基于机器学习的SAIR图像反演和目标检测方法研究
|
摘要
利用综合孔径微波辐射计（SAIR）系统进行目标探测，具有隐蔽性好、可全天时工作、基本不受天气和战场烟尘环境影响等优点，并且无需扫描即可瞬时高分辨成像，因而成为目标探测领域的研究热点。
高质量亮温图像的实时获取和有效的目标检测算法是开展综合孔径微波辐射计目标探测研究的关键技术与难点。本文以机器学习理论为基础，从研究SAIR亮温图像反演问题的本质出发，详细地分析了SAIR反演问题的模型选择问题，提出了实时高质量的SAIR亮温图像重建方法，并结合综合孔径微波辐射计反演图像的统计特性，研究适用于综合孔径微波辐射计探测空中目标的背景抑制及目标检测方法。主要研究内容包括：
从统计学的角度分析了现有的SAIR亮温反演方法，指出了现有SAIR反演方法的本质问题为机器学习的模型选择问题；并指出了现有的亮温反演方法在最优正则化参数的确定以及实际风险最小化的困难。
从贝叶斯框架分析了现有的SAIR反演方法，指出了现有SAIR反演方法中关于亮温分布和可见度采样的潜在统计特性。在分析SAIR反演问题的统计模型的基础上，提出了一种基于贝叶斯回归估计的SAIR亮温图像实时反演方法。基于贝叶斯模型选取原理，将先验概率引入至SAIR亮温图像反演的学习过程中，建立了SAIR反演问题的贝叶斯学习模型；推导了模型参数的估计方法。与现有的SAIR方法相比，该方法能在保证反演性能不下降的情况下实时地进行亮温图像重建。
分析了SAIR亮温反演问题实际风险的界，指出结构风险最小化原则比经验风险最小化原则更适合SAIR亮温图像反演。在通过主成分分析和偏最小二乘法建立SAIR亮温反演的稀疏回归模型的基础上，分别从确定性和贝叶斯观点提出了两种基于结构风险最小化的SAIR亮温重建方法。前者通过控制不敏感因子来实现结构风险最小化，类似于传统的SAIR正则化反演方法，需要人为选取最优模型参数；后者通过控制先验概率来实现结构风险最小化，可以自动地完成最优模型的选取。同经验风险最小化原则的SAIR图像反演方法相比，该方法具有更小的噪声扩展性能以及更低的计算复杂度。
建立SAIR目标检测的数学模型。利用SAIR图像的统计特性，结合高斯混合模型、核回归方法，提出了一种基于稳健核回归的SAIR目标检测算法。通过高斯混合模型，建立最优的SAIR背景估计风险泛函；利用核回归思想，在特征空间中最小化SAIR背景估计风险泛函，实现对SAIR亮温图像复杂背景的抑制和弱小目标检测。
本论文提出的基于机器学习的SAIR图像反演和目标检测方法均经过了严密的理论推导、仿真以及实验的验证，具有良好的实用前景。
Synthetic aperture interferometric radiometers (SAIRs) hold the same favorableconcealment and survival ability, and are applicable for most weather conditions andbattlefield environment in day and night. And high spatial resolution and instantaneousimaging without scanning is achieved by adopting the technique of aperture synthesis. Sothe researchers pay more and more attention to the novel detection method.
The high-quality real-time brightness temperature reconstruction method and theeffective target detection algorithm are the major problem of the synthetic aperturemicrowave radiometer target detection. In this paper, based on machine learning theory, atfirst, the nature of the SAIR brightness temperature reconstruction is analyzed, then basedon a detailed analysis of the model selection of the SAIR inverse problem, the real-timehigh-quality SAIR brightness temperature image reconstruction methods are addressed; atlast, based on the statistical properties of the SAIR image, we propose the backgroundsuppression and target detection of SAIR target detection. The main contents include:
The existing SAIR brightness temperature reconstruction methods are analyzed in theviewpoint of statistics. It is pointed out that the nature of the existing the SAIR inversionmethod is model selection problem. The difficulties of the optimal regularizationparameter determination and the actual risk minimization are also discussed.
The existing SAIR brightness temperature reconstruction methods are analyzed in theBayesian framework. The potential statistical properties of the brightness temperaturedistribution and visibility samples for the classical SAIR brightness temperaturereconstruction methods are presented. Based on the detailed analysis of the statisticalmodel of the SAIR inverse problem, a real-time brightness temperature reconstructionmethod based on Bayesian linear regression is proposed. Using the Bayesian modelselection, the priori probability is introduced into the learning process of the SAIRbrightness temperature reconstruction. The Bayesian estimation model of the SAIRinverse problem is established. The methods for model paramter estimation arepresented. Compared with the existing SAIR brightness temperature reconstructionmethods, this method can real-time reconstruct the brightness temperature image without reducing the quality of image.
The bound of the actual risk of SAIR brightness temperature reconstruction isanalyzed. It is pointed out that structural risk minimization is more suitable for SAIRinverse problem than empirical risk minimization. Based on the sparse regression modelestablishment to the SAIR inverse problem, two brightness temperature reconstructionmethods based on structural risk minimization, in the viewpoint of statistics and Bayesianframework, are proposed, respectively. Using the sensitive factor to control the structuralrisk minimization, the former is similar to the traditional regularization inversion method,and also need to artificially select the optimal model parameters; using the prioriprobability to achieve the structural risk minimization, the latter can automatic determinethe model parameters. Compared with the SAIR image inversion methods based onempirical risk minimization principle, these methods have a smaller expansionperformance of the noise and lower computational complexity.
A mathematical model of the the SAIR target detection is established. Using thestatistical peculiarities of the SAIR brightness temperature image, the Gaussian mixturemodel and kernel regression method, a robust kernel regression algorithm for SAIR targetdetection is proposed. To suppress complex background and detect small target, gaussianmixture model is used to establish the optimal loss function of the SAIR backgroundestimation, and kernel regression is used to minimize the risk function in the feature spaceof the SAIR background estimation.
In this paper, the SAIR brightness temperature reconstruction methods and targetdetection methods based on machine learning are undergone by a rigorous theoreticalanalysis, tested by simulation and experiment, and have a good practical prospect.’
高质量亮温图像的实时获取和有效的目标检测算法是开展综合孔径微波辐射计目标探测研究的关键技术与难点。本文以机器学习理论为基础，从研究SAIR亮温图像反演问题的本质出发，详细地分析了SAIR反演问题的模型选择问题，提出了实时高质量的SAIR亮温图像重建方法，并结合综合孔径微波辐射计反演图像的统计特性，研究适用于综合孔径微波辐射计探测空中目标的背景抑制及目标检测方法。主要研究内容包括：
从统计学的角度分析了现有的SAIR亮温反演方法，指出了现有SAIR反演方法的本质问题为机器学习的模型选择问题；并指出了现有的亮温反演方法在最优正则化参数的确定以及实际风险最小化的困难。
从贝叶斯框架分析了现有的SAIR反演方法，指出了现有SAIR反演方法中关于亮温分布和可见度采样的潜在统计特性。在分析SAIR反演问题的统计模型的基础上，提出了一种基于贝叶斯回归估计的SAIR亮温图像实时反演方法。基于贝叶斯模型选取原理，将先验概率引入至SAIR亮温图像反演的学习过程中，建立了SAIR反演问题的贝叶斯学习模型；推导了模型参数的估计方法。与现有的SAIR方法相比，该方法能在保证反演性能不下降的情况下实时地进行亮温图像重建。
分析了SAIR亮温反演问题实际风险的界，指出结构风险最小化原则比经验风险最小化原则更适合SAIR亮温图像反演。在通过主成分分析和偏最小二乘法建立SAIR亮温反演的稀疏回归模型的基础上，分别从确定性和贝叶斯观点提出了两种基于结构风险最小化的SAIR亮温重建方法。前者通过控制不敏感因子来实现结构风险最小化，类似于传统的SAIR正则化反演方法，需要人为选取最优模型参数；后者通过控制先验概率来实现结构风险最小化，可以自动地完成最优模型的选取。同经验风险最小化原则的SAIR图像反演方法相比，该方法具有更小的噪声扩展性能以及更低的计算复杂度。
建立SAIR目标检测的数学模型。利用SAIR图像的统计特性，结合高斯混合模型、核回归方法，提出了一种基于稳健核回归的SAIR目标检测算法。通过高斯混合模型，建立最优的SAIR背景估计风险泛函；利用核回归思想，在特征空间中最小化SAIR背景估计风险泛函，实现对SAIR亮温图像复杂背景的抑制和弱小目标检测。
本论文提出的基于机器学习的SAIR图像反演和目标检测方法均经过了严密的理论推导、仿真以及实验的验证，具有良好的实用前景。
Synthetic aperture interferometric radiometers (SAIRs) hold the same favorableconcealment and survival ability, and are applicable for most weather conditions andbattlefield environment in day and night. And high spatial resolution and instantaneousimaging without scanning is achieved by adopting the technique of aperture synthesis. Sothe researchers pay more and more attention to the novel detection method.
The high-quality real-time brightness temperature reconstruction method and theeffective target detection algorithm are the major problem of the synthetic aperturemicrowave radiometer target detection. In this paper, based on machine learning theory, atfirst, the nature of the SAIR brightness temperature reconstruction is analyzed, then basedon a detailed analysis of the model selection of the SAIR inverse problem, the real-timehigh-quality SAIR brightness temperature image reconstruction methods are addressed; atlast, based on the statistical properties of the SAIR image, we propose the backgroundsuppression and target detection of SAIR target detection. The main contents include:
The existing SAIR brightness temperature reconstruction methods are analyzed in theviewpoint of statistics. It is pointed out that the nature of the existing the SAIR inversionmethod is model selection problem. The difficulties of the optimal regularizationparameter determination and the actual risk minimization are also discussed.
