基于拉格朗日分解算法的SAR图像混合像元分解
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
为解决与光学遥感图像不同的合成孔径雷达(SAR)图像中存在大量混合像元的问题,本文提出了一种基于拉格朗日分解算法的SAR图像混合像元分解的方法,结合相关内容中具体定理的证明,文中给出拉格朗日分解算法用于SAR图像混合像元分解的系统的求解方法.用人工模拟SAR图像和ENVISAT SAR图像进行实验,结果表明拉格朗日分解算法的混合像元分解结果明显优于非约束类神经网络(文中实验以BP神经网络为例)的分解结果.
For resolving the problem of mixed pixels that the Synthetic Aperture Radar (SAR) image has which is different from optical remote sensing image, we apply the Lagrangian constrained neural network to decomposition of SAR image mixed pixels.Combining the demonstration of specific theorem in relevant content, we propose a systemic solving method which uses Lagrange constrained neural network decompose the mixed pixels of the SAR image.We make experiments on artificial simulated SAR images and ENVISAT SAR images.Experimental results show that the Lagrangian constrained neural network can get significantly more precise results than other neural network which does not contain restrictive conditions, (such as the BP neural network).
引文
[1] ChangC I, Ren H, Chang C C, Jensen J O, Amico F D.Estimation of subpixel target size for remotely sensed imagery[J].IEEE Trans.on Geoscience and Remote Sensing, 2004, 42(6) :1309~1320.
    [2] Shaw G, Burke H.Spectral imaging for remote sensing[J].Lincoln Laboratory Journal, 2003,14(1) : 3~28.
    [3] Chang C I, et al.Least squares subspace project ion approach to mixed pixel classification for hyperspectral images[J].IEEE Trans.on Geoscience and Remote Sensing, 1998,36(3) : 898~912.
    [4] Giles M F, Manoj K A.Incorporating mixed pixels in the training, allocation and testing stages of supervised elassifications[J].Pattern Recognition Letters, 1996,17 (13) : 389~398.
    [5] 周昊,王斌,张立明,一种新的遥感图像混合像元分解方法[J].红外与毫米波学报,2005,24(6) :463~466. Zhou H, Wang B, Zhang L M.New scheme for decomposition of mixed pixels of remote sensing images[J].Journal of Infrared and Millimeter Waves.2005,24(6) :463~466.
    [6] Bastin L.Comparison of fuzzy e-means classification, linear mixture modelling and MLC probabilities as tools for unmixing coarse pixels[J].International Journal of Remote Sensing , 1997,17:3629~3648.
    [7] Bressan M, Guillamet D, Vitria J.Using an ICA representation of local color histograms for object recognition[J].Pattern Recognition, 2003,36 (3) : 691~701.
    [8] 丛浩,张良培,李平湘.一种端元可变的混合像元分解方法[J].中国图象图形学报,2006,11(8) :1092~1096. Cong H, Zhang L P, Li P X.A method of selective endmember for pixel Unmixing[J].Journal of Image and Graphics,2006,11(8) :1092~1096.
    [9] Kanellopoulos I, Varfis A, Wilkinson G G, Mégier J.Classification of remotely-sensed satellite images using multi layer perception networks[A].in Proceedings of the 1991 International Conference on Artificial Neural Networks (ICANN-91) , 1991.
    [10] Zhang W, Yan T L, You S C.Analysis of advantage on radar remote sensing for agricultural application, towards digital earth-proceedings of the international symposium on digital earth[M].Beijing:Science Press ,1999.
    [11] 单新建,李建华,马超.昆仑山口西Ms8. 1级地震地表破裂带高分辨率卫星影像特征研究[J].地球物理学报,2005,48(2) :321~326. Shan X J, Li J H, Ma C.Study on the feature of surface rupture zone of the west of Kunlunshan pass earthquake ( Ms 8. 1) with high spatial resolution satellite images[J].Chinese J.Geophys.(in Chinese), 2005, 48(2) : 321~326.
    [12] 戴前伟,冯德山,何继善.KirchhOff偏移法在探地雷达正演图像处理中的应用[J].地球物理学进展,2005,20(3) :849~853. Dai Q W, Feng D S, He J S.The application of Kirchhoffs migration method in the image processing of the ground penetrating radar forward simulate[J].Progress in Geophysics (in Chinese), 2005,20(3) : 849~853.
    [13] 杨桄,陈克雄,周脉鱼,徐忠林,王宗.SAR图像中目标的检测和识别研究进展[J].地球物理学进展,2007,22(2) :617~621. Yang G, Chen K X, Zhou M Y, Xu Z L, Wang Z M.Study evolution of detection and recognition on target in SAR image[J].Progress in Geophysics (in Chinese) ,2007,22(2) :617~621.
    [14] 冯伟,吴如山,马在田.单向传播子的局部平面波分解以及在 定向照明分析和目标特征成像中的应用[J].地球物理学进展,2007,22(1) :171~178. Feng W,Wu R S, Ma Z T.Local plane wave decomposition of one-way propagator and the applications to directional illumination analysis and target-structure oriented imaging[J].Progress in Geophysics (in Chinese), 2007,22 (1) : 171~178.
    [15] Harold S,Ivica K.Artificial neural networks for noisy image super-resolution[J].Optics Communications, 2001,198 (1-3) :71~81.
    [16] Brian A T, Harold H S.Energy functions for minimizing misclassification error with minimum-complexity networks [J].Neural Networks, 1994,7(5) : 809~817.
    [17] Harold S.Future perspectives on neural network research[J].Neurocomputing, 1989,1 ( 1 ) : 37 ~ 43.
    [18] George W E,Harold S.Resource allocation using a constraint optimizing adaptive neural network.[J].Neural Networks, 1988,1(1) :435.
    [19] Wu C S.Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery[J].Remote Sensing of Environment, 2004, 93(4) :480~492.
    [20] Lu D S, Weng Q H.Use of impervious surface in urban land use classification.Remote Sensing of Environment, 2006, 102 (1-2) : 146~160.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心