基于迁移学习的SAR目标超分辨重建
收稿日期: 2014-07-07
修回日期: 2014-08-11
网络出版日期: 2014-12-26
基金资助
国家自然科学基金 (61102166); 山东省优秀中青年科学家科研奖励基金 (BS2013DX003)
SAR target super-resolution based on transfer learning
Received date: 2014-07-07
Revised date: 2014-08-11
Online published: 2014-12-26
Supported by
National Natural Science Foundation of China (61102166); Science Foundation for the Excellent Youth Scientist of ShanDong Province (BS2013DX003)
针对合成孔径雷达(SAR)目标超分辨重建问题,提出了一种基于迁移学习的超分辨方法。在光学图像梯度域中联合训练超完备字典与稀疏编码映射,利用半耦合字典联系SAR图像与光学图像,寻找SAR图像在半耦合字典下的稀疏编码,并在高分辨率字典下完成重建。结合SAR图像的先验信息,使用正则化方法对SAR目标进行特征增强。所提方法在TerraSAR-X数据和MSTAR数据上进行了仿真实验,重建结果表明,相比目前的插值方法和稀疏表示方法,所提方法空间分辨率可提高0.5~1.5个像素。正则化增强结果表明,引入稀疏先验的正则化增强能够进一步提高空间分辨率并抑制杂波比,最后分析了正则化参数的选取对图像质量的影响。
徐舟 , 曲长文 , 何令琪 . 基于迁移学习的SAR目标超分辨重建[J]. 航空学报, 2015 , 36(6) : 1940 -1952 . DOI: 10.7527/S1000-6893.2014.0348
Based on transfer learning, a method for synthetic aperture radar(SAR) target super-resolution reconstruction is proposed in this paper. A semi-coupled dictionary is jointly trained in the gradient domain of optical image. By utilizing the relationship revealed by semi-coupled dictionary, the sparse codes of SAR image are obtained. Then the image is reconstructed in the high resolution dictionary. Based on some prior knowledge of SAR image, the regularization method is also used in order to enhance the target feature. Several simulation experiments are conducted based on TerraSAR-X and MSTAR data, and the reconstructed results show that the spatial resolution obtained by the proposed method is 0.5-1.5 pixels higher compared to the current interpolation method as well as the sparse representation method. Regularization enhancement results show that it can further improve the spatial resolution and suppress clutters by introducing the sparse prior. Finally, the influences on the spatial resolution and target structure of the reconstruction image caused by regularization parameter are analyzed qualitatively.
[1] Zhou J X, Shi G Z, Hu L, et al. Radar target one dimensional high resolution imaging based on sparse and non-uniform samplings in frequency domain[J]. Acta Electronica Sinica, 2012, 40(5): 926-934 (in Chinese). 周建雄, 石志广, 胡磊, 等. 基于频域稀疏非均匀采样的雷达目标一维高分辨成像[J]. 电子学报, 2012, 40(5): 926-934.
[2] Mao X H, Zhu D Y, Zhu Z D. 2-D autofocus algorithm for ultra-high resolution airborne spotlight SAR imaging[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(7): 1289-1295 (in Chinese). 毛新华, 朱岱寅, 朱兆达. 一种超高分辨率机载聚束SAR两维自聚焦算法[J]. 航空学报, 2012, 33(7): 1289-1295.
[3] Freeman W T, Jones T R, Pasztor E C. Example based super-resolution[J]. IEEE Computer Graphics and Applications, 2002, 22(2): 56-65.
[4] Mallat S, Yu G. Super-resolution with sparse mixing estimators[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2889-2900.
[5] Peleg T, Elad M. A statistical prediction model based on sparse representations for single image super-resolution[J]. IEEE Transactions on Image Processing, 2014, 23(6): 2569-2582.
[6] Yang J, Wang Z, Lin Z, et al. Coupled dictionary training for image super-resolution[J]. IEEE Transactions on Image Processing, 2012, 21(8): 3467-3477.
[7] Yang J, Wright J, Huang T S, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2851-2873.
[8] Zeyde R, Elad M, Protter, M. On single image scale-up using sparse-representations [C]//Proceedings of the 7th International Conference on Curves and Surfaces, Avignon, Berlin: Springer Berlin Heidelberg, 2010, 711-730.
[9] Dong W S, Zhang L, Shi G M, et al. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J]. IEEE Transactions on Image Processing, 2011, 20(7): 1838-1857.
[10] Wang S L, Zhang L, Liang Y, et al. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence. Piscataway, NJ: IEEE Press, 2012, 2216-2223.
[11] Aharon M, Elad M, Bruckstein A. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11): 4311-4322.
[12] Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.
[13] Efron B, Hastie T, Johnstone I, et al. Least angle regression[J]. The Annals of Statistics, 2004, 32(2): 407-499.
[14] Wang J H, Huang Z T, Zhou Y Y, et al. Robust sparse recovery based on approximate l0 norm[J]. Acta Electronica Sinica, 2012, 40(6): 1185-1189 (in Chinese). 王军华, 黄知涛, 周一宇, 等. 基于近似l0范数的稳健稀疏重构算法[J]. 电子学报, 2012, 40(6): 1185-1189.
[15] Fergus R, Singh B, Hertzmann A, et al. Removing camera shake from a single photograph[J]. ACM Transactions on Graphics, 2006, 25(3): 787-794.
[16] Gao G. Statistical modeling of SAR images: A survey[J]. Sensors, 2010, 10(1): 775-795.
[17] Cho S, Lee S. Fast motion deblurring[J]. ACM Transactions on Graphics 2009, 28(5): 145-152.
[18] Hansen P, Nagy J, O'leary D. Deblurring images: Matrices, spectra, and filtering[M]. Philadelphia: SIAM, 2006: 33-51.
[19] Figueiredo M, Nowak R, Wright S. Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems[J]. IEEE Journal of Selected Topics in Signal Processing, 2007, 1(4): 586-597.
[20] Cetin M. Feature-enhanced synthetic aperture radar imaging[D]. Manchester: University of Stanford, 2001:142-146.
/
| 〈 |
|
〉 |
CJA