The existing SAIR brightness temperature reconstruction methods are analyzed in theBayesian framework. The potential statistical properties of the brightness temperaturedistribution and visibility samples for the classical SAIR brightness temperaturereconstruction methods are presented. Based on the detailed analysis of the statisticalmodel of the SAIR inverse problem, a real-time brightness temperature reconstructionmethod based on Bayesian linear regression is proposed. Using the Bayesian modelselection, the priori probability is introduced into the learning process of the SAIRbrightness temperature reconstruction. The Bayesian estimation model of the SAIRinverse problem is established. The methods for model paramter estimation arepresented. Compared with the existing SAIR brightness temperature reconstructionmethods, this method can real-time reconstruct the brightness temperature image without reducing the quality of image.
The bound of the actual risk of SAIR brightness temperature reconstruction isanalyzed. It is pointed out that structural risk minimization is more suitable for SAIRinverse problem than empirical risk minimization. Based on the sparse regression modelestablishment to the SAIR inverse problem, two brightness temperature reconstructionmethods based on structural risk minimization, in the viewpoint of statistics and Bayesianframework, are proposed, respectively. Using the sensitive factor to control the structuralrisk minimization, the former is similar to the traditional regularization inversion method,and also need to artificially select the optimal model parameters; using the prioriprobability to achieve the structural risk minimization, the latter can automatic determinethe model parameters. Compared with the SAIR image inversion methods based onempirical risk minimization principle, these methods have a smaller expansionperformance of the noise and lower computational complexity.
A mathematical model of the the SAIR target detection is established. Using thestatistical peculiarities of the SAIR brightness temperature image, the Gaussian mixturemodel and kernel regression method, a robust kernel regression algorithm for SAIR targetdetection is proposed. To suppress complex background and detect small target, gaussianmixture model is used to establish the optimal loss function of the SAIR backgroundestimation, and kernel regression is used to minimize the risk function in the feature spaceof the SAIR background estimation.
In this paper, the SAIR brightness temperature reconstruction methods and targetdetection methods based on machine learning are undergone by a rigorous theoreticalanalysis, tested by simulation and experiment, and have a good practical prospect.’
引文
[1] Skolnik, M. I. Radar Handbook, Third Edition. New York: McGraw-Hill,2008.
[2] Coleman, C., Yardley, H. Passive bistatic radar based on target illuminations bydigital audio broadcasting. Radar, Sonar&Navigation, IET.2008,2(5):366-375.
[3] Diani, M., Acito, N., Corsini, G. Airborne threat detection in navy IRST systems.Vision, Image and Signal Processing, IEE Proceedings-.2005,152(1):45-51.
[4] Kulpa,"Multi-static entirely passive detection of moving targets and its limitations,"Radar, Sonar and Navigation, IEE Proceedings, vol.152(3), pp.169-173,2005.
[5] J. A. Nanzer, Rogers,"Applying Millimeter-Wave Correlation Radiometry to theDetection of Self-Luminous Objects at Close Range," Microwave Theory andTechniques, IEEE Transactions, vol.56(9), pp.2054-2061,2008.
[6] Thomann. G. C. Experimental results of the remote sensing of sea-surface salinity at21-cm wavelength. IEEE Trans. Geosci. Electron.1976,14(3):198-214.
[7] Swift. C. T, Mcintosh. R. E. Consideration for microwave remote sensing ofocean-salinity. IEEE Trans. Geosci. Remote Sensing,1983,21(4):480-491.
[8] Wang. J. R, et al. Multifrequency measurements of the effects of soil moisture, soiltexture, and surface roughtness. IEEE Trans. Geosci. Remote Sensing,1983,12(1):44-51.
[9] Schmugge. T. J, O’Neill. P. E, Wang. J. R. Passive microwave soil moisture research.IEEE Trans. Geosci. Remote Sensing,1986,24(1):12-22.
[10] Arai. K. A preliminary assessment of radiometric accuracies for MOS-1sensors. Int.J. Remote Sensing,1988,9(1):5-21.
[11]周长宝.欧洲空间局的地球观测活动.遥感信息,1990,3:40-42.
[12] Carrer. K. R, Elachi. C, Ulaby. F. T. Microwave remote sensing from space.Proceedings of IEEE,1985,73(6):970-996.
[13] Notel. D, Huck. J, Neubert, S. A compact mmw imaging radiometer for concealedweapon detection. Proceedings of IEEE IRMMW-THz,2007:269-270.
[14] Sinclair. G. N. Outdoor passive millimetre wave security screening. SecurityTechnology Proceedings of IEEE,2001:172-179.
[15] Larry Yujiri. Passive millimeter wave imaging. IEEE Microwave Magazine,2003,4(3):39-50.
[16] Stewart. W. L. Passive millimeter wave imaging considerations for tactical aircraft.Proceedings of IEEE DASC,2001，1:2B2/1-2B2/8.
[17] Martin, C. Real time passive millimeter-wave imaging from a helicopter platform.Proceedings of IEEE DASC,2000,1:2B1/1-2B1/8.
[18]李辉，王子滨.国外毫米波制导技术的研究.制导与引信，1991，4:43-55.
[19]张俊荣.毫米波辐射计制导.微波学报，1997，13(4):296-306.
[20]吴冰,蔡晖.末修子弹敏感器试验结果及精度分析.现代防御技术,1999,1:11-17.
[21]张祖荫,郭伟,林士杰.无源毫米波末敏弹.华中理工大学学报.1994,22(5):20-25.
[22]严金海,李兴国,汪敏.毫米波辐射计探测直升机研究.探测与控制学报.2001,23(4):37-40.
[23] Markus. P, Helmut. S, Stephan. D. High resolution passive millimetre wave imagingtechnologies for reconnaissance and surveillance. Proceedings of SPIE,2003,V5077:77～86.
[24]董晓龙,吴季,姜景山.微波辐射计用于隐身目标探测的性能分析.系统工程与电子技术,2001,23(3):54-57.
[25]彭树生,李兴国.毫米波辐射计反空中涂层隐身飞机的分析.红外与毫米波学报,1998,17(6):454-458.
[26]张祖荫,林世杰.微波辐射测量技术及应用.北京：电子工业出版社,1995.
[27] C. S. Ruf, C. T. Swift, A. B. Tanner, et al. Interferometric synthetic aperturemicrowave radiometry for the remote sensing of the Earth. IEEE Trans., Geosci.Remote Sensing,1988,26(5):597-611.
[28] T乌拉比, R.K穆尔，冯健超.微波遥感(第一卷).北京：科学出版社,1987.
[29] A. R. Thompson, J. M. Moran, G. W. Swenson. Interferometric and synthesis in radioastronomy. John Wiley&Sons Inc.,2001.
[30] D. M. Le Vine. Synthetic aperture radiometer systems. IEEE Trans. Microw. TheoryTech.1999,47(12):2228-2236.
[31]卢军,张祖荫,林士杰.合成孔径微波辐射计灵敏度与分辨率关系的优化设计.通信学报，1996,17(2):131-136.
[32]卢军,张祖荫,林士杰,黄铁侠.利用合成孔径微波辐射计输出反演地物亮温分布.电子学报，1997,25(3):91-93.
[33]吴季,刘浩,孙伟英,姜景山.综合孔径微波辐射计的技术发展及其应用展望,遥感技术与应用,2005,20(1):24-29.
[34]王华力，李兴国，彭树生，王一丁.被动毫米波成像技术.红外与毫米波学报,1997,16(4):297-302.
[35] Huang Jian, Gan Tiguo. Image reconstruction of uiform circular array syntheticaperture radiometer. Proceedings of IEEE MAPE,2007,1481-1484.
[36] D. M. Le Vine. Initial results in the development of a synthetic aperture microwaveradiometer. IEEE Trans. Geosci. Remote Sensing,1990,28(4):614–619.
[37] D. M. Le Vine, A. J. Griffis, C. T. Swift, et al. ESTAR: a synthetic aperturemicrowave radiometer for remote sensing applications. Proceedings of the IGARSS,1994,1787-1801.
[38] J. Thomas, D. M. Le Vine, and Y. H. Ann. Soil moisture mapping at regional scalesusing microwave radiometry the Southern Great Plains Hydrology Experiment.IEEE Trans. Geosci. Remote Sensing,1999,37(5):2136–2151.
[39] D. M. Le Vine, J. Thomas, and C. T. Swift. ESTAR measurements during theSouthern Great Plains experiment. IEEE Trans. Geosci. Remote Sensing,2001,39(8):1680–1685.
[40] D. M. Le Vine, C. T. Swift, and M. Haken. Development of the synthetic aperturemicrowave radiometer ESTAR. IEEE Trans. Geosci. Remote Sensing,2001,39(1):199–202.
[41] D. M. Le Vine and M. Haken. RFI at L-band in synthetic aperture radiometers.Proceedings of IGARSS,2003,1742-1744.
[42] D. M. Le Vine, M. Haken, and C. T. Swift. Development of the synthetic apertureradiometer ESTAR and the next generation. Proceedings of IGARSS,2004,1260-1263.
[43] D. M. Le Vine, M. Haken, and D. Ryu. Two-dimensional synthetic apertureradiometry over land surface during soil moisture experiment in2003(SMEX03).Proceedings of IGARSS,2007,1842-1845.
[44] D. M. Le Vine, T. J. Jackson, and M. Haken. Initial images of the SyntheticApertureRadiomter2D-STAR. IEEE Trans. Geosci. Remote Sensing,2007,45(11):3623–3632.
[45] M. Martin-Neira, Y. Menard, J. M. Goutoule, et al. MIRAS: a two-dimensionalaperture synthesis radiometer. Proceedings of IGARSS,1994,1323-1325.
[46] Y. Kerr, J. Font, P. Waldteufel, et al. New radiometers: SMOS-a dual pol L-band2Daperture synthesis radiometer. Proceedings of IEEE Aerospace,2000,5:119-128.
