一种面向高异质性极化SAR图像的等效视数非监督估计方法

胡丁晟; 仇晓兰; StianN.Anfinsen; 雷斌

doi:10.11999/JEIT170014

一种面向高异质性极化SAR图像的等效视数非监督估计方法

doi: 10.11999/JEIT170014

基金项目:

国家自然科学基金(61331017), 高分三号共性关键技术(30-Y20A12-9004-15/16, 03-Y20A11-9001-15/16)

计量
- 文章访问数: 1495
- HTML全文浏览量: 134
- PDF下载量: 394
- 被引次数: 0
出版历程
- 收稿日期: 2017-01-03
- 修回日期: 2017-03-21
- 刊出日期: 2017-10-19

Unsupervised Estimation of the Equivalent Number of Looks in PolSAR Image with High Heterogeneity

Funds:

The National Natural Science Foundation of China (61331017), The GF-3 High-Resolution Earth Observation System (30-Y20A12-9004-15/16, 03-Y20A11-9001-15/16)

摘要

摘要: 等效视数(ENL)是极化SAR多视数据统计模型的重要参数。而一些极化SAR图像的自动化应用中，需要在没有人工干预下实现ENL非监督估计。现有的等效视数非监督估计方法在异质程度较高的图像中就难以得到准确估计结果。针对这一问题，该文提出一种将混合区域剔除与纹理信息聚类相结合的等效视数非监督估计方法，有效地减弱了地物混合及纹理两类主要异质因素对估计结果的影响。通过仿真数据和不同复杂度的实际图像验证了该方法的有效性。
- 极化SAR /
- 乘积模型 /
- 异质性 /
- 等效视数 /
- 非监督估计
Abstract: Equivalent Number of Looks (ENL) is an important parameter in statistical modelling of multi-look Polarimetric SAR (PolSAR) data. In some automated applications of PolSAR images, it is necessary to estimate the ENL in an unsupervised way without any manual intervention. The existing unsupervised estimation of ENL can not obtain accurate estimates for the images with high heterogeneity. To address this issue, a novel unsupervised estimation method is proposed here. It combines the mixture elimination and clustering based on texture, which reduces the effect of two main heterogeneity factors, mixture and texture. The validity of this method is evaluated with simulated and real data of different complexity.
- Polarimetric SAR (PolSAR) /
- Product model /
- Heterogeneity /
- Equivalent Number of Looks (ENL) /
- Unsupervised estimation

HTML全文

参考文献(20)

XU Qiao, CHEN Qihao, YANG Shuai, et al. Superpixel- based classification using K distribution and spatial context for polarimetric SAR images[J]. Remote Sensing, 2016, 8(8): 619. doi: 10.3390/rs8080619.

DOULGERIS A. An automatic U distribution and Markov random field segmentation algorithm for PolSAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(4): 1819-1827. doi: 10.1109/TGRS.2014.2349575.

LIU Fang, SHI Junfei, JIAO Lichen, et al. Hierarchical semantic model and scattering mechanism based PolSAR image classification[J]. Pattern Recognition, 2016, 59: 325-342. doi: 10.1016/j.patcog.2016.02.020.

AKBARI V, ANFINSEN S, DOULGERIS A, et al. Polarimetric SAR change detection with the complex Hotelling Lawley trace statistic[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(7): 3953-3966. doi: 10.1109/TGRS.2016.2532320.

LIU Meng, ZHANG Hong, WANG Chao, et al. Polarimetric synthetic aperture radar change detection for specific land cover types[J]. International Journal of Digital Earth, 2016, 8(4): 334-344. doi: 10.1080/17538947.2013.872702.

ANFINSEN S, DOULGERIS A, and ELTOFT T. Estimation of the equivalent number of looks in polarimetric synthetic aperture radar imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(11): 3795-3809. doi: 10.1109/ TGRS.2009.2019269.

LIU Tao, CUI Haogui, XI Zemin, et al. Texture-invariant estimation of equivalent number of looks based on trace moments in polarimetric radar imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(6): 1129-1133. doi: 10.1109/LGRS.2013.2288097.

CUI Yi, ZHOU Guangyi, YANG Jian, et al. Unsupervised estimation of the equivalent number of looks in SAR images [J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(4): 710-714. doi: 10.1109/LGRS.2010.2102335.

LEE J and HOPPEL K. Noise modeling and estimation of remotely-sensed images[C]. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Vancouver, 1989: 1005-1008. doi: 10.1109/IGARSS.1989.579061.

LEE J, HOPPEL K, and MANGO S. Unsupervised estimation of speckle noise in radar images[J]. International Journal of Imaging Systems and Technology, 1992, 4(4): 298-305. doi: 10.1002/ima.1850040409.

FOUCHER S, BOUCHER J, and BENIE G. Maximum likelihood estimation of the number of looks in SAR images in microwaves, radar and wireless communications[C]. 13th International Conference on MIKON-2000, 2000, 2: 657-660. doi: 10.1109/MIKON.2000.914020.

HU Dingsheng, ANFINSEN S, TAO Ding, et al. Investigation of variations in the equivalent number of looks for polarimetric channels[C]. International Workshop on Science and Applications SAR Polarimetry and Polarimetric Interferometry, Frascati, Rome, 2015.

OLIVER C and QUEGAN S. Understanding Synthetic Aperture Radar Images[M]. Raleigh, NC 27613: SciTech Publishing, Inc., 2004: 75-154.

FREITAS C, FRERY A, and CORREIA A. The polarimetric G distribution for SAR data analysis[J]. Environmetrics, 2005, 16(1): 13-31. doi: 10.1002/env.658.

ANFINSEN S. Statistical analysis of multilook polarimetric radar images with the Mellin transform[D]. [Ph.D. dissertation], University of Tromso, 2010.

LEE J, SCHULER D, LANG R, et al. K-distribution for multi-look processed polarimetric SAR imagery[C]. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Pasadena, 1994: 2179-2181. doi: 10.1109/ IGARSS.1994.399685.

BOMBRUN L and BEAULIEU J. Fisher distribution for texture modeling of polarimetric SAR data[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(3): 512-516. doi: 10.1109/LGRS.2008.923262.

ANFINSEN S and ELTOFT T. Application of the matrix- variate mellin transform to analysis of polarimetric radar images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(6): 2281-2295. doi: 10.1109/TGRS.2010. 2103945.

ZHU Tingting, LI Fei, HEYGSTER G, et al. Antarctic sea-ice classification based on conditional random fields from RADARSAT-2 dual-polarization satellite images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(6): 2451-2467. doi: 10.1109/ JSTARS.2016.2551318.

FORS A, BREKKE C, DOULGERIS A, et al. Late-summer sea ice segmentation with multi-polarisation SAR features in C and X band[J]. The Cryosphere, 2016, 10(1): 401-415. doi: 10.5194/tc-10-401-2016.

施引文献

资源附件(0)

访问统计