激光与光电子学进展, 2018, 55 (9): 091004, 网络出版: 2018-09-08   

红外遥感图像TGV正则化超分辨率重建 下载: 755次

TGV Regularized Super Resolution Reconstruction for Infrared Remote Sensing Image
作者单位
郑州升达经贸管理学院应用数学研究所, 河南 郑州 451191
摘要
为了克服图像超分辨重建中四阶全变分正则化模型存在的“斑点”现象和稀疏正则化模型中最优解不唯一的缺点, 结合红外遥感图像超分辨率重建的实际需求, 提出了一种基于总广义变分正则化的红外遥感图像超分辨重建模型。根据零阶张量空间和松弛解的相关概念, 分析了模型的优点和可行性。结合该模型的自身分裂性, 采用交替方向乘数法将模型分裂为两个子问题, 分别利用共轭梯度法和快速傅里叶变换方法进行数值求解。从测试结果分析, 无论是模拟图像还是真实图像利用提出模型重建后的图像分辨率均有明显提升; 客观评价中的不同指标值均优于近期文献中的方法, 其中峰值信噪比提高约2 dB, 信噪比、结构相似度和信息熵分别提高1、0.02和0.1个单位。
Abstract
To overcome the shortcoming of bright speck phenomenon in four order totally variational model and the non-unique optimal solution in sparse regularization model of regularization image super-resolution reconstruction, an infrared remote sensing image super-resolution reconstruction model based on total generalized variation regularization is proposed in combination with the actual demand of infrared remote sensing image super-resolution reconstruction. The advantages and feasibility are analyzed with the concept of zero-order tensor space and the relaxation solution. Combined with the self-fissility of this model, the reconstruction model is split into two sub-problems by alternating direction multiplier method. The conjugate gradient method and the fast Fourier transform method are used to solve the sub-problem in numerical solution process, respectively. From the analysis of the testing results, the proposed model has a significant improvement in the resolution of the reconstructed image for both the simulated image and the real image. The objective evaluation is better than the method used in the literature, in which the peak signal to noise ratio can are increased by 1, 0.02 and 0.1 unit, respectively.
参考文献

[1] 李俊山, 杨威, 张雄美. 红外图像处理、分析与融合[M]. 北京: 科学出版社, 2009.

    Li J S, Yang W, Zhang X M. Infrared image processing, analysis and fusion[M]. Beijing: Science Press, 2009.

[2] 温海滨, 毕笃彦, 马时平, 等. 消除阶梯效应与增强细节的变分Retinex红外图像增强算法[J]. 光学学报, 2016, 36(9): 0911005.

    Wen H B, Bi D Y, Ma S P, et al. Variational Retinex algorithm for infrared image enhancement with staircase effect suppression and detail enhancement[J]. Acta Optica Sinica, 2016, 36(9): 0911005.

[3] 王兵元, 陈玮婷, 马文娟, 等. 基于非负约束L1-范数正则化的乳腺扩散光学层析成像重建方法[J]. 光学学报, 2016, 36(11): 1117002.

    Wang B Y, Chen W T, Ma W J, et al. Reconstruction method of breast diffuse optical tomography based on non-negative-constraint L1-norm regularization[J]. Acta Optica Sinica, 2016, 36(11): 1117002.

[4] 曹嘉豪, 李春来, 金健, 等. 超分辨率重建算法在热红外图像中的应用[J]. 红外, 2016, 37(5): 27-32.

    Cao J H, Li C L, Jin J, et al. Application of super resolution reconstruction algorithm in thermal infrared image[J]. Infrared, 2016, 37(5): 27-32.

[5] Hong M C, Kang M G, Katsaggelos A K. A regularized multi-channel restoration approach for globally optimal high resolution video sequence[J]. Proceedings of SPIE, 1997, 3024: 1306-1316.

[6] Capel D, Zisserman A. Super-resolution enhancement of text image sequences[C]∥Proceedings 15th International Conference on Pattern Recognition, 2000: 600-605.