[47] M. Martin-Neira, et al. Polarimetric mode of MIRAS. IEEE Trans. Geosci. RemoteSensing,2002,40(8):1755–1768.
[48] O. Batz, U. Kraft, W. Lindemer, et al. Design and implementation of the MIRASdigital correlator. Proceedings of IGARSS,1996,2:872-874.
[49] N. Duffo, I. Corbella, M. Vall-llossera, et al. MIRAS imaging validation. Proceedingsof IGARSS,2003,2:1226-1228.
[50] B. Laursen and N. Skou. A spaceborne synthetic aperture radiometer simulated by theTUD demonstration model. Proceedings of IGARSS,1994,1314-1316.
[51] B. Laursen and N. Skou. Synthetic aperture radiometry evaluated by a two-channeldemonstration model. IEEE Trans. Geosci. Remote Sensing,1998,36(3):822–832.
[52] M. Martin-Neira, J. M. Goutoule,et al. Integration of MIRAS breadboard and futureactivities. Proceedings of IGARSS,1996,2:869-871.
[53] F. Torres, I. Corbella, A. Camps, et al. Receiver specifications of the MIRASdemonstrator. Proceedings of SPIE,2001, V4169:291-298.
[54] F. Bayle, J. Wigneron, Y. H. Kerr, et al. Two-dimensional synthetic aperture imagesover a land surface scene. IEEE Trans. Geosci. Remote Sensing,2002,40(3):710–714.
[55] S. Ribo, M. Martin-Neira, I. Cabeza, et al. MIRAS Airborne Demonstrator.Proceedings of IEEE MicroRad,2006,45-49.
[56] N. Duffo, F. Torres, I. Corbella, et al. Some results of the MIRAS-SMOSdemonstrator campaigns. Proceedings of IGARSS,2007,3639-3642.
[57] M. Martin-Neira, I. Cabeza, et al. AMIRAS—An Airborne MIRAS Demonstrator.IEEE Trans. Geosci. Remote Sensing,2002,46(3):705–716.
[58] M. Martin-Neira, I. Corbella, et al. MIRAS Functional Test Results for the SMOSMission. Proceedings of IEEE MicroRad,2006,29-34.
[59] S. Beraza, V. Gonzalez, F. Torres, et al. MIRAS-SMOS Demonstrator Test Campaignsat Polytechnic University of Catalonia. Proceedings of IGARSS,2006,1776-1779.
[60] H. M. J. P. Barré, B. Duesmann and Y. H. Kerr. SMOS: The Mission and the System.IEEE Trans. Geosci. Remote Sensing,2002,46(3):587–593.
[61] K. D. McMullan, M. A. Brown, M. Martín-Neira, et al. SMOS: The Payload. IEEETrans. Geosci. Remote Sensing,2002,46(3):594–605.
[62] H. Valmu, I. Mononen, and M. Hallikainen. The Helsinki University of Technologysynthetic aperture radiometer. Proceedings of IGARSS,1998,2:553-555.
[63] K. Rautiainen, R. Butora, T. Auer, et al. The Helsinki University of TechnologyYlinen electronics airborne L-band interferometric radiometer. Proceedings ofIGARSS,2000,7:2978-2980.
[64] K. Rautiainen, R. Butora, T. Auer, J. Kettunen, et al. Development of airborneaperture synthetic radiometer (HUT-2D). Proceedings of IGARSS,2003,2:1232-1234.
[65] K. Rautiainen, J. Kainulainen, T. Auer, et al. Helsinki University of TechnologySynthetic Aperture Radiometer－HUT-2D. Proceedings of IGARSS,2007,2:3635-3638.
[66] K. Rautiainen, R. Butora, M. Hallikainen, et al. Measurement of the HUT-2D aperturesynthesis radiometer four-element subassembly. Proceedings of IGARSS,2001,3074-3076.
[67] J. Kainulainen, K. Rautiainen, S. Tauriainen, et al. First2-D interferometricradiometer imaging of the earth from an aircraft. IEEE Trans. Geosci. RemoteSensing Letters,2007,4(2):241–245.
[68] K. Rautiainen, J. Kainulainen, T Auer, et al. Helsinki University of TechnologyL-Band Airborne Synthetic Aperture Radiometer. IEEE Trans. Geosci. RemoteSensing,2008,46(3):717–726.
[69] B. Lambrigtsen, W. Wilson, A. Tanner, et al. GeoSTAR-a microwave sounder forgeostationary satellites. Proceedings of IGARSS,2004,777-780.
[70] B. Lambrigtsen, W. Wilson, A. Tanner, T. Gaier. GeoSTAR-a synthetic apertureapproach for a geostationary microwave sounder. Proceedings of IEEE AerospaceConference,2004,2:1008-1014.
[71] A. B. Tanner, W. J. Wilson, P. P. Kangaslahti, et al. Prototype development of ageostationary synthetic thinned aperture radiometer, GeoSTAR. Proceedings ofIGARSS,2004,1256-1259.
[72] B. H. Lambrigsten, W. Wilson, A. B. Tanner, et al. GeoSTAR a synthetic aperturemicrowave sounder for geostationary missions. Proceedings of SPIE,2005, V5659:185-194.
[73] B. Lambrigtsen. GeoSTAR: Developing A New Payload for GOES Satellites, in IEEEAerospace Conference,2006,1-10.
[74] A. B. Tanner, S. T. Brown, T. C. Gaier, et a. Field tests of the GeoSTAR demonstratorinstrument. Proceedings of IGARSS,2007,2427-2430.
[75] A.B.Tanner, T. C. Gaier, and B. H. Lambrigtsen. GeoSTAR PerformanceDemonstration. Proceedings of IEEE Aerospace Conference,2008,1-6.
[76] A. B. Tanner, S. T. Brown, S. J. Dinardo, et al. Initial results of the GeoSTARprototype. Proceedings of IEEE Aerospace Conference,2006,1-9.
[77] A. B. Tanner, W. J. Wilson, B. H. Lambrigsten, et al. Initial Results of theGeosynchronous Synthetic Thinned Array Radiometer. Proceedings of IGARSS,2006,3968-3971.
[78] M. A. Fischman and A. W. England. An L-band direct-sampling digital radiometerdesign and performance evaluation. Proceedings of IGARSS,1999,1:237-239.
[79] L. Nieuwstadt, R. De Roo, D. Boprie, et al. A compact direct detection receiver forL-band STAR radiometry. Proceedings of IEEE MTT-S,2003,1:563-566.
[80] R. De Roo, A. W. England, and J. Munn. Circular polarization for L-band radiometricsoil moisture retrieval. Proceedings of IEEE Aerospace Conference,2004,2:1015-1023.
[81] M. A. Fischman and A. W. England. A direct-sampling receiver for synthetic thinnedarray radiometry. Proceedings of IGARSS,1998,3:1711-1713.
[82] M. A. Fischman and A. W. England. An L-band direct sampling digital radiometer forSTAR technology sensors. Proceedings of IGARSS,2000,5:129-139.
[83] A. W. England, H. Pham, R. De Roo, et al. Performance of STAR-Light receiversduring CLPX. Proceedings of IGARSS,2003,2:1235-1237.
[84] Dong Xiaolong, Wu Ji, and Jiang Jingshan. The signal analysis and imaging ofsynthetic aperture radiometer. Proceedings of IGARSS,1998,5:2650-2652.
[85]张升伟，董晓龙，吴季. L波段合成孔径微波辐射计机理及原理性实验.遥感技术与应用,2000,15(2):95-99.
[86] Dong Xiaolong, Wu Ji, et al. The design and implementation of CAS C-bandinterferometric synthetic aperture radiometer. Proceedings of IGARSS,2000,2:866-868.
[87] Zhang Shengwei and Wu Ji. Experimental results of synthetic aperture microwaveradiometer. Proceedings of IGARSS,2002,6:3635-3637.
[88] Lu Jie, Ban Souzheng, Wu Ji, et al. Receiver designing of the x-bandhigh-spatial-resolution radiometer. Proceedings of SPIE,2003, V4894:240-250.
[89] Liu Hao, Wu Ji, et al. The CAS airborne X-band synthetic aperture radiometer:system configuration and experimental results. Proceedings of IGARSS,2004,3:2230-2233.
[90] Huang Jian, Gan Tiguo. A novel millimeter wave synthetic aperture radiometerpassive imaging system. Proceedings of IEEE ICMMT,2004,414-417.
[91]卢军,林士杰,张祖荫.星载合成孔径微波辐射计的反演公式.微波学报，1994,39(4):20-27.
[92] Li Qingxia, Chen Ke, Guo Wei, et al. An Aperture Synthesis Radiometer at MillimeterWave Band. in Proc. Proceedings of IEEE ICMMT,2008,4:1699-1701.
[93] Li Qingxia, Hu Fei, Guo Wei, et al. A General Platform for Millimeter Wave SyntheticAperture Radiometers. Proceedings of IGARSS,2008,1156-1159.
[94]薛永,苗俊刚,万国龙.8mm波段二维综合孔径微波辐射计(BHU-2D).北京航空航天大学学报,2008,34(9):1020-1023.
[95] Xue Yong, Miao Jungang, et al. Development of the disk antenna array aperturesynthesis millimeter wave radiometer. Proceedings of IEEE ICMMT,2008,2:806-809.
[96]章勇,李兴国,王华力.毫米波合成孔径成像辐射计.系统工程与电子技术,1998,12:11-14.
[97] Zhou Xi, Sun Houjun, He Jiwei, et al. NUFFT-based iterative reconstructionalgorithm for synthetic aperture imaging radiometers. IEEE Trans. Geosci. RemoteSensing Letters,2009,6(2):273–276.
[98] A. Camps. The processing of Hexagonally Sampled Signals with StandardRectangular Techniques: Application to2-D Large Aperture SynthesisInterforometric Radiometers. IEEE Trans. Geosci. Remote Sensing,1997,GE-35(1):183~190.
[99]黄永辉.综合孔径成像微波辐射计反演算法及实验研究:[硕士学位论文].空间飞行器设计,中国科学院空间科学与应用研究中心,2001.
[100] A. Camps, J. Bara, F. Torres, et al. Extension of the CLEAN technique to themicrowave imaging of continuous thermal sources by means of aperture synthesisradiometers. in: Progress In Electromagnetics Research Symposium,1998,18:67-83.
[101] M. Bertero and P. Boccacci, Introduction to Inverse Problems in Imaging,1st ed.London, U.K.: Inst. Phys.,1998.
[102] A. B. Tanner, C. T. Swift. Calibration of a Synthetic Aperture Radiometer. IEEETrans. Geosci. Remote Sensing,1993,31(1):257~267.
[103] A. Lannes, E. Anterrieu, and K. Bouyoucef. Fourier interpolation and reconstructionvia Shannontype techniques; Part I: Regularization principle, J. Modern Opt.,1994,41(8):1537–1574.
[104] A. Lannes, E. Anterrieu, and K. Bouyoucef. Fourier interpolation and reconstructionvia Shannontype techniques Part II: Technical developments and applications, J.Modern Opt.,1996,43(1):105–138.
[105] M. A. Goodberlet. Improved image reconstruction techniques for synthetic apertureradiometers, IEEE Trans. Geosci. Remote Sens.,2000,38(3):1362–1366.
[106] M. Bertero and P. Boccacci, Introduction to Inverse Problems in Imaging,1st ed.London, U.K.: Inst. Phys.,1998.
[107] K. P. Gaikovich and A. V. Zhilin. Tikhonov's algorithm for two-dimensional imageretrieval, in Proc. MMET, Kharkov, Ukraine,1998,622-624.
[108] E. Anterrieu. A resolving matrix approach for synthetic aperture imagingradiometers. IEEE Trans. Geosci. Remote Sens.,2004,42(8):1649-1656.
[109] A. Parthiban, Madhavan, J., Radhakrishna, P., et al,"On the probability distributionfunction for airborne radar clutter.," Radar Conference,2005IEEE International, pp.464-468,2005.
[110] A. Farina, Russo, A., Studer," Coherent radar detection in log-normal clutter,"Communications, Radar and Signal Processing, IEE Proceedings F, vol.133(1), pp.39-53,1986.
[111] M. Sekine, Ohtani, S., Musha, T., et al,"Weibull-Distributed Ground Clutter,"Aerospace and Electronic Systems, IEEE Transactions, vol. AES-17(4), pp.596-598,1981.
[112] Baker,"K-distributed coherent sea clutter," Radar and Signal Processing, IEEProceedings, vol.138(2), pp.89-92,1991.
[113]何友、关键、彭应宁,"雷达自动检测与恒虚警处理,"北京:清华大学出版社,1999.
[114] R. Ravid, Levanon,"Maximum-likelihood CFAR for Weibull background," Radarand Signal Processing, IEE Proceedings, vol.139(3), pp.256-264,1992.
[115] Blake," OS-CFAR theory for multiple targets and nonuniform clutter," Aerospaceand Electronic Systems, IEEE Transactions, vol.24(6), pp.785-790,1988.
[116] C.-J. Kim, Lee,"Detection analysis of a generalized order statistics CFAR detectorfor a correlated Rayleigh target," Signal Processing, vol.47(2), pp.227-233,1995.
[117] F. Zhang, Li, C., Shi,"Detecting and tracking dim moving point target in IR imagesequence," Infrared Physics&Technology, vol.46(4), pp.323-328,2005.
[118] B. Porat, Friedlander,"A frequency domain algorithm for multiframe detection andestimation of dim targets," Pattern Analysis and Machine Intelligence, IEEETransactions, vol.12(4), pp.398-401,1990.
[119] L. A. Johnston, Krishnamurthy,"Performance analysis of a dynamic programmingtrack before detect algorithm," Aerospace and Electronic Systems, IEEETransactions, vol.38(1), pp.228-242,2002.
[120]杨磊.,"复杂背景条件下的红外小目标检测与跟踪算法研究:[博士学位论文],"图像处理与模式识别研究所,上海交通大学,2006.
[121]熊祖彪,"综合孔径微波辐射探测的统计特性研究[博士论文],"华中科技大学,2009.
[122] M. M. H. a. D. W. Thomas,"The Two-dimensional adaptive LMS algorithm," IEEETrans On Systems, vol.35(5), p.485～494,1988.
[123] M. O. a. S. Hashiguchi,"Two-dimensional LMS adaptive filters," IEEE TransConsumer Elect, vol.37, pp.66-73,1991.
[124] J. R. Z. Tarun Soni, Walter H. Ku,"Performance Evaluation of2-D AdaptivePrediction Filters For Detection of Small Objects in Image Data," IEEE Trans OnImage Processing, vol.2(3), pp.327-340,1993.
[125] J. D. P. Cassent, S. Smokelin and A. Ye,"Wavelet and Gabor Transform ForDetection," Opt. Eng, vol.31, pp.1893-1898,1992.
[126] R. N. S. a. H. I. Hahn,"Wavelet transform methods for object detection andrecovery," IEEE Trans On Image Processing, vol.6(5), pp.724-735,1997.
[127] Vapnik. V. N and Chervonenkis. A. J. On the Uniform Covergence of RelativeFrequencies of Events to their Probabilities. Theroy Probability Application.1971,16:264-280.
[128] Vapnik.Vladimir. N. The Nature of Statistical Learning Theroy. Spring: Verlag.1992.
[129] Cortes. C. and Vapnik.V. N. Support-Vector Network. Machine Learning.1995,20(3):273-297.
[130] M. E. Tipping. Sparse Bayesian Learning and the Relevance Vector Machine.Journal of Machine Learning Research.2001,1:211-244.
[131] Mercer. J. Functions of Positive and Nagative Type and their Connection with theTheory of Integral Equations. Philos. Trans. Roy. Soc.1909, A(209):415-446.
[132] E. Anterrieu. On the reduction of the reconstruction bias in synthetic apertureimaging radiometry, IEEE Trans. Geosci. Remote Sens.,2007,45(3):592-602.
[133] A. Camps, M. Vall-llossera, I. Corbella, et al. Improved image reconstructionalgorithms for aperture synthesis radiometers, IEEE Trans. Geosci. Remote Sens.,2008,46(1):146-158.
[134] C.L. Lawson and R.J. Hanson. Solving Least Squares Problems. Prentice-Hall,1974.
[135]张贤达.矩阵分析与应用.北京：清华大学出版社,2005.
[136] P. C. Hansen. Rank-Decient and Discrete Ill-Posed Problems. Numerical Aspects ofLinear Inversion. SIAM,1998.
[137] A. N. Tikhonov. Regularization of incorrectly posed problems. Soviet Math. Dokl.,1963,4:1624~1627.
[138] V. A. Morozov. On the solution of functional equations by the method ofregularization. Soviet Math. Dokl.,1966,7:414-417.
[139] H. Gfrerer. An a posteriori parameter choice for ordinary and iterated Tikhonovregularization of ill-posed problems leading to optimal convergence rates. Math.Comp.,1987,49:507-522.
[140] A. R. Barron and T. Cover. Minimum complexity density estimation. IEEE Trans.Inf. Theory,1991,37:1034-1054.
[141] D. Belsley, E.Kuh, and R.Welsch. Regression Diagnostics: Identifying InfluentialData and Sources of Collinearity, Wiley, New York,1980.
[142] J. Berger. Statistical Decision Theory and Bayesian Analysis. Springer, New York,1985.
[143] A. Blumer, A. Ehrenfeucht, D.Haussler and M.Warmuth. Learnability and theVapnik Chenvonenkis dimension. J.ACM,1985,36:929-965.
[144] N. N. Chentsov. On correctness of problem of statistical point estimation. TheoryProbab. Appl,1981.26:13-29.
[145] V. Cherkassky and F. Mulier. Learning from Data: Concepts, Theory, and Methods.Wiley, New York,1998.
[146] P. Craven and H. Wahba. Smoothing noisy data with spline functions: estimating thecorrect degree of smoothing by the method of generalized cross-validation. Numer.Math,1979.31:377-403.
[147] G. H. Golub, M. Heath, and G. Wahba. Generalized cross-validation as a method forchoosing a good ridge parameter. Technometrics,1979,21:215-223.
[148] P. C. Hansen and D. P. O'Leary. The use of the L-curve in the regularization ofdiscrete ill-posed problems. SIAM J. Sci. Comput.,1993,14:1487-1503.
[149] M. Hanke. Limitations of the L-curve method in ill-posed problem. BIT,1996,36:287-301.
[150] E. Gine and J. Zinn. Some limit theorems for empirical processed. Ann. Probab,1984,12:929-989.
[151] F. Girosi. Approximation error bounds that use VC bounds. ICANN95, Paris,1995.
[152] P. J. Wolfe, S. J. Godsill and W. J. Ng. Bayesian variable selection andregularization for time-frequency surface estimation. J. Roy. Stat. Soc. B, Aug,2004,vol.66:575-589.
[153] A. Tarantola. Inverse problem theory and methods for model parameters estimation.Philadelphia, PA:SIAM,2005.
[154] D. J. C. Mackay. A practical Bayesian framework for back propagation networks.Neural Computation,1992, vol.4, no.3:448-472.
[155] R. M. Neal. Bayesian Training of Backpropagation on Networks by the HybridMonte Carlo Method. Department of Statistics, University of Toronoto,1992.
[156] R. M. Neal. Bayesian Learning for Neural Network. Ser. Lecture Notes in Statistics,U. K: Springer,1996.
[157] C. K. I. Williams and C. E. Rasmussen. Gaussian processes for regression. Advancein Neural information Processing Syestems, D. S. Touretzky, M. C. Mozer and M. E.Hasselino, Eds, Cambridge, MA: MIT Press,1996.
