Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks
Abstract
:1. Introduction
2. Proposed Method
- Step 1 (Difference Image Generation): Three difference images are generated by the mean-ratio detector, the neighborhood-based ratio operator and the ratio operator, respectively.
- Step 2 (Training Sample Construction): Pixel vectors constructed by corresponding pixel patches from difference images are utilized as the to-be-selected training data. The PCA-kmeans algorithm is adopted to classify the pixel vectors into three clusters, of which those at a close distance from the cluster center are taken as training samples.
- Step 3 (Classification by gΓ-DBN): The training samples generated in Step 2 are fed into the gΓ-DBN for model training. After training, all the pixel vectors from the original difference images are fed into the learned gΓ-DBN for classification, before the final change map is generated.
2.1. Difference Images Generation
2.2. Training Sample Construction
2.3. Classification by a Generalized Gamma Deep Belief Network
Algorithm 1. The gΓB-RBM update for a mini-batch of size . |
Input: A gΓB-RBM with visual nodes and hidden nodes and training batch . Output: The gradient approximation of model parameter:, and , for and . Initialization: , and ; for all do ; for to do , sample ; , sample ; end for for and do Update :; Update : ; Update : ; end for end for return , and . |
3. Results
3.1. Experimental Setting
3.2. Reliability of the Training Sample Construction Method
3.3. Performance of the Deep Learning Method
3.4. Results and Analysis of the Real Data Sets
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Gong, M.; Cao, Y.; Wu, Q. A Neighborhood-Based Ratio Approach for Change Detection in SAR Images. IEEE Geosci. Remote Sens. Lett. 2012, 9, 307–311. [Google Scholar] [CrossRef]
- Radke, R.J.; Andra, S.; Al-Kofahi, O.; Roysam, B. Image change detection algorithms: A systematic survey. IEEE Trans. Image Process. 2005, 14, 294–307. [Google Scholar] [CrossRef] [PubMed]
- Wang, L.; Wu, Z.Z. Urban building change detection in SAR images using combined differential image and residual u-net network. Remote Sens. 2019, 11, 1091. [Google Scholar]
- Pantze, A.; Fransson, J.E.; Santoro, M. Forest change detection from L-band satellite SAR images using iterative histogram matching and thresholding together with data fusion. In Proceedings of the 2010 IEEE International Geoscience and Remote Sensing Symposium, Honolulu, HI, USA, 25–30 July 2010; pp. 1226–1229. [Google Scholar]
- Bovolo, F.; Bruzzone, L. A detail-preserving scale-driven approach to change detection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens. 2005, 43, 2963–2972. [Google Scholar] [CrossRef]
- Gong, M.; Jia, M.; Su, L.; Wang, S.; Jiao, L. Detecting changes of the Yellow River Estuary via SAR images based on a local fit-search model and kernel-induced graph cuts. Int. J. Remote Sens. 2014, 35, 4009–4030. [Google Scholar] [CrossRef]
- Jia, M.; Wang, L. Novel class-relativity non-local means with principal component analysis for multitemporal SAR image change detection. Int. J. Remote Sens. 2017, 39, 1068–1091. [Google Scholar] [CrossRef]
- Celik, T. Unsupervised change detection in satellite images using principal component analysis and k-means clustering. IEEE Geosci. Remote Sens. Lett. 2009, 6, 772–776. [Google Scholar] [CrossRef]
- Jia, L.; Li, M.; Zhang, P.; Wu, Y.; Zhu, H. SAR Image Change Detection Based on Multiple Kernel K-Means Clustering with Local-Neighborhood Information. IEEE Geosci. Remote Sens. Lett. 2016, 13, 856–860. [Google Scholar] [CrossRef]
- Gao, F.; Wang, X.; Gao, Y.; Dong, J.; Wang, S. Sea Ice Change Detection in SAR Images Based on Convolutional-Wavelet Neural Networks. IEEE Geosci. Remote Sens. Lett. 2019, 16, 1240–1244. [Google Scholar] [CrossRef]
- Samadi, F.; Akbarizadeh, G.; Kaabi, H. Change detection in SAR images using deep belief network: A new training approach based on morphological images. IET Image Process. 2019, 13, 2255–2264. [Google Scholar] [CrossRef]
