A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images
Abstract
:1. Introduction
2. Proposed Method
2.1. Network Architecture
2.2. Network Training
3. Experimental Results and Analysis
3.1. Datasets Description and Experiment Configures
3.2. Experiment Results within One Dataset
3.3. Experiment Results of Cross-Dataset Change Detection
3.4. Computation Evaluation
3.5. Discussion
4. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Théau, J. Change Detection. In Springer Handbook of Geographic Information; Kresse, W., Danko, D.M., Eds.; Springer: Berlin/Heidelberg, Germany, 2012; pp. 75–94. [Google Scholar] [CrossRef]
- Bruzzone, L.; Prieto, D.F. Unsupervised change detection in multisource and multisensor remote sensing images. In Proceedings of the IGARSS 2000, IEEE 2000 International Geoscience and Remote Sensing Symposium, Honolulu, HI, USA, 24–28 July 2000; Volume 6, pp. 2441–2443. [Google Scholar]
- Bruzzone, L.; Prieto, D.F. An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images. IEEE Trans. Image Process. 2002, 11, 452–466. [Google Scholar] [CrossRef] [PubMed]
- Zhang, X.; Chen, J.; Meng, H. A novel SAR image change detection based on graph-cut and generalized gaussian model. IEEE Geosci. Remote Sens. Lett. 2013, 10, 14–18. [Google Scholar] [CrossRef]
- Li, W.; Chen, J.; Yang, P.; Sun, H. Multitemporal SAR images change detection based on joint sparse representation of pair dictionaries. In Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Munich, Germany, 22–27 July 2012; pp. 6165–6168. [Google Scholar]
- Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 3431–3440. [Google Scholar]
- Li, Y.; Zhang, H.; Shen, Q. Spectral–spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens. 2017, 9, 67. [Google Scholar] [CrossRef] [Green Version]
- Sellami, A.; Farah, M.; Farah, I.R.; Solaiman, B. Hyperspectral imagery classification based on semi-supervised 3-D deep neural network and adaptive band selection. Expert Syst. Appl. 2019, 129, 246–259. [Google Scholar] [CrossRef]
- Zhang, H.; Li, Y.; Jiang, Y.; Wang, P.; Shen, Q.; Shen, C. Hyperspectral classification based on lightweight 3-D-CNN with transfer learning. IEEE Trans. Geosci. Remote Sens. 2019, 57, 5813–5828. [Google Scholar] [CrossRef] [Green Version]
- Jiang, Y.; Li, Y.; Zhang, H. Hyperspectral Image Classification Based on 3-D Separable ResNet and Transfer Learning. IEEE Geosci. Remote Sens. Lett. 2019, 16, 1949–1953. [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. 2017, 27, 125–138. [Google Scholar] [CrossRef] [PubMed]
- Gao, F.; Dong, J.; Li, B.; Xu, Q. Automatic Change Detection in Synthetic Aperture Radar Images Based on PCANet. IEEE Geosci. Remote Sens. Lett. 2016, 13, 1792–1796. [Google Scholar] [CrossRef]
- Li, Y.; Peng, C.; Chen, Y.; Jiao, L.; Zhou, L.; Shang, R. A Deep Learning Method for Change Detection in Synthetic Aperture Radar Images. IEEE Trans. Geosci. Remote Sens. 2019, 57, 5751–5763. [Google Scholar] [CrossRef]
- Wang, R.; Zhang, J.; Chen, J.; Jiao, L.; Wang, M. Imbalanced Learning-Based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net. IEEE Geosci. Remote Sens. Lett. 2019, 16, 554–558. [Google Scholar] [CrossRef] [Green Version]
- Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2881–2890. [Google Scholar]
- Kim, J.H.; Lee, H.; Hong, S.J.; Kim, S.; Park, J.; Hwang, J.Y.; Choi, J.P. Objects Segmentation from High-Resolution Aerial Images Using U-Net With Pyramid Pooling Layers. IEEE Geosci. Remote Sens. Lett. 2018, 16, 115–119. [Google Scholar] [CrossRef]
- Cui, W.; Wang, F.; He, X.; Zhang, D.; Xu, X.; Yao, M.; Wang, Z.; Huang, J. Multi-Scale Semantic Segmentation and Spatial Relationship Recognition of Remote Sensing Images Based on an Attention Model. Remote Sens. 2019, 11, 1044. [Google Scholar] [CrossRef] [Green Version]
- 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]
- Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention; Springer: Berlin, Germany, 2015; pp. 234–241. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Cui, S.; Schwarz, G.; Datcu, M. A Benchmark Evaluation of Similarity Measures for Multitemporal SAR Image Change Detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016, 9, 1101–1118. [Google Scholar] [CrossRef] [Green Version]
Layer | Tensor | Layer | Tensor | Layer | Tensor |
---|---|---|---|---|---|
Input | 32 × 32 × 3 | ||||
Conv-3.1 | 32 × 32 × 32 | Conv-3.2 | 32 × 32 × 64 | Conv-3.3 | 32 × 32 × 128 |
MP-2 | 16 × 16 × 128 | ||||
SP-2 | 8 × 8 × 128 | Conv-1.1 | 8 × 8 × 32 | DeConv.1 | 16 × 16 × 32 |
SP-4 | 4 × 4 × 128 | Conv-1.2 | 4 × 4 × 32 | DeConv.2 | 16 × 16 × 32 |
SP-8 | 2 × 2 × 128 | Conv-1.3 | 2 × 2 × 32 | DeConv.3 | 16 × 16 × 32 |
SP-16 | 1 × 1 × 128 | Conv-1.4 | 1 × 1 × 32 | DeConv.4 | 16 × 16 × 32 |
Contact | 16 × 16 × 256 | Conv-3.4 | 16 × 16 × 64 | Conv-1.5 | 16 × 16 × 2 |
DeConv.5 | 32 × 32 × 2 |
Datasets | U-PCA-Net | S-PCA-Net | CNN | DNN | MSSP-Net |
---|---|---|---|---|---|
YR-A | 98.93% | 99.98% | 98.98% | 97.31% | 99.41% |
YR-B | 95.70% | 97.92% | 95.38% | 94.74% | 97.21% |
Sendai-A | 90.30% | 90.75% | 93.17% | 89.64% | 95.06% |
Sendai-B | 86.63% | 96.00% | 95.93% | 90.30% | 96.54% |
Datasets | S-PCA-Net | CNN | MSSP-Net |
---|---|---|---|
YR-A | 99.45% | 98.43% | 98.41% |
YR-B | 97.64% | 95.38% | 96.85% |
Sendai-A | 82.72% | 91.86% | 93.98% |
Sendai-B | 89.87% | 95.38% | 95.66% |
Methods | S-PCA-Net | CNN | MSSP-Net |
---|---|---|---|
Training | 180 min | 30 min | 20 min |
Testing | 5 min | 3 min | 20 s |
© 2020 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 (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, J.-W.; Wang, R.; Ding, F.; Liu, B.; Jiao, L.; Zhang, J. A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images. Remote Sens. 2020, 12, 1619. https://doi.org/10.3390/rs12101619
Chen J-W, Wang R, Ding F, Liu B, Jiao L, Zhang J. A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images. Remote Sensing. 2020; 12(10):1619. https://doi.org/10.3390/rs12101619
Chicago/Turabian StyleChen, Jia-Wei, Rongfang Wang, Fan Ding, Bo Liu, Licheng Jiao, and Jie Zhang. 2020. "A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images" Remote Sensing 12, no. 10: 1619. https://doi.org/10.3390/rs12101619