[158] C. K. I. Williams. Prediction and Gaussian processes: from linear regression tolinear prediction and beyond. Learning and Inference in Graphical Models, Norwell,MA: Kluwer,1998.
[159] M. H. Law and J. T. Kwork. Applying the Bayesian evidence framework to supportvector regression. Proc.12th. Eur. Conf. Machine Learning, Freiburg, Germany,2001:312-323.
[160] Tipping, M. E and A. Faul. Fast marginal likehood maximization for sparseBayesian models. Proceedings Ninth International Workshop on ArtificialIntelligence and Statistics. Key West, Florida,2003.
[161] A. Bjorck. Numerical Methods for Least Squares Problems. Philadelphia, PA:SIAM,1996.
[162] V. N. Vapnik. The Nature of Statistical Learning Theory. New York: Springer-Verlag,1995.
[163]徐利治、林化夷等.现代数学手册*随机数学卷.武汉:华中科技大学出版社,2000.
[164] N. A. Ablitt, J. X. Gao, J. keegan, L.Stegger. Predictive Cardiac Motion Modelingand Correction With Partial Least Squares Regression. IEEE. Trans. Med. Imag,Vol.23, No.10:1315-1324Oct,2004.
[165] Hong Su and Gangtie Zheng. A Partial Least Squares Regression-Based FusionModel for Predicting the Trend in Drowsiness. IEEE. Trans. Sys, Man andCybernetics-Part A: Systems and Humans. Vol.38, No.10:1085-1092, Sept,2008.
[166] P. Stoica and Y. Selen. Model-order selection: A review of information criterionrules. IEEE Signal Process. Mag. Vol.21, pp:36-47, Jul,2004.
[167] S. S. Keerthi and S. K. Shevade. SMO algorithm for linear squares SVMformulations. Neural Computation. Vol.15, No.2:487-507. Feb.2003.
[168] S. K. Shevade, S. S. Keerthi, C. Bhattacharyya, and K. R. K. Murthy. Improvementto the SMO algorithm for SVM regression. IEEE. Trans. Neural Network. Vol.11,pp.1188-1194, Sept.2000.
[169] A. J. Smola and B. Scholkopf. A Tutorial on Support Vector Regression. GMD First.Technical Report NC2-TR-1998-30. Oct.1998.
[170] W. Chu. Bayesian approach to support vector machines. Ph.D, dissertation, Nat.Univ. Singaproe, Jan.2003.
[171] J. B. Gao, S. R. Gunn, C. J. Harris and M. Brown. Aprobabilitsit framework forSVM regression and error bar estimation. Machine Learning. Vol.46, pp.71-89,Mar.2002.
[172] W. Chu, S. S. Keerthi, and C. J. Ong. Bayesian Support Vector Regression Using aUnified Loss Function. IEEE. Trans. Neural Network. Vol.15, pp.29-44, Jan.2004.
[173] E. G. Larsson and Y. Selen. Linear Regression with a Sparse Parameter Vector.IEEE. Trans. Signal Processing. Vol.55, No.2:451-460, Feb.2007.
[174] Larry Yujiri, Merit Shoucri, and Philp Moffa,“Passive millimeter wave imaging”,IEEE Micowave magazine,1527-3342/02,2003, September, pp.39-50.
[175] P.Wang., J.W.Tian and C.Q.Gao, A. Martin,“Infrared small target detection usingdirectional highpass filters based on LS-SVM”, Electron.Lett,2003,Vol.45,pp.156-158.
[176] L.Yang, J.Yang, and K.Yang.,“Adaptive detection for infrared small terget undersea-sky complex background”, Electron.Lett,2004, Vol.40, pp.1083-1085.
[177] Y.F.Gu, C.Wang., et al.,“A Kernel-Based nonparametric Regression Method forClutter Removal in Infrared Small-Target Detection Application”,IEEE.Geosci.Remote Sens Lett, July.2010, Vol..7,No.3, pp.469-473.
[178] A.Ruiz and E.Lopez-de Terual..,“Nonlinear kernel-based statistical patternanalysis”, IEEE Trans.Neural Netw., Jan2001, Vol.12,No.1, pp.16-32.
[179] T.Evgeniou,M.Pontil,and T.Poggio.“Regularization networks and support vectormachines”,Adv.Comput.Math.Apr.2000.Vol.13,No.1, pp.1-50.
[180] G.Camps-Valls,L.Bruzzone,J.L.Rojo-Alvarez,et al.“Robust Support VectorRegression for Biophysical Variable Estimation From Remotely Sensed image”,IEEE.Geosci.Remote Sens Lett, July.2006, Vol.3,No.3, pp.339-343.
[181] W.F.Zhang,D.Q.Dai,H.Yan.”Framelet Kernels With Application to Support VectorRegression and Regularization Networks”, IEEE Trans.Syst.Man.Cybern.B.Cybern.Agust.2010,Vol.40,No.4,pp.1128-1144.
[182] G.M.Fung and O.L.Mangasarina.”A Feature Selection Newton method for Supportvector machine Classification”,Computational Optimization and Applications,2004,Vol.28,pp.185-202.
[183] S.Matteoli,N.Acito,M.Diani,et al.”An Automatic Approach to Adaptive LocalBackground Estimation and Supression in Hyperspectral Target Detection”,IEEE.Trans.Geosci.Remote.Sens,February.2011,Vol..49,No.2,pp.790-800.
[184] John M, M.Anderson,“A Generalized Likelihood Radio Test for Detecting LandMines Using Multispectral Images”, IEEE.Geosci.Remote Sens Lett, July.2008,Vol.5,No.3, pp.547-551.
[185] Jean-Matthien Monnet, Jocelyn Chanussot,“Suppot Vector Regression for theEstimation of Forest Stand Parameters Using Airborne Laser Scanning”,IEEE.Geosci.Remote Sens Lett, May.2011, Vol.8,No.3, pp.580-584.
[186] J.Shawe-Taylor and N.Cristianini,”Kernel Methods for Pattern Analysis”,Cambridge University Press,2004.
[2] Coleman, C., Yardley, H. Passive bistatic radar based on target illuminations bydigital audio broadcasting. Radar, Sonar&Navigation, IET.2008,2(5):366-375.
[3] Diani, M., Acito, N., Corsini, G. Airborne threat detection in navy IRST systems.Vision, Image and Signal Processing, IEE Proceedings-.2005,152(1):45-51.
[4] Kulpa,"Multi-static entirely passive detection of moving targets and its limitations,"Radar, Sonar and Navigation, IEE Proceedings, vol.152(3), pp.169-173,2005.
[5] J. A. Nanzer, Rogers,"Applying Millimeter-Wave Correlation Radiometry to theDetection of Self-Luminous Objects at Close Range," Microwave Theory andTechniques, IEEE Transactions, vol.56(9), pp.2054-2061,2008.
[6] Thomann. G. C. Experimental results of the remote sensing of sea-surface salinity at21-cm wavelength. IEEE Trans. Geosci. Electron.1976,14(3):198-214.
[7] Swift. C. T, Mcintosh. R. E. Consideration for microwave remote sensing ofocean-salinity. IEEE Trans. Geosci. Remote Sensing,1983,21(4):480-491.
[8] Wang. J. R, et al. Multifrequency measurements of the effects of soil moisture, soiltexture, and surface roughtness. IEEE Trans. Geosci. Remote Sensing,1983,12(1):44-51.
[9] Schmugge. T. J, O’Neill. P. E, Wang. J. R. Passive microwave soil moisture research.IEEE Trans. Geosci. Remote Sensing,1986,24(1):12-22.
[10] Arai. K. A preliminary assessment of radiometric accuracies for MOS-1sensors. Int.J. Remote Sensing,1988,9(1):5-21.
[11]周长宝.欧洲空间局的地球观测活动.遥感信息,1990,3:40-42.
[12] Carrer. K. R, Elachi. C, Ulaby. F. T. Microwave remote sensing from space.Proceedings of IEEE,1985,73(6):970-996.
[13] Notel. D, Huck. J, Neubert, S. A compact mmw imaging radiometer for concealedweapon detection. Proceedings of IEEE IRMMW-THz,2007:269-270.
[14] Sinclair. G. N. Outdoor passive millimetre wave security screening. SecurityTechnology Proceedings of IEEE,2001:172-179.
[15] Larry Yujiri. Passive millimeter wave imaging. IEEE Microwave Magazine,2003,4(3):39-50.
[16] Stewart. W. L. Passive millimeter wave imaging considerations for tactical aircraft.Proceedings of IEEE DASC,2001，1:2B2/1-2B2/8.
[17] Martin, C. Real time passive millimeter-wave imaging from a helicopter platform.Proceedings of IEEE DASC,2000,1:2B1/1-2B1/8.
[18]李辉，王子滨.国外毫米波制导技术的研究.制导与引信，1991，4:43-55.
[19]张俊荣.毫米波辐射计制导.微波学报，1997，13(4):296-306.
[20]吴冰,蔡晖.末修子弹敏感器试验结果及精度分析.现代防御技术,1999,1:11-17.
[21]张祖荫,郭伟,林士杰.无源毫米波末敏弹.华中理工大学学报.1994,22(5):20-25.
[22]严金海,李兴国,汪敏.毫米波辐射计探测直升机研究.探测与控制学报.2001,23(4):37-40.
[23] Markus. P, Helmut. S, Stephan. D. High resolution passive millimetre wave imagingtechnologies for reconnaissance and surveillance. Proceedings of SPIE,2003,V5077:77～86.
[24]董晓龙,吴季,姜景山.微波辐射计用于隐身目标探测的性能分析.系统工程与电子技术,2001,23(3):54-57.
[25]彭树生,李兴国.毫米波辐射计反空中涂层隐身飞机的分析.红外与毫米波学报,1998,17(6):454-458.
