Three-dimensional densely connected convolutional network for hyperspectral remote sensing image classification

Chunju Zhang; Guandong Li; Shihong Du; Wuzhou Tan; Fei Gao

doi:10.1117/1.JRS.13.016519

23 February 2019 Three-dimensional densely connected convolutional network for hyperspectral remote sensing image classification

Chunju Zhang, Guandong Li, Shihong Du, Wuzhou Tan, Fei Gao

Author Affiliations +

Funded by: National Natural Science Foundation of China

Journal of Applied Remote Sensing, Vol. 13, Issue 1, 016519 (February 2019). https://doi.org/10.1117/1.JRS.13.016519

Abstract

Hyperspectral remote sensing images (HSIs) are rich in spatial and spectral information, thus they help to enhance the ability to distinguish geographic objects. In recent years, great progress have been made in image classification using deep learning (such as 2D-CNN and 3D-CNN). Compared with traditional machine learning methods, deep learning methods can automatically extract the abstract features from low to high levels and convert the images into more easily recognizable features. Most HSI classification tasks focus on spectral information but often ignore the rich spatial structures in HSIs, leading to a low classification accuracy. Moreover, most supervised learning methods use shallow structures in HSI classifications and hence exhibit weak performance in finding sparse geographic objects. We proposed to use the three-dimensional (3-D) structure to extract spectral–spatial information to build a deep neural network for HSI classifications. Based on DenseNet, the 3D densely connected convolutional network was improved to learn spectral-spatial features of HSIs. The densely connected structure can enhance feature transmission, support feature reuse, improve information flow in the network, and make deeper networks easier to train. The 3D-DenseNet has a deeper structure than 3D-CNN, thus it can learn more robust spectral–spatial features from HSIs. In fact, the deeper network structure has a regularized effect, which can effectively reduce overfitting on small sample datasets. The network uses HSIs instead of feature engineering as input data and is trained in an end-to-end manner. The experimental results of this model on the Indian Pines datasets and the Pavia University datasets show that deeper neural networks further improve the classification of complex objects, especially in the areas where geographic objects are sparse. It effectively improves the classification accuracy of HSIs.

Citation Download Citation

Chunju Zhang, Guandong Li, Shihong Du, Wuzhou Tan, and Fei Gao "Three-dimensional densely connected convolutional network for hyperspectral remote sensing image classification," Journal of Applied Remote Sensing 13(1), 016519 (23 February 2019). https://doi.org/10.1117/1.JRS.13.016519

Received: 12 July 2018; Accepted: 22 December 2018; Published: 23 February 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE