volume | PIER Journals

Abstract

In order to improve the classification performance of Polarimetric Synthetic Aperture Radar (PolSAR) image by synthesizing various polarimetric features, a supervised manifold learning method is proposed in this paper for PolSAR feature extraction and classification. Under the umbrella of tensor algebra, the proposed method characterizes each pixel with a feature tensor by combining the high-dimensional feature information of all the pixels within its local neighborhood. The tensor representation mode integrates the polarimetric information and spatial information, which is beneficial for alleviating the influence of speckle noise. Then, the tensor discriminative locality alignment (TDLA) method is introduced to seek the multilinear transformation from the original polarimetric-spatial feature tensor to the low-dimensional feature. The label information of training samples is utilized during feature transformation and feature mapping; therefore, the discriminability of different classes can be well preserved. Based on the extracted features in the low-dimensional space, the SVM classifier is applied to achieve the final classification result. The experiments implemented on two real PolSAR data sets verify that the proposed method can extract the features with better stability and separability, and obtain superior classification results compared to several state-of-the-art methods.

1. Wang, Xuesong and Siwei Chen, "Polarimetric synthetic aperture radar interpretation and recognition: Advances and perspectives," Journal of Radars, Vol. 9, No. 2, 259-276, 2020.

2. Dong, Hongwei, Lingyu Si, Wenwen Qiang, Wuxia Miao, Changwen Zheng, Yuquan Wu, and Lamei Zhang, "A polarimetric scattering characteristics-guided adversarial learning approach for unsupervised PolSAR image classification," Remote Sensing, Vol. 15, No. 7, 1782, 2023.

3. Lee, Jong-Sen, Mitchell R. Grunes, and Ronald Kwok, "Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution," International Journal of Remote Sensing, Vol. 15, No. 11, 2299-2311, 1994.

4. Formont, Pierre, Frédéric Pascal, Gabriel Vasile, Jean-Philippe Ovarlez, and Laurent Ferro-Famil, "Statistical classification for heterogeneous polarimetric SAR images," IEEE Journal of Selected Topics in Signal Processing, Vol. 5, No. 3, 567-576, 2011.
doi:10.1109/JSTSP.2010.2101579

5. Cloude, Shane R. and Eric Pottier, "An entropy based classification scheme for land applications of polarimetric SAR," IEEE Transactions on Geoscience and Remote Sensing, Vol. 35, No. 1, 68-78, 1997.

6. Gou, Shuiping, Xin Qiao, Xiangrong Zhang, Weifang Wang, and Fangfang Du, "Eigenvalue analysis-based approach for POL-SAR image classification," IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, No. 2, 805-818, 2014.

7. Lee, Jong-Sen, Mitchell R. Grunes, Eric Pottier, and Laurent Ferro-Famil, "Unsupervised terrain classification preserving polarimetric scattering characteristics," IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, No. 4, 722-731, 2004.

8. Wang, Wei, Deliang Xiang, Jun Zhang, and Jianwei Wan, "Integrating contextual information with H/α decomposition for PolSAR data classification," IEEE Geoscience and Remote Sensing Letters, Vol. 13, No. 12, 2034-2038, 2016.
doi:10.1109/LGRS.2016.2622250

9. Zhang, Lamei, Siyu Zhang, Hongwei Dong, and Sha Zhu, "Robust classification of PolSAR images based on pinball loss support vector machine," Journal of Radars, Vol. 8, No. 4, 448-457, 2019.

10. Freeman, Anthony and Stephen L. Durden, "A three-component scattering model for polarimetric SAR data," IEEE Transactions on Geoscience and Remote Sensing, Vol. 36, No. 3, 963-973, 1998.

11. Yamaguchi, Yoshio, Toshifumi Moriyama, Motoi Ishido, and Hiroyoshi Yamada, "Four-component scattering model for polarimetric SAR image decomposition," IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, No. 8, 1699-1706, 2005.

12. Zhang, Lamei, Bin Zou, Hongjun Cai, and Ye Zhang, "Multiple-component scattering model for polarimetric SAR image decomposition," IEEE Geoscience and Remote Sensing Letters, Vol. 5, No. 4, 603-607, 2008.

13. Xiang, Deliang, Yifang Ban, and Yi Su, "Model-based decomposition with cross scattering for polarimetric SAR urban areas," IEEE Geoscience and Remote Sensing Letters, Vol. 12, No. 12, 2496-2500, 2015.

14. Quan, Sinong, Boli Xiong, Deliang Xiang, and Gangyao Kuang, "Derivation of the orientation parameters in built-up areas: With application to model-based decomposition," IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, No. 8, 4714-4730, 2018.

15. Huang, Xiayuan and Xiangli Nie, "Multi-view feature selection for PolSAR image classification via l₂,₁ sparsity regularization and manifold regularization," IEEE Transactions on Image Processing, Vol. 30, 8607-8618, 2021.