[26]张祖荫,林世杰.微波辐射测量技术及应用.北京：电子工业出版社,1995.
[27] C. S. Ruf, C. T. Swift, A. B. Tanner, et al. Interferometric synthetic aperturemicrowave radiometry for the remote sensing of the Earth. IEEE Trans., Geosci.Remote Sensing,1988,26(5):597-611.
[28] T乌拉比, R.K穆尔，冯健超.微波遥感(第一卷).北京：科学出版社,1987.
[29] A. R. Thompson, J. M. Moran, G. W. Swenson. Interferometric and synthesis in radioastronomy. John Wiley&Sons Inc.,2001.
[30] D. M. Le Vine. Synthetic aperture radiometer systems. IEEE Trans. Microw. TheoryTech.1999,47(12):2228-2236.
[31]卢军,张祖荫,林士杰.合成孔径微波辐射计灵敏度与分辨率关系的优化设计.通信学报，1996,17(2):131-136.
[32]卢军,张祖荫,林士杰,黄铁侠.利用合成孔径微波辐射计输出反演地物亮温分布.电子学报，1997,25(3):91-93.
[33]吴季,刘浩,孙伟英,姜景山.综合孔径微波辐射计的技术发展及其应用展望,遥感技术与应用,2005,20(1):24-29.
[34]王华力，李兴国，彭树生，王一丁.被动毫米波成像技术.红外与毫米波学报,1997,16(4):297-302.
[35] Huang Jian, Gan Tiguo. Image reconstruction of uiform circular array syntheticaperture radiometer. Proceedings of IEEE MAPE,2007,1481-1484.
[36] D. M. Le Vine. Initial results in the development of a synthetic aperture microwaveradiometer. IEEE Trans. Geosci. Remote Sensing,1990,28(4):614–619.
[37] D. M. Le Vine, A. J. Griffis, C. T. Swift, et al. ESTAR: a synthetic aperturemicrowave radiometer for remote sensing applications. Proceedings of the IGARSS,1994,1787-1801.
[38] J. Thomas, D. M. Le Vine, and Y. H. Ann. Soil moisture mapping at regional scalesusing microwave radiometry the Southern Great Plains Hydrology Experiment.IEEE Trans. Geosci. Remote Sensing,1999,37(5):2136–2151.
[39] D. M. Le Vine, J. Thomas, and C. T. Swift. ESTAR measurements during theSouthern Great Plains experiment. IEEE Trans. Geosci. Remote Sensing,2001,39(8):1680–1685.
[40] D. M. Le Vine, C. T. Swift, and M. Haken. Development of the synthetic aperturemicrowave radiometer ESTAR. IEEE Trans. Geosci. Remote Sensing,2001,39(1):199–202.
[41] D. M. Le Vine and M. Haken. RFI at L-band in synthetic aperture radiometers.Proceedings of IGARSS,2003,1742-1744.
[42] D. M. Le Vine, M. Haken, and C. T. Swift. Development of the synthetic apertureradiometer ESTAR and the next generation. Proceedings of IGARSS,2004,1260-1263.
[43] D. M. Le Vine, M. Haken, and D. Ryu. Two-dimensional synthetic apertureradiometry over land surface during soil moisture experiment in2003(SMEX03).Proceedings of IGARSS,2007,1842-1845.
[44] D. M. Le Vine, T. J. Jackson, and M. Haken. Initial images of the SyntheticApertureRadiomter2D-STAR. IEEE Trans. Geosci. Remote Sensing,2007,45(11):3623–3632.
[45] M. Martin-Neira, Y. Menard, J. M. Goutoule, et al. MIRAS: a two-dimensionalaperture synthesis radiometer. Proceedings of IGARSS,1994,1323-1325.
[46] Y. Kerr, J. Font, P. Waldteufel, et al. New radiometers: SMOS-a dual pol L-band2Daperture synthesis radiometer. Proceedings of IEEE Aerospace,2000,5:119-128.
[47] M. Martin-Neira, et al. Polarimetric mode of MIRAS. IEEE Trans. Geosci. RemoteSensing,2002,40(8):1755–1768.
[48] O. Batz, U. Kraft, W. Lindemer, et al. Design and implementation of the MIRASdigital correlator. Proceedings of IGARSS,1996,2:872-874.
[49] N. Duffo, I. Corbella, M. Vall-llossera, et al. MIRAS imaging validation. Proceedingsof IGARSS,2003,2:1226-1228.
[50] B. Laursen and N. Skou. A spaceborne synthetic aperture radiometer simulated by theTUD demonstration model. Proceedings of IGARSS,1994,1314-1316.
[51] B. Laursen and N. Skou. Synthetic aperture radiometry evaluated by a two-channeldemonstration model. IEEE Trans. Geosci. Remote Sensing,1998,36(3):822–832.
[52] M. Martin-Neira, J. M. Goutoule,et al. Integration of MIRAS breadboard and futureactivities. Proceedings of IGARSS,1996,2:869-871.
[53] F. Torres, I. Corbella, A. Camps, et al. Receiver specifications of the MIRASdemonstrator. Proceedings of SPIE,2001, V4169:291-298.
[54] F. Bayle, J. Wigneron, Y. H. Kerr, et al. Two-dimensional synthetic aperture imagesover a land surface scene. IEEE Trans. Geosci. Remote Sensing,2002,40(3):710–714.
[55] S. Ribo, M. Martin-Neira, I. Cabeza, et al. MIRAS Airborne Demonstrator.Proceedings of IEEE MicroRad,2006,45-49.
[56] N. Duffo, F. Torres, I. Corbella, et al. Some results of the MIRAS-SMOSdemonstrator campaigns. Proceedings of IGARSS,2007,3639-3642.
[57] M. Martin-Neira, I. Cabeza, et al. AMIRAS—An Airborne MIRAS Demonstrator.IEEE Trans. Geosci. Remote Sensing,2002,46(3):705–716.
[58] M. Martin-Neira, I. Corbella, et al. MIRAS Functional Test Results for the SMOSMission. Proceedings of IEEE MicroRad,2006,29-34.
[59] S. Beraza, V. Gonzalez, F. Torres, et al. MIRAS-SMOS Demonstrator Test Campaignsat Polytechnic University of Catalonia. Proceedings of IGARSS,2006,1776-1779.
[60] H. M. J. P. Barré, B. Duesmann and Y. H. Kerr. SMOS: The Mission and the System.IEEE Trans. Geosci. Remote Sensing,2002,46(3):587–593.
[61] K. D. McMullan, M. A. Brown, M. Martín-Neira, et al. SMOS: The Payload. IEEETrans. Geosci. Remote Sensing,2002,46(3):594–605.
[62] H. Valmu, I. Mononen, and M. Hallikainen. The Helsinki University of Technologysynthetic aperture radiometer. Proceedings of IGARSS,1998,2:553-555.
[63] K. Rautiainen, R. Butora, T. Auer, et al. The Helsinki University of TechnologyYlinen electronics airborne L-band interferometric radiometer. Proceedings ofIGARSS,2000,7:2978-2980.
[64] K. Rautiainen, R. Butora, T. Auer, J. Kettunen, et al. Development of airborneaperture synthetic radiometer (HUT-2D). Proceedings of IGARSS,2003,2:1232-1234.
[65] K. Rautiainen, J. Kainulainen, T. Auer, et al. Helsinki University of TechnologySynthetic Aperture Radiometer－HUT-2D. Proceedings of IGARSS,2007,2:3635-3638.
[66] K. Rautiainen, R. Butora, M. Hallikainen, et al. Measurement of the HUT-2D aperturesynthesis radiometer four-element subassembly. Proceedings of IGARSS,2001,3074-3076.
[67] J. Kainulainen, K. Rautiainen, S. Tauriainen, et al. First2-D interferometricradiometer imaging of the earth from an aircraft. IEEE Trans. Geosci. RemoteSensing Letters,2007,4(2):241–245.
[68] K. Rautiainen, J. Kainulainen, T Auer, et al. Helsinki University of TechnologyL-Band Airborne Synthetic Aperture Radiometer. IEEE Trans. Geosci. RemoteSensing,2008,46(3):717–726.
[69] B. Lambrigtsen, W. Wilson, A. Tanner, et al. GeoSTAR-a microwave sounder forgeostationary satellites. Proceedings of IGARSS,2004,777-780.
[70] B. Lambrigtsen, W. Wilson, A. Tanner, T. Gaier. GeoSTAR-a synthetic apertureapproach for a geostationary microwave sounder. Proceedings of IEEE AerospaceConference,2004,2:1008-1014.
[71] A. B. Tanner, W. J. Wilson, P. P. Kangaslahti, et al. Prototype development of ageostationary synthetic thinned aperture radiometer, GeoSTAR. Proceedings ofIGARSS,2004,1256-1259.
[72] B. H. Lambrigsten, W. Wilson, A. B. Tanner, et al. GeoSTAR a synthetic aperturemicrowave sounder for geostationary missions. Proceedings of SPIE,2005, V5659:185-194.
[73] B. Lambrigtsen. GeoSTAR: Developing A New Payload for GOES Satellites, in IEEEAerospace Conference,2006,1-10.
[74] A. B. Tanner, S. T. Brown, T. C. Gaier, et a. Field tests of the GeoSTAR demonstratorinstrument. Proceedings of IGARSS,2007,2427-2430.
[75] A.B.Tanner, T. C. Gaier, and B. H. Lambrigtsen. GeoSTAR PerformanceDemonstration. Proceedings of IEEE Aerospace Conference,2008,1-6.
[76] A. B. Tanner, S. T. Brown, S. J. Dinardo, et al. Initial results of the GeoSTARprototype. Proceedings of IEEE Aerospace Conference,2006,1-9.
[77] A. B. Tanner, W. J. Wilson, B. H. Lambrigsten, et al. Initial Results of theGeosynchronous Synthetic Thinned Array Radiometer. Proceedings of IGARSS,2006,3968-3971.
