. According to the character of CNN that its input is two-dimensional image data, two methods are proposed converting the spectral and spatial information of hyperspectral images into two dimensional images. One of them converts the spatial-spectral information into gray level images and uses the varying texture features between spectral bands. The other converts the spatial-spectral information into waveforms and uses the wave characteristics of the spectral bands. Experiments on KSC and Pavia U data sets demonstrate the feasibility and efficacy of CNN in hyperspectral image classification.
KW - Convolutional neural network (CNN)
KW - Hyperspectral image classification
KW - Joint spatial and spectral feature
UR - https://www.scopus.com/pages/publications/85006041920
U2 - 10.1007/978-3-319-50212-0_8
DO - 10.1007/978-3-319-50212-0_8
M3 - 会议稿件
AN - SCOPUS:85006041920
SN - 9783319502113
T3 - Smart Innovation, Systems and Technologies
SP - 61
EP - 68
BT - Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceeding of the 12th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2016
A2 - Pan, Jeng-Shyang
A2 - Tsai, Pei-Wei
A2 - Huang, Hsiang-Cheh
PB - Springer Science and Business Media Deutschland GmbH
T2 - 12th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2016
Y2 - 21 November 2016 through 23 November 2016
ER -