16. Licciardi, Giorgio, Ruggero Giuseppe Avezzano, Fabio Del Frate, Giovanni Schiavon, and Jocelyn Chanussot, "A novel approach to polarimetric SAR data processing based on nonlinear PCA," Pattern Recognition, Vol. 47, No. 5, 1953-1967, 2014.

17. Tu, Shang Tan, Jia Yu Chen, Wen Yang, and Hong Sun, "Laplacian eigenmaps-based polarimetric dimensionality reduction for SAR image classification," IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 1, 170-179, 2011.

18. Ainsworth, T. L. and J. S. Lee, "Optimal polarimetric decomposition variables-non-linear dimensionality reduction," IGARSS 2001, Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), Vol. 2, 928-930, 2001.

19. Ainsworth, Thomas L. and J.-S. Lee, "Polarimetric SAR image classification-exploiting optimal variables derived from multiple-image datasets," IGARSS 2004, 2004 IEEE International Geoscience and Remote Sensing Symposium, Vol. 1, 2004.

20. Huang, Xiayuan, Xiangli Nie, and Hong Qiao, "PolSAR image feature extraction via co-regularized graph embedding," Remote Sensing, Vol. 12, No. 11, 1738, 2020.

21. Shi, Lei, Lefei Zhang, Jie Yang, Liangpei Zhang, and Pingxiang Li, "Supervised graph embedding for polarimetric SAR image classification," IEEE Geoscience and Remote Sensing Letters, Vol. 10, No. 2, 216-220, 2013.

22. Lu, Haiping, Konstantinos N Plataniotis, and Anastasios N. Venetsanopoulos, "A survey of multilinear subspace learning for tensor data," Pattern Recognition, Vol. 44, No. 7, 1540-1551, 2011.

23. Deng, Yang-Jun, Heng-Chao Li, Kun Fu, Qian Du, and William J. Emery, "Tensor low-rank discriminant embedding for hyperspectral image dimensionality reduction," IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, No. 12, 7183-7194, 2018.

24. Wang, Qingwang and Yanfeng Gu, "A discriminative tensor representation model for feature extraction and classification of multispectral LiDAR data," IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, No. 3, 1568-1586, 2020.

25. Xu, Dong, Shuicheng Yan, Lei Zhang, Stephen Lin, Hong-Jiang Zhang, and Thomas S. Huang, "Reconstruction and recognition of tensor-based objects with concurrent subspaces analysis," IEEE Transactions on Circuits and Systems for Video Technology, Vol. 18, No. 1, 36-47, 2008.

26. Renard, Nadine and Salah Bourennane, "Dimensionality reduction based on tensor modeling for classification methods," IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 4, 1123-1131, 2009.

27. Zhang, Liangpei, Lefei Zhang, Dacheng Tao, and Xin Huang, "Tensor discriminative locality alignment for hyperspectral image spectral-spatial feature extraction," IEEE Transactions on Geoscience and Remote Sensing, Vol. 51, No. 1, 242-256, 2013.

28. Tao, Mingliang, Feng Zhou, Yan Liu, and Zijing Zhang, "Tensorial independent component analysis-based feature extraction for polarimetric SAR data classification," IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, No. 5, 2481-2495, 2015.

29. Huang, Xiayuan, Hong Qiao, Bo Zhang, and Xiangli Nie, "Supervised polarimetric SAR image classification using tensor local discriminant embedding," IEEE Transactions on Image Processing, Vol. 27, No. 6, 2966-2979, 2018.

30. Kolda, Tamara G. and Brett W. Bader, "Tensor decompositions and applications," SIAM Review, Vol. 51, No. 3, 455-500, 2009.
doi:10.1137/07070111X

31. Cloude, Shane Robert, "Target decomposition theorems in radar scattering," Electronics Letters, Vol. 21, 22-24, 1985.
doi:10.1049/el:19850018

32. Van Zyl, Jakob J., "Unsupervised classification of scattering behavior using radar polarimetry data," IEEE Transactions on Geoscience and Remote Sensing, Vol. 27, No. 1, 36-45, 1989.

33. Krogager, E., "New decomposition of the radar target scattering matrix," Electronics Letters, Vol. 18, No. 26, 1525-1527, 1990.
doi:10.1049/el:19900979

34. Huynen, Jean Richard, "Phenomenological theory of radar target," Technology University Delft, 1970.

35. An, Wentao, Chunhua Xie, Xinzhe Yuan, Yi Cui, and Jian Yang, "Four-component decomposition of polarimetric SAR images with deorientation," IEEE Geoscience and Remote Sensing Letters, Vol. 8, No. 6, 1090-1094, 2011.

36. Van der Maaten, Laurens and Geoffrey Hinton, "Visualizing data using t-SNE," Journal of Machine Learning Research, Vol. 9, No. 11, 2579-2605, 2008.

Dr. Hui Fan

Dr. Wei Wang

Dr. Sinong Quan

Dr. Xi He

Dr. Jie Deng