Next Article in Journal
Estimation of Evapotranspiration and Crop Coefficients of Tendone Vineyards Using Multi-Sensor Remote Sensing Data in a Mediterranean Environment
Previous Article in Journal
Assimilation of GRACE Terrestrial Water Storage Observations into a Land Surface Model for the Assessment of Regional Flood Potential
Open AccessArticle

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

by 1,2, 1,*, 1,2 and 1
1
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan 430079, China
2
Electronic Information School, Wuhan University, Wuhan 430072, China
*
Author to whom correspondence should be addressed.
Academic Editors: Giles M. Foody, Lizhe Wang and Prasad S. Thenkabail
Remote Sens. 2015, 7(11), 14680-14707; https://doi.org/10.3390/rs71114680
Received: 14 August 2015 / Revised: 20 October 2015 / Accepted: 22 October 2015 / Published: 5 November 2015
Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineered features or unsupervised feature learning, can only generate mid-level image features with limited representative ability, which essentially prevents them from achieving better performance. Recently, the deep convolutional neural networks (CNNs), which are hierarchical architectures trained on large-scale datasets, have shown astounding performance in object recognition and detection. However, it is still not clear how to use these deep convolutional neural networks for high-resolution remote sensing (HRRS) scene classification. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for HRRS scene classification. We propose two scenarios for generating image features via extracting CNN features from different layers. In the first scenario, the activation vectors extracted from fully-connected layers are regarded as the final image features; in the second scenario, we extract dense features from the last convolutional layer at multiple scales and then encode the dense features into global image features through commonly used feature coding approaches. Extensive experiments on two public scene classification datasets demonstrate that the image features obtained by the two proposed scenarios, even with a simple linear classifier, can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low- and mid-level features. Moreover, we tentatively combine features extracted from different CNN models for better performance. View Full-Text
Keywords: CNN; scene classification; feature representation; feature coding; convolutional layer; fully-connected layer CNN; scene classification; feature representation; feature coding; convolutional layer; fully-connected layer
Show Figures

Graphical abstract

MDPI and ACS Style

Hu, F.; Xia, G.-S.; Hu, J.; Zhang, L. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery. Remote Sens. 2015, 7, 14680-14707. https://doi.org/10.3390/rs71114680

AMA Style

Hu F, Xia G-S, Hu J, Zhang L. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery. Remote Sensing. 2015; 7(11):14680-14707. https://doi.org/10.3390/rs71114680

Chicago/Turabian Style

Hu, Fan; Xia, Gui-Song; Hu, Jingwen; Zhang, Liangpei. 2015. "Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery" Remote Sens. 7, no. 11: 14680-14707. https://doi.org/10.3390/rs71114680

Find Other Styles

Article Access Map by Country/Region

1
Only visits after 24 November 2015 are recorded.
Search more from Scilit
 
Search
Back to TopTop