-
针对红外图像分辨率低、视觉质量差等问题,提出基于局部约束群稀疏模型的红外图像超分辨率重建方法. 考虑到红外图像的纹理自相似性和原子系数的群结构稀疏性,首先建立了基于局部约束的群稀疏表示模型. 然后,在假定低分辨率图像空间和高分辨率图像空间具有相似流形的前提下,联合局部约束群稀疏表示模型和K-SVD(K奇异值分解)方法,训练得到高低分辨率图像对应的群结构字典对. 最后,通过高分辨字典和对应的红外图像群稀疏表示系数重建得到高分辨率的红外图像. 实验结果表明,本文方法具有更好的超分辨率效果,无论是在客观评价指标还是主观视觉效果方面都有明显的提高.Aiming at the problems of low-resolution and poor visual quality of infrared images, a locality-constrained group sparsity based infrared image super-resolution algorithm is proposed. Firstly with considering the texture self-similarity of infrared images and group structural sparsity of atom coefficients, a locality-constrained group sparse (LCGS) model is proposed. Secondly, under LCGS and K-singular value decomposition, a pair of group structural dictionaries is learned. The dictionary pair can well capture and preserve the intrinsic geometrical manifold of low and high resolution data. Finally, the high-resolution infrared images are recovered by the high-resolution dictionary and the corresponding low-resolution group sparse coefficients. Experimental results show that the proposed method obtains excellent performance in objective evaluation and subjective visual effect.
-
Keywords:
- infrared image /
- super-resolution /
- group sparse /
- dictionary learning
[1] Kang M, Chaudhuri S 2003 IEEE Signal Proc. Mag. 20 1920
[2] Farsiu S, Robinson D, Elad M, Milanfar P 2004 Int. J. Imag. Syst. Tech. 14 47
[3] Elad M, Datsenko D 2007 Comput. J. 50 1
[4] Elad M, Figueiredo M A T, Ma Y 2010 P. IEEE 98 972
[5] Zhao J J, Tang Z Y, Yang J, Liu E Q, Zhou Y 2011 J. Infrared Millim. Waves 30 156 (in Chinese) [赵佳佳, 唐峥远, 杨杰, 刘尔琦, 周越 2011 红外与毫米波学报 30 156]
[6] Song C X, Ma K, Qin C, Xiao P 2013 Acta Phys. Sin. 62 040702 (in Chinese) [宋长新, 马克, 秦川, 肖鹏 2013 物理学报 62 040702]
[7] Ning F L, He B J, Wei J 2013 Acta Phys. Sin. 62 174212 (in Chinese) [宁方立, 何碧静, 韦娟 2013 物理学报 62 174212]
[8] Yang J, Wright J, Huang T 2010 IEEE Trans. Image Process. 19 2861
[9] Sun Y B, Wei Z H, Xiao L, Zhang Z R 2010 Acta Electron. Sin. 38 2898 (in Chinese) [孙玉宝, 韦志辉, 肖亮, 张峥嵘 2010 电子学报 38 2898]
[10] Lian Q S, Zhang W 2012 Acta Electron. Sin. 40 920 (in Chinese) [练秋生, 张伟 2012 电子学报 40 920]
[11] Yang S Y, Wang M, Chen Y G, et al 2012 IEEE Trans. Image Process. 21 4016
[12] Tang Y, Yuan Y, Yan P K, Li X L 2013 J. Vis. Commun. Image R 24 148
[13] Huang J Z, Zhang T, Metaxas D 2011 J. Mach. Learn. Res. 12 3371
[14] Sun H, Zhang Z L, Yu L 2012 Signal Process. 28 759 (in Chinese) [孙洪, 张智林, 余磊 2012 信号处理 28 759]
[15] Huang J, Zhang T 2010 Ann. Stat. 38 1978
[16] Liu H C, Li S T, Yin H T 2013 Opt. Commun. 289 45
[17] Chang H, Yeung D, Xiong Y 2004 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Washington DC, USA, June 27-July 2, 2004 p275
[18] Wang J J, Yang J C, Yu K, L F J, Huang T, Gong Y H 2010 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition San Francisco, USA, June 13-18, 2010 p3360
[19] Majumda A, Ward R K 2009 Can. J. Elect. Comput. E 34 136
[20] Yang J, Zhang Y 2011 SIAM J. Sci. Comput. 33 250
[21] Xu Y, Zhong A N, Yang J, Zhang D 2011 Opt. Eng. 50 037202
[22] Brunet D, Vrscay E R, Wang Z 2012 IEEE Trans. Image Process. 21 1488
-
[1] Kang M, Chaudhuri S 2003 IEEE Signal Proc. Mag. 20 1920
[2] Farsiu S, Robinson D, Elad M, Milanfar P 2004 Int. J. Imag. Syst. Tech. 14 47
[3] Elad M, Datsenko D 2007 Comput. J. 50 1
[4] Elad M, Figueiredo M A T, Ma Y 2010 P. IEEE 98 972
[5] Zhao J J, Tang Z Y, Yang J, Liu E Q, Zhou Y 2011 J. Infrared Millim. Waves 30 156 (in Chinese) [赵佳佳, 唐峥远, 杨杰, 刘尔琦, 周越 2011 红外与毫米波学报 30 156]
[6] Song C X, Ma K, Qin C, Xiao P 2013 Acta Phys. Sin. 62 040702 (in Chinese) [宋长新, 马克, 秦川, 肖鹏 2013 物理学报 62 040702]
[7] Ning F L, He B J, Wei J 2013 Acta Phys. Sin. 62 174212 (in Chinese) [宁方立, 何碧静, 韦娟 2013 物理学报 62 174212]
[8] Yang J, Wright J, Huang T 2010 IEEE Trans. Image Process. 19 2861
[9] Sun Y B, Wei Z H, Xiao L, Zhang Z R 2010 Acta Electron. Sin. 38 2898 (in Chinese) [孙玉宝, 韦志辉, 肖亮, 张峥嵘 2010 电子学报 38 2898]
[10] Lian Q S, Zhang W 2012 Acta Electron. Sin. 40 920 (in Chinese) [练秋生, 张伟 2012 电子学报 40 920]
[11] Yang S Y, Wang M, Chen Y G, et al 2012 IEEE Trans. Image Process. 21 4016
[12] Tang Y, Yuan Y, Yan P K, Li X L 2013 J. Vis. Commun. Image R 24 148
[13] Huang J Z, Zhang T, Metaxas D 2011 J. Mach. Learn. Res. 12 3371
[14] Sun H, Zhang Z L, Yu L 2012 Signal Process. 28 759 (in Chinese) [孙洪, 张智林, 余磊 2012 信号处理 28 759]
[15] Huang J, Zhang T 2010 Ann. Stat. 38 1978
[16] Liu H C, Li S T, Yin H T 2013 Opt. Commun. 289 45
[17] Chang H, Yeung D, Xiong Y 2004 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Washington DC, USA, June 27-July 2, 2004 p275
[18] Wang J J, Yang J C, Yu K, L F J, Huang T, Gong Y H 2010 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition San Francisco, USA, June 13-18, 2010 p3360
[19] Majumda A, Ward R K 2009 Can. J. Elect. Comput. E 34 136
[20] Yang J, Zhang Y 2011 SIAM J. Sci. Comput. 33 250
[21] Xu Y, Zhong A N, Yang J, Zhang D 2011 Opt. Eng. 50 037202
[22] Brunet D, Vrscay E R, Wang Z 2012 IEEE Trans. Image Process. 21 1488
计量
- 文章访问数: 6600
- PDF下载量: 1035
- 被引次数: 0