Abstract
Due to the effect of the model mismatch error between the point spread function (PSF) and actual blur kernel, the performance of remote sensing image super-resolution (SR) is usually poor. In this paper, we propose a novel remote sensing image super-resolution method based on Lorentz fitting, to improve the reconstruction performance in actual application. Note that the actual blur kernel of remote sensing image is non-stationary and usually has non-smooth phenomenon in kernel edge. It is also asymmetric that the degree of blur is not same in radial and tangential directions, and blur is in a sense that the amount of blur depends on pixel locations in a sensor. This paper presents a flexible parametric blur kernel model based on a linear combination of Lorentz basic two-dimensional (2-D) patterns. The proposed model can provide flexible shapes for blur kernel with a different symmetry and non-smooth edge, which can model complicated blur due to various degradation factors accurately. Combining with the proposed PSF model and the optimized adaptive step size strategy, we proposed a remote sensing image super-resolution method to accelerate the convergence of super-resolution outputs. Experiment results have shown that the proposed method outperforms the other recent developed PSF model based remote sensing image super-resolution methods.
References
Guo L, Woźniak M (2021) An Image Super-Resolution Reconstruction Method with Single Frame Character Based on Wavelet Neural Network in Internet of Things. Mobile Netw Appl 26:390–403
Zhu L, Jin L, Zhu J et al (2021) Blind Image Deblurring Based on Local Rank. Mobile Netw Appl 25:1446–1456
Zhan Y, Fan Q, Bao F et al (2018) Single-Image Super-Resolution Based on Rational Fractal Interpolation. IEEE Trans Image Process 27(8):3782–3797
Dai S, Han M, Xu W, Wu Y, Gong Y, Katsaggelos AK (2009) Softcuts: a soft edge smoothness prior for color image super-resolution. IEEE Transactions on Image Processing 18(5):969–981
Cao F, Cai M, Tan Y (2015) mage Interpolation via Low-Rank Matrix Completion and Recovery. IEEE Transactions on Circuits and Systems for Video Technology 25(8):1261–1270
Qin J, Yanovsky I (2018) Robust super-resolution image reconstruction method for geometrically deformed remote sensing images. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp 8050–8053
Chang K, Ding PLK, LI B, (2018) Single Image Super Resolution Using Joint Regularization. IEEE Signal Process Lett 25(4):596–600
Liu X, Chen L, Wang W (2018) Robust Multi-Frame Super-Resolution Based on Spatially Weighted Half-Quadratic Estimation and Adaptive BTV Regularization. IEEE Trans Image Process 27(10):4971–4986
Dong C, C. C, Loy K, et al (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Jiang J, Ma X, Chen C et al (2017) Single image super resolution via locally regularized anchored neighborhood regression andnonlocal means. IEEE Trans Multimedia 19(1):15–26
Shen J (2021) Wang Y, Zhang J (2021) ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution. Mobile Netw Appl 26:13–26
Yang M, Wang Y (2013) A self-learning approach to single image super-resolution. IEEE Trans Multimedia 15(3):498–508
Huang J, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5197–5206
Levin A, Weiss Y, F Durand et al (2009) Understanding and evaluating blind deconvolution algorithms. IEEE Conference on Computer Vision and Pattern Recognition, pp 1964–1971
Huang L, Xia Y (2021) Fast Blind Image Super Resolution Using Matrix-Variable Optimization. IEEE Trans Circuits Syst Video Technol 31(3):945–955
Jang J, Yun JD, Yang S (2016) Modeling Non-Stationary Asymmetric Lens Blur by Normal Sinh-Arcsinh Model. IEEE Trans Image Process 25(5):2184–2195
