Next Article in Journal
An Exploration of Terrain Effects on Land Surface Phenology across the Qinghai–Tibet Plateau Using Landsat ETM+ and OLI Data
Next Article in Special Issue
Aircraft Type Recognition in Remote Sensing Images Based on Feature Learning with Conditional Generative Adversarial Networks
Previous Article in Journal / Special Issue
Deriving High Spatiotemporal Remote Sensing Images Using Deep Convolutional Network
Open AccessArticle

A Fast Dense Spectral–Spatial Convolution Network Framework for Hyperspectral Images Classification

College of Communication and Art Design, University of Shanghai for Science and Technology, Shanghai SH 021, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(7), 1068; https://doi.org/10.3390/rs10071068
Received: 1 June 2018 / Revised: 26 June 2018 / Accepted: 3 July 2018 / Published: 5 July 2018
(This article belongs to the Special Issue Deep Learning for Remote Sensing)
Recent research shows that deep-learning-derived methods based on a deep convolutional neural network have high accuracy when applied to hyperspectral image (HSI) classification, but long training times. To reduce the training time and improve accuracy, in this paper we propose an end-to-end fast dense spectral–spatial convolution (FDSSC) framework for HSI classification. The FDSSC framework uses different convolutional kernel sizes to extract spectral and spatial features separately, and the “valid” convolution method to reduce the high dimensions. Densely-connected structures—the input of each convolution consisting of the output of all previous convolution layers—was used for deep learning of features, leading to extremely accurate classification. To increase speed and prevent overfitting, the FDSSC framework uses a dynamic learning rate, parametric rectified linear units, batch normalization, and dropout layers. These attributes enable the FDSSC framework to achieve accuracy within as few as 80 epochs. The experimental results show that with the Indian Pines, Kennedy Space Center, and University of Pavia datasets, the proposed FDSSC framework achieved state-of-the-art performance compared with existing deep-learning-based methods while significantly reducing the training time. View Full-Text
Keywords: hyperspectral image classification; densely connected convolutional neural network; deep learning; parametric rectified linear unit hyperspectral image classification; densely connected convolutional neural network; deep learning; parametric rectified linear unit
Show Figures

Figure 1

MDPI and ACS Style

Wang, W.; Dou, S.; Jiang, Z.; Sun, L. A Fast Dense Spectral–Spatial Convolution Network Framework for Hyperspectral Images Classification. Remote Sens. 2018, 10, 1068.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop