一種基于多極化散射機(jī)理的極化SAR圖像艦船目標(biāo)檢測方法

文偉; 曹雪菲; 張學(xué)峰; 陳渤; 王英華; 劉宏偉

doi:10.11999/JEIT160204

一種基于多極化散射機(jī)理的極化SAR圖像艦船目標(biāo)檢測方法

doi: 10.11999/JEIT160204 cstr: 32379.14.JEIT160204

基金項目:

國家杰出青年科學(xué)基金(61525105)，國家自然科學(xué)基金(61201292, 61322103, 61372132)，全國優(yōu)秀博士學(xué)位論文作者專項資金(FANEDD-201156)，陜西省自然科學(xué)基礎(chǔ)研究計劃(2016JQ- 6048)，航空科學(xué)基金(20142081009)和航空電子系統(tǒng)射頻綜合方針航空科技重點(diǎn)實驗室基金聯(lián)合資助，上海航天科技創(chuàng)新基金(SAST- 2015009)

計量
- 文章訪問數(shù): 1423
- HTML全文瀏覽量: 118
- PDF下載量: 540
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-03-03
- 修回日期: 2016-08-23
- 刊出日期: 2017-01-19

PolSAR Ship Detection Method Based on Multiple Polarimetric Scattering Mechanisms

Funds:

The National Science Fund for Distinguished Young Scholars (61525105), The National Natural Science Foundation of China (61201292, 61322103, 61372132), The Program for New Century Excellent Talents in University (FANEDD-201156), The Natural Science Basic Research Plan in Shaanxi Province of China (2016JQ6048), The Aviation Science Fund (20142081009) and Key Laboratory Fund of RF Integrated Laboratory in Avionics System, Shanghai Aerospace Science and, Technology Innovation Fund (SAST2015009)

摘要

摘要: 針對基于單一極化特性增強(qiáng)的極化SAR圖像目標(biāo)檢測方法的缺陷，該文將DP(Dirichlet Process)混合隱變量SVM模型(DPLVSVM)應(yīng)用于極化SAR圖像艦船目標(biāo)檢測，提出一種基于多極化散射機(jī)理的檢測方法。該方法通過聯(lián)合Dirichlet過程混合與Bayes SVM模型，將信號空間劃分成若干局部區(qū)域，然后在每一局部區(qū)域?qū)W習(xí)一個獨(dú)立的極化檢測器，并將各局部檢測器進(jìn)行組合實現(xiàn)全局多極化散射機(jī)理的目標(biāo)檢測。模型采用非參數(shù)化Bayes方法自動確定局部區(qū)域數(shù)量，在完全Bayes框架下，將局部區(qū)域劃分及檢測器學(xué)習(xí)進(jìn)行聯(lián)合優(yōu)化，保證了各局部區(qū)域樣本的可分性。另外，為了降低極化特征冗余，該文進(jìn)一步提出帶特征選擇功能的稀疏提升DP混合隱變量SVM模型(SPDPLVSVM)，提高模型的推廣能力。該模型由于采用共軛先驗分布，因而可以利用Gibbs采樣方法進(jìn)行高效求解。在RADARSAT-2數(shù)據(jù)上進(jìn)行的實驗驗證了所提方法的有效性。
- 極化SAR /
- 目標(biāo)檢測 /
- Dirichlet過程混合模型 /
- Bayes SVM /
- 特征選擇
Abstract: Considering the shortcoming of detection method based on polarimetric contrast enhanced with single polarimetric scattering mechanism, a PolSAR detection method based on multiple polarimetric mechanisms called Dirichlet Process mixture of Latent Variable SVM (DPLVSVM) is proposed. By assembling a set of local polarimetric detectors that based on single polarimetric scattering mechanism, a global multiple polarimetric scattering mechanisms detector is obtained. With a fully Bayes treatment, DPLVSVM learns the clustering and the local detectors jointly. Taking the advantage of Bayes nonparametric, DPLVSVM handles the model selection problem flexibly. Further, in order to reduce the redundancy of polarimetric feature and improve the model generalization, a model with feature selection, Sparsity-Promoting Dirichlet Process mixture of Latent Variable SVM (SPDPLVSVM), is proposed. Thanks to the conjugate property, the parameters in both of models can be inferred efficiently via the Gibbs sampler. Finally, the proposed models on RADARSAR-2 dataset is implemented to validate their effectiveness.
- Polarimetric SAR /
- Target detection /
- Dirichlet process mixture model /
- Bayes SVM /
- Feature selection

HTML全文

參考文獻(xiàn)(31)

CRISP D J. The state of the art in ship detection in synthetic aperture radar imagery[R]. Technical Report DSTO-RR-0272, DSTO Information Sciences Laboratory, South Australia, Australia, 2004.

TOUZI R, CHARBONNEAU F, HAWKINS R K, et al. Ship- sea contrast optimization when using polarimetric SARS[C]. IEEE 2001 International Conference on Geoscience and Remote Sensing Symposium, Sydney, Australia, 2001: 426-428.

邢艷肖, 張毅, 李寧, 等. 一種聯(lián)合特征值信息的全極化SAR圖像監(jiān)督分類方法[J]. 雷達(dá)學(xué)報, 2016, 5(2): 217-227. doi: 10.12000/JR16019.

XING Yanxiao, ZHANG Yi, LI Ning, et al. Polarimetric SAR image supervised classification method integrating eigenvalues[J]. Journal of Radars, 2016, 5(2): 217-227 doi: 10.12000/JR16019.

ARMANDO Marino. A notch filter for ship detection with polarimetric SAR data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6(3): 1219-1232. doi: 10.1109/JSTARS.2013.2247741.

YEREMY M, CAMPBELL J W M, MATTAR K, et al. Ocean surveillance with polarimetric SAR[J]. Canadian Journal of Remote Sensing, 2001, 27: 328-344. doi: 10.1080/ 07038992.

NOVAK L M, MICHAEL B S, and MICHELE J C. Studies of target detection algorithms that use polarimetric radar data[J]. IEEE Transactions on Aerospace and Electronic Systems, 1989, 25(2): 150-165. doi: 10.1109/7.18677.

NOVAK L M, BURL M C, and IRVING W W. Optimal polarimetric processing for enhanced target detection[J]. IEEE Transactions on Aerospace and Electronic Systems, 1993, 29(1): 234-244. doi: 10.1109/NTC.1991.147989.

YANG Jian, ZHANG Hongji, and YOSHIO Yamaguchi. GOPCE-based approach to ship detection[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(6): 1089-1093. doi: 10.1109/LGRS.2012.2191611.

LEE Jongsen, HOPPEL K W, MANGO S A, et al. Intensity and phase statistics of multilook polarimetric and interferometric SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 1994, 32(5): 1017-1028. doi: 10.1109/36.312890.

WANG Yinghua and LIU Hongwei. PolSAR ship detection based on superpixel-level scattering mechanism distribution features[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(8): 1780-1784. doi: 10.1109/LGRS.2015.2425873.

陳博, 王爽, 焦李成, 等. 利用0-1矩陣分解集成的極化SAR圖像分類[J]. 電子與信息學(xué)報, 2015, 37(6): 1495-1501. doi: 10.11999/JEIT141059.

CHEN Bo, WANG Shuang, JIAO Licheng, et al. Polarimetric SAR image classification via weighted ensemble based on 0-1 matrix decomposition[J]. Journal of Electronics Information Technology, 2015, 37(6): 1495-1501. doi: 10.11999/JEIT141059.

崔浩貴, 劉濤, 蔣宇中, 等. 基于混合矩的極化SAR圖像K分布模型參數(shù)估計新方法[J]. 電子與信息學(xué)報, 2015, 37(2): 328-333. doi: 10.11999/JEIT140551.

CUI Haogui, LIU Tao, JIANG Yuzhong, et al. Parameter estimation for the K-distribution in PolSAR imagery based on hybrid moments[J]. Journal of Electronics Information Technology, 2015, 37(2): 328-333. doi: 10.11999/JEIT140551.

楊學(xué)志, 葉銘, 吳克偉, 等. 結(jié)構(gòu)保持的雙邊濾波極化SAR圖像降噪[J]. 電子與信息學(xué)報, 2015, 37(2): 268-275. doi: 10.11999/JEIT140199.

YANG Xuezhi, YE Ming, WU Kewei, et al. Speckle reduction for PolSAR image based on structure preserving Bilateral filtering[J]. Journal of Electronics Information Technology, 2015, 37(2): 268-275. doi: 10.11999/JEIT140199.

劉璐, 劉帥, 焦李成, 等. 采用聯(lián)合域字典稀疏表示的極化SAR圖像分類[J]. 華中科技大學(xué)學(xué)報(自然科學(xué)版), 2016, 44(2): 81-85. doi: 10.13245/j.hust.160217.

LIU Lu, LIU Shuai, JIAO Licheng, et al. Combined dictionary learning based sparse representation for PolSAR image classification[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2016, 44(2): 81-85. doi: 10.13245/j.hust.160217.

RINGROSE R and HARRIS N. Ship detection using polarimetric SAR data[C]. Proceedings of SAR Workshop: CEOS Committee on Earth Observation Satellites; Working Group on Calibration and Validation, Toulouse, France, 2000, 450: 687-691.

HIROYUKI W, YUTA M, and KAZUKI N. Sea ice detection in the sea of Okhotsk using POLSAR and MODIS data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6(3): 1516-1523. doi: 10.1109/JSTARS.2013.2258327.

WANG Na, SHI Gongtao, LIU Li, et al. Plarimetric SAR target detection using the reflection symmetry[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(6): 1104-1108. doi: 10.1109/LGRS.2012.2189548.

文偉, 王英華, 馮博, 等. 基于監(jiān)督非相干字典學(xué)習(xí)的極化SAR圖像艦船目標(biāo)檢測[J]. 自動化學(xué)報, 2015, 41(11): 1926-1940. doi: 10.16383/j.aas.2015.c140530.

WEN Wei, WANG Yinghua, FENG Bo, et al. Supervise incoherent dictionary learning for ship detection with PolSAR images[J]. Acta Automatica Sinica, 2015, 41(11): 1926-1940. doi: 10.16383/j.aas.2015.c140530.

KHALID E D, PETER M, DESMOND P, et al. Target detection in synthetic aperture radar imagery: A state of the art survey[J]. Journal of Applied Remote Sensing, 2013, 7(1): 071598. doi: 10.1117/1.JRS.7.071598.

張學(xué)峰, 陳渤, 王鵬輝, 等. 一種基于Dirichlet過程隱變量支撐向量機(jī)模型的目標(biāo)識別方法[J]. 電子與信息學(xué)報, 2015, 37(1): 29-36 doi: 10.11999/JEIT140129.

ZHANG Xuefeng, CHEN Bo, WANG Penghui, et al. A target recognition method based on Dirichlet process latent variable support vector machine model[J]. Journal of Electronics Information Technology, 2015, 37(1): 29-36 doi: 10.11999/ JEIT140129.

趙一博, 秦先祥, 鄒煥新. 基于目標(biāo)分解和SVM的極化SAR圖像分類方法[J]. 航天返回與遙感, 2013, 34(2): 50-56.

ZHAO Yibo, QIN Xianxiang, and ZOU Huanxin. Classification of polarimetric SAR image based on target decomposition and SVM[J]. Journal of Spacecraft Recovery Remote Sensing, 2013, 34(2): 50-56.

XU Danlei, DU Lan, LIU Hongwei, et al. Bayesian classifier for sparsity-promoting feature selection[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2015, 29(6): 1-28. doi: 10.1142/S0218001415500226.

LEE J S, MITCHELL R G, THOMAS L A, et al. Unsupervised classification using polarimetric decomposition and the complex wishart classifier[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(5): 2249-2258. doi: 10.1109/36.789621.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計