Share Email Print
cover

Proceedings Paper • new

Dilated convolutional neural network for hyperspectral image feature extraction and classification
Author(s): Feng-zhe Zhang; Lu Xiao; Hai-bin Wang; Hua-yu Gao; Jun-xiang Wang; Chao Lu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, a dilated convolutional neural network is proposed for hyperspectral image classification. Compared with other methods, 2-dimension dilated convolution is used for the first time to extract and classify the spatial-spectral features in hyperspectral image processing fields. Firstly, 1-dimension convolution is extended to 2-dimension convolution for spatial-spectral features extraction. Secondly, a dilated convolutional structure is utilized to fuse the multi-scale information, which is used to extract the multi-scale information without loss of resolution. The experiments of University of Pavia were repeated with the method proposed in this paper, and some better results are obtained, which proved the effectiveness of the proposed model.

Paper Details

Date Published: 3 January 2020
PDF: 5 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113730V (3 January 2020); doi: 10.1117/12.2558057
Show Author Affiliations
Feng-zhe Zhang, Beijing Institute of Astronautical Systems Engineering (China)
Lu Xiao, Beijing Institute of Astronautical Systems Engineering (China)
Hai-bin Wang, Beijing Institute of Astronautical Systems Engineering (China)
Hua-yu Gao, Beijing Institute of Astronautical Systems Engineering (China)
Jun-xiang Wang, Beijing Institute of Astronautical Systems Engineering (China)
Chao Lu, Beijing Institute of Astronautical Systems Engineering (China)


Published in SPIE Proceedings Vol. 11373:
Eleventh International Conference on Graphics and Image Processing (ICGIP 2019)
Zhigeng Pan; Xun Wang, Editor(s)

© SPIE. Terms of Use
Back to Top