Next Article in Journal
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification
Previous Article in Journal
MODIS Sea Ice Thickness and Open Water–Sea Ice Charts over the Barents and Kara Seas for Development and Validation of Sea Ice Products from Microwave Sensor Data
Article Menu
Issue 12 (December) cover image

Export Article

Open AccessArticle
Remote Sens. 2017, 9(12), 1328;

GAN-Assisted Two-Stream Neural Network for High-Resolution Remote Sensing Image Classification

The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan 430079, China
Author to whom correspondence should be addressed.
Received: 17 October 2017 / Revised: 30 November 2017 / Accepted: 16 December 2017 / Published: 18 December 2017
(This article belongs to the Section Remote Sensing Image Processing)
Full-Text   |   PDF [10383 KB, uploaded 18 December 2017]   |  


Using deep learning to improve the capabilities of high-resolution satellite images has emerged recently as an important topic in automatic classification. Deep networks track hierarchical high-level features to identify objects; however, enhancing the classification accuracy from low-level features is often disregarded. We therefore proposed a two-stream deep-learning neural network strategy, with a main stream utilizing fine spatial-resolution panchromatic images to retain low-level information under a supervised residual network structure. An auxiliary line employed an unsupervised net to extract high-level abstract and discriminative features from multispectral images to supplement the spectral information in the main stream. Various feature extraction types from the neural network were selected and jointed in the novel net, as the combined high- and low-level features could provide a superior solution to image classification. In traditional convolutional neural networks, increased network depth might not influence the network performance perceptibly; however, we introduced a residual neural network to develop the expressive ability of the deeper net, increasing the role of net depth in feature extraction. To enhance feature robustness, we proposed a novel consolidation part in feature extraction. An adversarial net improved the feature extraction capabilities and aided digging the inherent and discriminative features from data, with increased extraction efficacy. Tests on satellite images indicated the high overall accuracy of our novel net, verifying that net depth or number of convolution kernels affected the classification capability. Various comparative tests proved the structural rationality for our two-stream structure. View Full-Text
Keywords: remote sensing image per-pixel classification; two-stream net; residual net; GAN; unsupervised learning; supervised learning remote sensing image per-pixel classification; two-stream net; residual net; GAN; unsupervised learning; supervised learning

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Tao, Y.; Xu, M.; Zhong, Y.; Cheng, Y. GAN-Assisted Two-Stream Neural Network for High-Resolution Remote Sensing Image Classification. Remote Sens. 2017, 9, 1328.

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.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top