The Unsupervised Classification Method with KummerU Distribution of High Resolution PolSAR Images

ZHU Teng; HE Hanwu; HUANG Tielan; ZHANG Po

doi:10.6054/j.jscnun.2020013

Journal of South China Normal University (Natural Science Edition) > 2020 > 52(1): 85-90. > DOI: 10.6054/j.jscnun.2020013

ZHU Teng, HE Hanwu, HUANG Tielan, ZHANG Po. The Unsupervised Classification Method with KummerU Distribution of High Resolution PolSAR Images[J]. Journal of South China Normal University (Natural Science Edition), 2020, 52(1): 85-90. DOI: 10.6054/j.jscnun.2020013

Citation:

PDF (2842 KB)

The Unsupervised Classification Method with KummerU Distribution of High Resolution PolSAR Images

ZHU Teng¹,
HE Hanwu^{2, 3},
HUANG Tielan^1, ,,
ZHANG Po³

1.
School of Surveying and Remote Sensing Information, Guangdong Polytechnic of Industry and Commerce, Guangzhou 510510, China
2.
School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou 510039, China
3.
School of Computer and Information Engineering, Guangdong Polytechnic of Industry and Commerce, Guangzhou 510510, China

More Information

Received Date: October 16, 2019
Available Online: March 21, 2021

Graphical Abstract

Abstract

Abstract

The feature distribution of high-resolution polarimetric SAR data no longer conforms to the hypothesis of homogeneous region, which leads to the decline of unsupervised classification accuracy of polarimetric SAR image based on statistical distribution. A novel unsupervised classification algorithm for PolSAR image is proposed by embedding the widely applicable KummerU distribution into the Particle Swarm Optimization clustering algorithm. Firstly, the PolSAR data was classified based on the polarimetric statistical characteristics. Then combining the PolSAR statistical characteristics with PSO algorithm, a further solution to the clustering centers was found with the PSO-KummerU algorithm. In the part of the classification criteria, KummerU distance was used to replace the traditional Wishart distance to improve the classification result. Finally, 3 kinds of unsupervised classification methods (H/α-Wishart, PSO-Wishart, PSO-KummerU) were used for the comparison experiments. The experimental results show that the visual effect of PSO-KummerU clustering method based on KummerU distribution is significantly improved compared with the Wishart distance clustering method, and the overall classification accuracy is improved by more than 14%.
- KummerU distribution,
- polarimetric SAR,
- high resolution,
- particle swarm optimization algorithm,
- unsupervised classification

FullText(HTML)

References (19)