[7] Ng M K, Shen H, Lam E Y, et al. A total variation regularization based super-resolution reconstruction algorithm for digital video[J]. EURASIP Journal on Advances in Signal Processing, 2007: 074585.

[8] Yuan Q, Zhang L, Shen H. Multi-frame super-resolution employing a spatially weighted variation model[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2012, 22(3): 379-392.

[9] 邓承志, 田伟, 汪胜前, 等. 近似稀疏正则化的红外图像超分辨率重建[J]. 光学 精密工程, 2014, 22(6): 1648-1654.

    Deng C Z, Tian W, Wang S Q, et al. Super-resolution reconstruction of approximate sparsity regularized infrared images[J]. Optics and Precision Engineering, 2014, 22(6): 1648-1654.

[10] 闫敬文, 谢婷婷, 彭鸿, 等. 基于L0范数正则项的运动图像去模糊[J]. 激光与光电子学进展, 2017, 54(2): 021005.

    Yan J W, Xie T T, Peng H, et al. Motion image deblurring based on L0 norms regularization term[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021005.

[11] Bredies K, Kunisch K, Pock T. Total generalized variation[J]. SIAM Journal of Imaging Sciences, 2010, 3(3): 492-526.

[12] Knoll F, Bredies K, Pock T, et al. Second order total generalized variation (TGV) for MRI[J]. Magnetic Resonance in Medicine, 2011, 65(2): 480-491.

[13] Xu J, Feng X, Hao Y, et al. Image decomposition using adaptive second-order total generalized variation[J]. Signal, Image and Video Processing, 2014, 8(1): 39-47.

[14] 许建楼, 冯象初, 郝岩. 自适应二阶总广义变分图像恢复方法[J]. 光电子·激光, 2013, 24(2): 378-383.

    Xu J L, Feng X C, Hao Y. Image restoration method with adaptive second order total generalized variation[J]. Journal of Optoelectronics·Laser, 2013, 24(2): 378-383.

[15] Bredies K, Valkonen T. Inverse problems with second-order total generalized variation constraints[EB/OL]. (2011-06-28)[2017-10-01]. http:∥tuomov.iki.fi/mathematics/SampTA2011.pdf.

[16] Frestl D, Reinbacher C, Ranftl R, et al. Image guided depth up-sampling using anisotropic total generalized variation[C]∥IEEE International Conference on Computer Vision, 2013: 993-1000.

[17] 刘孝艳, 冯象初. 对称张量空间下高阶正则化的图像恢复模型[J]. 计算机科学, 2013, 40(11A): 359-362.

    Liu X Y, Feng X C. High-order regularization model for image denoising in symmetric tensor space[J]. Computer Science, 2013, 40(11A): 359-362.

[18] 张煜林, 孔慧华, 潘晋孝, 等. 基于Split-Bregman算法的能谱计算机层析图像重建[J]. 光学学报, 2017, 37(4): 0411003.

    Zhang Y L, Kong H H, Pan J X, et al. Spectral computed tomographic image reconstruction based on Split-Bregman algorithm[J]. Acta Optica Sinica, 2017, 37(4): 0411003.

[19] Warren R E, Osher S J. Hyperspectral unmixing by the alternating direction method of multipliers[J]. Inverse Problems and Imaging, 2017, 9(3): 917-933.

[20] Boyd S, Parikh N, Chu E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J]. Foundations and Trends in Machine Learning, 2011, 3(1): 1-122.

[21] He R, Zheng W S, Tan T N, et al. Half-quadratic-based iterative minimization for robust sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(2): 261-275.

[22] Guitton A, Symes W W. Robust and stable velocity analysis using the Huber function[J]. SEG Technical Program Expanded Abstracts, 1999, 18(1): 1166-1169.

时文俊. 红外遥感图像TGV正则化超分辨率重建[J]. 激光与光电子学进展, 2018, 55(9): 091004. Shi Wenjun. TGV Regularized Super Resolution Reconstruction for Infrared Remote Sensing Image[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091004.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!