Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification

Shaohui Mei; Jingyu Ji; Qianqian Bi; Junhui Hou; Qian Du; Wei Li

doi:10.1109/IGARSS.2016.7730321

Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification

Shaohui Mei, Jingyu Ji, Qianqian Bi, Junhui Hou, Qian Du, Wei Li

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

64 Citations (Scopus)

Abstract

Deep convolutional neural networks (CNNs) have brought in achievements in image classification and tar- get detection. In this paper, we propose a novel five-layer CNN for hyperspectral classification by encountering recent achievement in deep learning area, such as batch normaliza- tion, dropout, Parametric Rectified Linear Unit (PReLu) acti- vation function. By taking advantage of the specific charac- teristics of hyperspectral images, spatial context and spectral information are elegantly integrated into the framework. Ex- perimental results demonstrate that our proposed CNN out- performs the state-of-the-art methods.

Original language	English
Title of host publication	2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5067-5070
Number of pages	4
ISBN (Electronic)	9781509033324
DOIs	https://doi.org/10.1109/IGARSS.2016.7730321
Publication status	Published - 1 Nov 2016
Externally published	Yes
Event	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China Duration: 10 Jul 2016 → 15 Jul 2016

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2016-November

Conference

Conference	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
Country/Territory	China
City	Beijing
Period	10/07/16 → 15/07/16

Keywords

Convolutional Neural Networks
deep learning
hyperspectral classification

Access to Document

10.1109/IGARSS.2016.7730321

Cite this

Mei, S., Ji, J., Bi, Q., Hou, J., Du, Q., & Li, W. (2016). Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings (pp. 5067-5070). Article 7730321 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2016.7730321

Mei, Shaohui ; Ji, Jingyu ; Bi, Qianqian et al. / Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification. 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 5067-5070 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{226bfdf945aa41c1bd5178618a936afe,

title = "Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification",

abstract = "Deep convolutional neural networks (CNNs) have brought in achievements in image classification and tar- get detection. In this paper, we propose a novel five-layer CNN for hyperspectral classification by encountering recent achievement in deep learning area, such as batch normaliza- tion, dropout, Parametric Rectified Linear Unit (PReLu) acti- vation function. By taking advantage of the specific charac- teristics of hyperspectral images, spatial context and spectral information are elegantly integrated into the framework. Ex- perimental results demonstrate that our proposed CNN out- performs the state-of-the-art methods.",

keywords = "Convolutional Neural Networks, deep learning, hyperspectral classification",

author = "Shaohui Mei and Jingyu Ji and Qianqian Bi and Junhui Hou and Qian Du and Wei Li",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

year = "2016",

month = nov,

day = "1",

doi = "10.1109/IGARSS.2016.7730321",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5067--5070",

booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings",

address = "United States",

}

Mei, S, Ji, J, Bi, Q, Hou, J, Du, Q & Li, W 2016, Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification. in 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings., 7730321, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2016-November, Institute of Electrical and Electronics Engineers Inc., pp. 5067-5070, 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016, Beijing, China, 10/07/16. https://doi.org/10.1109/IGARSS.2016.7730321

Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification. / Mei, Shaohui; Ji, Jingyu; Bi, Qianqian et al.
2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 5067-5070 7730321 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November).

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

TY - GEN

T1 - Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification

AU - Mei, Shaohui

AU - Ji, Jingyu

AU - Bi, Qianqian

AU - Hou, Junhui

AU - Du, Qian

AU - Li, Wei

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Deep convolutional neural networks (CNNs) have brought in achievements in image classification and tar- get detection. In this paper, we propose a novel five-layer CNN for hyperspectral classification by encountering recent achievement in deep learning area, such as batch normaliza- tion, dropout, Parametric Rectified Linear Unit (PReLu) acti- vation function. By taking advantage of the specific charac- teristics of hyperspectral images, spatial context and spectral information are elegantly integrated into the framework. Ex- perimental results demonstrate that our proposed CNN out- performs the state-of-the-art methods.

AB - Deep convolutional neural networks (CNNs) have brought in achievements in image classification and tar- get detection. In this paper, we propose a novel five-layer CNN for hyperspectral classification by encountering recent achievement in deep learning area, such as batch normaliza- tion, dropout, Parametric Rectified Linear Unit (PReLu) acti- vation function. By taking advantage of the specific charac- teristics of hyperspectral images, spatial context and spectral information are elegantly integrated into the framework. Ex- perimental results demonstrate that our proposed CNN out- performs the state-of-the-art methods.

KW - Convolutional Neural Networks

KW - deep learning

KW - hyperspectral classification

UR - http://www.scopus.com/inward/record.url?scp=85007420689&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2016.7730321

DO - 10.1109/IGARSS.2016.7730321

M3 - Conference contribution

AN - SCOPUS:85007420689

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 5067

EP - 5070

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016

Y2 - 10 July 2016 through 15 July 2016

ER -

Mei S, Ji J, Bi Q, Hou J, Du Q, Li W. Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 5067-5070. 7730321. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2016.7730321

Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this