References

[1]	马姣娇, 牛安逸, 徐颂军, 等.基于地学信息图谱的珠海淇澳岛土地利用格局分析[J].华南师范大学学报(自然科学版), 2018, 50(2):77-85. http://journal-n.scnu.edu.cn/article/id/4099 MA J J, NIU A Y, XIU S J, et al. Analysis of land use pattern based on Geo-information TUPU in Zhuhai Qi'ao Island[J]. Journal of South China Normal University(Natural Science Edition), 2018, 50(2):77-85. http://journal-n.scnu.edu.cn/article/id/4099
[2]	YU P, QIN A K, CLAUSI D A. Unsupervised polarimetric SAR image segmentation and classification using region growing with edge penalty[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(4):1302-1317. doi: 10.1109/TGRS.2011.2164085
[3]	LEE J S, GRUNES M R, AINSWORTH T L. Unsupervised classification using polarimetric decomposition and the complex Wishart classifier[J]. IEEE Transactions on Geo-science and Remote Sensing, 1999, 37(5):2249-2258. doi: 10.1109/36.789621
[4]	杨杰, 郎丰铠, 李德仁.一种利用Cloude-Pottier分解和极化白化滤波的全极化SAR图像分类算法[J].武汉大学学报(信息科学版), 2011, 36(1):104-107. http://www.cnki.com.cn/Article/CJFDTotal-WHCH201101023.htm YANG J, LANG F K, LI D R. An unsupervised wishart classification for fully polarimetric SAR image based on cloude-pottier decomposition and polarimetric whitening filter[J]. Geomatics and Information Science of Wuhan University, 2011, 36(1):104-107. http://www.cnki.com.cn/Article/CJFDTotal-WHCH201101023.htm
[5]	TISON C, NICOLAS J M, TUPIN F, et al. A new statistical model for markovian classification of urban areas in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(10):2046-2057. doi: 10.1109/TGRS.2004.834630
[6]	BOMBRUN L, VASILE G, GAY M, et al. Hierarchical segmentation of polarimetric SAR images using heterogeneous clutter models[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(2):726-737. doi: 10.1109/TGRS.2010.2060730
[7]	HARANT O, BOMBRUN L, GAY M, et al. Segmentation and classification of polarimetric SAR data based on the KummerU distribution[C]//Proceedings of the Fourth International Workshop on Science and Application of SAR Polarimetry & Polarimetric Interferometry Poiinsar. Frascati, Italy: [s.n.], 2009: 668-673.
[8]	邹鹏飞, 李震, 田帮森.高分辨率极化SAR图像水平集分割[J].中国图象图形学报, 2014, 19(12):1829-1835. doi: 10.11834/jig.20141215 ZOU P F, LI Z, TIAN B S. High-resolution PolSAR image level set segmentation[J]. Journal of Image and Graphics, 2014, 19(12):1829-1835. doi: 10.11834/jig.20141215
[9]	石俊飞, 林耀海, 刘璐.基于KummerU和MRF的极化SAR分类算法研究[J].火控雷达技术, 2015, 44(4):51-54. doi: 10.3969/j.issn.1008-8652.2015.04.012 SHI J F, LIN Y H, LIU L. Study on polarmetric SAR classification algorithm based on KummerU and MRF[J]. Fire Control Radar Technology, 2015, 44(4):51-54. doi: 10.3969/j.issn.1008-8652.2015.04.012
[10]	管翔辉, 秦先祥.一种基于KummerU分布的SAR图像统计建模方法[J].科学技术与工程, 2016, 16(28):235-240. doi: 10.3969/j.issn.1671-1815.2016.28.043 GUAN X H, QIN X X. A statistical modeling method for SAR images based on KummerU distribution[J]. Science Technology and Engineering, 2016, 16(28):235-240. doi: 10.3969/j.issn.1671-1815.2016.28.043
[11]	李林宜, 李德仁.粒子群优化算法在遥感影像增强中的应用[J].测绘科学技术学报, 2010, 27(2):116-119. doi: 10.3969/j.issn.1673-6338.2010.02.011 LI L Y, LI D R. Research on particle swarm optimization in remote sensing image enhancement[J]. Journal of Geomatics Science and Technology, 2010, 27(2):116-119. doi: 10.3969/j.issn.1673-6338.2010.02.011
[12]	YI H, YANG J, LI P, et al. A PolSAR image segmentation algorithm based on scattering characteristics and the revised wishart distance[J]. Sensors, 2018, 18(7):2262-2271. doi: 10.3390/s18072262
[13]	ZHANG Y, ZOU H X, LUO T C, et al. A fast superpixel segmentation algorithm for PolSAR images based on edge refinement and revised wishart distance[J]. Sensors, 2016, 16(10):1687-1695. doi: 10.3390/s16101687
[14]	WANG W, XIANG D L, BAN Y F, et al. Superpixel segmentation of polarimetric SAR images based on integrated distance measure and entropy rate method[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(9):1-14. doi: 10.1109/JSTARS.2017.2751699
[15]	秦先祥.基于广义Gamma分布的SAR图像统计建模及应用研究[D].长沙: 国防科学技术大学, 2015. http://cdmd.cnki.com.cn/Article/CDMD-90002-1017834267.htm QIN X X. Research on statistical modeling of SAR images and its application based on generalized Gamma distribution[D]. Changsha: National University of Defense Technology, 2015. http://cdmd.cnki.com.cn/Article/CDMD-90002-1017834267.htm
[16]	KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks. Perth, Australia: IEEE, 1995: 1942-1948.
[17]	CAI J H, ZHANG J F, ZHAO X J. Research on two-stage fuzzy clustering method for spectrum data based on PSO[J]. Spectroscopy and Spectral Analysis, 2009, 29(4):1137-1141. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gpxygpfx200904061
[18]	AMOON M, REZAI-RAD G A, DALIRI M R. PSO-based optimal selection of zernike moments for target discrimination in high-resolution SAR imagery[J]. Journal of the Indian Society of Remote Sensing, 2014, 42(3):483-493. doi: 10.1007/s12524-013-0344-6
[19]	ZHU T, YU J, LI X J, et al. PolSAR image classification using fuzzy logic in the H/α-Wishart algorithm[J]. Journal of Applied Remote Sensing, 2015, 9(1):096098/1-18.

Cited By

Get Citation

PDF

XML

Article views (1923) PDF downloads (39)

Turn off MathJax

Article Contents

Abstract

References

The Unsupervised Classification Method with KummerU Distribution of High Resolution PolSAR Images

Abstract

References

Catalog

Export File

Citation

Format

Content