Composite Kernel Method for PolSAR Image Classification Based on Polarimetric-Spatial Information
Source abstract
Abstract
The composite kernel feature fusion proposed in this paper attempts to solve the problem of classifying polarimetric synthetic aperture radar (PolSAR) images. Here, PolSAR images take into account both polarimetric and spatial information. Various polarimetric signatures are collected to form the polarimetric feature space, and the morphological profile (MP) is used for capturing spatial information and constructing the spatial feature space. The main idea is that the composite kernel method encodes diverse information within a new kernel matrix and tunes the contribution of different types of features. A support vector machine (SVM) is used as the classifier for PolSAR images. The proposed approach is tested on a Flevoland PolSAR data set and a San Francisco Bay data set, which are in fine quad-pol mode. For the Flevoland PolSAR data set, the overall accuracy and kappa coefficient of the proposed method, compared with the traditional method, increased from 95.7% to 96.1% and from 0.920 to 0.942, respectively. For the San Francisco Bay data set, the overall accuracy and kappa coefficient of the proposed method increased from 92.6% to 94.4% and from 0.879 to 0.909, respectively. Experimental results verify the benefits of using both polarimetric and spatial information via composite kernel feature fusion for the classification of PolSAR images.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Synthetic Aperture Radar (SAR) Applications and Techniques · Remote-Sensing Image Classification · Advanced SAR Imaging Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Center for Information Geoscience, University of Electronic Science and Technology of China, Chengdu 611731, China
Huiding Technology Co. Ltd., Chengdu 611731, China
References (40)
Show source-provided references
1. A review of polarimetry in the context of synthetic aperture radar: Concepts and information extraction10.5589/m04-013 ↗
2. Lee, J.-S., and Pottier, E. (2009). Polarimetric Radar Imaging: From Basics to Applications, CRC Press.
3. Automated non-Gaussian clustering of polarimetric synthetic aperture radar images10.1109/TGRS.2011.2140120 ↗
4. A framework for classification of urban areas using polarimetric SAR images integrating color features and statistical model
5. Fan, K.T., Chen, Y.S., and Lin, C.W. (2015, January 26–31). Identification of rice paddy fields from multitemporal polarimetric SAR images by scattering matrix decomposition. Proceedings of the IEEE International Symposium on Geoscience and Remote Sensing IGARSS, Milan, Italy.10.1109/IGARSS.2015.7326498 ↗
6. A review of target decomposition theorems in radar polarimetry10.1109/36.485127 ↗
7. Spectral-Spatial Shared Linear Regression for Hyperspectral Image Classification10.1109/TCYB.2016.2533430 ↗
8. Polarimetric SAR Image Classification Using Multifeatures Combination and Extremely Randomized Clustering Forests
9. Laplacian eigenmaps based polarimetric dimensionality reduction for SAR image classification10.1109/TGRS.2011.2168532 ↗
10. Supervised graph embedding for polarimetric SAR image classification10.1109/LGRS.2012.2198612 ↗
11. Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields10.1109/TGRS.2011.2162649 ↗
12. Land-cover mapping by Markov modeling of spatial–contextual information in very-high-resolution remote sensing images10.1109/JPROC.2012.2211551 ↗
13. Graph-based feature selection for object-oriented classification in VHR airborne imagery10.1109/TGRS.2010.2054832 ↗
14. Superpixel-based classification with an adaptive number of classes for polarimetric SAR images10.1109/TGRS.2012.2203358 ↗
15. Multilevel local pattern histogram for SAR image classification10.1109/LGRS.2010.2058997 ↗
16. Discriminative Gabor feature selection for hyperspectral image classification10.1109/LGRS.2012.2191761 ↗
17. An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery10.1109/TGRS.2012.2202912 ↗
18. Soille, P. (2004). Morphological Image Analysis, Springer.10.1007/978-3-662-05088-0 ↗
19. Composite kernels for Urban-image classification10.1109/LGRS.2009.2015341 ↗
20. Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features10.1016/j.isprsjprs.2015.03.002 ↗
21. Molinier, M., Laaksonen, J., Rauste, Y., and Häme, T. (2007, January 23–28). Detecting changes in polarimetric SAR data with content-based image retrieval. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain.10.1109/IGARSS.2007.4423323 ↗
22. New decomposition of the radar target scattering matrix10.1049/el:19900979 ↗
23. An entropy based classification scheme for land applications of polarimetric SAR10.1109/36.551935 ↗
24. Four component scattering model for polarimetric SAR image decomposition10.1109/TGRS.2005.852084 ↗
25. A three-component scattering model for polarimetric SAR data10.1109/36.673687 ↗
26. Advances in mathematical morphology applied to geoscience and remote sensing10.1109/TGRS.2002.804618 ↗
27. Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles10.1109/TGRS.2008.922034 ↗
28. Medical image segmentation based on morphological reconstruction operation
29. Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations10.1109/TGRS.2004.841417 ↗
30. Composite kernels for hyperspectral image classification10.1109/LGRS.2005.857031 ↗
31. Vapnik, V.N. (2000). The Nature of Statistical Learning Theory, Springer. [2nd ed.].10.1007/978-1-4757-3264-1 ↗
32. A tutorial on support vector machines for pattern recognition10.1023/A:1009715923555 ↗
33. A Robust Regularization Path Algorithm for ν-Support Vector Classification10.1109/TNNLS.2016.2527796 ↗
34. Incremental Support Vector Learning for Ordinal Regression10.1109/TNNLS.2014.2342533 ↗
35. Kim, E. (2016, June 01). Every You Wanted to Know about the Kernel Trick (But Were Too Afraid to Ask). Available online: http://www.eric-kim.net/eric-kim-net/posts/1/kernel_trick.html.
36. Incremental learning for ν-Support Vector Regression10.1016/j.neunet.2015.03.013 ↗
37. (2016, June 01). LIBSVM Tools. Available online: http://www.csie.ntu.edu.tw/~cjlin/libsvmtools.
38. (2016, June 01). Mercer’s Theorem. Available online: https://en.wikipedia.org/wiki/Mercer%27s_theorem.
39. Multisource composite kernels for urban-image classification10.1109/LGRS.2009.2015341 ↗
40. (2016, June 01). Kappa Coefficients: A Critical Appraisal. Available online: http://john-uebersax.com/stat/kappa.htm.