HAN Jinghong,WANG Haijiang.PolSAR Image Classification based on MV and Wishart Distance[J].Journal of Chengdu University of Information Technology,2019,(01):31-34.[doi:10.16836/j.cnki.jcuit.2019.01.007]
基于MV与Wishart距离的极化SAR图像分类
- Title:
- PolSAR Image Classification based on MV and Wishart Distance
- 文章编号:
- 2096-1618(2019)01-0031-04
- Keywords:
- PolSAR image; SLIC; classification; Majority Voting; superpixel
- 分类号:
- TN911.73
- 文献标志码:
- A
- 摘要:
- 传统的极化SAR图像分类都是基于像素点的分类,准确率普遍不高。为提高极化SAR图像的分类准确率,提出了一种基于超像素的分类算法。首先,对极化SAR数据进行预处理,并提取高维特征空间。然后,利用降维算法对高维特征空间降维,减少特征空间的冗余信息,提取主要信息。利用SLIC算法对Pauli分解后的极化SAR图像进行超像素分割。最后,以超像素为单元,利用多数投票原则与Wishart分类相结合的方法对超像素进行分类。实验结果表明该算法对极化SAR图像分类能够得到更好的分类效果。
- Abstract:
- Traditional polarimetric SAR image classification is based on pixel point classification, and the accuracy is generally not high. In order to improve the classification accuracy of polarimetric SAR image, a classification algorithm based on superpixel is proposed. Firstly, the polarimetric SAR data is preprocessed and the high dimension feature space is extracted. Then, the dimension reduction algorithm is used to reduce the dimension of the high dimension feature space because it can reduce the redundant information in the feature space and extract the main information. Next, the SLIC algorithm is used to segment the polarimetric SAR image after Pauli decomposition. Finally, the superpixel instead of pixel is used as the processing unit, and a combination of majority voting algorithm and Wishart classification algorithm is used to class the superpixels. The experimental results show that the proposed algorithm can achieve better classification result in classifying polarimetric SAR image.
参考文献/References:
[1] Huynen J R.Phenomenological theory of radar targets[J].Electromagnetic Scattering,1978:653-712.
[2] Freeman A,Durden S L.A three-component scattering model for polarimetric SAR data[J].IEEE Transactions on Geoscience&Remote Sensing,1998,36(3):963-973.
[3] Cloude S R. Group theory and polarisation algebra[J].1986,75:26-36.
[4] Krogager E.New decomposition of the radar target scattering matrix[J].Electronics Letters,2002,26(18):1525-1527.
[5] Yong J,Zhang X L,Shi J.Unsupervised classification of polarimetric SAR Image by Quad-tree Segment and SVM[C].Synthetic Aperture Radar,2007.Apsar 2007.Asian and Pacific Conference on.IEEE,2008:480-483.
[6] Fu Z L,Zhang W Y,Meng Q X.SAR image classification based on SVM with fusion of gray scale and texture features[J].Journal of Applied Sciences,2012,30(5):498-504.
[7] Chen C T,Chen K S,Lee J S.The use of fully polarimetric information for the fuzzy neural classification of SAR images[J].IEEE Transactions on Geoscience & Remote Sensing,2003,41(9):2089-2100.
[8] Zhang T,Sun J T,Yang R L.Fuzzy classification of polarimetric SAR images[J].Systems Engineering & Electronics,2011,33(5):1036-1039.
[9] Zhang Z,Wang H,Xu F,et al.Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification[J].IEEE Transactions on Geoscience & Remote Sensing,2017,99:1-12.
[10] Zhao J,Guo W,Cui S,et al.Convolutional Neural Network for SAR image classification at patch level[C].Geoscience and Remote Sensing Symposium.IEEE,2016:945-948.
备注/Memo
收稿日期:2018-10-10