[78] M. A. Fischman and A. W. England. An L-band direct-sampling digital radiometerdesign and performance evaluation. Proceedings of IGARSS,1999,1:237-239.
[79] L. Nieuwstadt, R. De Roo, D. Boprie, et al. A compact direct detection receiver forL-band STAR radiometry. Proceedings of IEEE MTT-S,2003,1:563-566.
[80] R. De Roo, A. W. England, and J. Munn. Circular polarization for L-band radiometricsoil moisture retrieval. Proceedings of IEEE Aerospace Conference,2004,2:1015-1023.
[81] M. A. Fischman and A. W. England. A direct-sampling receiver for synthetic thinnedarray radiometry. Proceedings of IGARSS,1998,3:1711-1713.
[82] M. A. Fischman and A. W. England. An L-band direct sampling digital radiometer forSTAR technology sensors. Proceedings of IGARSS,2000,5:129-139.
[83] A. W. England, H. Pham, R. De Roo, et al. Performance of STAR-Light receiversduring CLPX. Proceedings of IGARSS,2003,2:1235-1237.
[84] Dong Xiaolong, Wu Ji, and Jiang Jingshan. The signal analysis and imaging ofsynthetic aperture radiometer. Proceedings of IGARSS,1998,5:2650-2652.
[85]张升伟，董晓龙，吴季. L波段合成孔径微波辐射计机理及原理性实验.遥感技术与应用,2000,15(2):95-99.
[86] Dong Xiaolong, Wu Ji, et al. The design and implementation of CAS C-bandinterferometric synthetic aperture radiometer. Proceedings of IGARSS,2000,2:866-868.
[87] Zhang Shengwei and Wu Ji. Experimental results of synthetic aperture microwaveradiometer. Proceedings of IGARSS,2002,6:3635-3637.
[88] Lu Jie, Ban Souzheng, Wu Ji, et al. Receiver designing of the x-bandhigh-spatial-resolution radiometer. Proceedings of SPIE,2003, V4894:240-250.
[89] Liu Hao, Wu Ji, et al. The CAS airborne X-band synthetic aperture radiometer:system configuration and experimental results. Proceedings of IGARSS,2004,3:2230-2233.
[90] Huang Jian, Gan Tiguo. A novel millimeter wave synthetic aperture radiometerpassive imaging system. Proceedings of IEEE ICMMT,2004,414-417.
[91]卢军,林士杰,张祖荫.星载合成孔径微波辐射计的反演公式.微波学报，1994,39(4):20-27.
[92] Li Qingxia, Chen Ke, Guo Wei, et al. An Aperture Synthesis Radiometer at MillimeterWave Band. in Proc. Proceedings of IEEE ICMMT,2008,4:1699-1701.
[93] Li Qingxia, Hu Fei, Guo Wei, et al. A General Platform for Millimeter Wave SyntheticAperture Radiometers. Proceedings of IGARSS,2008,1156-1159.
[94]薛永,苗俊刚,万国龙.8mm波段二维综合孔径微波辐射计(BHU-2D).北京航空航天大学学报,2008,34(9):1020-1023.
[95] Xue Yong, Miao Jungang, et al. Development of the disk antenna array aperturesynthesis millimeter wave radiometer. Proceedings of IEEE ICMMT,2008,2:806-809.
[96]章勇,李兴国,王华力.毫米波合成孔径成像辐射计.系统工程与电子技术,1998,12:11-14.
[97] Zhou Xi, Sun Houjun, He Jiwei, et al. NUFFT-based iterative reconstructionalgorithm for synthetic aperture imaging radiometers. IEEE Trans. Geosci. RemoteSensing Letters,2009,6(2):273–276.
[98] A. Camps. The processing of Hexagonally Sampled Signals with StandardRectangular Techniques: Application to2-D Large Aperture SynthesisInterforometric Radiometers. IEEE Trans. Geosci. Remote Sensing,1997,GE-35(1):183~190.
[99]黄永辉.综合孔径成像微波辐射计反演算法及实验研究:[硕士学位论文].空间飞行器设计,中国科学院空间科学与应用研究中心,2001.
[100] A. Camps, J. Bara, F. Torres, et al. Extension of the CLEAN technique to themicrowave imaging of continuous thermal sources by means of aperture synthesisradiometers. in: Progress In Electromagnetics Research Symposium,1998,18:67-83.
[101] M. Bertero and P. Boccacci, Introduction to Inverse Problems in Imaging,1st ed.London, U.K.: Inst. Phys.,1998.
[102] A. B. Tanner, C. T. Swift. Calibration of a Synthetic Aperture Radiometer. IEEETrans. Geosci. Remote Sensing,1993,31(1):257~267.
[103] A. Lannes, E. Anterrieu, and K. Bouyoucef. Fourier interpolation and reconstructionvia Shannontype techniques; Part I: Regularization principle, J. Modern Opt.,1994,41(8):1537–1574.
[104] A. Lannes, E. Anterrieu, and K. Bouyoucef. Fourier interpolation and reconstructionvia Shannontype techniques Part II: Technical developments and applications, J.Modern Opt.,1996,43(1):105–138.
[105] M. A. Goodberlet. Improved image reconstruction techniques for synthetic apertureradiometers, IEEE Trans. Geosci. Remote Sens.,2000,38(3):1362–1366.
[106] M. Bertero and P. Boccacci, Introduction to Inverse Problems in Imaging,1st ed.London, U.K.: Inst. Phys.,1998.
[107] K. P. Gaikovich and A. V. Zhilin. Tikhonov's algorithm for two-dimensional imageretrieval, in Proc. MMET, Kharkov, Ukraine,1998,622-624.
[108] E. Anterrieu. A resolving matrix approach for synthetic aperture imagingradiometers. IEEE Trans. Geosci. Remote Sens.,2004,42(8):1649-1656.
[109] A. Parthiban, Madhavan, J., Radhakrishna, P., et al,"On the probability distributionfunction for airborne radar clutter.," Radar Conference,2005IEEE International, pp.464-468,2005.
[110] A. Farina, Russo, A., Studer," Coherent radar detection in log-normal clutter,"Communications, Radar and Signal Processing, IEE Proceedings F, vol.133(1), pp.39-53,1986.
[111] M. Sekine, Ohtani, S., Musha, T., et al,"Weibull-Distributed Ground Clutter,"Aerospace and Electronic Systems, IEEE Transactions, vol. AES-17(4), pp.596-598,1981.
[112] Baker,"K-distributed coherent sea clutter," Radar and Signal Processing, IEEProceedings, vol.138(2), pp.89-92,1991.
[113]何友、关键、彭应宁,"雷达自动检测与恒虚警处理,"北京:清华大学出版社,1999.
[114] R. Ravid, Levanon,"Maximum-likelihood CFAR for Weibull background," Radarand Signal Processing, IEE Proceedings, vol.139(3), pp.256-264,1992.
[115] Blake," OS-CFAR theory for multiple targets and nonuniform clutter," Aerospaceand Electronic Systems, IEEE Transactions, vol.24(6), pp.785-790,1988.
[116] C.-J. Kim, Lee,"Detection analysis of a generalized order statistics CFAR detectorfor a correlated Rayleigh target," Signal Processing, vol.47(2), pp.227-233,1995.
[117] F. Zhang, Li, C., Shi,"Detecting and tracking dim moving point target in IR imagesequence," Infrared Physics&Technology, vol.46(4), pp.323-328,2005.
[118] B. Porat, Friedlander,"A frequency domain algorithm for multiframe detection andestimation of dim targets," Pattern Analysis and Machine Intelligence, IEEETransactions, vol.12(4), pp.398-401,1990.
[119] L. A. Johnston, Krishnamurthy,"Performance analysis of a dynamic programmingtrack before detect algorithm," Aerospace and Electronic Systems, IEEETransactions, vol.38(1), pp.228-242,2002.
[120]杨磊.,"复杂背景条件下的红外小目标检测与跟踪算法研究:[博士学位论文],"图像处理与模式识别研究所,上海交通大学,2006.
[121]熊祖彪,"综合孔径微波辐射探测的统计特性研究[博士论文],"华中科技大学,2009.
[122] M. M. H. a. D. W. Thomas,"The Two-dimensional adaptive LMS algorithm," IEEETrans On Systems, vol.35(5), p.485～494,1988.
[123] M. O. a. S. Hashiguchi,"Two-dimensional LMS adaptive filters," IEEE TransConsumer Elect, vol.37, pp.66-73,1991.
[124] J. R. Z. Tarun Soni, Walter H. Ku,"Performance Evaluation of2-D AdaptivePrediction Filters For Detection of Small Objects in Image Data," IEEE Trans OnImage Processing, vol.2(3), pp.327-340,1993.
[125] J. D. P. Cassent, S. Smokelin and A. Ye,"Wavelet and Gabor Transform ForDetection," Opt. Eng, vol.31, pp.1893-1898,1992.
[126] R. N. S. a. H. I. Hahn,"Wavelet transform methods for object detection andrecovery," IEEE Trans On Image Processing, vol.6(5), pp.724-735,1997.
[127] Vapnik. V. N and Chervonenkis. A. J. On the Uniform Covergence of RelativeFrequencies of Events to their Probabilities. Theroy Probability Application.1971,16:264-280.
[128] Vapnik.Vladimir. N. The Nature of Statistical Learning Theroy. Spring: Verlag.1992.
[129] Cortes. C. and Vapnik.V. N. Support-Vector Network. Machine Learning.1995,20(3):273-297.
[130] M. E. Tipping. Sparse Bayesian Learning and the Relevance Vector Machine.Journal of Machine Learning Research.2001,1:211-244.
[131] Mercer. J. Functions of Positive and Nagative Type and their Connection with theTheory of Integral Equations. Philos. Trans. Roy. Soc.1909, A(209):415-446.