Liu S, Zhou F, Liao Q (2016) Defocus Map Estimation From a Single Image Based on Two-Parameter Defocus Model. IEEE Trans Image Process 25(12):5943–5956
Oliveira JP, Figueiredo MAT, Bioucas-Dias JM (2014) Parametric Blur Estimation for Blind Restoration of Natural Images: Linear Motion and Out-of-Focus. IEEE Trans Image Process 23(1):466–477
Zhang F, Lu W, Liu H, Xue F (2018) Natural image deblurring based on l0-regularization and kernel shape optimization. Multimedia Tools Appl 77(20):26 239-26 257
Liu S, Wang H, Wang J, Pan C (2016) Blur-kernel bound estimation from pyramid statistics. IEEE Trans Circuits Syst Video Techn 26(5):1012–1016
Shen H, Du L, Zhang L, Gong W (2012) A blind restoration method for remote sensing images. IEEE Geosci Remote Sens Lett 9(6):1137–1141
Dong W, Zhang L, Shi G, Li X (2013) Nonlocally Centralized Sparse Representation for Image Restoration. IEEE Trans Image Process 22(4):1620–1630
Liu YQ, Du X, Shen LH, Chen SJ (2021) Estimating Generalized Gaussian Blur Kernels for Out-of-Focus Image Deblurring. IEEE Trans Circuits Syst Video Technol 31(3):829–843
Perrone D, Favaro P (2016) A clearer picture of total variation blind deconvolution. IEEE Trans Pattern Anal Mach Intell 38(6):1041–1055
Galatsanos N, Mesarovic V, Molina R (2000) Hierarchical Bayesian image restoration from partially known blurs. IEEE Trans Image Process 9(10):1784–1797
Yang L, Zhang X, Ren J(2011) Adaptive wiener filtering with Gaussian fitted point spread function in image restoration. IEEE 2nd International Conference on Software Engineering and Service Science, pp. 890–894
Pan J, Hu Z, Su Z, Yang M (2017) L0-regularized intensity and gradient prior for deblurring text images and beyond. IEEE Trans Pattern Anal Mach Intell 39(2):342–355
Hosseini MS, Plataniotis KN (2020) Convolutional Deblurring for Natural Imaging. IEEE Trans Image Process 29:250–264
Oh S, Kim G (2014) Robust estimation of motion blur kernel using apiecewise-linear model. IEEE Transactions on Image Process 23(3):1394–1407
Baechler G, Scholefield A, Baboulaz L, Vetterli M (2017) Sampling and Exact Reconstruction of Pulses with Variable Width. IEEE Trans Signal Process 65(10):2629–2644
Bardsley JM, Laobeul N (2008) Tikhonov regularized Poisson likelihood estimation: Theoretical justification and a computational method. Inverse Problems Sci. Eng. 16(2):199–215
Dong W, Tao S, Xu G et al (2021) Blind Deconvolution for Poissonian Blurred Image With Total Variation and L0-Norm Gradient Regularizations. IEEE Trans Image Process 30:1030–1043
Buades A, Coll B, Morel JM (2005) A Non-Local Algorithm for Image Denoising. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2:60–65
Zhuo S, Sim T (2011) Defocus map estimation from a single image. Pattern Recognition 44(9):1852–1858
Moghaddam M E(2007) A mathematical model to estimate out of focus blur,” in Proceedings of International Symposium on Image and Signal Processing and Analysis. IEEE, pp. 278–281
Wang Z, Bovik A (2006) Modern image quality assessment. Morgan and Claypool Publishing Company, New York, pp 106–199
Li Y, Zhang Y, Huang X, Ma J (2018) Learning source-invariant deep hashing convolutional neural networks for cross-source remote sensing image retrieval. IEEE Trans Geosci Remote Sens 56(11):6521–6536
Funding
This work was supported by the Natural Science Foundation of Zhejiang Province (No. LQ21F010014) and the National Natural Science Foundation of China (NSFC, No. 61871348).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Huang, G., Liu, Y., Lu, W. et al. Remote Sensing Image Super-Resolution Based on Lorentz Fitting. Mobile Netw Appl 27, 1615–1628 (2022). https://doi.org/10.1007/s11036-021-01870-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11036-021-01870-x