- Gong, M.; Zhao, J.; Liu, J.; Miao, Q.; Jiao, L. Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks. IEEE Trans. Neural Netw. Learn. Syst. 2016, 27, 125–138. [Google Scholar] [CrossRef]
- Lv, N.; Chen, C.; Qiu, T.; Sangaiah, A.K. Deep Learning and Superpixel Feature Extraction Based on Contractive Autoencoder for Change Detection in SAR Images. IEEE Trans. Ind. Inform. 2018, 14, 5530–5538. [Google Scholar] [CrossRef]
- Zhang, N.; Ding, S.; Zhang, J.; Xue, Y. An overview on Restricted Boltzmann Machines. Neurocomputing 2018, 275, 1186–1199. [Google Scholar] [CrossRef]
- Cui, Z.; Cao, Z.; Yang, J.; Ren, H. Hierarchical Recognition System for Target Recognition from Sparse Representations. Math. Probl. Eng. 2015, 2015, 527095. [Google Scholar] [CrossRef]
- Liu, F.; Jiao, L.; Hou, B.; Yang, S. POL-SAR Image Classification Based on Wishart DBN and Local Spatial Information. IEEE Trans. Geosci. Remote Sens. 2016, 54, 3292–3308. [Google Scholar] [CrossRef]
- Inglada, J.; Mercier, G. A New Statistical Similarity Measure for Change Detection in Multitemporal SAR Images and Its Extension to Multiscale Change Analysis. IEEE Trans. Geosci. Remote Sens. 2007, 45, 1432–1445. [Google Scholar] [CrossRef] [Green Version]
- Rignot, E.; Van Zyl, J. Change detection techniques for ERS-1 SAR data. IEEE Trans. Geosci. Remote Sens. 1993, 31, 896–906. [Google Scholar] [CrossRef] [Green Version]
- Zhao, Z.; Guo, L.; Jia, M.; Wang, L. The Generalized Gamma-DBN for High-Resolution SAR Image Classification. Remote Sens. 2018, 10, 878. [Google Scholar] [CrossRef] [Green Version]
- Li, H.-C.; Hong, W.; Wu, Y.-R.; Fan, P.-Z. On the Empirical-Statistical Modeling of SAR Images with Generalized Gamma Distribution. IEEE J. Sel. Top. Signal Process. 2011, 5, 386–397. [Google Scholar] [CrossRef]
- Fischer, A.; Igel, C. Training restricted Boltzmann machines: An introduction. Pattern Recognit. 2014, 47, 25–39. [Google Scholar] [CrossRef]
- Brennan, R.L.; Prediger, D.J. Coefficient kappa: Some uses, misuses, and alternatives. Educ. Psychol. Meas. 1981, 41, 687–699. [Google Scholar] [CrossRef]
Data Sets | Methods | ||||
---|---|---|---|---|---|
Farmland data set | Supervised | 469 | 604 | 1073 | 0.8931 |
JDBN | 456 | 656 | 1112 | 0.8898 | |
River data set | Supervised | 865 | 870 | 1795 | 0.7893 |
JDBN | 892 | 887 | 1779 | 0.7837 | |
Coastline data set | Supervised | 96 | 145 | 241 | 0.8894 |
JDBN | 99 | 145 | 244 | 0.8879 |
Data Set | ||||||
---|---|---|---|---|---|---|
Farmland | 1395 | 0.8597 | 1047 | 0.8956 | 944 | 0.9060 |
River | 1843 | 0.7699 | 1595 | 0.8019 | 1664 | 0.7978 |
Coastline | 238 | 0.8882 | 225 | 0.8932 | 255 | 0.8824 |
Methods | ||||
---|---|---|---|---|
PCA-kmeans | 135 | 1440 | 1575 | 0.8366 |
CWNN | 1570 | 57 | 1627 | 0.8104 |
DBN | 1053 | 874 | 1927 | 0.8025 |
JDBN | 456 | 656 | 1112 | 0.8898 |
gΓ-DBN | 458 | 589 | 1047 | 0.8956 |
Methods | ||||
---|---|---|---|---|
PCA-kmeans | 581 | 2050 | 2631 | 0.7260 |
CWNN | 722 | 1006 | 1728 | 0.7965 |
DBN | 1298 | 842 | 2040 | 0.7258 |
JDBN | 892 | 887 | 1779 | 0.7837 |
gΓ-DBN | 892 | 703 | 1595 | 0.8019 |
Methods | ||||
---|---|---|---|---|
PCA-kmeans | 29 | 445 | 474 | 0.8134 |
CWNN | 22 | 375 | 397 | 0.8398 |
DBN | 178 | 96 | 274 | 0.8664 |
JDBN | 99 | 145 | 244 | 0.8879 |
gΓ-DBN | 125 | 100 | 225 | 0.8932 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jia, M.; Zhao, Z. Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks. Sensors 2021, 21, 8290. https://doi.org/10.3390/s21248290
Jia M, Zhao Z. Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks. Sensors. 2021; 21(24):8290. https://doi.org/10.3390/s21248290
Chicago/Turabian StyleJia, Meng, and Zhiqiang Zhao. 2021. "Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks" Sensors 21, no. 24: 8290. https://doi.org/10.3390/s21248290
APA StyleJia, M., & Zhao, Z. (2021). Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks. Sensors, 21(24), 8290. https://doi.org/10.3390/s21248290