Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification

Chunyan Yu; Fang Li; Chein I. Chang; Kun Cen; Meng Zhao

doi:10.1007/978-981-13-6504-1_20

Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification

Chunyan Yu, Fang Li, Chein I. Chang, Kun Cen, Meng Zhao

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

Feature extraction and classification technology based on hyperspectral data have been a hot issue. Recently, the convolutional neural network (CNN) has attracted more attention in the field of hyperspectral image classification. To enhance the feature extracted from the hidden layers, in this paper a deconvolution layer is introduced in the deep 2DCNN model. Analyzing the function of convolution and pooling to determine the structure of the convolutional neural network, deconvolution is used to map low-dimensional features into high-dimensional input; the target pixel and its pixels in a certain neighborhood are input into the network as input data. Experiments on two public available hyperspectral data sets show that the deconvolution layer can better generalize features for the hyperspectral image and the proposed 2DCNN classification method can effectively improve the classification accuracy in comparison with other feature extraction methods.

Original language	English
Title of host publication	Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II
Subtitle of host publication	Signal Processing
Editors	Qilian Liang, Xin Liu, Zhenyu Na, Wei Wang, Jiasong Mu, Baoju Zhang
Publisher	Springer Verlag
Pages	149-156
Number of pages	8
ISBN (Print)	9789811365034
DOIs	https://doi.org/10.1007/978-981-13-6504-1_20
Publication status	Published - 2020
Event	International Conference on Communications, Signal Processing, and Systems, CSPS 2018 - Dalian, China Duration: 2018 Jul 14 → 2018 Jul 16

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	516
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Communications, Signal Processing, and Systems, CSPS 2018
Country/Territory	China
City	Dalian
Period	18-07-14 → 18-07-16

All Science Journal Classification (ASJC) codes

Industrial and Manufacturing Engineering

Access to Document

10.1007/978-981-13-6504-1_20

Cite this

Yu, C., Li, F., Chang, C. I., Cen, K., & Zhao, M. (2020). Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification. In Q. Liang, X. Liu, Z. Na, W. Wang, J. Mu, & B. Zhang (Eds.), Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II: Signal Processing (pp. 149-156). (Lecture Notes in Electrical Engineering; Vol. 516). Springer Verlag. https://doi.org/10.1007/978-981-13-6504-1_20

Yu, Chunyan ; Li, Fang ; Chang, Chein I. et al. / Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification. Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II: Signal Processing. editor / Qilian Liang ; Xin Liu ; Zhenyu Na ; Wei Wang ; Jiasong Mu ; Baoju Zhang. Springer Verlag, 2020. pp. 149-156 (Lecture Notes in Electrical Engineering).

@inproceedings{7276d571f5d846408e6200ee19b95961,

title = "Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification",

abstract = "Feature extraction and classification technology based on hyperspectral data have been a hot issue. Recently, the convolutional neural network (CNN) has attracted more attention in the field of hyperspectral image classification. To enhance the feature extracted from the hidden layers, in this paper a deconvolution layer is introduced in the deep 2DCNN model. Analyzing the function of convolution and pooling to determine the structure of the convolutional neural network, deconvolution is used to map low-dimensional features into high-dimensional input; the target pixel and its pixels in a certain neighborhood are input into the network as input data. Experiments on two public available hyperspectral data sets show that the deconvolution layer can better generalize features for the hyperspectral image and the proposed 2DCNN classification method can effectively improve the classification accuracy in comparison with other feature extraction methods.",

author = "Chunyan Yu and Fang Li and Chang, {Chein I.} and Kun Cen and Meng Zhao",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; International Conference on Communications, Signal Processing, and Systems, CSPS 2018 ; Conference date: 14-07-2018 Through 16-07-2018",

year = "2020",

doi = "10.1007/978-981-13-6504-1_20",

language = "English",

isbn = "9789811365034",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "149--156",

editor = "Qilian Liang and Xin Liu and Zhenyu Na and Wei Wang and Jiasong Mu and Baoju Zhang",

booktitle = "Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II",

address = "Germany",

}

Yu, C, Li, F, Chang, CI, Cen, K & Zhao, M 2020, Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification. in Q Liang, X Liu, Z Na, W Wang, J Mu & B Zhang (eds), Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II: Signal Processing. Lecture Notes in Electrical Engineering, vol. 516, Springer Verlag, pp. 149-156, International Conference on Communications, Signal Processing, and Systems, CSPS 2018, Dalian, China, 18-07-14. https://doi.org/10.1007/978-981-13-6504-1_20

Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification. / Yu, Chunyan; Li, Fang; Chang, Chein I. et al.
Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II: Signal Processing. ed. / Qilian Liang; Xin Liu; Zhenyu Na; Wei Wang; Jiasong Mu; Baoju Zhang. Springer Verlag, 2020. p. 149-156 (Lecture Notes in Electrical Engineering; Vol. 516).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification

AU - Yu, Chunyan

AU - Li, Fang

AU - Chang, Chein I.

AU - Cen, Kun

AU - Zhao, Meng

PY - 2020

Y1 - 2020

N2 - Feature extraction and classification technology based on hyperspectral data have been a hot issue. Recently, the convolutional neural network (CNN) has attracted more attention in the field of hyperspectral image classification. To enhance the feature extracted from the hidden layers, in this paper a deconvolution layer is introduced in the deep 2DCNN model. Analyzing the function of convolution and pooling to determine the structure of the convolutional neural network, deconvolution is used to map low-dimensional features into high-dimensional input; the target pixel and its pixels in a certain neighborhood are input into the network as input data. Experiments on two public available hyperspectral data sets show that the deconvolution layer can better generalize features for the hyperspectral image and the proposed 2DCNN classification method can effectively improve the classification accuracy in comparison with other feature extraction methods.

AB - Feature extraction and classification technology based on hyperspectral data have been a hot issue. Recently, the convolutional neural network (CNN) has attracted more attention in the field of hyperspectral image classification. To enhance the feature extracted from the hidden layers, in this paper a deconvolution layer is introduced in the deep 2DCNN model. Analyzing the function of convolution and pooling to determine the structure of the convolutional neural network, deconvolution is used to map low-dimensional features into high-dimensional input; the target pixel and its pixels in a certain neighborhood are input into the network as input data. Experiments on two public available hyperspectral data sets show that the deconvolution layer can better generalize features for the hyperspectral image and the proposed 2DCNN classification method can effectively improve the classification accuracy in comparison with other feature extraction methods.

UR - http://www.scopus.com/inward/record.url?scp=85071458735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071458735&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-6504-1_20

DO - 10.1007/978-981-13-6504-1_20

M3 - Conference contribution

AN - SCOPUS:85071458735

SN - 9789811365034

T3 - Lecture Notes in Electrical Engineering

SP - 149

EP - 156

BT - Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II

A2 - Liang, Qilian

A2 - Liu, Xin

A2 - Na, Zhenyu

A2 - Wang, Wei

A2 - Mu, Jiasong

A2 - Zhang, Baoju

PB - Springer Verlag

T2 - International Conference on Communications, Signal Processing, and Systems, CSPS 2018

Y2 - 14 July 2018 through 16 July 2018

ER -

Yu C, Li F, Chang CI, Cen K, Zhao M. Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification. In Liang Q, Liu X, Na Z, Wang W, Mu J, Zhang B, editors, Communications, Signal Processing, and Systems - Proceedings of the 2018 CSPS Volume II: Signal Processing. Springer Verlag. 2020. p. 149-156. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-13-6504-1_20

Deep 2D Convolutional Neural Network with Deconvolution Layer for Hyperspectral Image Classification

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this