Next Article in Journal
Methodology for Participatory GIS Risk Mapping and Citizen Science for Solotvyno Salt Mines
Next Article in Special Issue
Using TanDEM-X Pursuit Monostatic Observations with a Large Perpendicular Baseline to Extract Glacial Topography
Previous Article in Journal
TomoSAR Imaging for the Study of Forested Areas: A Virtual Adaptive Beamforming Approach
Previous Article in Special Issue
Comparison of Pre-Event VHR Optical Data and Post-Event PolSAR Data to Investigate Damage Caused by the 2011 Japan Tsunami in Built-Up Areas
Open AccessArticle

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

1
Department of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea
2
School of Civil Engineering, Chungbuk National University, 1 Chungdae-ro, Seowon-gu, Cheongju, Chungbuk 28644, Korea
3
School of Convergence and Fusion System Engineering, Kyungpook National University, Sangju 37224, Korea
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(11), 1827; https://doi.org/10.3390/rs10111827
Received: 12 October 2018 / Revised: 12 November 2018 / Accepted: 15 November 2018 / Published: 17 November 2018
Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM. View Full-Text
Keywords: change detection; fully convolutional network; 3D convolution; convolutional LSTM; hyperspectral image change detection; fully convolutional network; 3D convolution; convolutional LSTM; hyperspectral image
Show Figures

Graphical abstract

MDPI and ACS Style

Song, A.; Choi, J.; Han, Y.; Kim, Y. Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks. Remote Sens. 2018, 10, 1827. https://doi.org/10.3390/rs10111827

AMA Style

Song A, Choi J, Han Y, Kim Y. Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks. Remote Sensing. 2018; 10(11):1827. https://doi.org/10.3390/rs10111827

Chicago/Turabian Style

Song, Ahram; Choi, Jaewan; Han, Youkyung; Kim, Yongil. 2018. "Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks" Remote Sens. 10, no. 11: 1827. https://doi.org/10.3390/rs10111827

Find Other Styles
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