Share Email Print

Proceedings Paper • new

An improved hybrid CNN for hyperspectral image classification
Author(s): Yuting Li; Lin He
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The application of convolutional neural network (CNN) in hyperspectral image (HSI) classification has aroused widespread concern, especially spectral 1D CNN and spatial 2D CNN. Due to intense requirements of calculations and memories, 3D CNN, which is able to process jointly spectral and spatial features, has not yet been widely adopted. Recently, researchers have proposed a hybrid CNN for HSI classification, which obtained better performance than 3D CNN alone. Nevertheless, such a hybrid network has excessive parameters and limited capacity for feature utilization, where smaller training samples are prone to lower accuracy. This paper proposes an improved hybrid CNN to enhance the classification performance, which involves global average pooling, skip connection and appropriate adjustments of the convolution kernels and overall structure. Experimental results from benchmark HSI datasets suggest the effectiveness of our CNN for HSI classification in the situation of limited training set.

Paper Details

Date Published: 3 January 2020
PDF: 6 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113731R (3 January 2020); doi: 10.1117/12.2557384
Show Author Affiliations
Yuting Li, South China Univ. of Technology (China)
Lin He, South China Univ. of Technology (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