[132] E. Anterrieu. On the reduction of the reconstruction bias in synthetic apertureimaging radiometry, IEEE Trans. Geosci. Remote Sens.,2007,45(3):592-602.
[133] A. Camps, M. Vall-llossera, I. Corbella, et al. Improved image reconstructionalgorithms for aperture synthesis radiometers, IEEE Trans. Geosci. Remote Sens.,2008,46(1):146-158.
[134] C.L. Lawson and R.J. Hanson. Solving Least Squares Problems. Prentice-Hall,1974.
[135]张贤达.矩阵分析与应用.北京：清华大学出版社,2005.
[136] P. C. Hansen. Rank-Decient and Discrete Ill-Posed Problems. Numerical Aspects ofLinear Inversion. SIAM,1998.
[137] A. N. Tikhonov. Regularization of incorrectly posed problems. Soviet Math. Dokl.,1963,4:1624~1627.
[138] V. A. Morozov. On the solution of functional equations by the method ofregularization. Soviet Math. Dokl.,1966,7:414-417.
[139] H. Gfrerer. An a posteriori parameter choice for ordinary and iterated Tikhonovregularization of ill-posed problems leading to optimal convergence rates. Math.Comp.,1987,49:507-522.
[140] A. R. Barron and T. Cover. Minimum complexity density estimation. IEEE Trans.Inf. Theory,1991,37:1034-1054.
[141] D. Belsley, E.Kuh, and R.Welsch. Regression Diagnostics: Identifying InfluentialData and Sources of Collinearity, Wiley, New York,1980.
[142] J. Berger. Statistical Decision Theory and Bayesian Analysis. Springer, New York,1985.
[143] A. Blumer, A. Ehrenfeucht, D.Haussler and M.Warmuth. Learnability and theVapnik Chenvonenkis dimension. J.ACM,1985,36:929-965.
[144] N. N. Chentsov. On correctness of problem of statistical point estimation. TheoryProbab. Appl,1981.26:13-29.
[145] V. Cherkassky and F. Mulier. Learning from Data: Concepts, Theory, and Methods.Wiley, New York,1998.
[146] P. Craven and H. Wahba. Smoothing noisy data with spline functions: estimating thecorrect degree of smoothing by the method of generalized cross-validation. Numer.Math,1979.31:377-403.
[147] G. H. Golub, M. Heath, and G. Wahba. Generalized cross-validation as a method forchoosing a good ridge parameter. Technometrics,1979,21:215-223.
[148] P. C. Hansen and D. P. O'Leary. The use of the L-curve in the regularization ofdiscrete ill-posed problems. SIAM J. Sci. Comput.,1993,14:1487-1503.
[149] M. Hanke. Limitations of the L-curve method in ill-posed problem. BIT,1996,36:287-301.
[150] E. Gine and J. Zinn. Some limit theorems for empirical processed. Ann. Probab,1984,12:929-989.
[151] F. Girosi. Approximation error bounds that use VC bounds. ICANN95, Paris,1995.
[152] P. J. Wolfe, S. J. Godsill and W. J. Ng. Bayesian variable selection andregularization for time-frequency surface estimation. J. Roy. Stat. Soc. B, Aug,2004,vol.66:575-589.
[153] A. Tarantola. Inverse problem theory and methods for model parameters estimation.Philadelphia, PA:SIAM,2005.
[154] D. J. C. Mackay. A practical Bayesian framework for back propagation networks.Neural Computation,1992, vol.4, no.3:448-472.
[155] R. M. Neal. Bayesian Training of Backpropagation on Networks by the HybridMonte Carlo Method. Department of Statistics, University of Toronoto,1992.
[156] R. M. Neal. Bayesian Learning for Neural Network. Ser. Lecture Notes in Statistics,U. K: Springer,1996.
[157] C. K. I. Williams and C. E. Rasmussen. Gaussian processes for regression. Advancein Neural information Processing Syestems, D. S. Touretzky, M. C. Mozer and M. E.Hasselino, Eds, Cambridge, MA: MIT Press,1996.
[158] C. K. I. Williams. Prediction and Gaussian processes: from linear regression tolinear prediction and beyond. Learning and Inference in Graphical Models, Norwell,MA: Kluwer,1998.
[159] M. H. Law and J. T. Kwork. Applying the Bayesian evidence framework to supportvector regression. Proc.12th. Eur. Conf. Machine Learning, Freiburg, Germany,2001:312-323.
[160] Tipping, M. E and A. Faul. Fast marginal likehood maximization for sparseBayesian models. Proceedings Ninth International Workshop on ArtificialIntelligence and Statistics. Key West, Florida,2003.
[161] A. Bjorck. Numerical Methods for Least Squares Problems. Philadelphia, PA:SIAM,1996.
[162] V. N. Vapnik. The Nature of Statistical Learning Theory. New York: Springer-Verlag,1995.
[163]徐利治、林化夷等.现代数学手册*随机数学卷.武汉:华中科技大学出版社,2000.
[164] N. A. Ablitt, J. X. Gao, J. keegan, L.Stegger. Predictive Cardiac Motion Modelingand Correction With Partial Least Squares Regression. IEEE. Trans. Med. Imag,Vol.23, No.10:1315-1324Oct,2004.
[165] Hong Su and Gangtie Zheng. A Partial Least Squares Regression-Based FusionModel for Predicting the Trend in Drowsiness. IEEE. Trans. Sys, Man andCybernetics-Part A: Systems and Humans. Vol.38, No.10:1085-1092, Sept,2008.
[166] P. Stoica and Y. Selen. Model-order selection: A review of information criterionrules. IEEE Signal Process. Mag. Vol.21, pp:36-47, Jul,2004.
[167] S. S. Keerthi and S. K. Shevade. SMO algorithm for linear squares SVMformulations. Neural Computation. Vol.15, No.2:487-507. Feb.2003.
[168] S. K. Shevade, S. S. Keerthi, C. Bhattacharyya, and K. R. K. Murthy. Improvementto the SMO algorithm for SVM regression. IEEE. Trans. Neural Network. Vol.11,pp.1188-1194, Sept.2000.
[169] A. J. Smola and B. Scholkopf. A Tutorial on Support Vector Regression. GMD First.Technical Report NC2-TR-1998-30. Oct.1998.
[170] W. Chu. Bayesian approach to support vector machines. Ph.D, dissertation, Nat.Univ. Singaproe, Jan.2003.
[171] J. B. Gao, S. R. Gunn, C. J. Harris and M. Brown. Aprobabilitsit framework forSVM regression and error bar estimation. Machine Learning. Vol.46, pp.71-89,Mar.2002.
[172] W. Chu, S. S. Keerthi, and C. J. Ong. Bayesian Support Vector Regression Using aUnified Loss Function. IEEE. Trans. Neural Network. Vol.15, pp.29-44, Jan.2004.
[173] E. G. Larsson and Y. Selen. Linear Regression with a Sparse Parameter Vector.IEEE. Trans. Signal Processing. Vol.55, No.2:451-460, Feb.2007.
[174] Larry Yujiri, Merit Shoucri, and Philp Moffa,“Passive millimeter wave imaging”,IEEE Micowave magazine,1527-3342/02,2003, September, pp.39-50.
[175] P.Wang., J.W.Tian and C.Q.Gao, A. Martin,“Infrared small target detection usingdirectional highpass filters based on LS-SVM”, Electron.Lett,2003,Vol.45,pp.156-158.
[176] L.Yang, J.Yang, and K.Yang.,“Adaptive detection for infrared small terget undersea-sky complex background”, Electron.Lett,2004, Vol.40, pp.1083-1085.
[177] Y.F.Gu, C.Wang., et al.,“A Kernel-Based nonparametric Regression Method forClutter Removal in Infrared Small-Target Detection Application”,IEEE.Geosci.Remote Sens Lett, July.2010, Vol..7,No.3, pp.469-473.
[178] A.Ruiz and E.Lopez-de Terual..,“Nonlinear kernel-based statistical patternanalysis”, IEEE Trans.Neural Netw., Jan2001, Vol.12,No.1, pp.16-32.
[179] T.Evgeniou,M.Pontil,and T.Poggio.“Regularization networks and support vectormachines”,Adv.Comput.Math.Apr.2000.Vol.13,No.1, pp.1-50.
[180] G.Camps-Valls,L.Bruzzone,J.L.Rojo-Alvarez,et al.“Robust Support VectorRegression for Biophysical Variable Estimation From Remotely Sensed image”,IEEE.Geosci.Remote Sens Lett, July.2006, Vol.3,No.3, pp.339-343.
[181] W.F.Zhang,D.Q.Dai,H.Yan.”Framelet Kernels With Application to Support VectorRegression and Regularization Networks”, IEEE Trans.Syst.Man.Cybern.B.Cybern.Agust.2010,Vol.40,No.4,pp.1128-1144.
[182] G.M.Fung and O.L.Mangasarina.”A Feature Selection Newton method for Supportvector machine Classification”,Computational Optimization and Applications,2004,Vol.28,pp.185-202.
[183] S.Matteoli,N.Acito,M.Diani,et al.”An Automatic Approach to Adaptive LocalBackground Estimation and Supression in Hyperspectral Target Detection”,IEEE.Trans.Geosci.Remote.Sens,February.2011,Vol..49,No.2,pp.790-800.
[184] John M, M.Anderson,“A Generalized Likelihood Radio Test for Detecting LandMines Using Multispectral Images”, IEEE.Geosci.Remote Sens Lett, July.2008,Vol.5,No.3, pp.547-551.
[185] Jean-Matthien Monnet, Jocelyn Chanussot,“Suppot Vector Regression for theEstimation of Forest Stand Parameters Using Airborne Laser Scanning”,IEEE.Geosci.Remote Sens Lett, May.2011, Vol.8,No.3, pp.580-584.
[186] J.Shawe-Taylor and N.Cristianini,”Kernel Methods for Pattern Analysis”,Cambridge University Press,2004.